linux-sg2042/mm/vmscan.c

3492 lines
98 KiB
C
Raw Normal View History

/*
* linux/mm/vmscan.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*
* Swap reorganised 29.12.95, Stephen Tweedie.
* kswapd added: 7.1.96 sct
* Removed kswapd_ctl limits, and swap out as many pages as needed
* to bring the system back to freepages.high: 2.4.97, Rik van Riel.
* Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com).
* Multiqueue VM started 5.8.00, Rik van Riel.
*/
#include <linux/mm.h>
#include <linux/module.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/vmstat.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h> /* for try_to_release_page(),
buffer_heads_over_limit */
#include <linux/mm_inline.h>
#include <linux/backing-dev.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/compaction.h>
#include <linux/notifier.h>
#include <linux/rwsem.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/memcontrol.h>
per-task-delay-accounting: add memory reclaim delay Sometimes, application responses become bad under heavy memory load. Applications take a bit time to reclaim memory. The statistics, how long memory reclaim takes, will be useful to measure memory usage. This patch adds accounting memory reclaim to per-task-delay-accounting for accounting the time of do_try_to_free_pages(). <i.e> - When System is under low memory load, memory reclaim may not occur. $ free total used free shared buffers cached Mem: 8197800 1577300 6620500 0 4808 1516724 -/+ buffers/cache: 55768 8142032 Swap: 16386292 0 16386292 $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 0 5069748 10612 3014060 0 0 0 0 3 26 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 4 22 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 3 18 0 0 100 0 Measure the time of tar command. $ ls -s test.dat 1501472 test.dat $ time tar cvf test.tar test.dat real 0m13.388s user 0m0.116s sys 0m5.304s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 428 5528345500 5477116080 62749891 IO count delay total 338 8078977189 SWAP count delay total 0 0 RECLAIM count delay total 0 0 - When system is under heavy memory load memory reclaim may occur. $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 7159032 49724 1812 3012 0 0 0 0 3 24 0 0 100 0 0 0 7159032 49724 1812 3012 0 0 0 0 4 24 0 0 100 0 0 0 7159032 49848 1812 3012 0 0 0 0 3 22 0 0 100 0 In this case, one process uses more 8G memory by execution of malloc() and memset(). $ time tar cvf test.tar test.dat real 1m38.563s <- increased by 85 sec user 0m0.140s sys 0m7.060s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 9021 7140446250 7315277975 923201824 IO count delay total 8965 90466349669 SWAP count delay total 3 21036367 RECLAIM count delay total 740 61011951153 In the later case, the value of RECLAIM is increasing. So, taskstats can show how much memory reclaim influences TAT. Signed-off-by: Keika Kobayashi <kobayashi.kk@ncos.nec.co.jp> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujistu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 16:48:52 +08:00
#include <linux/delayacct.h>
#include <linux/sysctl.h>
vmscan: all_unreclaimable() use zone->all_unreclaimable as a name all_unreclaimable check in direct reclaim has been introduced at 2.6.19 by following commit. 2006 Sep 25; commit 408d8544; oom: use unreclaimable info And it went through strange history. firstly, following commit broke the logic unintentionally. 2008 Apr 29; commit a41f24ea; page allocator: smarter retry of costly-order allocations Two years later, I've found obvious meaningless code fragment and restored original intention by following commit. 2010 Jun 04; commit bb21c7ce; vmscan: fix do_try_to_free_pages() return value when priority==0 But, the logic didn't works when 32bit highmem system goes hibernation and Minchan slightly changed the algorithm and fixed it . 2010 Sep 22: commit d1908362: vmscan: check all_unreclaimable in direct reclaim path But, recently, Andrey Vagin found the new corner case. Look, struct zone { .. int all_unreclaimable; .. unsigned long pages_scanned; .. } zone->all_unreclaimable and zone->pages_scanned are neigher atomic variables nor protected by lock. Therefore zones can become a state of zone->page_scanned=0 and zone->all_unreclaimable=1. In this case, current all_unreclaimable() return false even though zone->all_unreclaimabe=1. This resulted in the kernel hanging up when executing a loop of the form 1. fork 2. mmap 3. touch memory 4. read memory 5. munmmap as described in http://www.gossamer-threads.com/lists/linux/kernel/1348725#1348725 Is this ignorable minor issue? No. Unfortunately, x86 has very small dma zone and it become zone->all_unreclamble=1 easily. and if it become all_unreclaimable=1, it never restore all_unreclaimable=0. Why? if all_unreclaimable=1, vmscan only try DEF_PRIORITY reclaim and a-few-lru-pages>>DEF_PRIORITY always makes 0. that mean no page scan at all! Eventually, oom-killer never works on such systems. That said, we can't use zone->pages_scanned for this purpose. This patch restore all_unreclaimable() use zone->all_unreclaimable as old. and in addition, to add oom_killer_disabled check to avoid reintroduce the issue of commit d1908362 ("vmscan: check all_unreclaimable in direct reclaim path"). Reported-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: David Rientjes <rientjes@google.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-15 06:22:12 +08:00
#include <linux/oom.h>
#include <linux/prefetch.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include <linux/swapops.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
#include <trace/events/vmscan.h>
struct scan_control {
/* Incremented by the number of inactive pages that were scanned */
unsigned long nr_scanned;
vmscan: bail out of direct reclaim after swap_cluster_max pages When the VM is under pressure, it can happen that several direct reclaim processes are in the pageout code simultaneously. It also happens that the reclaiming processes run into mostly referenced, mapped and dirty pages in the first round. This results in multiple direct reclaim processes having a lower pageout priority, which corresponds to a higher target of pages to scan. This in turn can result in each direct reclaim process freeing many pages. Together, they can end up freeing way too many pages. This kicks useful data out of memory (in some cases more than half of all memory is swapped out). It also impacts performance by keeping tasks stuck in the pageout code for too long. A 30% improvement in hackbench has been observed with this patch. The fix is relatively simple: in shrink_zone() we can check how many pages we have already freed, direct reclaim tasks break out of the scanning loop if they have already freed enough pages and have reached a lower priority level. We do not break out of shrink_zone() when priority == DEF_PRIORITY, to ensure that equal pressure is applied to every zone in the common case. However, in order to do this we do need to know how many pages we already freed, so move nr_reclaimed into scan_control. akpm: a historical interlude... We tried this in 2004: :commit e468e46a9bea3297011d5918663ce6d19094cf87 :Author: akpm <akpm> :Date: Thu Jun 24 15:53:52 2004 +0000 : :[PATCH] vmscan.c: dont reclaim too many pages : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly hit : a large number of reclaimable pages on the LRU. : Change things so we bale out when SWAP_CLUSTER_MAX pages have been reclaimed. And we reverted it in 2006: :commit 210fe530305ee50cd889fe9250168228b2994f32 :Author: Andrew Morton <akpm@osdl.org> :Date: Fri Jan 6 00:11:14 2006 -0800 : : [PATCH] vmscan: balancing fix : : Revert a patch which went into 2.6.8-rc1. The changelog for that patch was: : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly : hit a large number of reclaimable pages on the LRU. : : Change things so we bale out when SWAP_CLUSTER_MAX pages have been : reclaimed. : : Problem is, this change caused significant imbalance in inter-zone scan : balancing by truncating scans of larger zones. : : Suppose, for example, ZONE_HIGHMEM is 10x the size of ZONE_NORMAL. The zone : balancing algorithm would require that if we're scanning 100 pages of : ZONE_HIGHMEM, we should scan 10 pages of ZONE_NORMAL. But this logic will : cause the scanning of ZONE_HIGHMEM to bale out after only 32 pages are : reclaimed. Thus effectively causing smaller zones to be scanned relatively : harder than large ones. : : Now I need to remember what the workload was which caused me to write this : patch originally, then fix it up in a different way... And we haven't demonstrated that whatever problem caused that reversion is not being reintroduced by this change in 2008. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:01 +08:00
/* Number of pages freed so far during a call to shrink_zones() */
unsigned long nr_reclaimed;
/* How many pages shrink_list() should reclaim */
unsigned long nr_to_reclaim;
vmscan: kill hibernation specific reclaim logic and unify it shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing memory for suspend). commit a06fe4d307 said Without the patch: Freed 14600 pages in 1749 jiffies = 32.61 MB/s (Anomolous!) Freed 88563 pages in 14719 jiffies = 23.50 MB/s Freed 205734 pages in 32389 jiffies = 24.81 MB/s With the patch: Freed 68252 pages in 496 jiffies = 537.52 MB/s Freed 116464 pages in 569 jiffies = 798.54 MB/s Freed 209699 pages in 705 jiffies = 1161.89 MB/s At that time, their patch was pretty worth. However, Modern Hardware trend and recent VM improvement broke its worth. From several reason, I think we should remove shrink_all_zones() at all. detail: 1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle at no i/o congestion. but current shrink_zone() is sane, not slow. 2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works fine on numa system. example) System has 4GB memory and each node have 2GB. and hibernate need 1GB. optimal) steal 500MB from each node. shrink_all_zones) steal 1GB from node-0. Oh, Cache balancing logic was broken. ;) Unfortunately, Desktop system moved ahead NUMA at nowadays. (Side note, if hibernate require 2GB, shrink_all_zones() never success on above machine) 3) if the node has several I/O flighting pages, shrink_all_zones() makes pretty bad result. schenario) hibernate need 1GB 1) shrink_all_zones() try to reclaim 1GB from Node-0 2) but it only reclaimed 990MB 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1 4) it reclaimed 990MB Oh, well. it reclaimed twice much than required. In the other hand, current shrink_zone() has sane baling out logic. then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk. 4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal. Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages(). it bring good reviewability and debuggability, and solve above problems. side note: Reclaim logic unificication makes two good side effect. - Fix recursive reclaim bug on shrink_all_memory(). it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock. - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 09:59:12 +08:00
unsigned long hibernation_mode;
/* This context's GFP mask */
gfp_t gfp_mask;
int may_writepage;
/* Can mapped pages be reclaimed? */
int may_unmap;
/* Can pages be swapped as part of reclaim? */
int may_swap;
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
int order;
/* Scan (total_size >> priority) pages at once */
int priority;
/*
* The memory cgroup that hit its limit and as a result is the
* primary target of this reclaim invocation.
*/
struct mem_cgroup *target_mem_cgroup;
/*
* Nodemask of nodes allowed by the caller. If NULL, all nodes
* are scanned.
*/
nodemask_t *nodemask;
};
#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
#ifdef ARCH_HAS_PREFETCH
#define prefetch_prev_lru_page(_page, _base, _field) \
do { \
if ((_page)->lru.prev != _base) { \
struct page *prev; \
\
prev = lru_to_page(&(_page->lru)); \
prefetch(&prev->_field); \
} \
} while (0)
#else
#define prefetch_prev_lru_page(_page, _base, _field) do { } while (0)
#endif
#ifdef ARCH_HAS_PREFETCHW
#define prefetchw_prev_lru_page(_page, _base, _field) \
do { \
if ((_page)->lru.prev != _base) { \
struct page *prev; \
\
prev = lru_to_page(&(_page->lru)); \
prefetchw(&prev->_field); \
} \
} while (0)
#else
#define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0)
#endif
/*
* From 0 .. 100. Higher means more swappy.
*/
int vm_swappiness = 60;
long vm_total_pages; /* The total number of pages which the VM controls */
static LIST_HEAD(shrinker_list);
static DECLARE_RWSEM(shrinker_rwsem);
#ifdef CONFIG_MEMCG
static bool global_reclaim(struct scan_control *sc)
{
return !sc->target_mem_cgroup;
}
#else
static bool global_reclaim(struct scan_control *sc)
{
return true;
}
#endif
static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
{
if (!mem_cgroup_disabled())
return mem_cgroup_get_lru_size(lruvec, lru);
return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru);
}
/*
* Add a shrinker callback to be called from the vm
*/
void register_shrinker(struct shrinker *shrinker)
{
atomic_long_set(&shrinker->nr_in_batch, 0);
down_write(&shrinker_rwsem);
list_add_tail(&shrinker->list, &shrinker_list);
up_write(&shrinker_rwsem);
}
EXPORT_SYMBOL(register_shrinker);
/*
* Remove one
*/
void unregister_shrinker(struct shrinker *shrinker)
{
down_write(&shrinker_rwsem);
list_del(&shrinker->list);
up_write(&shrinker_rwsem);
}
EXPORT_SYMBOL(unregister_shrinker);
static inline int do_shrinker_shrink(struct shrinker *shrinker,
struct shrink_control *sc,
unsigned long nr_to_scan)
{
sc->nr_to_scan = nr_to_scan;
return (*shrinker->shrink)(shrinker, sc);
}
#define SHRINK_BATCH 128
/*
* Call the shrink functions to age shrinkable caches
*
* Here we assume it costs one seek to replace a lru page and that it also
* takes a seek to recreate a cache object. With this in mind we age equal
* percentages of the lru and ageable caches. This should balance the seeks
* generated by these structures.
*
* If the vm encountered mapped pages on the LRU it increase the pressure on
* slab to avoid swapping.
*
* We do weird things to avoid (scanned*seeks*entries) overflowing 32 bits.
*
* `lru_pages' represents the number of on-LRU pages in all the zones which
* are eligible for the caller's allocation attempt. It is used for balancing
* slab reclaim versus page reclaim.
*
* Returns the number of slab objects which we shrunk.
*/
unsigned long shrink_slab(struct shrink_control *shrink,
unsigned long nr_pages_scanned,
unsigned long lru_pages)
{
struct shrinker *shrinker;
unsigned long ret = 0;
if (nr_pages_scanned == 0)
nr_pages_scanned = SWAP_CLUSTER_MAX;
mm: vmscan: correctly check if reclaimer should schedule during shrink_slab It has been reported on some laptops that kswapd is consuming large amounts of CPU and not being scheduled when SLUB is enabled during large amounts of file copying. It is expected that this is due to kswapd missing every cond_resched() point because; shrink_page_list() calls cond_resched() if inactive pages were isolated which in turn may not happen if all_unreclaimable is set in shrink_zones(). If for whatver reason, all_unreclaimable is set on all zones, we can miss calling cond_resched(). balance_pgdat() only calls cond_resched if the zones are not balanced. For a high-order allocation that is balanced, it checks order-0 again. During that window, order-0 might have become unbalanced so it loops again for order-0 and returns that it was reclaiming for order-0 to kswapd(). It can then find that a caller has rewoken kswapd for a high-order and re-enters balance_pgdat() without ever calling cond_resched(). shrink_slab only calls cond_resched() if we are reclaiming slab pages. If there are a large number of direct reclaimers, the shrinker_rwsem can be contended and prevent kswapd calling cond_resched(). This patch modifies the shrink_slab() case. If the semaphore is contended, the caller will still check cond_resched(). After each successful call into a shrinker, the check for cond_resched() remains in case one shrinker is particularly slow. [mgorman@suse.de: preserve call to cond_resched after each call into shrinker] Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Tested-by: Colin King <colin.king@canonical.com> Cc: Raghavendra D Prabhu <raghu.prabhu13@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Chris Mason <chris.mason@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: <stable@kernel.org> [2.6.38+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 08:11:11 +08:00
if (!down_read_trylock(&shrinker_rwsem)) {
/* Assume we'll be able to shrink next time */
ret = 1;
goto out;
}
list_for_each_entry(shrinker, &shrinker_list, list) {
unsigned long long delta;
long total_scan;
long max_pass;
int shrink_ret = 0;
long nr;
long new_nr;
long batch_size = shrinker->batch ? shrinker->batch
: SHRINK_BATCH;
max_pass = do_shrinker_shrink(shrinker, shrink, 0);
if (max_pass <= 0)
continue;
/*
* copy the current shrinker scan count into a local variable
* and zero it so that other concurrent shrinker invocations
* don't also do this scanning work.
*/
nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
total_scan = nr;
delta = (4 * nr_pages_scanned) / shrinker->seeks;
delta *= max_pass;
do_div(delta, lru_pages + 1);
total_scan += delta;
if (total_scan < 0) {
printk(KERN_ERR "shrink_slab: %pF negative objects to "
"delete nr=%ld\n",
shrinker->shrink, total_scan);
total_scan = max_pass;
}
vmscan: reduce wind up shrinker->nr when shrinker can't do work When a shrinker returns -1 to shrink_slab() to indicate it cannot do any work given the current memory reclaim requirements, it adds the entire total_scan count to shrinker->nr. The idea ehind this is that whenteh shrinker is next called and can do work, it will do the work of the previously aborted shrinker call as well. However, if a filesystem is doing lots of allocation with GFP_NOFS set, then we get many, many more aborts from the shrinkers than we do successful calls. The result is that shrinker->nr winds up to it's maximum permissible value (twice the current cache size) and then when the next shrinker call that can do work is issued, it has enough scan count built up to free the entire cache twice over. This manifests itself in the cache going from full to empty in a matter of seconds, even when only a small part of the cache is needed to be emptied to free sufficient memory. Under metadata intensive workloads on ext4 and XFS, I'm seeing the VFS caches increase memory consumption up to 75% of memory (no page cache pressure) over a period of 30-60s, and then the shrinker empties them down to zero in the space of 2-3s. This cycle repeats over and over again, with the shrinker completely trashing the inode and dentry caches every minute or so the workload continues. This behaviour was made obvious by the shrink_slab tracepoints added earlier in the series, and made worse by the patch that corrected the concurrent accounting of shrinker->nr. To avoid this problem, stop repeated small increments of the total scan value from winding shrinker->nr up to a value that can cause the entire cache to be freed. We still need to allow it to wind up, so use the delta as the "large scan" threshold check - if the delta is more than a quarter of the entire cache size, then it is a large scan and allowed to cause lots of windup because we are clearly needing to free lots of memory. If it isn't a large scan then limit the total scan to half the size of the cache so that windup never increases to consume the whole cache. Reducing the total scan limit further does not allow enough wind-up to maintain the current levels of performance, whilst a higher threshold does not prevent the windup from freeing the entire cache under sustained workloads. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-07-08 12:14:36 +08:00
/*
* We need to avoid excessive windup on filesystem shrinkers
* due to large numbers of GFP_NOFS allocations causing the
* shrinkers to return -1 all the time. This results in a large
* nr being built up so when a shrink that can do some work
* comes along it empties the entire cache due to nr >>>
* max_pass. This is bad for sustaining a working set in
* memory.
*
* Hence only allow the shrinker to scan the entire cache when
* a large delta change is calculated directly.
*/
if (delta < max_pass / 4)
total_scan = min(total_scan, max_pass / 2);
/*
* Avoid risking looping forever due to too large nr value:
* never try to free more than twice the estimate number of
* freeable entries.
*/
if (total_scan > max_pass * 2)
total_scan = max_pass * 2;
trace_mm_shrink_slab_start(shrinker, shrink, nr,
nr_pages_scanned, lru_pages,
max_pass, delta, total_scan);
while (total_scan >= batch_size) {
int nr_before;
nr_before = do_shrinker_shrink(shrinker, shrink, 0);
shrink_ret = do_shrinker_shrink(shrinker, shrink,
batch_size);
if (shrink_ret == -1)
break;
if (shrink_ret < nr_before)
ret += nr_before - shrink_ret;
count_vm_events(SLABS_SCANNED, batch_size);
total_scan -= batch_size;
cond_resched();
}
/*
* move the unused scan count back into the shrinker in a
* manner that handles concurrent updates. If we exhausted the
* scan, there is no need to do an update.
*/
if (total_scan > 0)
new_nr = atomic_long_add_return(total_scan,
&shrinker->nr_in_batch);
else
new_nr = atomic_long_read(&shrinker->nr_in_batch);
trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
}
up_read(&shrinker_rwsem);
mm: vmscan: correctly check if reclaimer should schedule during shrink_slab It has been reported on some laptops that kswapd is consuming large amounts of CPU and not being scheduled when SLUB is enabled during large amounts of file copying. It is expected that this is due to kswapd missing every cond_resched() point because; shrink_page_list() calls cond_resched() if inactive pages were isolated which in turn may not happen if all_unreclaimable is set in shrink_zones(). If for whatver reason, all_unreclaimable is set on all zones, we can miss calling cond_resched(). balance_pgdat() only calls cond_resched if the zones are not balanced. For a high-order allocation that is balanced, it checks order-0 again. During that window, order-0 might have become unbalanced so it loops again for order-0 and returns that it was reclaiming for order-0 to kswapd(). It can then find that a caller has rewoken kswapd for a high-order and re-enters balance_pgdat() without ever calling cond_resched(). shrink_slab only calls cond_resched() if we are reclaiming slab pages. If there are a large number of direct reclaimers, the shrinker_rwsem can be contended and prevent kswapd calling cond_resched(). This patch modifies the shrink_slab() case. If the semaphore is contended, the caller will still check cond_resched(). After each successful call into a shrinker, the check for cond_resched() remains in case one shrinker is particularly slow. [mgorman@suse.de: preserve call to cond_resched after each call into shrinker] Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Tested-by: Colin King <colin.king@canonical.com> Cc: Raghavendra D Prabhu <raghu.prabhu13@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Chris Mason <chris.mason@oracle.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: <stable@kernel.org> [2.6.38+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 08:11:11 +08:00
out:
cond_resched();
return ret;
}
static inline int is_page_cache_freeable(struct page *page)
{
/*
* A freeable page cache page is referenced only by the caller
* that isolated the page, the page cache radix tree and
* optional buffer heads at page->private.
*/
return page_count(page) - page_has_private(page) == 2;
}
vmscan: narrow the scenarios in whcih lumpy reclaim uses synchrounous reclaim shrink_page_list() can decide to give up reclaiming a page under a number of conditions such as 1. trylock_page() failure 2. page is unevictable 3. zone reclaim and page is mapped 4. PageWriteback() is true 5. page is swapbacked and swap is full 6. add_to_swap() failure 7. page is dirty and gfpmask don't have GFP_IO, GFP_FS 8. page is pinned 9. IO queue is congested 10. pageout() start IO, but not finished With lumpy reclaim, failures result in entering synchronous lumpy reclaim but this can be unnecessary. In cases (2), (3), (5), (6), (7) and (8), there is no point retrying. This patch causes lumpy reclaim to abort when it is known it will fail. Case (9) is more interesting. current behavior is, 1. start shrink_page_list(async) 2. found queue_congested() 3. skip pageout write 4. still start shrink_page_list(sync) 5. wait on a lot of pages 6. again, found queue_congested() 7. give up pageout write again So, it's useless time wasting. However, just skipping page reclaim is also notgood as x86 allocating a huge page needs 512 pages for example. It can have more dirty pages than queue congestion threshold (~=128). After this patch, pageout() behaves as follows; - If order > PAGE_ALLOC_COSTLY_ORDER Ignore queue congestion always. - If order <= PAGE_ALLOC_COSTLY_ORDER skip write page and disable lumpy reclaim. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:42 +08:00
static int may_write_to_queue(struct backing_dev_info *bdi,
struct scan_control *sc)
{
if (current->flags & PF_SWAPWRITE)
return 1;
if (!bdi_write_congested(bdi))
return 1;
if (bdi == current->backing_dev_info)
return 1;
return 0;
}
/*
* We detected a synchronous write error writing a page out. Probably
* -ENOSPC. We need to propagate that into the address_space for a subsequent
* fsync(), msync() or close().
*
* The tricky part is that after writepage we cannot touch the mapping: nothing
* prevents it from being freed up. But we have a ref on the page and once
* that page is locked, the mapping is pinned.
*
* We're allowed to run sleeping lock_page() here because we know the caller has
* __GFP_FS.
*/
static void handle_write_error(struct address_space *mapping,
struct page *page, int error)
{
lock_page(page);
if (page_mapping(page) == mapping)
mapping_set_error(mapping, error);
unlock_page(page);
}
/* possible outcome of pageout() */
typedef enum {
/* failed to write page out, page is locked */
PAGE_KEEP,
/* move page to the active list, page is locked */
PAGE_ACTIVATE,
/* page has been sent to the disk successfully, page is unlocked */
PAGE_SUCCESS,
/* page is clean and locked */
PAGE_CLEAN,
} pageout_t;
/*
* pageout is called by shrink_page_list() for each dirty page.
* Calls ->writepage().
*/
static pageout_t pageout(struct page *page, struct address_space *mapping,
vmscan: narrow the scenarios in whcih lumpy reclaim uses synchrounous reclaim shrink_page_list() can decide to give up reclaiming a page under a number of conditions such as 1. trylock_page() failure 2. page is unevictable 3. zone reclaim and page is mapped 4. PageWriteback() is true 5. page is swapbacked and swap is full 6. add_to_swap() failure 7. page is dirty and gfpmask don't have GFP_IO, GFP_FS 8. page is pinned 9. IO queue is congested 10. pageout() start IO, but not finished With lumpy reclaim, failures result in entering synchronous lumpy reclaim but this can be unnecessary. In cases (2), (3), (5), (6), (7) and (8), there is no point retrying. This patch causes lumpy reclaim to abort when it is known it will fail. Case (9) is more interesting. current behavior is, 1. start shrink_page_list(async) 2. found queue_congested() 3. skip pageout write 4. still start shrink_page_list(sync) 5. wait on a lot of pages 6. again, found queue_congested() 7. give up pageout write again So, it's useless time wasting. However, just skipping page reclaim is also notgood as x86 allocating a huge page needs 512 pages for example. It can have more dirty pages than queue congestion threshold (~=128). After this patch, pageout() behaves as follows; - If order > PAGE_ALLOC_COSTLY_ORDER Ignore queue congestion always. - If order <= PAGE_ALLOC_COSTLY_ORDER skip write page and disable lumpy reclaim. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:42 +08:00
struct scan_control *sc)
{
/*
* If the page is dirty, only perform writeback if that write
* will be non-blocking. To prevent this allocation from being
* stalled by pagecache activity. But note that there may be
* stalls if we need to run get_block(). We could test
* PagePrivate for that.
*
* If this process is currently in __generic_file_aio_write() against
* this page's queue, we can perform writeback even if that
* will block.
*
* If the page is swapcache, write it back even if that would
* block, for some throttling. This happens by accident, because
* swap_backing_dev_info is bust: it doesn't reflect the
* congestion state of the swapdevs. Easy to fix, if needed.
*/
if (!is_page_cache_freeable(page))
return PAGE_KEEP;
if (!mapping) {
/*
* Some data journaling orphaned pages can have
* page->mapping == NULL while being dirty with clean buffers.
*/
if (page_has_private(page)) {
if (try_to_free_buffers(page)) {
ClearPageDirty(page);
printk("%s: orphaned page\n", __func__);
return PAGE_CLEAN;
}
}
return PAGE_KEEP;
}
if (mapping->a_ops->writepage == NULL)
return PAGE_ACTIVATE;
if (!may_write_to_queue(mapping->backing_dev_info, sc))
return PAGE_KEEP;
if (clear_page_dirty_for_io(page)) {
int res;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = SWAP_CLUSTER_MAX,
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:26 +08:00
.range_start = 0,
.range_end = LLONG_MAX,
.for_reclaim = 1,
};
SetPageReclaim(page);
res = mapping->a_ops->writepage(page, &wbc);
if (res < 0)
handle_write_error(mapping, page, res);
if (res == AOP_WRITEPAGE_ACTIVATE) {
ClearPageReclaim(page);
return PAGE_ACTIVATE;
}
if (!PageWriteback(page)) {
/* synchronous write or broken a_ops? */
ClearPageReclaim(page);
}
trace_mm_vmscan_writepage(page, trace_reclaim_flags(page));
inc_zone_page_state(page, NR_VMSCAN_WRITE);
return PAGE_SUCCESS;
}
return PAGE_CLEAN;
}
/*
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
* Same as remove_mapping, but if the page is removed from the mapping, it
* gets returned with a refcount of 0.
*/
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
static int __remove_mapping(struct address_space *mapping, struct page *page)
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
{
BUG_ON(!PageLocked(page));
BUG_ON(mapping != page_mapping(page));
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
spin_lock_irq(&mapping->tree_lock);
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
/*
* The non racy check for a busy page.
*
* Must be careful with the order of the tests. When someone has
* a ref to the page, it may be possible that they dirty it then
* drop the reference. So if PageDirty is tested before page_count
* here, then the following race may occur:
*
* get_user_pages(&page);
* [user mapping goes away]
* write_to(page);
* !PageDirty(page) [good]
* SetPageDirty(page);
* put_page(page);
* !page_count(page) [good, discard it]
*
* [oops, our write_to data is lost]
*
* Reversing the order of the tests ensures such a situation cannot
* escape unnoticed. The smp_rmb is needed to ensure the page->flags
* load is not satisfied before that of page->_count.
*
* Note that if SetPageDirty is always performed via set_page_dirty,
* and thus under tree_lock, then this ordering is not required.
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
*/
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
if (!page_freeze_refs(page, 2))
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
goto cannot_free;
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
/* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */
if (unlikely(PageDirty(page))) {
page_unfreeze_refs(page, 2);
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
goto cannot_free;
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
}
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
if (PageSwapCache(page)) {
swp_entry_t swap = { .val = page_private(page) };
__delete_from_swap_cache(page);
spin_unlock_irq(&mapping->tree_lock);
swapcache_free(swap, page);
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
} else {
void (*freepage)(struct page *);
freepage = mapping->a_ops->freepage;
__delete_from_page_cache(page);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);
if (freepage != NULL)
freepage(page);
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
}
return 1;
cannot_free:
spin_unlock_irq(&mapping->tree_lock);
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
return 0;
}
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
/*
* Attempt to detach a locked page from its ->mapping. If it is dirty or if
* someone else has a ref on the page, abort and return 0. If it was
* successfully detached, return 1. Assumes the caller has a single ref on
* this page.
*/
int remove_mapping(struct address_space *mapping, struct page *page)
{
if (__remove_mapping(mapping, page)) {
/*
* Unfreezing the refcount with 1 rather than 2 effectively
* drops the pagecache ref for us without requiring another
* atomic operation.
*/
page_unfreeze_refs(page, 1);
return 1;
}
return 0;
}
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
/**
* putback_lru_page - put previously isolated page onto appropriate LRU list
* @page: page to be put back to appropriate lru list
*
* Add previously isolated @page to appropriate LRU list.
* Page may still be unevictable for other reasons.
*
* lru_lock must not be held, interrupts must be enabled.
*/
void putback_lru_page(struct page *page)
{
int lru;
int active = !!TestClearPageActive(page);
int was_unevictable = PageUnevictable(page);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
VM_BUG_ON(PageLRU(page));
redo:
ClearPageUnevictable(page);
if (page_evictable(page, NULL)) {
/*
* For evictable pages, we can use the cache.
* In event of a race, worst case is we end up with an
* unevictable page on [in]active list.
* We know how to handle that.
*/
lru = active + page_lru_base_type(page);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
lru_cache_add_lru(page, lru);
} else {
/*
* Put unevictable pages directly on zone's unevictable
* list.
*/
lru = LRU_UNEVICTABLE;
add_page_to_unevictable_list(page);
vmscan: order evictable rescue in LRU putback Isolators putting a page back to the LRU do not hold the page lock, and if the page is mlocked, another thread might munlock it concurrently. Expecting this, the putback code re-checks the evictability of a page when it just moved it to the unevictable list in order to correct its decision. The problem, however, is that ordering is not garuanteed between setting PG_lru when moving the page to the list and checking PG_mlocked afterwards: #0: #1 spin_lock() if (TestClearPageMlocked()) if (PageLRU()) move to evictable list SetPageLRU() spin_unlock() if (!PageMlocked()) move to evictable list The PageMlocked() check may get reordered before SetPageLRU() in #0, resulting in #0 not moving the still mlocked page, and in #1 failing to isolate and move the page as well. The page is now stranded on the unevictable list. The race condition is very unlikely. The consequence currently is one page falling off the reclaim grid and eventually getting freed with PG_unevictable set, which triggers a warning in the page allocator. TestClearPageMlocked() in #1 already provides full memory barrier semantics. This patch adds an explicit full barrier to force ordering between SetPageLRU() and PageMlocked() so that either one of the competitors rescues the page. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-10-27 07:50:00 +08:00
/*
* When racing with an mlock or AS_UNEVICTABLE clearing
* (page is unlocked) make sure that if the other thread
* does not observe our setting of PG_lru and fails
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
* isolation/check_move_unevictable_pages,
* we see PG_mlocked/AS_UNEVICTABLE cleared below and move
vmscan: order evictable rescue in LRU putback Isolators putting a page back to the LRU do not hold the page lock, and if the page is mlocked, another thread might munlock it concurrently. Expecting this, the putback code re-checks the evictability of a page when it just moved it to the unevictable list in order to correct its decision. The problem, however, is that ordering is not garuanteed between setting PG_lru when moving the page to the list and checking PG_mlocked afterwards: #0: #1 spin_lock() if (TestClearPageMlocked()) if (PageLRU()) move to evictable list SetPageLRU() spin_unlock() if (!PageMlocked()) move to evictable list The PageMlocked() check may get reordered before SetPageLRU() in #0, resulting in #0 not moving the still mlocked page, and in #1 failing to isolate and move the page as well. The page is now stranded on the unevictable list. The race condition is very unlikely. The consequence currently is one page falling off the reclaim grid and eventually getting freed with PG_unevictable set, which triggers a warning in the page allocator. TestClearPageMlocked() in #1 already provides full memory barrier semantics. This patch adds an explicit full barrier to force ordering between SetPageLRU() and PageMlocked() so that either one of the competitors rescues the page. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-10-27 07:50:00 +08:00
* the page back to the evictable list.
*
* The other side is TestClearPageMlocked() or shmem_lock().
vmscan: order evictable rescue in LRU putback Isolators putting a page back to the LRU do not hold the page lock, and if the page is mlocked, another thread might munlock it concurrently. Expecting this, the putback code re-checks the evictability of a page when it just moved it to the unevictable list in order to correct its decision. The problem, however, is that ordering is not garuanteed between setting PG_lru when moving the page to the list and checking PG_mlocked afterwards: #0: #1 spin_lock() if (TestClearPageMlocked()) if (PageLRU()) move to evictable list SetPageLRU() spin_unlock() if (!PageMlocked()) move to evictable list The PageMlocked() check may get reordered before SetPageLRU() in #0, resulting in #0 not moving the still mlocked page, and in #1 failing to isolate and move the page as well. The page is now stranded on the unevictable list. The race condition is very unlikely. The consequence currently is one page falling off the reclaim grid and eventually getting freed with PG_unevictable set, which triggers a warning in the page allocator. TestClearPageMlocked() in #1 already provides full memory barrier semantics. This patch adds an explicit full barrier to force ordering between SetPageLRU() and PageMlocked() so that either one of the competitors rescues the page. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-10-27 07:50:00 +08:00
*/
smp_mb();
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
}
/*
* page's status can change while we move it among lru. If an evictable
* page is on unevictable list, it never be freed. To avoid that,
* check after we added it to the list, again.
*/
if (lru == LRU_UNEVICTABLE && page_evictable(page, NULL)) {
if (!isolate_lru_page(page)) {
put_page(page);
goto redo;
}
/* This means someone else dropped this page from LRU
* So, it will be freed or putback to LRU again. There is
* nothing to do here.
*/
}
if (was_unevictable && lru != LRU_UNEVICTABLE)
count_vm_event(UNEVICTABLE_PGRESCUED);
else if (!was_unevictable && lru == LRU_UNEVICTABLE)
count_vm_event(UNEVICTABLE_PGCULLED);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
put_page(page); /* drop ref from isolate */
}
vmscan: factor out page reference checks The used-once mapped file page detection patchset. It is meant to help workloads with large amounts of shortly used file mappings, like rtorrent hashing a file or git when dealing with loose objects (git gc on a bigger site?). Right now, the VM activates referenced mapped file pages on first encounter on the inactive list and it takes a full memory cycle to reclaim them again. When those pages dominate memory, the system no longer has a meaningful notion of 'working set' and is required to give up the active list to make reclaim progress. Obviously, this results in rather bad scanning latencies and the wrong pages being reclaimed. This patch makes the VM be more careful about activating mapped file pages in the first place. The minimum granted lifetime without another memory access becomes an inactive list cycle instead of the full memory cycle, which is more natural given the mentioned loads. This test resembles a hashing rtorrent process. Sequentially, 32MB chunks of a file are mapped into memory, hashed (sha1) and unmapped again. While this happens, every 5 seconds a process is launched and its execution time taken: python2.4 -c 'import pydoc' old: max=2.31s mean=1.26s (0.34) new: max=1.25s mean=0.32s (0.32) find /etc -type f old: max=2.52s mean=1.44s (0.43) new: max=1.92s mean=0.12s (0.17) vim -c ':quit' old: max=6.14s mean=4.03s (0.49) new: max=3.48s mean=2.41s (0.25) mplayer --help old: max=8.08s mean=5.74s (1.02) new: max=3.79s mean=1.32s (0.81) overall hash time (stdev): old: time=1192.30 (12.85) thruput=25.78mb/s (0.27) new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%) I also tested kernbench with regular IO streaming in the background to see whether the delayed activation of frequently used mapped file pages had a negative impact on performance in the presence of pressure on the inactive list. The patch made no significant difference in timing, neither for kernbench nor for the streaming IO throughput. The first patch submission raised concerns about the cost of the extra faults for actually activated pages on machines that have no hardware support for young page table entries. I created an artificial worst case scenario on an ARM machine with around 300MHz and 64MB of memory to figure out the dimensions involved. The test would mmap a file of 20MB, then 1. touch all its pages to fault them in 2. force one full scan cycle on the inactive file LRU -- old: mapping pages activated -- new: mapping pages inactive 3. touch the mapping pages again -- old and new: fault exceptions to set the young bits 4. force another full scan cycle on the inactive file LRU 5. touch the mapping pages one last time -- new: fault exceptions to set the young bits The test showed an overall increase of 6% in time over 100 iterations of the above (old: ~212sec, new: ~225sec). 13 secs total overhead / (100 * 5k pages), ignoring the execution time of the test itself, makes for about 25us overhead for every page that gets actually activated. Note: 1. File mapping the size of one third of main memory, _completely_ in active use across memory pressure - i.e., most pages referenced within one LRU cycle. This should be rare to non-existant, especially on such embedded setups. 2. Many huge activation batches. Those batches only occur when the working set fluctuates. If it changes completely between every full LRU cycle, you have problematic reclaim overhead anyway. 3. Access of activated pages at maximum speed: sequential loads from every single page without doing anything in between. In reality, the extra faults will get distributed between actual operations on the data. So even if a workload manages to get the VM into the situation of activating a third of memory in one go on such a setup, it will take 2.2 seconds instead 2.1 without the patch. Comparing the numbers (and my user-experience over several months), I think this change is an overall improvement to the VM. Patch 1 is only refactoring to break up that ugly compound conditional in shrink_page_list() and make it easy to document and add new checks in a readable fashion. Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not strictly related to #3, but it was in the original submission and is a net simplification, so I kept it. Patch 3 implements used-once detection of mapped file pages. This patch: Moving the big conditional into its own predicate function makes the code a bit easier to read and allows for better commenting on the checks one-by-one. This is just cleaning up, no semantics should have been changed. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:19 +08:00
enum page_references {
PAGEREF_RECLAIM,
PAGEREF_RECLAIM_CLEAN,
vmscan: detect mapped file pages used only once The VM currently assumes that an inactive, mapped and referenced file page is in use and promotes it to the active list. However, every mapped file page starts out like this and thus a problem arises when workloads create a stream of such pages that are used only for a short time. By flooding the active list with those pages, the VM quickly gets into trouble finding eligible reclaim canditates. The result is long allocation latencies and eviction of the wrong pages. This patch reuses the PG_referenced page flag (used for unmapped file pages) to implement a usage detection that scales with the speed of LRU list cycling (i.e. memory pressure). If the scanner encounters those pages, the flag is set and the page cycled again on the inactive list. Only if it returns with another page table reference it is activated. Otherwise it is reclaimed as 'not recently used cache'. This effectively changes the minimum lifetime of a used-once mapped file page from a full memory cycle to an inactive list cycle, which allows it to occur in linear streams without affecting the stable working set of the system. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:22 +08:00
PAGEREF_KEEP,
vmscan: factor out page reference checks The used-once mapped file page detection patchset. It is meant to help workloads with large amounts of shortly used file mappings, like rtorrent hashing a file or git when dealing with loose objects (git gc on a bigger site?). Right now, the VM activates referenced mapped file pages on first encounter on the inactive list and it takes a full memory cycle to reclaim them again. When those pages dominate memory, the system no longer has a meaningful notion of 'working set' and is required to give up the active list to make reclaim progress. Obviously, this results in rather bad scanning latencies and the wrong pages being reclaimed. This patch makes the VM be more careful about activating mapped file pages in the first place. The minimum granted lifetime without another memory access becomes an inactive list cycle instead of the full memory cycle, which is more natural given the mentioned loads. This test resembles a hashing rtorrent process. Sequentially, 32MB chunks of a file are mapped into memory, hashed (sha1) and unmapped again. While this happens, every 5 seconds a process is launched and its execution time taken: python2.4 -c 'import pydoc' old: max=2.31s mean=1.26s (0.34) new: max=1.25s mean=0.32s (0.32) find /etc -type f old: max=2.52s mean=1.44s (0.43) new: max=1.92s mean=0.12s (0.17) vim -c ':quit' old: max=6.14s mean=4.03s (0.49) new: max=3.48s mean=2.41s (0.25) mplayer --help old: max=8.08s mean=5.74s (1.02) new: max=3.79s mean=1.32s (0.81) overall hash time (stdev): old: time=1192.30 (12.85) thruput=25.78mb/s (0.27) new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%) I also tested kernbench with regular IO streaming in the background to see whether the delayed activation of frequently used mapped file pages had a negative impact on performance in the presence of pressure on the inactive list. The patch made no significant difference in timing, neither for kernbench nor for the streaming IO throughput. The first patch submission raised concerns about the cost of the extra faults for actually activated pages on machines that have no hardware support for young page table entries. I created an artificial worst case scenario on an ARM machine with around 300MHz and 64MB of memory to figure out the dimensions involved. The test would mmap a file of 20MB, then 1. touch all its pages to fault them in 2. force one full scan cycle on the inactive file LRU -- old: mapping pages activated -- new: mapping pages inactive 3. touch the mapping pages again -- old and new: fault exceptions to set the young bits 4. force another full scan cycle on the inactive file LRU 5. touch the mapping pages one last time -- new: fault exceptions to set the young bits The test showed an overall increase of 6% in time over 100 iterations of the above (old: ~212sec, new: ~225sec). 13 secs total overhead / (100 * 5k pages), ignoring the execution time of the test itself, makes for about 25us overhead for every page that gets actually activated. Note: 1. File mapping the size of one third of main memory, _completely_ in active use across memory pressure - i.e., most pages referenced within one LRU cycle. This should be rare to non-existant, especially on such embedded setups. 2. Many huge activation batches. Those batches only occur when the working set fluctuates. If it changes completely between every full LRU cycle, you have problematic reclaim overhead anyway. 3. Access of activated pages at maximum speed: sequential loads from every single page without doing anything in between. In reality, the extra faults will get distributed between actual operations on the data. So even if a workload manages to get the VM into the situation of activating a third of memory in one go on such a setup, it will take 2.2 seconds instead 2.1 without the patch. Comparing the numbers (and my user-experience over several months), I think this change is an overall improvement to the VM. Patch 1 is only refactoring to break up that ugly compound conditional in shrink_page_list() and make it easy to document and add new checks in a readable fashion. Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not strictly related to #3, but it was in the original submission and is a net simplification, so I kept it. Patch 3 implements used-once detection of mapped file pages. This patch: Moving the big conditional into its own predicate function makes the code a bit easier to read and allows for better commenting on the checks one-by-one. This is just cleaning up, no semantics should have been changed. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:19 +08:00
PAGEREF_ACTIVATE,
};
static enum page_references page_check_references(struct page *page,
struct scan_control *sc)
{
vmscan: detect mapped file pages used only once The VM currently assumes that an inactive, mapped and referenced file page is in use and promotes it to the active list. However, every mapped file page starts out like this and thus a problem arises when workloads create a stream of such pages that are used only for a short time. By flooding the active list with those pages, the VM quickly gets into trouble finding eligible reclaim canditates. The result is long allocation latencies and eviction of the wrong pages. This patch reuses the PG_referenced page flag (used for unmapped file pages) to implement a usage detection that scales with the speed of LRU list cycling (i.e. memory pressure). If the scanner encounters those pages, the flag is set and the page cycled again on the inactive list. Only if it returns with another page table reference it is activated. Otherwise it is reclaimed as 'not recently used cache'. This effectively changes the minimum lifetime of a used-once mapped file page from a full memory cycle to an inactive list cycle, which allows it to occur in linear streams without affecting the stable working set of the system. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:22 +08:00
int referenced_ptes, referenced_page;
vmscan: factor out page reference checks The used-once mapped file page detection patchset. It is meant to help workloads with large amounts of shortly used file mappings, like rtorrent hashing a file or git when dealing with loose objects (git gc on a bigger site?). Right now, the VM activates referenced mapped file pages on first encounter on the inactive list and it takes a full memory cycle to reclaim them again. When those pages dominate memory, the system no longer has a meaningful notion of 'working set' and is required to give up the active list to make reclaim progress. Obviously, this results in rather bad scanning latencies and the wrong pages being reclaimed. This patch makes the VM be more careful about activating mapped file pages in the first place. The minimum granted lifetime without another memory access becomes an inactive list cycle instead of the full memory cycle, which is more natural given the mentioned loads. This test resembles a hashing rtorrent process. Sequentially, 32MB chunks of a file are mapped into memory, hashed (sha1) and unmapped again. While this happens, every 5 seconds a process is launched and its execution time taken: python2.4 -c 'import pydoc' old: max=2.31s mean=1.26s (0.34) new: max=1.25s mean=0.32s (0.32) find /etc -type f old: max=2.52s mean=1.44s (0.43) new: max=1.92s mean=0.12s (0.17) vim -c ':quit' old: max=6.14s mean=4.03s (0.49) new: max=3.48s mean=2.41s (0.25) mplayer --help old: max=8.08s mean=5.74s (1.02) new: max=3.79s mean=1.32s (0.81) overall hash time (stdev): old: time=1192.30 (12.85) thruput=25.78mb/s (0.27) new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%) I also tested kernbench with regular IO streaming in the background to see whether the delayed activation of frequently used mapped file pages had a negative impact on performance in the presence of pressure on the inactive list. The patch made no significant difference in timing, neither for kernbench nor for the streaming IO throughput. The first patch submission raised concerns about the cost of the extra faults for actually activated pages on machines that have no hardware support for young page table entries. I created an artificial worst case scenario on an ARM machine with around 300MHz and 64MB of memory to figure out the dimensions involved. The test would mmap a file of 20MB, then 1. touch all its pages to fault them in 2. force one full scan cycle on the inactive file LRU -- old: mapping pages activated -- new: mapping pages inactive 3. touch the mapping pages again -- old and new: fault exceptions to set the young bits 4. force another full scan cycle on the inactive file LRU 5. touch the mapping pages one last time -- new: fault exceptions to set the young bits The test showed an overall increase of 6% in time over 100 iterations of the above (old: ~212sec, new: ~225sec). 13 secs total overhead / (100 * 5k pages), ignoring the execution time of the test itself, makes for about 25us overhead for every page that gets actually activated. Note: 1. File mapping the size of one third of main memory, _completely_ in active use across memory pressure - i.e., most pages referenced within one LRU cycle. This should be rare to non-existant, especially on such embedded setups. 2. Many huge activation batches. Those batches only occur when the working set fluctuates. If it changes completely between every full LRU cycle, you have problematic reclaim overhead anyway. 3. Access of activated pages at maximum speed: sequential loads from every single page without doing anything in between. In reality, the extra faults will get distributed between actual operations on the data. So even if a workload manages to get the VM into the situation of activating a third of memory in one go on such a setup, it will take 2.2 seconds instead 2.1 without the patch. Comparing the numbers (and my user-experience over several months), I think this change is an overall improvement to the VM. Patch 1 is only refactoring to break up that ugly compound conditional in shrink_page_list() and make it easy to document and add new checks in a readable fashion. Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not strictly related to #3, but it was in the original submission and is a net simplification, so I kept it. Patch 3 implements used-once detection of mapped file pages. This patch: Moving the big conditional into its own predicate function makes the code a bit easier to read and allows for better commenting on the checks one-by-one. This is just cleaning up, no semantics should have been changed. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:19 +08:00
unsigned long vm_flags;
mm: memcg: count pte references from every member of the reclaimed hierarchy The rmap walker checking page table references has historically ignored references from VMAs that were not part of the memcg that was being reclaimed during memcg hard limit reclaim. When transitioning global reclaim to memcg hierarchy reclaim, I missed that bit and now references from outside a memcg are ignored even during global reclaim. Reverting back to traditional behaviour - count all references during global reclaim and only mind references of the memcg being reclaimed during limit reclaim would be one option. However, the more generic idea is to ignore references exactly then when they are outside the hierarchy that is currently under reclaim; because only then will their reclamation be of any use to help the pressure situation. It makes no sense to ignore references from a sibling memcg and then evict a page that will be immediately refaulted by that sibling which contributes to the same usage of the common ancestor under reclaim. The solution: make the rmap walker ignore references from VMAs that are not part of the hierarchy that is being reclaimed. Flat limit reclaim will stay the same, hierarchical limit reclaim will mind the references only to pages that the hierarchy owns. Global reclaim, since it reclaims from all memcgs, will be fixed to regard all references. [akpm@linux-foundation.org: name the args in the declaration] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Acked-by: Konstantin Khlebnikov<khlebnikov@openvz.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-30 06:06:25 +08:00
referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
&vm_flags);
vmscan: detect mapped file pages used only once The VM currently assumes that an inactive, mapped and referenced file page is in use and promotes it to the active list. However, every mapped file page starts out like this and thus a problem arises when workloads create a stream of such pages that are used only for a short time. By flooding the active list with those pages, the VM quickly gets into trouble finding eligible reclaim canditates. The result is long allocation latencies and eviction of the wrong pages. This patch reuses the PG_referenced page flag (used for unmapped file pages) to implement a usage detection that scales with the speed of LRU list cycling (i.e. memory pressure). If the scanner encounters those pages, the flag is set and the page cycled again on the inactive list. Only if it returns with another page table reference it is activated. Otherwise it is reclaimed as 'not recently used cache'. This effectively changes the minimum lifetime of a used-once mapped file page from a full memory cycle to an inactive list cycle, which allows it to occur in linear streams without affecting the stable working set of the system. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:22 +08:00
referenced_page = TestClearPageReferenced(page);
vmscan: factor out page reference checks The used-once mapped file page detection patchset. It is meant to help workloads with large amounts of shortly used file mappings, like rtorrent hashing a file or git when dealing with loose objects (git gc on a bigger site?). Right now, the VM activates referenced mapped file pages on first encounter on the inactive list and it takes a full memory cycle to reclaim them again. When those pages dominate memory, the system no longer has a meaningful notion of 'working set' and is required to give up the active list to make reclaim progress. Obviously, this results in rather bad scanning latencies and the wrong pages being reclaimed. This patch makes the VM be more careful about activating mapped file pages in the first place. The minimum granted lifetime without another memory access becomes an inactive list cycle instead of the full memory cycle, which is more natural given the mentioned loads. This test resembles a hashing rtorrent process. Sequentially, 32MB chunks of a file are mapped into memory, hashed (sha1) and unmapped again. While this happens, every 5 seconds a process is launched and its execution time taken: python2.4 -c 'import pydoc' old: max=2.31s mean=1.26s (0.34) new: max=1.25s mean=0.32s (0.32) find /etc -type f old: max=2.52s mean=1.44s (0.43) new: max=1.92s mean=0.12s (0.17) vim -c ':quit' old: max=6.14s mean=4.03s (0.49) new: max=3.48s mean=2.41s (0.25) mplayer --help old: max=8.08s mean=5.74s (1.02) new: max=3.79s mean=1.32s (0.81) overall hash time (stdev): old: time=1192.30 (12.85) thruput=25.78mb/s (0.27) new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%) I also tested kernbench with regular IO streaming in the background to see whether the delayed activation of frequently used mapped file pages had a negative impact on performance in the presence of pressure on the inactive list. The patch made no significant difference in timing, neither for kernbench nor for the streaming IO throughput. The first patch submission raised concerns about the cost of the extra faults for actually activated pages on machines that have no hardware support for young page table entries. I created an artificial worst case scenario on an ARM machine with around 300MHz and 64MB of memory to figure out the dimensions involved. The test would mmap a file of 20MB, then 1. touch all its pages to fault them in 2. force one full scan cycle on the inactive file LRU -- old: mapping pages activated -- new: mapping pages inactive 3. touch the mapping pages again -- old and new: fault exceptions to set the young bits 4. force another full scan cycle on the inactive file LRU 5. touch the mapping pages one last time -- new: fault exceptions to set the young bits The test showed an overall increase of 6% in time over 100 iterations of the above (old: ~212sec, new: ~225sec). 13 secs total overhead / (100 * 5k pages), ignoring the execution time of the test itself, makes for about 25us overhead for every page that gets actually activated. Note: 1. File mapping the size of one third of main memory, _completely_ in active use across memory pressure - i.e., most pages referenced within one LRU cycle. This should be rare to non-existant, especially on such embedded setups. 2. Many huge activation batches. Those batches only occur when the working set fluctuates. If it changes completely between every full LRU cycle, you have problematic reclaim overhead anyway. 3. Access of activated pages at maximum speed: sequential loads from every single page without doing anything in between. In reality, the extra faults will get distributed between actual operations on the data. So even if a workload manages to get the VM into the situation of activating a third of memory in one go on such a setup, it will take 2.2 seconds instead 2.1 without the patch. Comparing the numbers (and my user-experience over several months), I think this change is an overall improvement to the VM. Patch 1 is only refactoring to break up that ugly compound conditional in shrink_page_list() and make it easy to document and add new checks in a readable fashion. Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not strictly related to #3, but it was in the original submission and is a net simplification, so I kept it. Patch 3 implements used-once detection of mapped file pages. This patch: Moving the big conditional into its own predicate function makes the code a bit easier to read and allows for better commenting on the checks one-by-one. This is just cleaning up, no semantics should have been changed. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:19 +08:00
/*
* Mlock lost the isolation race with us. Let try_to_unmap()
* move the page to the unevictable list.
*/
if (vm_flags & VM_LOCKED)
return PAGEREF_RECLAIM;
vmscan: detect mapped file pages used only once The VM currently assumes that an inactive, mapped and referenced file page is in use and promotes it to the active list. However, every mapped file page starts out like this and thus a problem arises when workloads create a stream of such pages that are used only for a short time. By flooding the active list with those pages, the VM quickly gets into trouble finding eligible reclaim canditates. The result is long allocation latencies and eviction of the wrong pages. This patch reuses the PG_referenced page flag (used for unmapped file pages) to implement a usage detection that scales with the speed of LRU list cycling (i.e. memory pressure). If the scanner encounters those pages, the flag is set and the page cycled again on the inactive list. Only if it returns with another page table reference it is activated. Otherwise it is reclaimed as 'not recently used cache'. This effectively changes the minimum lifetime of a used-once mapped file page from a full memory cycle to an inactive list cycle, which allows it to occur in linear streams without affecting the stable working set of the system. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:22 +08:00
if (referenced_ptes) {
mm: consider all swapped back pages in used-once logic Commit 645747462435 ("vmscan: detect mapped file pages used only once") made mapped pages have another round in inactive list because they might be just short lived and so we could consider them again next time. This heuristic helps to reduce pressure on the active list with a streaming IO worklods. This patch fixes a regression introduced by this commit for heavy shmem based workloads because unlike Anon pages, which are excluded from this heuristic because they are usually long lived, shmem pages are handled as a regular page cache. This doesn't work quite well, unfortunately, if the workload is mostly backed by shmem (in memory database sitting on 80% of memory) with a streaming IO in the background (backup - up to 20% of memory). Anon inactive list is full of (dirty) shmem pages when watermarks are hit. Shmem pages are kept in the inactive list (they are referenced) in the first round and it is hard to reclaim anything else so we reach lower scanning priorities very quickly which leads to an excessive swap out. Let's fix this by excluding all swap backed pages (they tend to be long lived wrt. the regular page cache anyway) from used-once heuristic and rather activate them if they are referenced. The customer's workload is shmem backed database (80% of RAM) and they are measuring transactions/s with an IO in the background (20%). Transactions touch more or less random rows in the table. The transaction rate fell by a factor of 3 (in the worst case) because of commit 64574746. This patch restores the previous numbers. Signed-off-by: Michal Hocko <mhocko@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan@kernel.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: <stable@vger.kernel.org> [2.6.34+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-30 06:06:45 +08:00
if (PageSwapBacked(page))
vmscan: detect mapped file pages used only once The VM currently assumes that an inactive, mapped and referenced file page is in use and promotes it to the active list. However, every mapped file page starts out like this and thus a problem arises when workloads create a stream of such pages that are used only for a short time. By flooding the active list with those pages, the VM quickly gets into trouble finding eligible reclaim canditates. The result is long allocation latencies and eviction of the wrong pages. This patch reuses the PG_referenced page flag (used for unmapped file pages) to implement a usage detection that scales with the speed of LRU list cycling (i.e. memory pressure). If the scanner encounters those pages, the flag is set and the page cycled again on the inactive list. Only if it returns with another page table reference it is activated. Otherwise it is reclaimed as 'not recently used cache'. This effectively changes the minimum lifetime of a used-once mapped file page from a full memory cycle to an inactive list cycle, which allows it to occur in linear streams without affecting the stable working set of the system. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:22 +08:00
return PAGEREF_ACTIVATE;
/*
* All mapped pages start out with page table
* references from the instantiating fault, so we need
* to look twice if a mapped file page is used more
* than once.
*
* Mark it and spare it for another trip around the
* inactive list. Another page table reference will
* lead to its activation.
*
* Note: the mark is set for activated pages as well
* so that recently deactivated but used pages are
* quickly recovered.
*/
SetPageReferenced(page);
vmscan: promote shared file mapped pages Commit 645747462435 ("vmscan: detect mapped file pages used only once") greatly decreases lifetime of single-used mapped file pages. Unfortunately it also decreases life time of all shared mapped file pages. Because after commit bf3f3bc5e7347 ("mm: don't mark_page_accessed in fault path") page-fault handler does not mark page active or even referenced. Thus page_check_references() activates file page only if it was used twice while it stays in inactive list, meanwhile it activates anon pages after first access. Inactive list can be small enough, this way reclaimer can accidentally throw away any widely used page if it wasn't used twice in short period. After this patch page_check_references() also activate file mapped page at first inactive list scan if this page is already used multiple times via several ptes. I found this while trying to fix degragation in rhel6 (~2.6.32) from rhel5 (~2.6.18). There a complete mess with >100 web/mail/spam/ftp containers, they share all their files but there a lot of anonymous pages: ~500mb shared file mapped memory and 15-20Gb non-shared anonymous memory. In this situation major-pagefaults are very costly, because all containers share the same page. In my load kernel created a disproportionate pressure on the file memory, compared with the anonymous, they equaled only if I raise swappiness up to 150 =) These patches actually wasn't helped a lot in my problem, but I saw noticable (10-20 times) reduce in count and average time of major-pagefault in file-mapped areas. Actually both patches are fixes for commit v2.6.33-5448-g6457474, because it was aimed at one scenario (singly used pages), but it breaks the logic in other scenarios (shared and/or executable pages) Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Acked-by: Pekka Enberg <penberg@kernel.org> Acked-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-11 07:06:59 +08:00
if (referenced_page || referenced_ptes > 1)
vmscan: detect mapped file pages used only once The VM currently assumes that an inactive, mapped and referenced file page is in use and promotes it to the active list. However, every mapped file page starts out like this and thus a problem arises when workloads create a stream of such pages that are used only for a short time. By flooding the active list with those pages, the VM quickly gets into trouble finding eligible reclaim canditates. The result is long allocation latencies and eviction of the wrong pages. This patch reuses the PG_referenced page flag (used for unmapped file pages) to implement a usage detection that scales with the speed of LRU list cycling (i.e. memory pressure). If the scanner encounters those pages, the flag is set and the page cycled again on the inactive list. Only if it returns with another page table reference it is activated. Otherwise it is reclaimed as 'not recently used cache'. This effectively changes the minimum lifetime of a used-once mapped file page from a full memory cycle to an inactive list cycle, which allows it to occur in linear streams without affecting the stable working set of the system. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:22 +08:00
return PAGEREF_ACTIVATE;
/*
* Activate file-backed executable pages after first usage.
*/
if (vm_flags & VM_EXEC)
return PAGEREF_ACTIVATE;
vmscan: detect mapped file pages used only once The VM currently assumes that an inactive, mapped and referenced file page is in use and promotes it to the active list. However, every mapped file page starts out like this and thus a problem arises when workloads create a stream of such pages that are used only for a short time. By flooding the active list with those pages, the VM quickly gets into trouble finding eligible reclaim canditates. The result is long allocation latencies and eviction of the wrong pages. This patch reuses the PG_referenced page flag (used for unmapped file pages) to implement a usage detection that scales with the speed of LRU list cycling (i.e. memory pressure). If the scanner encounters those pages, the flag is set and the page cycled again on the inactive list. Only if it returns with another page table reference it is activated. Otherwise it is reclaimed as 'not recently used cache'. This effectively changes the minimum lifetime of a used-once mapped file page from a full memory cycle to an inactive list cycle, which allows it to occur in linear streams without affecting the stable working set of the system. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:22 +08:00
return PAGEREF_KEEP;
}
vmscan: factor out page reference checks The used-once mapped file page detection patchset. It is meant to help workloads with large amounts of shortly used file mappings, like rtorrent hashing a file or git when dealing with loose objects (git gc on a bigger site?). Right now, the VM activates referenced mapped file pages on first encounter on the inactive list and it takes a full memory cycle to reclaim them again. When those pages dominate memory, the system no longer has a meaningful notion of 'working set' and is required to give up the active list to make reclaim progress. Obviously, this results in rather bad scanning latencies and the wrong pages being reclaimed. This patch makes the VM be more careful about activating mapped file pages in the first place. The minimum granted lifetime without another memory access becomes an inactive list cycle instead of the full memory cycle, which is more natural given the mentioned loads. This test resembles a hashing rtorrent process. Sequentially, 32MB chunks of a file are mapped into memory, hashed (sha1) and unmapped again. While this happens, every 5 seconds a process is launched and its execution time taken: python2.4 -c 'import pydoc' old: max=2.31s mean=1.26s (0.34) new: max=1.25s mean=0.32s (0.32) find /etc -type f old: max=2.52s mean=1.44s (0.43) new: max=1.92s mean=0.12s (0.17) vim -c ':quit' old: max=6.14s mean=4.03s (0.49) new: max=3.48s mean=2.41s (0.25) mplayer --help old: max=8.08s mean=5.74s (1.02) new: max=3.79s mean=1.32s (0.81) overall hash time (stdev): old: time=1192.30 (12.85) thruput=25.78mb/s (0.27) new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%) I also tested kernbench with regular IO streaming in the background to see whether the delayed activation of frequently used mapped file pages had a negative impact on performance in the presence of pressure on the inactive list. The patch made no significant difference in timing, neither for kernbench nor for the streaming IO throughput. The first patch submission raised concerns about the cost of the extra faults for actually activated pages on machines that have no hardware support for young page table entries. I created an artificial worst case scenario on an ARM machine with around 300MHz and 64MB of memory to figure out the dimensions involved. The test would mmap a file of 20MB, then 1. touch all its pages to fault them in 2. force one full scan cycle on the inactive file LRU -- old: mapping pages activated -- new: mapping pages inactive 3. touch the mapping pages again -- old and new: fault exceptions to set the young bits 4. force another full scan cycle on the inactive file LRU 5. touch the mapping pages one last time -- new: fault exceptions to set the young bits The test showed an overall increase of 6% in time over 100 iterations of the above (old: ~212sec, new: ~225sec). 13 secs total overhead / (100 * 5k pages), ignoring the execution time of the test itself, makes for about 25us overhead for every page that gets actually activated. Note: 1. File mapping the size of one third of main memory, _completely_ in active use across memory pressure - i.e., most pages referenced within one LRU cycle. This should be rare to non-existant, especially on such embedded setups. 2. Many huge activation batches. Those batches only occur when the working set fluctuates. If it changes completely between every full LRU cycle, you have problematic reclaim overhead anyway. 3. Access of activated pages at maximum speed: sequential loads from every single page without doing anything in between. In reality, the extra faults will get distributed between actual operations on the data. So even if a workload manages to get the VM into the situation of activating a third of memory in one go on such a setup, it will take 2.2 seconds instead 2.1 without the patch. Comparing the numbers (and my user-experience over several months), I think this change is an overall improvement to the VM. Patch 1 is only refactoring to break up that ugly compound conditional in shrink_page_list() and make it easy to document and add new checks in a readable fashion. Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not strictly related to #3, but it was in the original submission and is a net simplification, so I kept it. Patch 3 implements used-once detection of mapped file pages. This patch: Moving the big conditional into its own predicate function makes the code a bit easier to read and allows for better commenting on the checks one-by-one. This is just cleaning up, no semantics should have been changed. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:19 +08:00
/* Reclaim if clean, defer dirty pages to writeback */
if (referenced_page && !PageSwapBacked(page))
vmscan: detect mapped file pages used only once The VM currently assumes that an inactive, mapped and referenced file page is in use and promotes it to the active list. However, every mapped file page starts out like this and thus a problem arises when workloads create a stream of such pages that are used only for a short time. By flooding the active list with those pages, the VM quickly gets into trouble finding eligible reclaim canditates. The result is long allocation latencies and eviction of the wrong pages. This patch reuses the PG_referenced page flag (used for unmapped file pages) to implement a usage detection that scales with the speed of LRU list cycling (i.e. memory pressure). If the scanner encounters those pages, the flag is set and the page cycled again on the inactive list. Only if it returns with another page table reference it is activated. Otherwise it is reclaimed as 'not recently used cache'. This effectively changes the minimum lifetime of a used-once mapped file page from a full memory cycle to an inactive list cycle, which allows it to occur in linear streams without affecting the stable working set of the system. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:22 +08:00
return PAGEREF_RECLAIM_CLEAN;
return PAGEREF_RECLAIM;
vmscan: factor out page reference checks The used-once mapped file page detection patchset. It is meant to help workloads with large amounts of shortly used file mappings, like rtorrent hashing a file or git when dealing with loose objects (git gc on a bigger site?). Right now, the VM activates referenced mapped file pages on first encounter on the inactive list and it takes a full memory cycle to reclaim them again. When those pages dominate memory, the system no longer has a meaningful notion of 'working set' and is required to give up the active list to make reclaim progress. Obviously, this results in rather bad scanning latencies and the wrong pages being reclaimed. This patch makes the VM be more careful about activating mapped file pages in the first place. The minimum granted lifetime without another memory access becomes an inactive list cycle instead of the full memory cycle, which is more natural given the mentioned loads. This test resembles a hashing rtorrent process. Sequentially, 32MB chunks of a file are mapped into memory, hashed (sha1) and unmapped again. While this happens, every 5 seconds a process is launched and its execution time taken: python2.4 -c 'import pydoc' old: max=2.31s mean=1.26s (0.34) new: max=1.25s mean=0.32s (0.32) find /etc -type f old: max=2.52s mean=1.44s (0.43) new: max=1.92s mean=0.12s (0.17) vim -c ':quit' old: max=6.14s mean=4.03s (0.49) new: max=3.48s mean=2.41s (0.25) mplayer --help old: max=8.08s mean=5.74s (1.02) new: max=3.79s mean=1.32s (0.81) overall hash time (stdev): old: time=1192.30 (12.85) thruput=25.78mb/s (0.27) new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%) I also tested kernbench with regular IO streaming in the background to see whether the delayed activation of frequently used mapped file pages had a negative impact on performance in the presence of pressure on the inactive list. The patch made no significant difference in timing, neither for kernbench nor for the streaming IO throughput. The first patch submission raised concerns about the cost of the extra faults for actually activated pages on machines that have no hardware support for young page table entries. I created an artificial worst case scenario on an ARM machine with around 300MHz and 64MB of memory to figure out the dimensions involved. The test would mmap a file of 20MB, then 1. touch all its pages to fault them in 2. force one full scan cycle on the inactive file LRU -- old: mapping pages activated -- new: mapping pages inactive 3. touch the mapping pages again -- old and new: fault exceptions to set the young bits 4. force another full scan cycle on the inactive file LRU 5. touch the mapping pages one last time -- new: fault exceptions to set the young bits The test showed an overall increase of 6% in time over 100 iterations of the above (old: ~212sec, new: ~225sec). 13 secs total overhead / (100 * 5k pages), ignoring the execution time of the test itself, makes for about 25us overhead for every page that gets actually activated. Note: 1. File mapping the size of one third of main memory, _completely_ in active use across memory pressure - i.e., most pages referenced within one LRU cycle. This should be rare to non-existant, especially on such embedded setups. 2. Many huge activation batches. Those batches only occur when the working set fluctuates. If it changes completely between every full LRU cycle, you have problematic reclaim overhead anyway. 3. Access of activated pages at maximum speed: sequential loads from every single page without doing anything in between. In reality, the extra faults will get distributed between actual operations on the data. So even if a workload manages to get the VM into the situation of activating a third of memory in one go on such a setup, it will take 2.2 seconds instead 2.1 without the patch. Comparing the numbers (and my user-experience over several months), I think this change is an overall improvement to the VM. Patch 1 is only refactoring to break up that ugly compound conditional in shrink_page_list() and make it easy to document and add new checks in a readable fashion. Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not strictly related to #3, but it was in the original submission and is a net simplification, so I kept it. Patch 3 implements used-once detection of mapped file pages. This patch: Moving the big conditional into its own predicate function makes the code a bit easier to read and allows for better commenting on the checks one-by-one. This is just cleaning up, no semantics should have been changed. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:19 +08:00
}
/*
* shrink_page_list() returns the number of reclaimed pages
*/
static unsigned long shrink_page_list(struct list_head *page_list,
struct zone *zone,
struct scan_control *sc,
mm: vmscan: throttle reclaim if encountering too many dirty pages under writeback Workloads that are allocating frequently and writing files place a large number of dirty pages on the LRU. With use-once logic, it is possible for them to reach the end of the LRU quickly requiring the reclaimer to scan more to find clean pages. Ordinarily, processes that are dirtying memory will get throttled by dirty balancing but this is a global heuristic and does not take into account that LRUs are maintained on a per-zone basis. This can lead to a situation whereby reclaim is scanning heavily, skipping over a large number of pages under writeback and recycling them around the LRU consuming CPU. This patch checks how many of the number of pages isolated from the LRU were dirty and under writeback. If a percentage of them under writeback, the process will be throttled if a backing device or the zone is congested. Note that this applies whether it is anonymous or file-backed pages that are under writeback meaning that swapping is potentially throttled. This is intentional due to the fact if the swap device is congested, scanning more pages and dispatching more IO is not going to help matters. The percentage that must be in writeback depends on the priority. At default priority, all of them must be dirty. At DEF_PRIORITY-1, 50% of them must be, DEF_PRIORITY-2, 25% etc. i.e. as pressure increases the greater the likelihood the process will get throttled to allow the flusher threads to make some progress. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Johannes Weiner <jweiner@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Alex Elder <aelder@sgi.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 08:07:56 +08:00
unsigned long *ret_nr_dirty,
unsigned long *ret_nr_writeback)
{
LIST_HEAD(ret_pages);
LIST_HEAD(free_pages);
int pgactivate = 0;
unsigned long nr_dirty = 0;
unsigned long nr_congested = 0;
unsigned long nr_reclaimed = 0;
mm: vmscan: throttle reclaim if encountering too many dirty pages under writeback Workloads that are allocating frequently and writing files place a large number of dirty pages on the LRU. With use-once logic, it is possible for them to reach the end of the LRU quickly requiring the reclaimer to scan more to find clean pages. Ordinarily, processes that are dirtying memory will get throttled by dirty balancing but this is a global heuristic and does not take into account that LRUs are maintained on a per-zone basis. This can lead to a situation whereby reclaim is scanning heavily, skipping over a large number of pages under writeback and recycling them around the LRU consuming CPU. This patch checks how many of the number of pages isolated from the LRU were dirty and under writeback. If a percentage of them under writeback, the process will be throttled if a backing device or the zone is congested. Note that this applies whether it is anonymous or file-backed pages that are under writeback meaning that swapping is potentially throttled. This is intentional due to the fact if the swap device is congested, scanning more pages and dispatching more IO is not going to help matters. The percentage that must be in writeback depends on the priority. At default priority, all of them must be dirty. At DEF_PRIORITY-1, 50% of them must be, DEF_PRIORITY-2, 25% etc. i.e. as pressure increases the greater the likelihood the process will get throttled to allow the flusher threads to make some progress. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Johannes Weiner <jweiner@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Alex Elder <aelder@sgi.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 08:07:56 +08:00
unsigned long nr_writeback = 0;
cond_resched();
mem_cgroup_uncharge_start();
while (!list_empty(page_list)) {
vmscan: factor out page reference checks The used-once mapped file page detection patchset. It is meant to help workloads with large amounts of shortly used file mappings, like rtorrent hashing a file or git when dealing with loose objects (git gc on a bigger site?). Right now, the VM activates referenced mapped file pages on first encounter on the inactive list and it takes a full memory cycle to reclaim them again. When those pages dominate memory, the system no longer has a meaningful notion of 'working set' and is required to give up the active list to make reclaim progress. Obviously, this results in rather bad scanning latencies and the wrong pages being reclaimed. This patch makes the VM be more careful about activating mapped file pages in the first place. The minimum granted lifetime without another memory access becomes an inactive list cycle instead of the full memory cycle, which is more natural given the mentioned loads. This test resembles a hashing rtorrent process. Sequentially, 32MB chunks of a file are mapped into memory, hashed (sha1) and unmapped again. While this happens, every 5 seconds a process is launched and its execution time taken: python2.4 -c 'import pydoc' old: max=2.31s mean=1.26s (0.34) new: max=1.25s mean=0.32s (0.32) find /etc -type f old: max=2.52s mean=1.44s (0.43) new: max=1.92s mean=0.12s (0.17) vim -c ':quit' old: max=6.14s mean=4.03s (0.49) new: max=3.48s mean=2.41s (0.25) mplayer --help old: max=8.08s mean=5.74s (1.02) new: max=3.79s mean=1.32s (0.81) overall hash time (stdev): old: time=1192.30 (12.85) thruput=25.78mb/s (0.27) new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%) I also tested kernbench with regular IO streaming in the background to see whether the delayed activation of frequently used mapped file pages had a negative impact on performance in the presence of pressure on the inactive list. The patch made no significant difference in timing, neither for kernbench nor for the streaming IO throughput. The first patch submission raised concerns about the cost of the extra faults for actually activated pages on machines that have no hardware support for young page table entries. I created an artificial worst case scenario on an ARM machine with around 300MHz and 64MB of memory to figure out the dimensions involved. The test would mmap a file of 20MB, then 1. touch all its pages to fault them in 2. force one full scan cycle on the inactive file LRU -- old: mapping pages activated -- new: mapping pages inactive 3. touch the mapping pages again -- old and new: fault exceptions to set the young bits 4. force another full scan cycle on the inactive file LRU 5. touch the mapping pages one last time -- new: fault exceptions to set the young bits The test showed an overall increase of 6% in time over 100 iterations of the above (old: ~212sec, new: ~225sec). 13 secs total overhead / (100 * 5k pages), ignoring the execution time of the test itself, makes for about 25us overhead for every page that gets actually activated. Note: 1. File mapping the size of one third of main memory, _completely_ in active use across memory pressure - i.e., most pages referenced within one LRU cycle. This should be rare to non-existant, especially on such embedded setups. 2. Many huge activation batches. Those batches only occur when the working set fluctuates. If it changes completely between every full LRU cycle, you have problematic reclaim overhead anyway. 3. Access of activated pages at maximum speed: sequential loads from every single page without doing anything in between. In reality, the extra faults will get distributed between actual operations on the data. So even if a workload manages to get the VM into the situation of activating a third of memory in one go on such a setup, it will take 2.2 seconds instead 2.1 without the patch. Comparing the numbers (and my user-experience over several months), I think this change is an overall improvement to the VM. Patch 1 is only refactoring to break up that ugly compound conditional in shrink_page_list() and make it easy to document and add new checks in a readable fashion. Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not strictly related to #3, but it was in the original submission and is a net simplification, so I kept it. Patch 3 implements used-once detection of mapped file pages. This patch: Moving the big conditional into its own predicate function makes the code a bit easier to read and allows for better commenting on the checks one-by-one. This is just cleaning up, no semantics should have been changed. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:19 +08:00
enum page_references references;
struct address_space *mapping;
struct page *page;
int may_enter_fs;
cond_resched();
page = lru_to_page(page_list);
list_del(&page->lru);
if (!trylock_page(page))
goto keep;
VM_BUG_ON(PageActive(page));
VM_BUG_ON(page_zone(page) != zone);
sc->nr_scanned++;
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
if (unlikely(!page_evictable(page, NULL)))
goto cull_mlocked;
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
if (!sc->may_unmap && page_mapped(page))
goto keep_locked;
/* Double the slab pressure for mapped and swapcache pages */
if (page_mapped(page) || PageSwapCache(page))
sc->nr_scanned++;
may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
if (PageWriteback(page)) {
memcg: prevent OOM with too many dirty pages The current implementation of dirty pages throttling is not memcg aware which makes it easy to have memcg LRUs full of dirty pages. Without throttling, these LRUs can be scanned faster than the rate of writeback, leading to memcg OOM conditions when the hard limit is small. This patch fixes the problem by throttling the allocating process (possibly a writer) during the hard limit reclaim by waiting on PageReclaim pages. We are waiting only for PageReclaim pages because those are the pages that made one full round over LRU and that means that the writeback is much slower than scanning. The solution is far from being ideal - long term solution is memcg aware dirty throttling - but it is meant to be a band aid until we have a real fix. We are seeing this happening during nightly backups which are placed into containers to prevent from eviction of the real working set. The change affects only memcg reclaim and only when we encounter PageReclaim pages which is a signal that the reclaim doesn't catch up on with the writers so somebody should be throttled. This could be potentially unfair because it could be somebody else from the group who gets throttled on behalf of the writer but as writers need to allocate as well and they allocate in higher rate the probability that only innocent processes would be penalized is not that high. I have tested this change by a simple dd copying /dev/zero to tmpfs or ext3 running under small memcg (1G copy under 5M, 60M, 300M and 2G containers) and dd got killed by OOM killer every time. With the patch I could run the dd with the same size under 5M controller without any OOM. The issue is more visible with slower devices for output. * With the patch ================ * tmpfs size=2G --------------- $ vim cgroup_cache_oom_test.sh $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.4049 s, 34.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 31.4561 s, 33.3 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.4618 s, 51.2 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.42172 s, 738 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 27.9547 s, 37.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.3221 s, 34.6 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.5764 s, 42.7 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 3.35828 s, 312 MB/s * Without the patch =================== * tmpfs size=2G --------------- $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4668 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 25.4989 s, 41.1 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.3928 s, 43.0 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.49797 s, 700 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4689 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group ./cgroup_cache_oom_test.sh: line 46: 4692 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.248 s, 51.8 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 2.85201 s, 368 MB/s [akpm@linux-foundation.org: tweak changelog, reordered the test to optimize for CONFIG_CGROUP_MEM_RES_CTLR=n] [hughd@google.com: fix deadlock with loop driver] Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:55 +08:00
/*
* memcg doesn't have any dirty pages throttling so we
* could easily OOM just because too many pages are in
memcg: further prevent OOM with too many dirty pages The may_enter_fs test turns out to be too restrictive: though I saw no problem with it when testing on 3.5-rc6, it very soon OOMed when I tested on 3.5-rc6-mm1. I don't know what the difference there is, perhaps I just slightly changed the way I started off the testing: dd if=/dev/zero of=/mnt/temp bs=1M count=1024; rm -f /mnt/temp; sync repeatedly, in 20M memory.limit_in_bytes cgroup to ext4 on USB stick. ext4 (and gfs2 and xfs) turn out to allocate new pages for writing with AOP_FLAG_NOFS: that seems a little worrying, and it's unclear to me why the transaction needs to be started even before allocating pagecache memory. But it may not be worth worrying about these days: if direct reclaim avoids FS writeback, does __GFP_FS now mean anything? Anyway, we insisted on the may_enter_fs test to avoid hangs with the loop device; but since that also masks off __GFP_IO, we can test for __GFP_IO directly, ignoring may_enter_fs and __GFP_FS. But even so, the test still OOMs sometimes: when originally testing on 3.5-rc6, it OOMed about one time in five or ten; when testing just now on 3.5-rc6-mm1, it OOMed on the first iteration. This residual problem comes from an accumulation of pages under ordinary writeback, not marked PageReclaim, so rightly not causing the memcg check to wait on their writeback: these too can prevent shrink_page_list() from freeing any pages, so many times that memcg reclaim fails and OOMs. Deal with these in the same way as direct reclaim now deals with dirty FS pages: mark them PageReclaim. It is appropriate to rotate these to tail of list when writepage completes, but more importantly, the PageReclaim flag makes memcg reclaim wait on them if encountered again. Increment NR_VMSCAN_IMMEDIATE? That's arguable: I chose not. Setting PageReclaim here may occasionally race with end_page_writeback() clearing it: lru_deactivate_fn() already faced the same race, and correctly concluded that the window is small and the issue non-critical. With these changes, the test runs indefinitely without OOMing on ext4, ext3 and ext2: I'll move on to test with other filesystems later. Trivia: invert conditions for a clearer block without an else, and goto keep_locked to do the unlock_page. Signed-off-by: Hugh Dickins <hughd@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:59 +08:00
* writeback and there is nothing else to reclaim.
memcg: prevent OOM with too many dirty pages The current implementation of dirty pages throttling is not memcg aware which makes it easy to have memcg LRUs full of dirty pages. Without throttling, these LRUs can be scanned faster than the rate of writeback, leading to memcg OOM conditions when the hard limit is small. This patch fixes the problem by throttling the allocating process (possibly a writer) during the hard limit reclaim by waiting on PageReclaim pages. We are waiting only for PageReclaim pages because those are the pages that made one full round over LRU and that means that the writeback is much slower than scanning. The solution is far from being ideal - long term solution is memcg aware dirty throttling - but it is meant to be a band aid until we have a real fix. We are seeing this happening during nightly backups which are placed into containers to prevent from eviction of the real working set. The change affects only memcg reclaim and only when we encounter PageReclaim pages which is a signal that the reclaim doesn't catch up on with the writers so somebody should be throttled. This could be potentially unfair because it could be somebody else from the group who gets throttled on behalf of the writer but as writers need to allocate as well and they allocate in higher rate the probability that only innocent processes would be penalized is not that high. I have tested this change by a simple dd copying /dev/zero to tmpfs or ext3 running under small memcg (1G copy under 5M, 60M, 300M and 2G containers) and dd got killed by OOM killer every time. With the patch I could run the dd with the same size under 5M controller without any OOM. The issue is more visible with slower devices for output. * With the patch ================ * tmpfs size=2G --------------- $ vim cgroup_cache_oom_test.sh $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.4049 s, 34.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 31.4561 s, 33.3 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.4618 s, 51.2 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.42172 s, 738 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 27.9547 s, 37.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.3221 s, 34.6 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.5764 s, 42.7 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 3.35828 s, 312 MB/s * Without the patch =================== * tmpfs size=2G --------------- $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4668 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 25.4989 s, 41.1 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.3928 s, 43.0 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.49797 s, 700 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4689 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group ./cgroup_cache_oom_test.sh: line 46: 4692 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.248 s, 51.8 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 2.85201 s, 368 MB/s [akpm@linux-foundation.org: tweak changelog, reordered the test to optimize for CONFIG_CGROUP_MEM_RES_CTLR=n] [hughd@google.com: fix deadlock with loop driver] Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:55 +08:00
*
memcg: further prevent OOM with too many dirty pages The may_enter_fs test turns out to be too restrictive: though I saw no problem with it when testing on 3.5-rc6, it very soon OOMed when I tested on 3.5-rc6-mm1. I don't know what the difference there is, perhaps I just slightly changed the way I started off the testing: dd if=/dev/zero of=/mnt/temp bs=1M count=1024; rm -f /mnt/temp; sync repeatedly, in 20M memory.limit_in_bytes cgroup to ext4 on USB stick. ext4 (and gfs2 and xfs) turn out to allocate new pages for writing with AOP_FLAG_NOFS: that seems a little worrying, and it's unclear to me why the transaction needs to be started even before allocating pagecache memory. But it may not be worth worrying about these days: if direct reclaim avoids FS writeback, does __GFP_FS now mean anything? Anyway, we insisted on the may_enter_fs test to avoid hangs with the loop device; but since that also masks off __GFP_IO, we can test for __GFP_IO directly, ignoring may_enter_fs and __GFP_FS. But even so, the test still OOMs sometimes: when originally testing on 3.5-rc6, it OOMed about one time in five or ten; when testing just now on 3.5-rc6-mm1, it OOMed on the first iteration. This residual problem comes from an accumulation of pages under ordinary writeback, not marked PageReclaim, so rightly not causing the memcg check to wait on their writeback: these too can prevent shrink_page_list() from freeing any pages, so many times that memcg reclaim fails and OOMs. Deal with these in the same way as direct reclaim now deals with dirty FS pages: mark them PageReclaim. It is appropriate to rotate these to tail of list when writepage completes, but more importantly, the PageReclaim flag makes memcg reclaim wait on them if encountered again. Increment NR_VMSCAN_IMMEDIATE? That's arguable: I chose not. Setting PageReclaim here may occasionally race with end_page_writeback() clearing it: lru_deactivate_fn() already faced the same race, and correctly concluded that the window is small and the issue non-critical. With these changes, the test runs indefinitely without OOMing on ext4, ext3 and ext2: I'll move on to test with other filesystems later. Trivia: invert conditions for a clearer block without an else, and goto keep_locked to do the unlock_page. Signed-off-by: Hugh Dickins <hughd@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:59 +08:00
* Check __GFP_IO, certainly because a loop driver
memcg: prevent OOM with too many dirty pages The current implementation of dirty pages throttling is not memcg aware which makes it easy to have memcg LRUs full of dirty pages. Without throttling, these LRUs can be scanned faster than the rate of writeback, leading to memcg OOM conditions when the hard limit is small. This patch fixes the problem by throttling the allocating process (possibly a writer) during the hard limit reclaim by waiting on PageReclaim pages. We are waiting only for PageReclaim pages because those are the pages that made one full round over LRU and that means that the writeback is much slower than scanning. The solution is far from being ideal - long term solution is memcg aware dirty throttling - but it is meant to be a band aid until we have a real fix. We are seeing this happening during nightly backups which are placed into containers to prevent from eviction of the real working set. The change affects only memcg reclaim and only when we encounter PageReclaim pages which is a signal that the reclaim doesn't catch up on with the writers so somebody should be throttled. This could be potentially unfair because it could be somebody else from the group who gets throttled on behalf of the writer but as writers need to allocate as well and they allocate in higher rate the probability that only innocent processes would be penalized is not that high. I have tested this change by a simple dd copying /dev/zero to tmpfs or ext3 running under small memcg (1G copy under 5M, 60M, 300M and 2G containers) and dd got killed by OOM killer every time. With the patch I could run the dd with the same size under 5M controller without any OOM. The issue is more visible with slower devices for output. * With the patch ================ * tmpfs size=2G --------------- $ vim cgroup_cache_oom_test.sh $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.4049 s, 34.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 31.4561 s, 33.3 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.4618 s, 51.2 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.42172 s, 738 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 27.9547 s, 37.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.3221 s, 34.6 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.5764 s, 42.7 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 3.35828 s, 312 MB/s * Without the patch =================== * tmpfs size=2G --------------- $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4668 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 25.4989 s, 41.1 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.3928 s, 43.0 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.49797 s, 700 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4689 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group ./cgroup_cache_oom_test.sh: line 46: 4692 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.248 s, 51.8 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 2.85201 s, 368 MB/s [akpm@linux-foundation.org: tweak changelog, reordered the test to optimize for CONFIG_CGROUP_MEM_RES_CTLR=n] [hughd@google.com: fix deadlock with loop driver] Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:55 +08:00
* thread might enter reclaim, and deadlock if it waits
* on a page for which it is needed to do the write
* (loop masks off __GFP_IO|__GFP_FS for this reason);
* but more thought would probably show more reasons.
memcg: further prevent OOM with too many dirty pages The may_enter_fs test turns out to be too restrictive: though I saw no problem with it when testing on 3.5-rc6, it very soon OOMed when I tested on 3.5-rc6-mm1. I don't know what the difference there is, perhaps I just slightly changed the way I started off the testing: dd if=/dev/zero of=/mnt/temp bs=1M count=1024; rm -f /mnt/temp; sync repeatedly, in 20M memory.limit_in_bytes cgroup to ext4 on USB stick. ext4 (and gfs2 and xfs) turn out to allocate new pages for writing with AOP_FLAG_NOFS: that seems a little worrying, and it's unclear to me why the transaction needs to be started even before allocating pagecache memory. But it may not be worth worrying about these days: if direct reclaim avoids FS writeback, does __GFP_FS now mean anything? Anyway, we insisted on the may_enter_fs test to avoid hangs with the loop device; but since that also masks off __GFP_IO, we can test for __GFP_IO directly, ignoring may_enter_fs and __GFP_FS. But even so, the test still OOMs sometimes: when originally testing on 3.5-rc6, it OOMed about one time in five or ten; when testing just now on 3.5-rc6-mm1, it OOMed on the first iteration. This residual problem comes from an accumulation of pages under ordinary writeback, not marked PageReclaim, so rightly not causing the memcg check to wait on their writeback: these too can prevent shrink_page_list() from freeing any pages, so many times that memcg reclaim fails and OOMs. Deal with these in the same way as direct reclaim now deals with dirty FS pages: mark them PageReclaim. It is appropriate to rotate these to tail of list when writepage completes, but more importantly, the PageReclaim flag makes memcg reclaim wait on them if encountered again. Increment NR_VMSCAN_IMMEDIATE? That's arguable: I chose not. Setting PageReclaim here may occasionally race with end_page_writeback() clearing it: lru_deactivate_fn() already faced the same race, and correctly concluded that the window is small and the issue non-critical. With these changes, the test runs indefinitely without OOMing on ext4, ext3 and ext2: I'll move on to test with other filesystems later. Trivia: invert conditions for a clearer block without an else, and goto keep_locked to do the unlock_page. Signed-off-by: Hugh Dickins <hughd@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:59 +08:00
*
* Don't require __GFP_FS, since we're not going into
* the FS, just waiting on its writeback completion.
* Worryingly, ext4 gfs2 and xfs allocate pages with
* grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so
* testing may_enter_fs here is liable to OOM on them.
memcg: prevent OOM with too many dirty pages The current implementation of dirty pages throttling is not memcg aware which makes it easy to have memcg LRUs full of dirty pages. Without throttling, these LRUs can be scanned faster than the rate of writeback, leading to memcg OOM conditions when the hard limit is small. This patch fixes the problem by throttling the allocating process (possibly a writer) during the hard limit reclaim by waiting on PageReclaim pages. We are waiting only for PageReclaim pages because those are the pages that made one full round over LRU and that means that the writeback is much slower than scanning. The solution is far from being ideal - long term solution is memcg aware dirty throttling - but it is meant to be a band aid until we have a real fix. We are seeing this happening during nightly backups which are placed into containers to prevent from eviction of the real working set. The change affects only memcg reclaim and only when we encounter PageReclaim pages which is a signal that the reclaim doesn't catch up on with the writers so somebody should be throttled. This could be potentially unfair because it could be somebody else from the group who gets throttled on behalf of the writer but as writers need to allocate as well and they allocate in higher rate the probability that only innocent processes would be penalized is not that high. I have tested this change by a simple dd copying /dev/zero to tmpfs or ext3 running under small memcg (1G copy under 5M, 60M, 300M and 2G containers) and dd got killed by OOM killer every time. With the patch I could run the dd with the same size under 5M controller without any OOM. The issue is more visible with slower devices for output. * With the patch ================ * tmpfs size=2G --------------- $ vim cgroup_cache_oom_test.sh $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.4049 s, 34.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 31.4561 s, 33.3 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.4618 s, 51.2 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.42172 s, 738 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 27.9547 s, 37.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.3221 s, 34.6 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.5764 s, 42.7 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 3.35828 s, 312 MB/s * Without the patch =================== * tmpfs size=2G --------------- $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4668 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 25.4989 s, 41.1 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.3928 s, 43.0 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.49797 s, 700 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4689 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group ./cgroup_cache_oom_test.sh: line 46: 4692 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.248 s, 51.8 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 2.85201 s, 368 MB/s [akpm@linux-foundation.org: tweak changelog, reordered the test to optimize for CONFIG_CGROUP_MEM_RES_CTLR=n] [hughd@google.com: fix deadlock with loop driver] Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:55 +08:00
*/
memcg: further prevent OOM with too many dirty pages The may_enter_fs test turns out to be too restrictive: though I saw no problem with it when testing on 3.5-rc6, it very soon OOMed when I tested on 3.5-rc6-mm1. I don't know what the difference there is, perhaps I just slightly changed the way I started off the testing: dd if=/dev/zero of=/mnt/temp bs=1M count=1024; rm -f /mnt/temp; sync repeatedly, in 20M memory.limit_in_bytes cgroup to ext4 on USB stick. ext4 (and gfs2 and xfs) turn out to allocate new pages for writing with AOP_FLAG_NOFS: that seems a little worrying, and it's unclear to me why the transaction needs to be started even before allocating pagecache memory. But it may not be worth worrying about these days: if direct reclaim avoids FS writeback, does __GFP_FS now mean anything? Anyway, we insisted on the may_enter_fs test to avoid hangs with the loop device; but since that also masks off __GFP_IO, we can test for __GFP_IO directly, ignoring may_enter_fs and __GFP_FS. But even so, the test still OOMs sometimes: when originally testing on 3.5-rc6, it OOMed about one time in five or ten; when testing just now on 3.5-rc6-mm1, it OOMed on the first iteration. This residual problem comes from an accumulation of pages under ordinary writeback, not marked PageReclaim, so rightly not causing the memcg check to wait on their writeback: these too can prevent shrink_page_list() from freeing any pages, so many times that memcg reclaim fails and OOMs. Deal with these in the same way as direct reclaim now deals with dirty FS pages: mark them PageReclaim. It is appropriate to rotate these to tail of list when writepage completes, but more importantly, the PageReclaim flag makes memcg reclaim wait on them if encountered again. Increment NR_VMSCAN_IMMEDIATE? That's arguable: I chose not. Setting PageReclaim here may occasionally race with end_page_writeback() clearing it: lru_deactivate_fn() already faced the same race, and correctly concluded that the window is small and the issue non-critical. With these changes, the test runs indefinitely without OOMing on ext4, ext3 and ext2: I'll move on to test with other filesystems later. Trivia: invert conditions for a clearer block without an else, and goto keep_locked to do the unlock_page. Signed-off-by: Hugh Dickins <hughd@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:59 +08:00
if (global_reclaim(sc) ||
!PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) {
/*
* This is slightly racy - end_page_writeback()
* might have just cleared PageReclaim, then
* setting PageReclaim here end up interpreted
* as PageReadahead - but that does not matter
* enough to care. What we do want is for this
* page to have PageReclaim set next time memcg
* reclaim reaches the tests above, so it will
* then wait_on_page_writeback() to avoid OOM;
* and it's also appropriate in global reclaim.
*/
SetPageReclaim(page);
memcg: prevent OOM with too many dirty pages The current implementation of dirty pages throttling is not memcg aware which makes it easy to have memcg LRUs full of dirty pages. Without throttling, these LRUs can be scanned faster than the rate of writeback, leading to memcg OOM conditions when the hard limit is small. This patch fixes the problem by throttling the allocating process (possibly a writer) during the hard limit reclaim by waiting on PageReclaim pages. We are waiting only for PageReclaim pages because those are the pages that made one full round over LRU and that means that the writeback is much slower than scanning. The solution is far from being ideal - long term solution is memcg aware dirty throttling - but it is meant to be a band aid until we have a real fix. We are seeing this happening during nightly backups which are placed into containers to prevent from eviction of the real working set. The change affects only memcg reclaim and only when we encounter PageReclaim pages which is a signal that the reclaim doesn't catch up on with the writers so somebody should be throttled. This could be potentially unfair because it could be somebody else from the group who gets throttled on behalf of the writer but as writers need to allocate as well and they allocate in higher rate the probability that only innocent processes would be penalized is not that high. I have tested this change by a simple dd copying /dev/zero to tmpfs or ext3 running under small memcg (1G copy under 5M, 60M, 300M and 2G containers) and dd got killed by OOM killer every time. With the patch I could run the dd with the same size under 5M controller without any OOM. The issue is more visible with slower devices for output. * With the patch ================ * tmpfs size=2G --------------- $ vim cgroup_cache_oom_test.sh $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.4049 s, 34.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 31.4561 s, 33.3 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.4618 s, 51.2 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.42172 s, 738 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 27.9547 s, 37.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.3221 s, 34.6 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.5764 s, 42.7 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 3.35828 s, 312 MB/s * Without the patch =================== * tmpfs size=2G --------------- $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4668 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 25.4989 s, 41.1 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.3928 s, 43.0 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.49797 s, 700 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4689 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group ./cgroup_cache_oom_test.sh: line 46: 4692 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.248 s, 51.8 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 2.85201 s, 368 MB/s [akpm@linux-foundation.org: tweak changelog, reordered the test to optimize for CONFIG_CGROUP_MEM_RES_CTLR=n] [hughd@google.com: fix deadlock with loop driver] Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:55 +08:00
nr_writeback++;
memcg: further prevent OOM with too many dirty pages The may_enter_fs test turns out to be too restrictive: though I saw no problem with it when testing on 3.5-rc6, it very soon OOMed when I tested on 3.5-rc6-mm1. I don't know what the difference there is, perhaps I just slightly changed the way I started off the testing: dd if=/dev/zero of=/mnt/temp bs=1M count=1024; rm -f /mnt/temp; sync repeatedly, in 20M memory.limit_in_bytes cgroup to ext4 on USB stick. ext4 (and gfs2 and xfs) turn out to allocate new pages for writing with AOP_FLAG_NOFS: that seems a little worrying, and it's unclear to me why the transaction needs to be started even before allocating pagecache memory. But it may not be worth worrying about these days: if direct reclaim avoids FS writeback, does __GFP_FS now mean anything? Anyway, we insisted on the may_enter_fs test to avoid hangs with the loop device; but since that also masks off __GFP_IO, we can test for __GFP_IO directly, ignoring may_enter_fs and __GFP_FS. But even so, the test still OOMs sometimes: when originally testing on 3.5-rc6, it OOMed about one time in five or ten; when testing just now on 3.5-rc6-mm1, it OOMed on the first iteration. This residual problem comes from an accumulation of pages under ordinary writeback, not marked PageReclaim, so rightly not causing the memcg check to wait on their writeback: these too can prevent shrink_page_list() from freeing any pages, so many times that memcg reclaim fails and OOMs. Deal with these in the same way as direct reclaim now deals with dirty FS pages: mark them PageReclaim. It is appropriate to rotate these to tail of list when writepage completes, but more importantly, the PageReclaim flag makes memcg reclaim wait on them if encountered again. Increment NR_VMSCAN_IMMEDIATE? That's arguable: I chose not. Setting PageReclaim here may occasionally race with end_page_writeback() clearing it: lru_deactivate_fn() already faced the same race, and correctly concluded that the window is small and the issue non-critical. With these changes, the test runs indefinitely without OOMing on ext4, ext3 and ext2: I'll move on to test with other filesystems later. Trivia: invert conditions for a clearer block without an else, and goto keep_locked to do the unlock_page. Signed-off-by: Hugh Dickins <hughd@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:59 +08:00
goto keep_locked;
memcg: prevent OOM with too many dirty pages The current implementation of dirty pages throttling is not memcg aware which makes it easy to have memcg LRUs full of dirty pages. Without throttling, these LRUs can be scanned faster than the rate of writeback, leading to memcg OOM conditions when the hard limit is small. This patch fixes the problem by throttling the allocating process (possibly a writer) during the hard limit reclaim by waiting on PageReclaim pages. We are waiting only for PageReclaim pages because those are the pages that made one full round over LRU and that means that the writeback is much slower than scanning. The solution is far from being ideal - long term solution is memcg aware dirty throttling - but it is meant to be a band aid until we have a real fix. We are seeing this happening during nightly backups which are placed into containers to prevent from eviction of the real working set. The change affects only memcg reclaim and only when we encounter PageReclaim pages which is a signal that the reclaim doesn't catch up on with the writers so somebody should be throttled. This could be potentially unfair because it could be somebody else from the group who gets throttled on behalf of the writer but as writers need to allocate as well and they allocate in higher rate the probability that only innocent processes would be penalized is not that high. I have tested this change by a simple dd copying /dev/zero to tmpfs or ext3 running under small memcg (1G copy under 5M, 60M, 300M and 2G containers) and dd got killed by OOM killer every time. With the patch I could run the dd with the same size under 5M controller without any OOM. The issue is more visible with slower devices for output. * With the patch ================ * tmpfs size=2G --------------- $ vim cgroup_cache_oom_test.sh $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.4049 s, 34.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 31.4561 s, 33.3 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.4618 s, 51.2 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.42172 s, 738 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 27.9547 s, 37.5 MB/s $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 30.3221 s, 34.6 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.5764 s, 42.7 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 3.35828 s, 312 MB/s * Without the patch =================== * tmpfs size=2G --------------- $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4668 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 25.4989 s, 41.1 MB/s $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 24.3928 s, 43.0 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 1.49797 s, 700 MB/s * ext3 ------ $ ./cgroup_cache_oom_test.sh 5M using Limit 5M for group ./cgroup_cache_oom_test.sh: line 46: 4689 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 60M using Limit 60M for group ./cgroup_cache_oom_test.sh: line 46: 4692 Killed dd if=/dev/zero of=$OUT/zero bs=1M count=$count $ ./cgroup_cache_oom_test.sh 300M using Limit 300M for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 20.248 s, 51.8 MB/s $ ./cgroup_cache_oom_test.sh 2G using Limit 2G for group 1000+0 records in 1000+0 records out 1048576000 bytes (1.0 GB) copied, 2.85201 s, 368 MB/s [akpm@linux-foundation.org: tweak changelog, reordered the test to optimize for CONFIG_CGROUP_MEM_RES_CTLR=n] [hughd@google.com: fix deadlock with loop driver] Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Reviewed-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:55 +08:00
}
memcg: further prevent OOM with too many dirty pages The may_enter_fs test turns out to be too restrictive: though I saw no problem with it when testing on 3.5-rc6, it very soon OOMed when I tested on 3.5-rc6-mm1. I don't know what the difference there is, perhaps I just slightly changed the way I started off the testing: dd if=/dev/zero of=/mnt/temp bs=1M count=1024; rm -f /mnt/temp; sync repeatedly, in 20M memory.limit_in_bytes cgroup to ext4 on USB stick. ext4 (and gfs2 and xfs) turn out to allocate new pages for writing with AOP_FLAG_NOFS: that seems a little worrying, and it's unclear to me why the transaction needs to be started even before allocating pagecache memory. But it may not be worth worrying about these days: if direct reclaim avoids FS writeback, does __GFP_FS now mean anything? Anyway, we insisted on the may_enter_fs test to avoid hangs with the loop device; but since that also masks off __GFP_IO, we can test for __GFP_IO directly, ignoring may_enter_fs and __GFP_FS. But even so, the test still OOMs sometimes: when originally testing on 3.5-rc6, it OOMed about one time in five or ten; when testing just now on 3.5-rc6-mm1, it OOMed on the first iteration. This residual problem comes from an accumulation of pages under ordinary writeback, not marked PageReclaim, so rightly not causing the memcg check to wait on their writeback: these too can prevent shrink_page_list() from freeing any pages, so many times that memcg reclaim fails and OOMs. Deal with these in the same way as direct reclaim now deals with dirty FS pages: mark them PageReclaim. It is appropriate to rotate these to tail of list when writepage completes, but more importantly, the PageReclaim flag makes memcg reclaim wait on them if encountered again. Increment NR_VMSCAN_IMMEDIATE? That's arguable: I chose not. Setting PageReclaim here may occasionally race with end_page_writeback() clearing it: lru_deactivate_fn() already faced the same race, and correctly concluded that the window is small and the issue non-critical. With these changes, the test runs indefinitely without OOMing on ext4, ext3 and ext2: I'll move on to test with other filesystems later. Trivia: invert conditions for a clearer block without an else, and goto keep_locked to do the unlock_page. Signed-off-by: Hugh Dickins <hughd@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujtisu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Ying Han <yinghan@google.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Dave Chinner <david@fromorbit.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:45:59 +08:00
wait_on_page_writeback(page);
}
references = page_check_references(page, sc);
vmscan: factor out page reference checks The used-once mapped file page detection patchset. It is meant to help workloads with large amounts of shortly used file mappings, like rtorrent hashing a file or git when dealing with loose objects (git gc on a bigger site?). Right now, the VM activates referenced mapped file pages on first encounter on the inactive list and it takes a full memory cycle to reclaim them again. When those pages dominate memory, the system no longer has a meaningful notion of 'working set' and is required to give up the active list to make reclaim progress. Obviously, this results in rather bad scanning latencies and the wrong pages being reclaimed. This patch makes the VM be more careful about activating mapped file pages in the first place. The minimum granted lifetime without another memory access becomes an inactive list cycle instead of the full memory cycle, which is more natural given the mentioned loads. This test resembles a hashing rtorrent process. Sequentially, 32MB chunks of a file are mapped into memory, hashed (sha1) and unmapped again. While this happens, every 5 seconds a process is launched and its execution time taken: python2.4 -c 'import pydoc' old: max=2.31s mean=1.26s (0.34) new: max=1.25s mean=0.32s (0.32) find /etc -type f old: max=2.52s mean=1.44s (0.43) new: max=1.92s mean=0.12s (0.17) vim -c ':quit' old: max=6.14s mean=4.03s (0.49) new: max=3.48s mean=2.41s (0.25) mplayer --help old: max=8.08s mean=5.74s (1.02) new: max=3.79s mean=1.32s (0.81) overall hash time (stdev): old: time=1192.30 (12.85) thruput=25.78mb/s (0.27) new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%) I also tested kernbench with regular IO streaming in the background to see whether the delayed activation of frequently used mapped file pages had a negative impact on performance in the presence of pressure on the inactive list. The patch made no significant difference in timing, neither for kernbench nor for the streaming IO throughput. The first patch submission raised concerns about the cost of the extra faults for actually activated pages on machines that have no hardware support for young page table entries. I created an artificial worst case scenario on an ARM machine with around 300MHz and 64MB of memory to figure out the dimensions involved. The test would mmap a file of 20MB, then 1. touch all its pages to fault them in 2. force one full scan cycle on the inactive file LRU -- old: mapping pages activated -- new: mapping pages inactive 3. touch the mapping pages again -- old and new: fault exceptions to set the young bits 4. force another full scan cycle on the inactive file LRU 5. touch the mapping pages one last time -- new: fault exceptions to set the young bits The test showed an overall increase of 6% in time over 100 iterations of the above (old: ~212sec, new: ~225sec). 13 secs total overhead / (100 * 5k pages), ignoring the execution time of the test itself, makes for about 25us overhead for every page that gets actually activated. Note: 1. File mapping the size of one third of main memory, _completely_ in active use across memory pressure - i.e., most pages referenced within one LRU cycle. This should be rare to non-existant, especially on such embedded setups. 2. Many huge activation batches. Those batches only occur when the working set fluctuates. If it changes completely between every full LRU cycle, you have problematic reclaim overhead anyway. 3. Access of activated pages at maximum speed: sequential loads from every single page without doing anything in between. In reality, the extra faults will get distributed between actual operations on the data. So even if a workload manages to get the VM into the situation of activating a third of memory in one go on such a setup, it will take 2.2 seconds instead 2.1 without the patch. Comparing the numbers (and my user-experience over several months), I think this change is an overall improvement to the VM. Patch 1 is only refactoring to break up that ugly compound conditional in shrink_page_list() and make it easy to document and add new checks in a readable fashion. Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not strictly related to #3, but it was in the original submission and is a net simplification, so I kept it. Patch 3 implements used-once detection of mapped file pages. This patch: Moving the big conditional into its own predicate function makes the code a bit easier to read and allows for better commenting on the checks one-by-one. This is just cleaning up, no semantics should have been changed. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:19 +08:00
switch (references) {
case PAGEREF_ACTIVATE:
goto activate_locked;
vmscan: detect mapped file pages used only once The VM currently assumes that an inactive, mapped and referenced file page is in use and promotes it to the active list. However, every mapped file page starts out like this and thus a problem arises when workloads create a stream of such pages that are used only for a short time. By flooding the active list with those pages, the VM quickly gets into trouble finding eligible reclaim canditates. The result is long allocation latencies and eviction of the wrong pages. This patch reuses the PG_referenced page flag (used for unmapped file pages) to implement a usage detection that scales with the speed of LRU list cycling (i.e. memory pressure). If the scanner encounters those pages, the flag is set and the page cycled again on the inactive list. Only if it returns with another page table reference it is activated. Otherwise it is reclaimed as 'not recently used cache'. This effectively changes the minimum lifetime of a used-once mapped file page from a full memory cycle to an inactive list cycle, which allows it to occur in linear streams without affecting the stable working set of the system. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:22 +08:00
case PAGEREF_KEEP:
goto keep_locked;
vmscan: factor out page reference checks The used-once mapped file page detection patchset. It is meant to help workloads with large amounts of shortly used file mappings, like rtorrent hashing a file or git when dealing with loose objects (git gc on a bigger site?). Right now, the VM activates referenced mapped file pages on first encounter on the inactive list and it takes a full memory cycle to reclaim them again. When those pages dominate memory, the system no longer has a meaningful notion of 'working set' and is required to give up the active list to make reclaim progress. Obviously, this results in rather bad scanning latencies and the wrong pages being reclaimed. This patch makes the VM be more careful about activating mapped file pages in the first place. The minimum granted lifetime without another memory access becomes an inactive list cycle instead of the full memory cycle, which is more natural given the mentioned loads. This test resembles a hashing rtorrent process. Sequentially, 32MB chunks of a file are mapped into memory, hashed (sha1) and unmapped again. While this happens, every 5 seconds a process is launched and its execution time taken: python2.4 -c 'import pydoc' old: max=2.31s mean=1.26s (0.34) new: max=1.25s mean=0.32s (0.32) find /etc -type f old: max=2.52s mean=1.44s (0.43) new: max=1.92s mean=0.12s (0.17) vim -c ':quit' old: max=6.14s mean=4.03s (0.49) new: max=3.48s mean=2.41s (0.25) mplayer --help old: max=8.08s mean=5.74s (1.02) new: max=3.79s mean=1.32s (0.81) overall hash time (stdev): old: time=1192.30 (12.85) thruput=25.78mb/s (0.27) new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%) I also tested kernbench with regular IO streaming in the background to see whether the delayed activation of frequently used mapped file pages had a negative impact on performance in the presence of pressure on the inactive list. The patch made no significant difference in timing, neither for kernbench nor for the streaming IO throughput. The first patch submission raised concerns about the cost of the extra faults for actually activated pages on machines that have no hardware support for young page table entries. I created an artificial worst case scenario on an ARM machine with around 300MHz and 64MB of memory to figure out the dimensions involved. The test would mmap a file of 20MB, then 1. touch all its pages to fault them in 2. force one full scan cycle on the inactive file LRU -- old: mapping pages activated -- new: mapping pages inactive 3. touch the mapping pages again -- old and new: fault exceptions to set the young bits 4. force another full scan cycle on the inactive file LRU 5. touch the mapping pages one last time -- new: fault exceptions to set the young bits The test showed an overall increase of 6% in time over 100 iterations of the above (old: ~212sec, new: ~225sec). 13 secs total overhead / (100 * 5k pages), ignoring the execution time of the test itself, makes for about 25us overhead for every page that gets actually activated. Note: 1. File mapping the size of one third of main memory, _completely_ in active use across memory pressure - i.e., most pages referenced within one LRU cycle. This should be rare to non-existant, especially on such embedded setups. 2. Many huge activation batches. Those batches only occur when the working set fluctuates. If it changes completely between every full LRU cycle, you have problematic reclaim overhead anyway. 3. Access of activated pages at maximum speed: sequential loads from every single page without doing anything in between. In reality, the extra faults will get distributed between actual operations on the data. So even if a workload manages to get the VM into the situation of activating a third of memory in one go on such a setup, it will take 2.2 seconds instead 2.1 without the patch. Comparing the numbers (and my user-experience over several months), I think this change is an overall improvement to the VM. Patch 1 is only refactoring to break up that ugly compound conditional in shrink_page_list() and make it easy to document and add new checks in a readable fashion. Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not strictly related to #3, but it was in the original submission and is a net simplification, so I kept it. Patch 3 implements used-once detection of mapped file pages. This patch: Moving the big conditional into its own predicate function makes the code a bit easier to read and allows for better commenting on the checks one-by-one. This is just cleaning up, no semantics should have been changed. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:19 +08:00
case PAGEREF_RECLAIM:
case PAGEREF_RECLAIM_CLEAN:
; /* try to reclaim the page below */
}
/*
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
*/
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
if (PageAnon(page) && !PageSwapCache(page)) {
if (!(sc->gfp_mask & __GFP_IO))
goto keep_locked;
if (!add_to_swap(page))
goto activate_locked;
may_enter_fs = 1;
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
}
mapping = page_mapping(page);
/*
* The page is mapped into the page tables of one or more
* processes. Try to unmap it here.
*/
if (page_mapped(page) && mapping) {
switch (try_to_unmap(page, TTU_UNMAP)) {
case SWAP_FAIL:
goto activate_locked;
case SWAP_AGAIN:
goto keep_locked;
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
case SWAP_MLOCK:
goto cull_mlocked;
case SWAP_SUCCESS:
; /* try to free the page below */
}
}
if (PageDirty(page)) {
nr_dirty++;
mm: vmscan: do not writeback filesystem pages in direct reclaim Testing from the XFS folk revealed that there is still too much I/O from the end of the LRU in kswapd. Previously it was considered acceptable by VM people for a small number of pages to be written back from reclaim with testing generally showing about 0.3% of pages reclaimed were written back (higher if memory was low). That writing back a small number of pages is ok has been heavily disputed for quite some time and Dave Chinner explained it well; It doesn't have to be a very high number to be a problem. IO is orders of magnitude slower than the CPU time it takes to flush a page, so the cost of making a bad flush decision is very high. And single page writeback from the LRU is almost always a bad flush decision. To complicate matters, filesystems respond very differently to requests from reclaim according to Christoph Hellwig; xfs tries to write it back if the requester is kswapd ext4 ignores the request if it's a delayed allocation btrfs ignores the request As a result, each filesystem has different performance characteristics when under memory pressure and there are many pages being dirtied. In some cases, the request is ignored entirely so the VM cannot depend on the IO being dispatched. The objective of this series is to reduce writing of filesystem-backed pages from reclaim, play nicely with writeback that is already in progress and throttle reclaim appropriately when writeback pages are encountered. The assumption is that the flushers will always write pages faster than if reclaim issues the IO. A secondary goal is to avoid the problem whereby direct reclaim splices two potentially deep call stacks together. There is a potential new problem as reclaim has less control over how long before a page in a particularly zone or container is cleaned and direct reclaimers depend on kswapd or flusher threads to do the necessary work. However, as filesystems sometimes ignore direct reclaim requests already, it is not expected to be a serious issue. Patch 1 disables writeback of filesystem pages from direct reclaim entirely. Anonymous pages are still written. Patch 2 removes dead code in lumpy reclaim as it is no longer able to synchronously write pages. This hurts lumpy reclaim but there is an expectation that compaction is used for hugepage allocations these days and lumpy reclaim's days are numbered. Patches 3-4 add warnings to XFS and ext4 if called from direct reclaim. With patch 1, this "never happens" and is intended to catch regressions in this logic in the future. Patch 5 disables writeback of filesystem pages from kswapd unless the priority is raised to the point where kswapd is considered to be in trouble. Patch 6 throttles reclaimers if too many dirty pages are being encountered and the zones or backing devices are congested. Patch 7 invalidates dirty pages found at the end of the LRU so they are reclaimed quickly after being written back rather than waiting for a reclaimer to find them I consider this series to be orthogonal to the writeback work but it is worth noting that the writeback work affects the viability of patch 8 in particular. I tested this on ext4 and xfs using fs_mark, a simple writeback test based on dd and a micro benchmark that does a streaming write to a large mapping (exercises use-once LRU logic) followed by streaming writes to a mix of anonymous and file-backed mappings. The command line for fs_mark when botted with 512M looked something like ./fs_mark -d /tmp/fsmark-2676 -D 100 -N 150 -n 150 -L 25 -t 1 -S0 -s 10485760 The number of files was adjusted depending on the amount of available memory so that the files created was about 3xRAM. For multiple threads, the -d switch is specified multiple times. The test machine is x86-64 with an older generation of AMD processor with 4 cores. The underlying storage was 4 disks configured as RAID-0 as this was the best configuration of storage I had available. Swap is on a separate disk. Dirty ratio was tuned to 40% instead of the default of 20%. Testing was run with and without monitors to both verify that the patches were operating as expected and that any performance gain was real and not due to interference from monitors. Here is a summary of results based on testing XFS. 512M1P-xfs Files/s mean 32.69 ( 0.00%) 34.44 ( 5.08%) 512M1P-xfs Elapsed Time fsmark 51.41 48.29 512M1P-xfs Elapsed Time simple-wb 114.09 108.61 512M1P-xfs Elapsed Time mmap-strm 113.46 109.34 512M1P-xfs Kswapd efficiency fsmark 62% 63% 512M1P-xfs Kswapd efficiency simple-wb 56% 61% 512M1P-xfs Kswapd efficiency mmap-strm 44% 42% 512M-xfs Files/s mean 30.78 ( 0.00%) 35.94 (14.36%) 512M-xfs Elapsed Time fsmark 56.08 48.90 512M-xfs Elapsed Time simple-wb 112.22 98.13 512M-xfs Elapsed Time mmap-strm 219.15 196.67 512M-xfs Kswapd efficiency fsmark 54% 56% 512M-xfs Kswapd efficiency simple-wb 54% 55% 512M-xfs Kswapd efficiency mmap-strm 45% 44% 512M-4X-xfs Files/s mean 30.31 ( 0.00%) 33.33 ( 9.06%) 512M-4X-xfs Elapsed Time fsmark 63.26 55.88 512M-4X-xfs Elapsed Time simple-wb 100.90 90.25 512M-4X-xfs Elapsed Time mmap-strm 261.73 255.38 512M-4X-xfs Kswapd efficiency fsmark 49% 50% 512M-4X-xfs Kswapd efficiency simple-wb 54% 56% 512M-4X-xfs Kswapd efficiency mmap-strm 37% 36% 512M-16X-xfs Files/s mean 60.89 ( 0.00%) 65.22 ( 6.64%) 512M-16X-xfs Elapsed Time fsmark 67.47 58.25 512M-16X-xfs Elapsed Time simple-wb 103.22 90.89 512M-16X-xfs Elapsed Time mmap-strm 237.09 198.82 512M-16X-xfs Kswapd efficiency fsmark 45% 46% 512M-16X-xfs Kswapd efficiency simple-wb 53% 55% 512M-16X-xfs Kswapd efficiency mmap-strm 33% 33% Up until 512-4X, the FSmark improvements were statistically significant. For the 4X and 16X tests the results were within standard deviations but just barely. The time to completion for all tests is improved which is an important result. In general, kswapd efficiency is not affected by skipping dirty pages. 1024M1P-xfs Files/s mean 39.09 ( 0.00%) 41.15 ( 5.01%) 1024M1P-xfs Elapsed Time fsmark 84.14 80.41 1024M1P-xfs Elapsed Time simple-wb 210.77 184.78 1024M1P-xfs Elapsed Time mmap-strm 162.00 160.34 1024M1P-xfs Kswapd efficiency fsmark 69% 75% 1024M1P-xfs Kswapd efficiency simple-wb 71% 77% 1024M1P-xfs Kswapd efficiency mmap-strm 43% 44% 1024M-xfs Files/s mean 35.45 ( 0.00%) 37.00 ( 4.19%) 1024M-xfs Elapsed Time fsmark 94.59 91.00 1024M-xfs Elapsed Time simple-wb 229.84 195.08 1024M-xfs Elapsed Time mmap-strm 405.38 440.29 1024M-xfs Kswapd efficiency fsmark 79% 71% 1024M-xfs Kswapd efficiency simple-wb 74% 74% 1024M-xfs Kswapd efficiency mmap-strm 39% 42% 1024M-4X-xfs Files/s mean 32.63 ( 0.00%) 35.05 ( 6.90%) 1024M-4X-xfs Elapsed Time fsmark 103.33 97.74 1024M-4X-xfs Elapsed Time simple-wb 204.48 178.57 1024M-4X-xfs Elapsed Time mmap-strm 528.38 511.88 1024M-4X-xfs Kswapd efficiency fsmark 81% 70% 1024M-4X-xfs Kswapd efficiency simple-wb 73% 72% 1024M-4X-xfs Kswapd efficiency mmap-strm 39% 38% 1024M-16X-xfs Files/s mean 42.65 ( 0.00%) 42.97 ( 0.74%) 1024M-16X-xfs Elapsed Time fsmark 103.11 99.11 1024M-16X-xfs Elapsed Time simple-wb 200.83 178.24 1024M-16X-xfs Elapsed Time mmap-strm 397.35 459.82 1024M-16X-xfs Kswapd efficiency fsmark 84% 69% 1024M-16X-xfs Kswapd efficiency simple-wb 74% 73% 1024M-16X-xfs Kswapd efficiency mmap-strm 39% 40% All FSMark tests up to 16X had statistically significant improvements. For the most part, tests are completing faster with the exception of the streaming writes to a mixture of anonymous and file-backed mappings which were slower in two cases In the cases where the mmap-strm tests were slower, there was more swapping due to dirty pages being skipped. The number of additional pages swapped is almost identical to the fewer number of pages written from reclaim. In other words, roughly the same number of pages were reclaimed but swapping was slower. As the test is a bit unrealistic and stresses memory heavily, the small shift is acceptable. 4608M1P-xfs Files/s mean 29.75 ( 0.00%) 30.96 ( 3.91%) 4608M1P-xfs Elapsed Time fsmark 512.01 492.15 4608M1P-xfs Elapsed Time simple-wb 618.18 566.24 4608M1P-xfs Elapsed Time mmap-strm 488.05 465.07 4608M1P-xfs Kswapd efficiency fsmark 93% 86% 4608M1P-xfs Kswapd efficiency simple-wb 88% 84% 4608M1P-xfs Kswapd efficiency mmap-strm 46% 45% 4608M-xfs Files/s mean 27.60 ( 0.00%) 28.85 ( 4.33%) 4608M-xfs Elapsed Time fsmark 555.96 532.34 4608M-xfs Elapsed Time simple-wb 659.72 571.85 4608M-xfs Elapsed Time mmap-strm 1082.57 1146.38 4608M-xfs Kswapd efficiency fsmark 89% 91% 4608M-xfs Kswapd efficiency simple-wb 88% 82% 4608M-xfs Kswapd efficiency mmap-strm 48% 46% 4608M-4X-xfs Files/s mean 26.00 ( 0.00%) 27.47 ( 5.35%) 4608M-4X-xfs Elapsed Time fsmark 592.91 564.00 4608M-4X-xfs Elapsed Time simple-wb 616.65 575.07 4608M-4X-xfs Elapsed Time mmap-strm 1773.02 1631.53 4608M-4X-xfs Kswapd efficiency fsmark 90% 94% 4608M-4X-xfs Kswapd efficiency simple-wb 87% 82% 4608M-4X-xfs Kswapd efficiency mmap-strm 43% 43% 4608M-16X-xfs Files/s mean 26.07 ( 0.00%) 26.42 ( 1.32%) 4608M-16X-xfs Elapsed Time fsmark 602.69 585.78 4608M-16X-xfs Elapsed Time simple-wb 606.60 573.81 4608M-16X-xfs Elapsed Time mmap-strm 1549.75 1441.86 4608M-16X-xfs Kswapd efficiency fsmark 98% 98% 4608M-16X-xfs Kswapd efficiency simple-wb 88% 82% 4608M-16X-xfs Kswapd efficiency mmap-strm 44% 42% Unlike the other tests, the fsmark results are not statistically significant but the min and max times are both improved and for the most part, tests completed faster. There are other indications that this is an improvement as well. For example, in the vast majority of cases, there were fewer pages scanned by direct reclaim implying in many cases that stalls due to direct reclaim are reduced. KSwapd is scanning more due to skipping dirty pages which is unfortunate but the CPU usage is still acceptable In an earlier set of tests, I used blktrace and in almost all cases throughput throughout the entire test was higher. However, I ended up discarding those results as recording blktrace data was too heavy for my liking. On a laptop, I plugged in a USB stick and ran a similar tests of tests using it as backing storage. A desktop environment was running and for the entire duration of the tests, firefox and gnome terminal were launching and exiting to vaguely simulate a user. 1024M-xfs Files/s mean 0.41 ( 0.00%) 0.44 ( 6.82%) 1024M-xfs Elapsed Time fsmark 2053.52 1641.03 1024M-xfs Elapsed Time simple-wb 1229.53 768.05 1024M-xfs Elapsed Time mmap-strm 4126.44 4597.03 1024M-xfs Kswapd efficiency fsmark 84% 85% 1024M-xfs Kswapd efficiency simple-wb 92% 81% 1024M-xfs Kswapd efficiency mmap-strm 60% 51% 1024M-xfs Avg wait ms fsmark 5404.53 4473.87 1024M-xfs Avg wait ms simple-wb 2541.35 1453.54 1024M-xfs Avg wait ms mmap-strm 3400.25 3852.53 The mmap-strm results were hurt because firefox launching had a tendency to push the test out of memory. On the postive side, firefox launched marginally faster with the patches applied. Time to completion for many tests was faster but more importantly - the "Avg wait" time as measured by iostat was far lower implying the system would be more responsive. It was also the case that "Avg wait ms" on the root filesystem was lower. I tested it manually and while the system felt slightly more responsive while copying data to a USB stick, it was marginal enough that it could be my imagination. This patch: do not writeback filesystem pages in direct reclaim. When kswapd is failing to keep zones above the min watermark, a process will enter direct reclaim in the same manner kswapd does. If a dirty page is encountered during the scan, this page is written to backing storage using mapping->writepage. This causes two problems. First, it can result in very deep call stacks, particularly if the target storage or filesystem are complex. Some filesystems ignore write requests from direct reclaim as a result. The second is that a single-page flush is inefficient in terms of IO. While there is an expectation that the elevator will merge requests, this does not always happen. Quoting Christoph Hellwig; The elevator has a relatively small window it can operate on, and can never fix up a bad large scale writeback pattern. This patch prevents direct reclaim writing back filesystem pages by checking if current is kswapd. Anonymous pages are still written to swap as there is not the equivalent of a flusher thread for anonymous pages. If the dirty pages cannot be written back, they are placed back on the LRU lists. There is now a direct dependency on dirty page balancing to prevent too many pages in the system being dirtied which would prevent reclaim making forward progress. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Alex Elder <aelder@sgi.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 08:07:38 +08:00
/*
* Only kswapd can writeback filesystem pages to
* avoid risk of stack overflow but do not writeback
* unless under significant pressure.
mm: vmscan: do not writeback filesystem pages in direct reclaim Testing from the XFS folk revealed that there is still too much I/O from the end of the LRU in kswapd. Previously it was considered acceptable by VM people for a small number of pages to be written back from reclaim with testing generally showing about 0.3% of pages reclaimed were written back (higher if memory was low). That writing back a small number of pages is ok has been heavily disputed for quite some time and Dave Chinner explained it well; It doesn't have to be a very high number to be a problem. IO is orders of magnitude slower than the CPU time it takes to flush a page, so the cost of making a bad flush decision is very high. And single page writeback from the LRU is almost always a bad flush decision. To complicate matters, filesystems respond very differently to requests from reclaim according to Christoph Hellwig; xfs tries to write it back if the requester is kswapd ext4 ignores the request if it's a delayed allocation btrfs ignores the request As a result, each filesystem has different performance characteristics when under memory pressure and there are many pages being dirtied. In some cases, the request is ignored entirely so the VM cannot depend on the IO being dispatched. The objective of this series is to reduce writing of filesystem-backed pages from reclaim, play nicely with writeback that is already in progress and throttle reclaim appropriately when writeback pages are encountered. The assumption is that the flushers will always write pages faster than if reclaim issues the IO. A secondary goal is to avoid the problem whereby direct reclaim splices two potentially deep call stacks together. There is a potential new problem as reclaim has less control over how long before a page in a particularly zone or container is cleaned and direct reclaimers depend on kswapd or flusher threads to do the necessary work. However, as filesystems sometimes ignore direct reclaim requests already, it is not expected to be a serious issue. Patch 1 disables writeback of filesystem pages from direct reclaim entirely. Anonymous pages are still written. Patch 2 removes dead code in lumpy reclaim as it is no longer able to synchronously write pages. This hurts lumpy reclaim but there is an expectation that compaction is used for hugepage allocations these days and lumpy reclaim's days are numbered. Patches 3-4 add warnings to XFS and ext4 if called from direct reclaim. With patch 1, this "never happens" and is intended to catch regressions in this logic in the future. Patch 5 disables writeback of filesystem pages from kswapd unless the priority is raised to the point where kswapd is considered to be in trouble. Patch 6 throttles reclaimers if too many dirty pages are being encountered and the zones or backing devices are congested. Patch 7 invalidates dirty pages found at the end of the LRU so they are reclaimed quickly after being written back rather than waiting for a reclaimer to find them I consider this series to be orthogonal to the writeback work but it is worth noting that the writeback work affects the viability of patch 8 in particular. I tested this on ext4 and xfs using fs_mark, a simple writeback test based on dd and a micro benchmark that does a streaming write to a large mapping (exercises use-once LRU logic) followed by streaming writes to a mix of anonymous and file-backed mappings. The command line for fs_mark when botted with 512M looked something like ./fs_mark -d /tmp/fsmark-2676 -D 100 -N 150 -n 150 -L 25 -t 1 -S0 -s 10485760 The number of files was adjusted depending on the amount of available memory so that the files created was about 3xRAM. For multiple threads, the -d switch is specified multiple times. The test machine is x86-64 with an older generation of AMD processor with 4 cores. The underlying storage was 4 disks configured as RAID-0 as this was the best configuration of storage I had available. Swap is on a separate disk. Dirty ratio was tuned to 40% instead of the default of 20%. Testing was run with and without monitors to both verify that the patches were operating as expected and that any performance gain was real and not due to interference from monitors. Here is a summary of results based on testing XFS. 512M1P-xfs Files/s mean 32.69 ( 0.00%) 34.44 ( 5.08%) 512M1P-xfs Elapsed Time fsmark 51.41 48.29 512M1P-xfs Elapsed Time simple-wb 114.09 108.61 512M1P-xfs Elapsed Time mmap-strm 113.46 109.34 512M1P-xfs Kswapd efficiency fsmark 62% 63% 512M1P-xfs Kswapd efficiency simple-wb 56% 61% 512M1P-xfs Kswapd efficiency mmap-strm 44% 42% 512M-xfs Files/s mean 30.78 ( 0.00%) 35.94 (14.36%) 512M-xfs Elapsed Time fsmark 56.08 48.90 512M-xfs Elapsed Time simple-wb 112.22 98.13 512M-xfs Elapsed Time mmap-strm 219.15 196.67 512M-xfs Kswapd efficiency fsmark 54% 56% 512M-xfs Kswapd efficiency simple-wb 54% 55% 512M-xfs Kswapd efficiency mmap-strm 45% 44% 512M-4X-xfs Files/s mean 30.31 ( 0.00%) 33.33 ( 9.06%) 512M-4X-xfs Elapsed Time fsmark 63.26 55.88 512M-4X-xfs Elapsed Time simple-wb 100.90 90.25 512M-4X-xfs Elapsed Time mmap-strm 261.73 255.38 512M-4X-xfs Kswapd efficiency fsmark 49% 50% 512M-4X-xfs Kswapd efficiency simple-wb 54% 56% 512M-4X-xfs Kswapd efficiency mmap-strm 37% 36% 512M-16X-xfs Files/s mean 60.89 ( 0.00%) 65.22 ( 6.64%) 512M-16X-xfs Elapsed Time fsmark 67.47 58.25 512M-16X-xfs Elapsed Time simple-wb 103.22 90.89 512M-16X-xfs Elapsed Time mmap-strm 237.09 198.82 512M-16X-xfs Kswapd efficiency fsmark 45% 46% 512M-16X-xfs Kswapd efficiency simple-wb 53% 55% 512M-16X-xfs Kswapd efficiency mmap-strm 33% 33% Up until 512-4X, the FSmark improvements were statistically significant. For the 4X and 16X tests the results were within standard deviations but just barely. The time to completion for all tests is improved which is an important result. In general, kswapd efficiency is not affected by skipping dirty pages. 1024M1P-xfs Files/s mean 39.09 ( 0.00%) 41.15 ( 5.01%) 1024M1P-xfs Elapsed Time fsmark 84.14 80.41 1024M1P-xfs Elapsed Time simple-wb 210.77 184.78 1024M1P-xfs Elapsed Time mmap-strm 162.00 160.34 1024M1P-xfs Kswapd efficiency fsmark 69% 75% 1024M1P-xfs Kswapd efficiency simple-wb 71% 77% 1024M1P-xfs Kswapd efficiency mmap-strm 43% 44% 1024M-xfs Files/s mean 35.45 ( 0.00%) 37.00 ( 4.19%) 1024M-xfs Elapsed Time fsmark 94.59 91.00 1024M-xfs Elapsed Time simple-wb 229.84 195.08 1024M-xfs Elapsed Time mmap-strm 405.38 440.29 1024M-xfs Kswapd efficiency fsmark 79% 71% 1024M-xfs Kswapd efficiency simple-wb 74% 74% 1024M-xfs Kswapd efficiency mmap-strm 39% 42% 1024M-4X-xfs Files/s mean 32.63 ( 0.00%) 35.05 ( 6.90%) 1024M-4X-xfs Elapsed Time fsmark 103.33 97.74 1024M-4X-xfs Elapsed Time simple-wb 204.48 178.57 1024M-4X-xfs Elapsed Time mmap-strm 528.38 511.88 1024M-4X-xfs Kswapd efficiency fsmark 81% 70% 1024M-4X-xfs Kswapd efficiency simple-wb 73% 72% 1024M-4X-xfs Kswapd efficiency mmap-strm 39% 38% 1024M-16X-xfs Files/s mean 42.65 ( 0.00%) 42.97 ( 0.74%) 1024M-16X-xfs Elapsed Time fsmark 103.11 99.11 1024M-16X-xfs Elapsed Time simple-wb 200.83 178.24 1024M-16X-xfs Elapsed Time mmap-strm 397.35 459.82 1024M-16X-xfs Kswapd efficiency fsmark 84% 69% 1024M-16X-xfs Kswapd efficiency simple-wb 74% 73% 1024M-16X-xfs Kswapd efficiency mmap-strm 39% 40% All FSMark tests up to 16X had statistically significant improvements. For the most part, tests are completing faster with the exception of the streaming writes to a mixture of anonymous and file-backed mappings which were slower in two cases In the cases where the mmap-strm tests were slower, there was more swapping due to dirty pages being skipped. The number of additional pages swapped is almost identical to the fewer number of pages written from reclaim. In other words, roughly the same number of pages were reclaimed but swapping was slower. As the test is a bit unrealistic and stresses memory heavily, the small shift is acceptable. 4608M1P-xfs Files/s mean 29.75 ( 0.00%) 30.96 ( 3.91%) 4608M1P-xfs Elapsed Time fsmark 512.01 492.15 4608M1P-xfs Elapsed Time simple-wb 618.18 566.24 4608M1P-xfs Elapsed Time mmap-strm 488.05 465.07 4608M1P-xfs Kswapd efficiency fsmark 93% 86% 4608M1P-xfs Kswapd efficiency simple-wb 88% 84% 4608M1P-xfs Kswapd efficiency mmap-strm 46% 45% 4608M-xfs Files/s mean 27.60 ( 0.00%) 28.85 ( 4.33%) 4608M-xfs Elapsed Time fsmark 555.96 532.34 4608M-xfs Elapsed Time simple-wb 659.72 571.85 4608M-xfs Elapsed Time mmap-strm 1082.57 1146.38 4608M-xfs Kswapd efficiency fsmark 89% 91% 4608M-xfs Kswapd efficiency simple-wb 88% 82% 4608M-xfs Kswapd efficiency mmap-strm 48% 46% 4608M-4X-xfs Files/s mean 26.00 ( 0.00%) 27.47 ( 5.35%) 4608M-4X-xfs Elapsed Time fsmark 592.91 564.00 4608M-4X-xfs Elapsed Time simple-wb 616.65 575.07 4608M-4X-xfs Elapsed Time mmap-strm 1773.02 1631.53 4608M-4X-xfs Kswapd efficiency fsmark 90% 94% 4608M-4X-xfs Kswapd efficiency simple-wb 87% 82% 4608M-4X-xfs Kswapd efficiency mmap-strm 43% 43% 4608M-16X-xfs Files/s mean 26.07 ( 0.00%) 26.42 ( 1.32%) 4608M-16X-xfs Elapsed Time fsmark 602.69 585.78 4608M-16X-xfs Elapsed Time simple-wb 606.60 573.81 4608M-16X-xfs Elapsed Time mmap-strm 1549.75 1441.86 4608M-16X-xfs Kswapd efficiency fsmark 98% 98% 4608M-16X-xfs Kswapd efficiency simple-wb 88% 82% 4608M-16X-xfs Kswapd efficiency mmap-strm 44% 42% Unlike the other tests, the fsmark results are not statistically significant but the min and max times are both improved and for the most part, tests completed faster. There are other indications that this is an improvement as well. For example, in the vast majority of cases, there were fewer pages scanned by direct reclaim implying in many cases that stalls due to direct reclaim are reduced. KSwapd is scanning more due to skipping dirty pages which is unfortunate but the CPU usage is still acceptable In an earlier set of tests, I used blktrace and in almost all cases throughput throughout the entire test was higher. However, I ended up discarding those results as recording blktrace data was too heavy for my liking. On a laptop, I plugged in a USB stick and ran a similar tests of tests using it as backing storage. A desktop environment was running and for the entire duration of the tests, firefox and gnome terminal were launching and exiting to vaguely simulate a user. 1024M-xfs Files/s mean 0.41 ( 0.00%) 0.44 ( 6.82%) 1024M-xfs Elapsed Time fsmark 2053.52 1641.03 1024M-xfs Elapsed Time simple-wb 1229.53 768.05 1024M-xfs Elapsed Time mmap-strm 4126.44 4597.03 1024M-xfs Kswapd efficiency fsmark 84% 85% 1024M-xfs Kswapd efficiency simple-wb 92% 81% 1024M-xfs Kswapd efficiency mmap-strm 60% 51% 1024M-xfs Avg wait ms fsmark 5404.53 4473.87 1024M-xfs Avg wait ms simple-wb 2541.35 1453.54 1024M-xfs Avg wait ms mmap-strm 3400.25 3852.53 The mmap-strm results were hurt because firefox launching had a tendency to push the test out of memory. On the postive side, firefox launched marginally faster with the patches applied. Time to completion for many tests was faster but more importantly - the "Avg wait" time as measured by iostat was far lower implying the system would be more responsive. It was also the case that "Avg wait ms" on the root filesystem was lower. I tested it manually and while the system felt slightly more responsive while copying data to a USB stick, it was marginal enough that it could be my imagination. This patch: do not writeback filesystem pages in direct reclaim. When kswapd is failing to keep zones above the min watermark, a process will enter direct reclaim in the same manner kswapd does. If a dirty page is encountered during the scan, this page is written to backing storage using mapping->writepage. This causes two problems. First, it can result in very deep call stacks, particularly if the target storage or filesystem are complex. Some filesystems ignore write requests from direct reclaim as a result. The second is that a single-page flush is inefficient in terms of IO. While there is an expectation that the elevator will merge requests, this does not always happen. Quoting Christoph Hellwig; The elevator has a relatively small window it can operate on, and can never fix up a bad large scale writeback pattern. This patch prevents direct reclaim writing back filesystem pages by checking if current is kswapd. Anonymous pages are still written to swap as there is not the equivalent of a flusher thread for anonymous pages. If the dirty pages cannot be written back, they are placed back on the LRU lists. There is now a direct dependency on dirty page balancing to prevent too many pages in the system being dirtied which would prevent reclaim making forward progress. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Alex Elder <aelder@sgi.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 08:07:38 +08:00
*/
if (page_is_file_cache(page) &&
(!current_is_kswapd() ||
sc->priority >= DEF_PRIORITY - 2)) {
/*
* Immediately reclaim when written back.
* Similar in principal to deactivate_page()
* except we already have the page isolated
* and know it's dirty
*/
inc_zone_page_state(page, NR_VMSCAN_IMMEDIATE);
SetPageReclaim(page);
mm: vmscan: do not writeback filesystem pages in direct reclaim Testing from the XFS folk revealed that there is still too much I/O from the end of the LRU in kswapd. Previously it was considered acceptable by VM people for a small number of pages to be written back from reclaim with testing generally showing about 0.3% of pages reclaimed were written back (higher if memory was low). That writing back a small number of pages is ok has been heavily disputed for quite some time and Dave Chinner explained it well; It doesn't have to be a very high number to be a problem. IO is orders of magnitude slower than the CPU time it takes to flush a page, so the cost of making a bad flush decision is very high. And single page writeback from the LRU is almost always a bad flush decision. To complicate matters, filesystems respond very differently to requests from reclaim according to Christoph Hellwig; xfs tries to write it back if the requester is kswapd ext4 ignores the request if it's a delayed allocation btrfs ignores the request As a result, each filesystem has different performance characteristics when under memory pressure and there are many pages being dirtied. In some cases, the request is ignored entirely so the VM cannot depend on the IO being dispatched. The objective of this series is to reduce writing of filesystem-backed pages from reclaim, play nicely with writeback that is already in progress and throttle reclaim appropriately when writeback pages are encountered. The assumption is that the flushers will always write pages faster than if reclaim issues the IO. A secondary goal is to avoid the problem whereby direct reclaim splices two potentially deep call stacks together. There is a potential new problem as reclaim has less control over how long before a page in a particularly zone or container is cleaned and direct reclaimers depend on kswapd or flusher threads to do the necessary work. However, as filesystems sometimes ignore direct reclaim requests already, it is not expected to be a serious issue. Patch 1 disables writeback of filesystem pages from direct reclaim entirely. Anonymous pages are still written. Patch 2 removes dead code in lumpy reclaim as it is no longer able to synchronously write pages. This hurts lumpy reclaim but there is an expectation that compaction is used for hugepage allocations these days and lumpy reclaim's days are numbered. Patches 3-4 add warnings to XFS and ext4 if called from direct reclaim. With patch 1, this "never happens" and is intended to catch regressions in this logic in the future. Patch 5 disables writeback of filesystem pages from kswapd unless the priority is raised to the point where kswapd is considered to be in trouble. Patch 6 throttles reclaimers if too many dirty pages are being encountered and the zones or backing devices are congested. Patch 7 invalidates dirty pages found at the end of the LRU so they are reclaimed quickly after being written back rather than waiting for a reclaimer to find them I consider this series to be orthogonal to the writeback work but it is worth noting that the writeback work affects the viability of patch 8 in particular. I tested this on ext4 and xfs using fs_mark, a simple writeback test based on dd and a micro benchmark that does a streaming write to a large mapping (exercises use-once LRU logic) followed by streaming writes to a mix of anonymous and file-backed mappings. The command line for fs_mark when botted with 512M looked something like ./fs_mark -d /tmp/fsmark-2676 -D 100 -N 150 -n 150 -L 25 -t 1 -S0 -s 10485760 The number of files was adjusted depending on the amount of available memory so that the files created was about 3xRAM. For multiple threads, the -d switch is specified multiple times. The test machine is x86-64 with an older generation of AMD processor with 4 cores. The underlying storage was 4 disks configured as RAID-0 as this was the best configuration of storage I had available. Swap is on a separate disk. Dirty ratio was tuned to 40% instead of the default of 20%. Testing was run with and without monitors to both verify that the patches were operating as expected and that any performance gain was real and not due to interference from monitors. Here is a summary of results based on testing XFS. 512M1P-xfs Files/s mean 32.69 ( 0.00%) 34.44 ( 5.08%) 512M1P-xfs Elapsed Time fsmark 51.41 48.29 512M1P-xfs Elapsed Time simple-wb 114.09 108.61 512M1P-xfs Elapsed Time mmap-strm 113.46 109.34 512M1P-xfs Kswapd efficiency fsmark 62% 63% 512M1P-xfs Kswapd efficiency simple-wb 56% 61% 512M1P-xfs Kswapd efficiency mmap-strm 44% 42% 512M-xfs Files/s mean 30.78 ( 0.00%) 35.94 (14.36%) 512M-xfs Elapsed Time fsmark 56.08 48.90 512M-xfs Elapsed Time simple-wb 112.22 98.13 512M-xfs Elapsed Time mmap-strm 219.15 196.67 512M-xfs Kswapd efficiency fsmark 54% 56% 512M-xfs Kswapd efficiency simple-wb 54% 55% 512M-xfs Kswapd efficiency mmap-strm 45% 44% 512M-4X-xfs Files/s mean 30.31 ( 0.00%) 33.33 ( 9.06%) 512M-4X-xfs Elapsed Time fsmark 63.26 55.88 512M-4X-xfs Elapsed Time simple-wb 100.90 90.25 512M-4X-xfs Elapsed Time mmap-strm 261.73 255.38 512M-4X-xfs Kswapd efficiency fsmark 49% 50% 512M-4X-xfs Kswapd efficiency simple-wb 54% 56% 512M-4X-xfs Kswapd efficiency mmap-strm 37% 36% 512M-16X-xfs Files/s mean 60.89 ( 0.00%) 65.22 ( 6.64%) 512M-16X-xfs Elapsed Time fsmark 67.47 58.25 512M-16X-xfs Elapsed Time simple-wb 103.22 90.89 512M-16X-xfs Elapsed Time mmap-strm 237.09 198.82 512M-16X-xfs Kswapd efficiency fsmark 45% 46% 512M-16X-xfs Kswapd efficiency simple-wb 53% 55% 512M-16X-xfs Kswapd efficiency mmap-strm 33% 33% Up until 512-4X, the FSmark improvements were statistically significant. For the 4X and 16X tests the results were within standard deviations but just barely. The time to completion for all tests is improved which is an important result. In general, kswapd efficiency is not affected by skipping dirty pages. 1024M1P-xfs Files/s mean 39.09 ( 0.00%) 41.15 ( 5.01%) 1024M1P-xfs Elapsed Time fsmark 84.14 80.41 1024M1P-xfs Elapsed Time simple-wb 210.77 184.78 1024M1P-xfs Elapsed Time mmap-strm 162.00 160.34 1024M1P-xfs Kswapd efficiency fsmark 69% 75% 1024M1P-xfs Kswapd efficiency simple-wb 71% 77% 1024M1P-xfs Kswapd efficiency mmap-strm 43% 44% 1024M-xfs Files/s mean 35.45 ( 0.00%) 37.00 ( 4.19%) 1024M-xfs Elapsed Time fsmark 94.59 91.00 1024M-xfs Elapsed Time simple-wb 229.84 195.08 1024M-xfs Elapsed Time mmap-strm 405.38 440.29 1024M-xfs Kswapd efficiency fsmark 79% 71% 1024M-xfs Kswapd efficiency simple-wb 74% 74% 1024M-xfs Kswapd efficiency mmap-strm 39% 42% 1024M-4X-xfs Files/s mean 32.63 ( 0.00%) 35.05 ( 6.90%) 1024M-4X-xfs Elapsed Time fsmark 103.33 97.74 1024M-4X-xfs Elapsed Time simple-wb 204.48 178.57 1024M-4X-xfs Elapsed Time mmap-strm 528.38 511.88 1024M-4X-xfs Kswapd efficiency fsmark 81% 70% 1024M-4X-xfs Kswapd efficiency simple-wb 73% 72% 1024M-4X-xfs Kswapd efficiency mmap-strm 39% 38% 1024M-16X-xfs Files/s mean 42.65 ( 0.00%) 42.97 ( 0.74%) 1024M-16X-xfs Elapsed Time fsmark 103.11 99.11 1024M-16X-xfs Elapsed Time simple-wb 200.83 178.24 1024M-16X-xfs Elapsed Time mmap-strm 397.35 459.82 1024M-16X-xfs Kswapd efficiency fsmark 84% 69% 1024M-16X-xfs Kswapd efficiency simple-wb 74% 73% 1024M-16X-xfs Kswapd efficiency mmap-strm 39% 40% All FSMark tests up to 16X had statistically significant improvements. For the most part, tests are completing faster with the exception of the streaming writes to a mixture of anonymous and file-backed mappings which were slower in two cases In the cases where the mmap-strm tests were slower, there was more swapping due to dirty pages being skipped. The number of additional pages swapped is almost identical to the fewer number of pages written from reclaim. In other words, roughly the same number of pages were reclaimed but swapping was slower. As the test is a bit unrealistic and stresses memory heavily, the small shift is acceptable. 4608M1P-xfs Files/s mean 29.75 ( 0.00%) 30.96 ( 3.91%) 4608M1P-xfs Elapsed Time fsmark 512.01 492.15 4608M1P-xfs Elapsed Time simple-wb 618.18 566.24 4608M1P-xfs Elapsed Time mmap-strm 488.05 465.07 4608M1P-xfs Kswapd efficiency fsmark 93% 86% 4608M1P-xfs Kswapd efficiency simple-wb 88% 84% 4608M1P-xfs Kswapd efficiency mmap-strm 46% 45% 4608M-xfs Files/s mean 27.60 ( 0.00%) 28.85 ( 4.33%) 4608M-xfs Elapsed Time fsmark 555.96 532.34 4608M-xfs Elapsed Time simple-wb 659.72 571.85 4608M-xfs Elapsed Time mmap-strm 1082.57 1146.38 4608M-xfs Kswapd efficiency fsmark 89% 91% 4608M-xfs Kswapd efficiency simple-wb 88% 82% 4608M-xfs Kswapd efficiency mmap-strm 48% 46% 4608M-4X-xfs Files/s mean 26.00 ( 0.00%) 27.47 ( 5.35%) 4608M-4X-xfs Elapsed Time fsmark 592.91 564.00 4608M-4X-xfs Elapsed Time simple-wb 616.65 575.07 4608M-4X-xfs Elapsed Time mmap-strm 1773.02 1631.53 4608M-4X-xfs Kswapd efficiency fsmark 90% 94% 4608M-4X-xfs Kswapd efficiency simple-wb 87% 82% 4608M-4X-xfs Kswapd efficiency mmap-strm 43% 43% 4608M-16X-xfs Files/s mean 26.07 ( 0.00%) 26.42 ( 1.32%) 4608M-16X-xfs Elapsed Time fsmark 602.69 585.78 4608M-16X-xfs Elapsed Time simple-wb 606.60 573.81 4608M-16X-xfs Elapsed Time mmap-strm 1549.75 1441.86 4608M-16X-xfs Kswapd efficiency fsmark 98% 98% 4608M-16X-xfs Kswapd efficiency simple-wb 88% 82% 4608M-16X-xfs Kswapd efficiency mmap-strm 44% 42% Unlike the other tests, the fsmark results are not statistically significant but the min and max times are both improved and for the most part, tests completed faster. There are other indications that this is an improvement as well. For example, in the vast majority of cases, there were fewer pages scanned by direct reclaim implying in many cases that stalls due to direct reclaim are reduced. KSwapd is scanning more due to skipping dirty pages which is unfortunate but the CPU usage is still acceptable In an earlier set of tests, I used blktrace and in almost all cases throughput throughout the entire test was higher. However, I ended up discarding those results as recording blktrace data was too heavy for my liking. On a laptop, I plugged in a USB stick and ran a similar tests of tests using it as backing storage. A desktop environment was running and for the entire duration of the tests, firefox and gnome terminal were launching and exiting to vaguely simulate a user. 1024M-xfs Files/s mean 0.41 ( 0.00%) 0.44 ( 6.82%) 1024M-xfs Elapsed Time fsmark 2053.52 1641.03 1024M-xfs Elapsed Time simple-wb 1229.53 768.05 1024M-xfs Elapsed Time mmap-strm 4126.44 4597.03 1024M-xfs Kswapd efficiency fsmark 84% 85% 1024M-xfs Kswapd efficiency simple-wb 92% 81% 1024M-xfs Kswapd efficiency mmap-strm 60% 51% 1024M-xfs Avg wait ms fsmark 5404.53 4473.87 1024M-xfs Avg wait ms simple-wb 2541.35 1453.54 1024M-xfs Avg wait ms mmap-strm 3400.25 3852.53 The mmap-strm results were hurt because firefox launching had a tendency to push the test out of memory. On the postive side, firefox launched marginally faster with the patches applied. Time to completion for many tests was faster but more importantly - the "Avg wait" time as measured by iostat was far lower implying the system would be more responsive. It was also the case that "Avg wait ms" on the root filesystem was lower. I tested it manually and while the system felt slightly more responsive while copying data to a USB stick, it was marginal enough that it could be my imagination. This patch: do not writeback filesystem pages in direct reclaim. When kswapd is failing to keep zones above the min watermark, a process will enter direct reclaim in the same manner kswapd does. If a dirty page is encountered during the scan, this page is written to backing storage using mapping->writepage. This causes two problems. First, it can result in very deep call stacks, particularly if the target storage or filesystem are complex. Some filesystems ignore write requests from direct reclaim as a result. The second is that a single-page flush is inefficient in terms of IO. While there is an expectation that the elevator will merge requests, this does not always happen. Quoting Christoph Hellwig; The elevator has a relatively small window it can operate on, and can never fix up a bad large scale writeback pattern. This patch prevents direct reclaim writing back filesystem pages by checking if current is kswapd. Anonymous pages are still written to swap as there is not the equivalent of a flusher thread for anonymous pages. If the dirty pages cannot be written back, they are placed back on the LRU lists. There is now a direct dependency on dirty page balancing to prevent too many pages in the system being dirtied which would prevent reclaim making forward progress. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Alex Elder <aelder@sgi.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 08:07:38 +08:00
goto keep_locked;
}
vmscan: factor out page reference checks The used-once mapped file page detection patchset. It is meant to help workloads with large amounts of shortly used file mappings, like rtorrent hashing a file or git when dealing with loose objects (git gc on a bigger site?). Right now, the VM activates referenced mapped file pages on first encounter on the inactive list and it takes a full memory cycle to reclaim them again. When those pages dominate memory, the system no longer has a meaningful notion of 'working set' and is required to give up the active list to make reclaim progress. Obviously, this results in rather bad scanning latencies and the wrong pages being reclaimed. This patch makes the VM be more careful about activating mapped file pages in the first place. The minimum granted lifetime without another memory access becomes an inactive list cycle instead of the full memory cycle, which is more natural given the mentioned loads. This test resembles a hashing rtorrent process. Sequentially, 32MB chunks of a file are mapped into memory, hashed (sha1) and unmapped again. While this happens, every 5 seconds a process is launched and its execution time taken: python2.4 -c 'import pydoc' old: max=2.31s mean=1.26s (0.34) new: max=1.25s mean=0.32s (0.32) find /etc -type f old: max=2.52s mean=1.44s (0.43) new: max=1.92s mean=0.12s (0.17) vim -c ':quit' old: max=6.14s mean=4.03s (0.49) new: max=3.48s mean=2.41s (0.25) mplayer --help old: max=8.08s mean=5.74s (1.02) new: max=3.79s mean=1.32s (0.81) overall hash time (stdev): old: time=1192.30 (12.85) thruput=25.78mb/s (0.27) new: time=1060.27 (32.58) thruput=29.02mb/s (0.88) (-11%) I also tested kernbench with regular IO streaming in the background to see whether the delayed activation of frequently used mapped file pages had a negative impact on performance in the presence of pressure on the inactive list. The patch made no significant difference in timing, neither for kernbench nor for the streaming IO throughput. The first patch submission raised concerns about the cost of the extra faults for actually activated pages on machines that have no hardware support for young page table entries. I created an artificial worst case scenario on an ARM machine with around 300MHz and 64MB of memory to figure out the dimensions involved. The test would mmap a file of 20MB, then 1. touch all its pages to fault them in 2. force one full scan cycle on the inactive file LRU -- old: mapping pages activated -- new: mapping pages inactive 3. touch the mapping pages again -- old and new: fault exceptions to set the young bits 4. force another full scan cycle on the inactive file LRU 5. touch the mapping pages one last time -- new: fault exceptions to set the young bits The test showed an overall increase of 6% in time over 100 iterations of the above (old: ~212sec, new: ~225sec). 13 secs total overhead / (100 * 5k pages), ignoring the execution time of the test itself, makes for about 25us overhead for every page that gets actually activated. Note: 1. File mapping the size of one third of main memory, _completely_ in active use across memory pressure - i.e., most pages referenced within one LRU cycle. This should be rare to non-existant, especially on such embedded setups. 2. Many huge activation batches. Those batches only occur when the working set fluctuates. If it changes completely between every full LRU cycle, you have problematic reclaim overhead anyway. 3. Access of activated pages at maximum speed: sequential loads from every single page without doing anything in between. In reality, the extra faults will get distributed between actual operations on the data. So even if a workload manages to get the VM into the situation of activating a third of memory in one go on such a setup, it will take 2.2 seconds instead 2.1 without the patch. Comparing the numbers (and my user-experience over several months), I think this change is an overall improvement to the VM. Patch 1 is only refactoring to break up that ugly compound conditional in shrink_page_list() and make it easy to document and add new checks in a readable fashion. Patch 2 gets rid of the obsolete page_mapping_inuse(). It's not strictly related to #3, but it was in the original submission and is a net simplification, so I kept it. Patch 3 implements used-once detection of mapped file pages. This patch: Moving the big conditional into its own predicate function makes the code a bit easier to read and allows for better commenting on the checks one-by-one. This is just cleaning up, no semantics should have been changed. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: OSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 05:42:19 +08:00
if (references == PAGEREF_RECLAIM_CLEAN)
goto keep_locked;
if (!may_enter_fs)
goto keep_locked;
if (!sc->may_writepage)
goto keep_locked;
/* Page is dirty, try to write it out here */
vmscan: narrow the scenarios in whcih lumpy reclaim uses synchrounous reclaim shrink_page_list() can decide to give up reclaiming a page under a number of conditions such as 1. trylock_page() failure 2. page is unevictable 3. zone reclaim and page is mapped 4. PageWriteback() is true 5. page is swapbacked and swap is full 6. add_to_swap() failure 7. page is dirty and gfpmask don't have GFP_IO, GFP_FS 8. page is pinned 9. IO queue is congested 10. pageout() start IO, but not finished With lumpy reclaim, failures result in entering synchronous lumpy reclaim but this can be unnecessary. In cases (2), (3), (5), (6), (7) and (8), there is no point retrying. This patch causes lumpy reclaim to abort when it is known it will fail. Case (9) is more interesting. current behavior is, 1. start shrink_page_list(async) 2. found queue_congested() 3. skip pageout write 4. still start shrink_page_list(sync) 5. wait on a lot of pages 6. again, found queue_congested() 7. give up pageout write again So, it's useless time wasting. However, just skipping page reclaim is also notgood as x86 allocating a huge page needs 512 pages for example. It can have more dirty pages than queue congestion threshold (~=128). After this patch, pageout() behaves as follows; - If order > PAGE_ALLOC_COSTLY_ORDER Ignore queue congestion always. - If order <= PAGE_ALLOC_COSTLY_ORDER skip write page and disable lumpy reclaim. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:42 +08:00
switch (pageout(page, mapping, sc)) {
case PAGE_KEEP:
nr_congested++;
goto keep_locked;
case PAGE_ACTIVATE:
goto activate_locked;
case PAGE_SUCCESS:
vmscan: narrow the scenarios in whcih lumpy reclaim uses synchrounous reclaim shrink_page_list() can decide to give up reclaiming a page under a number of conditions such as 1. trylock_page() failure 2. page is unevictable 3. zone reclaim and page is mapped 4. PageWriteback() is true 5. page is swapbacked and swap is full 6. add_to_swap() failure 7. page is dirty and gfpmask don't have GFP_IO, GFP_FS 8. page is pinned 9. IO queue is congested 10. pageout() start IO, but not finished With lumpy reclaim, failures result in entering synchronous lumpy reclaim but this can be unnecessary. In cases (2), (3), (5), (6), (7) and (8), there is no point retrying. This patch causes lumpy reclaim to abort when it is known it will fail. Case (9) is more interesting. current behavior is, 1. start shrink_page_list(async) 2. found queue_congested() 3. skip pageout write 4. still start shrink_page_list(sync) 5. wait on a lot of pages 6. again, found queue_congested() 7. give up pageout write again So, it's useless time wasting. However, just skipping page reclaim is also notgood as x86 allocating a huge page needs 512 pages for example. It can have more dirty pages than queue congestion threshold (~=128). After this patch, pageout() behaves as follows; - If order > PAGE_ALLOC_COSTLY_ORDER Ignore queue congestion always. - If order <= PAGE_ALLOC_COSTLY_ORDER skip write page and disable lumpy reclaim. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:42 +08:00
if (PageWriteback(page))
goto keep;
vmscan: narrow the scenarios in whcih lumpy reclaim uses synchrounous reclaim shrink_page_list() can decide to give up reclaiming a page under a number of conditions such as 1. trylock_page() failure 2. page is unevictable 3. zone reclaim and page is mapped 4. PageWriteback() is true 5. page is swapbacked and swap is full 6. add_to_swap() failure 7. page is dirty and gfpmask don't have GFP_IO, GFP_FS 8. page is pinned 9. IO queue is congested 10. pageout() start IO, but not finished With lumpy reclaim, failures result in entering synchronous lumpy reclaim but this can be unnecessary. In cases (2), (3), (5), (6), (7) and (8), there is no point retrying. This patch causes lumpy reclaim to abort when it is known it will fail. Case (9) is more interesting. current behavior is, 1. start shrink_page_list(async) 2. found queue_congested() 3. skip pageout write 4. still start shrink_page_list(sync) 5. wait on a lot of pages 6. again, found queue_congested() 7. give up pageout write again So, it's useless time wasting. However, just skipping page reclaim is also notgood as x86 allocating a huge page needs 512 pages for example. It can have more dirty pages than queue congestion threshold (~=128). After this patch, pageout() behaves as follows; - If order > PAGE_ALLOC_COSTLY_ORDER Ignore queue congestion always. - If order <= PAGE_ALLOC_COSTLY_ORDER skip write page and disable lumpy reclaim. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:42 +08:00
if (PageDirty(page))
goto keep;
vmscan: narrow the scenarios in whcih lumpy reclaim uses synchrounous reclaim shrink_page_list() can decide to give up reclaiming a page under a number of conditions such as 1. trylock_page() failure 2. page is unevictable 3. zone reclaim and page is mapped 4. PageWriteback() is true 5. page is swapbacked and swap is full 6. add_to_swap() failure 7. page is dirty and gfpmask don't have GFP_IO, GFP_FS 8. page is pinned 9. IO queue is congested 10. pageout() start IO, but not finished With lumpy reclaim, failures result in entering synchronous lumpy reclaim but this can be unnecessary. In cases (2), (3), (5), (6), (7) and (8), there is no point retrying. This patch causes lumpy reclaim to abort when it is known it will fail. Case (9) is more interesting. current behavior is, 1. start shrink_page_list(async) 2. found queue_congested() 3. skip pageout write 4. still start shrink_page_list(sync) 5. wait on a lot of pages 6. again, found queue_congested() 7. give up pageout write again So, it's useless time wasting. However, just skipping page reclaim is also notgood as x86 allocating a huge page needs 512 pages for example. It can have more dirty pages than queue congestion threshold (~=128). After this patch, pageout() behaves as follows; - If order > PAGE_ALLOC_COSTLY_ORDER Ignore queue congestion always. - If order <= PAGE_ALLOC_COSTLY_ORDER skip write page and disable lumpy reclaim. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:42 +08:00
/*
* A synchronous write - probably a ramdisk. Go
* ahead and try to reclaim the page.
*/
if (!trylock_page(page))
goto keep;
if (PageDirty(page) || PageWriteback(page))
goto keep_locked;
mapping = page_mapping(page);
case PAGE_CLEAN:
; /* try to free the page below */
}
}
/*
* If the page has buffers, try to free the buffer mappings
* associated with this page. If we succeed we try to free
* the page as well.
*
* We do this even if the page is PageDirty().
* try_to_release_page() does not perform I/O, but it is
* possible for a page to have PageDirty set, but it is actually
* clean (all its buffers are clean). This happens if the
* buffers were written out directly, with submit_bh(). ext3
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
* will do this, as well as the blockdev mapping.
* try_to_release_page() will discover that cleanness and will
* drop the buffers and mark the page clean - it can be freed.
*
* Rarely, pages can have buffers and no ->mapping. These are
* the pages which were not successfully invalidated in
* truncate_complete_page(). We try to drop those buffers here
* and if that worked, and the page is no longer mapped into
* process address space (page_count == 1) it can be freed.
* Otherwise, leave the page on the LRU so it is swappable.
*/
if (page_has_private(page)) {
if (!try_to_release_page(page, sc->gfp_mask))
goto activate_locked;
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
if (!mapping && page_count(page) == 1) {
unlock_page(page);
if (put_page_testzero(page))
goto free_it;
else {
/*
* rare race with speculative reference.
* the speculative reference will free
* this page shortly, so we may
* increment nr_reclaimed here (and
* leave it off the LRU).
*/
nr_reclaimed++;
continue;
}
}
}
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
if (!mapping || !__remove_mapping(mapping, page))
[PATCH] Swap Migration V5: migrate_pages() function This adds the basic page migration function with a minimal implementation that only allows the eviction of pages to swap space. Page eviction and migration may be useful to migrate pages, to suspend programs or for remapping single pages (useful for faulty pages or pages with soft ECC failures) The process is as follows: The function wanting to migrate pages must first build a list of pages to be migrated or evicted and take them off the lru lists via isolate_lru_page(). isolate_lru_page determines that a page is freeable based on the LRU bit set. Then the actual migration or swapout can happen by calling migrate_pages(). migrate_pages does its best to migrate or swapout the pages and does multiple passes over the list. Some pages may only be swappable if they are not dirty. migrate_pages may start writing out dirty pages in the initial passes over the pages. However, migrate_pages may not be able to migrate or evict all pages for a variety of reasons. The remaining pages may be returned to the LRU lists using putback_lru_pages(). Changelog V4->V5: - Use the lru caches to return pages to the LRU Changelog V3->V4: - Restructure code so that applying patches to support full migration does require minimal changes. Rename swapout_pages() to migrate_pages(). Changelog V2->V3: - Extract common code from shrink_list() and swapout_pages() Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: "Michael Kerrisk" <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:48 +08:00
goto keep_locked;
/*
* At this point, we have no other references and there is
* no way to pick any more up (removed from LRU, removed
* from pagecache). Can use non-atomic bitops now (and
* we obviously don't have to worry about waking up a process
* waiting on the page lock, because there are no references.
*/
__clear_page_locked(page);
mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:45:30 +08:00
free_it:
nr_reclaimed++;
/*
* Is there need to periodically free_page_list? It would
* appear not as the counts should be low
*/
list_add(&page->lru, &free_pages);
continue;
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
cull_mlocked:
if (PageSwapCache(page))
try_to_free_swap(page);
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
unlock_page(page);
putback_lru_page(page);
continue;
activate_locked:
/* Not a candidate for swapping, so reclaim swap space. */
if (PageSwapCache(page) && vm_swap_full())
mm: try_to_free_swap replaces remove_exclusive_swap_page remove_exclusive_swap_page(): its problem is in living up to its name. It doesn't matter if someone else has a reference to the page (raised page_count); it doesn't matter if the page is mapped into userspace (raised page_mapcount - though that hints it may be worth keeping the swap): all that matters is that there be no more references to the swap (and no writeback in progress). swapoff (try_to_unuse) has been removing pages from swapcache for years, with no concern for page count or page mapcount, and we used to have a comment in lookup_swap_cache() recognizing that: if you go for a page of swapcache, you'll get the right page, but it could have been removed from swapcache by the time you get page lock. So, give up asking for exclusivity: get rid of remove_exclusive_swap_page(), and remove_exclusive_swap_page_ref() and remove_exclusive_swap_page_count() which were spawned for the recent LRU work: replace them by the simpler try_to_free_swap() which just checks page_swapcount(). Similarly, remove the page_count limitation from free_swap_and_count(), but assume that it's worth holding on to the swap if page is mapped and swap nowhere near full. Add a vm_swap_full() test in free_swap_cache()? It would be consistent, but I think we probably have enough for now. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:39:36 +08:00
try_to_free_swap(page);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
VM_BUG_ON(PageActive(page));
SetPageActive(page);
pgactivate++;
keep_locked:
unlock_page(page);
keep:
list_add(&page->lru, &ret_pages);
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
}
/*
* Tag a zone as congested if all the dirty pages encountered were
* backed by a congested BDI. In this case, reclaimers should just
* back off and wait for congestion to clear because further reclaim
* will encounter the same problem
*/
if (nr_dirty && nr_dirty == nr_congested && global_reclaim(sc))
zone_set_flag(zone, ZONE_CONGESTED);
free_hot_cold_page_list(&free_pages, 1);
list_splice(&ret_pages, page_list);
[PATCH] Light weight event counters The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 16:55:45 +08:00
count_vm_events(PGACTIVATE, pgactivate);
mem_cgroup_uncharge_end();
mm: vmscan: throttle reclaim if encountering too many dirty pages under writeback Workloads that are allocating frequently and writing files place a large number of dirty pages on the LRU. With use-once logic, it is possible for them to reach the end of the LRU quickly requiring the reclaimer to scan more to find clean pages. Ordinarily, processes that are dirtying memory will get throttled by dirty balancing but this is a global heuristic and does not take into account that LRUs are maintained on a per-zone basis. This can lead to a situation whereby reclaim is scanning heavily, skipping over a large number of pages under writeback and recycling them around the LRU consuming CPU. This patch checks how many of the number of pages isolated from the LRU were dirty and under writeback. If a percentage of them under writeback, the process will be throttled if a backing device or the zone is congested. Note that this applies whether it is anonymous or file-backed pages that are under writeback meaning that swapping is potentially throttled. This is intentional due to the fact if the swap device is congested, scanning more pages and dispatching more IO is not going to help matters. The percentage that must be in writeback depends on the priority. At default priority, all of them must be dirty. At DEF_PRIORITY-1, 50% of them must be, DEF_PRIORITY-2, 25% etc. i.e. as pressure increases the greater the likelihood the process will get throttled to allow the flusher threads to make some progress. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Johannes Weiner <jweiner@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Alex Elder <aelder@sgi.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 08:07:56 +08:00
*ret_nr_dirty += nr_dirty;
*ret_nr_writeback += nr_writeback;
return nr_reclaimed;
}
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
/*
* Attempt to remove the specified page from its LRU. Only take this page
* if it is of the appropriate PageActive status. Pages which are being
* freed elsewhere are also ignored.
*
* page: page to consider
* mode: one of the LRU isolation modes defined above
*
* returns 0 on success, -ve errno on failure.
*/
int __isolate_lru_page(struct page *page, isolate_mode_t mode)
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
{
int ret = -EINVAL;
/* Only take pages on the LRU. */
if (!PageLRU(page))
return ret;
mm: vmscan: remove lumpy reclaim This series removes lumpy reclaim and some stalling logic that was unintentionally being used by memory compaction. The end result is that stalling on dirty pages during page reclaim now depends on wait_iff_congested(). Four kernels were compared 3.3.0 vanilla 3.4.0-rc2 vanilla 3.4.0-rc2 lumpyremove-v2 is patch one from this series 3.4.0-rc2 nosync-v2r3 is the full series Removing lumpy reclaim saves almost 900 bytes of text whereas the full series removes 1200 bytes. text data bss dec hex filename 6740375 1927944 2260992 10929311 a6c49f vmlinux-3.4.0-rc2-vanilla 6739479 1927944 2260992 10928415 a6c11f vmlinux-3.4.0-rc2-lumpyremove-v2 6739159 1927944 2260992 10928095 a6bfdf vmlinux-3.4.0-rc2-nosync-v2 There are behaviour changes in the series and so tests were run with monitoring of ftrace events. This disrupts results so the performance results are distorted but the new behaviour should be clearer. fs-mark running in a threaded configuration showed little of interest as it did not push reclaim aggressively FS-Mark Multi Threaded 3.3.0-vanilla rc2-vanilla lumpyremove-v2r3 nosync-v2r3 Files/s min 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) Files/s mean 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) Files/s stddev 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) Files/s max 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) Overhead min 508667.00 ( 0.00%) 521350.00 (-2.49%) 544292.00 (-7.00%) 547168.00 (-7.57%) Overhead mean 551185.00 ( 0.00%) 652690.73 (-18.42%) 991208.40 (-79.83%) 570130.53 (-3.44%) Overhead stddev 18200.69 ( 0.00%) 331958.29 (-1723.88%) 1579579.43 (-8578.68%) 9576.81 (47.38%) Overhead max 576775.00 ( 0.00%) 1846634.00 (-220.17%) 6901055.00 (-1096.49%) 585675.00 (-1.54%) MMTests Statistics: duration Sys Time Running Test (seconds) 309.90 300.95 307.33 298.95 User+Sys Time Running Test (seconds) 319.32 309.67 315.69 307.51 Total Elapsed Time (seconds) 1187.85 1193.09 1191.98 1193.73 MMTests Statistics: vmstat Page Ins 80532 82212 81420 79480 Page Outs 111434984 111456240 111437376 111582628 Swap Ins 0 0 0 0 Swap Outs 0 0 0 0 Direct pages scanned 44881 27889 27453 34843 Kswapd pages scanned 25841428 25860774 25861233 25843212 Kswapd pages reclaimed 25841393 25860741 25861199 25843179 Direct pages reclaimed 44881 27889 27453 34843 Kswapd efficiency 99% 99% 99% 99% Kswapd velocity 21754.791 21675.460 21696.029 21649.127 Direct efficiency 100% 100% 100% 100% Direct velocity 37.783 23.375 23.031 29.188 Percentage direct scans 0% 0% 0% 0% ftrace showed that there was no stalling on writeback or pages submitted for IO from reclaim context. postmark was similar and while it was more interesting, it also did not push reclaim heavily. POSTMARK 3.3.0-vanilla rc2-vanilla lumpyremove-v2r3 nosync-v2r3 Transactions per second: 16.00 ( 0.00%) 20.00 (25.00%) 18.00 (12.50%) 17.00 ( 6.25%) Data megabytes read per second: 18.80 ( 0.00%) 24.27 (29.10%) 22.26 (18.40%) 20.54 ( 9.26%) Data megabytes written per second: 35.83 ( 0.00%) 46.25 (29.08%) 42.42 (18.39%) 39.14 ( 9.24%) Files created alone per second: 28.00 ( 0.00%) 38.00 (35.71%) 34.00 (21.43%) 30.00 ( 7.14%) Files create/transact per second: 8.00 ( 0.00%) 10.00 (25.00%) 9.00 (12.50%) 8.00 ( 0.00%) Files deleted alone per second: 556.00 ( 0.00%) 1224.00 (120.14%) 3062.00 (450.72%) 6124.00 (1001.44%) Files delete/transact per second: 8.00 ( 0.00%) 10.00 (25.00%) 9.00 (12.50%) 8.00 ( 0.00%) MMTests Statistics: duration Sys Time Running Test (seconds) 113.34 107.99 109.73 108.72 User+Sys Time Running Test (seconds) 145.51 139.81 143.32 143.55 Total Elapsed Time (seconds) 1159.16 899.23 980.17 1062.27 MMTests Statistics: vmstat Page Ins 13710192 13729032 13727944 13760136 Page Outs 43071140 42987228 42733684 42931624 Swap Ins 0 0 0 0 Swap Outs 0 0 0 0 Direct pages scanned 0 0 0 0 Kswapd pages scanned 9941613 9937443 9939085 9929154 Kswapd pages reclaimed 9940926 9936751 9938397 9928465 Direct pages reclaimed 0 0 0 0 Kswapd efficiency 99% 99% 99% 99% Kswapd velocity 8576.567 11051.058 10140.164 9347.109 Direct efficiency 100% 100% 100% 100% Direct velocity 0.000 0.000 0.000 0.000 It looks like here that the full series regresses performance but as ftrace showed no usage of wait_iff_congested() or sync reclaim I am assuming it's a disruption due to monitoring. Other data such as memory usage, page IO, swap IO all looked similar. Running a benchmark with a plain DD showed nothing very interesting. The full series stalled in wait_iff_congested() slightly less but stall times on vanilla kernels were marginal. Running a benchmark that hammered on file-backed mappings showed stalls due to congestion but not in sync writebacks MICRO 3.3.0-vanilla rc2-vanilla lumpyremove-v2r3 nosync-v2r3 MMTests Statistics: duration Sys Time Running Test (seconds) 308.13 294.50 298.75 299.53 User+Sys Time Running Test (seconds) 330.45 316.28 318.93 320.79 Total Elapsed Time (seconds) 1814.90 1833.88 1821.14 1832.91 MMTests Statistics: vmstat Page Ins 108712 120708 97224 110344 Page Outs 155514576 156017404 155813676 156193256 Swap Ins 0 0 0 0 Swap Outs 0 0 0 0 Direct pages scanned 2599253 1550480 2512822 2414760 Kswapd pages scanned 69742364 71150694 68839041 69692533 Kswapd pages reclaimed 34824488 34773341 34796602 34799396 Direct pages reclaimed 53693 94750 61792 75205 Kswapd efficiency 49% 48% 50% 49% Kswapd velocity 38427.662 38797.901 37799.972 38022.889 Direct efficiency 2% 6% 2% 3% Direct velocity 1432.174 845.464 1379.807 1317.446 Percentage direct scans 3% 2% 3% 3% Page writes by reclaim 0 0 0 0 Page writes file 0 0 0 0 Page writes anon 0 0 0 0 Page reclaim immediate 0 0 0 1218 Page rescued immediate 0 0 0 0 Slabs scanned 15360 16384 13312 16384 Direct inode steals 0 0 0 0 Kswapd inode steals 4340 4327 1630 4323 FTrace Reclaim Statistics: congestion_wait Direct number congest waited 0 0 0 0 Direct time congest waited 0ms 0ms 0ms 0ms Direct full congest waited 0 0 0 0 Direct number conditional waited 900 870 754 789 Direct time conditional waited 0ms 0ms 0ms 20ms Direct full conditional waited 0 0 0 0 KSwapd number congest waited 2106 2308 2116 1915 KSwapd time congest waited 139924ms 157832ms 125652ms 132516ms KSwapd full congest waited 1346 1530 1202 1278 KSwapd number conditional waited 12922 16320 10943 14670 KSwapd time conditional waited 0ms 0ms 0ms 0ms KSwapd full conditional waited 0 0 0 0 Reclaim statistics are not radically changed. The stall times in kswapd are massive but it is clear that it is due to calls to congestion_wait() and that is almost certainly the call in balance_pgdat(). Otherwise stalls due to dirty pages are non-existant. I ran a benchmark that stressed high-order allocation. This is very artifical load but was used in the past to evaluate lumpy reclaim and compaction. Generally I look at allocation success rates and latency figures. STRESS-HIGHALLOC 3.3.0-vanilla rc2-vanilla lumpyremove-v2r3 nosync-v2r3 Pass 1 81.00 ( 0.00%) 28.00 (-53.00%) 24.00 (-57.00%) 28.00 (-53.00%) Pass 2 82.00 ( 0.00%) 39.00 (-43.00%) 38.00 (-44.00%) 43.00 (-39.00%) while Rested 88.00 ( 0.00%) 87.00 (-1.00%) 88.00 ( 0.00%) 88.00 ( 0.00%) MMTests Statistics: duration Sys Time Running Test (seconds) 740.93 681.42 685.14 684.87 User+Sys Time Running Test (seconds) 2922.65 3269.52 3281.35 3279.44 Total Elapsed Time (seconds) 1161.73 1152.49 1159.55 1161.44 MMTests Statistics: vmstat Page Ins 4486020 2807256 2855944 2876244 Page Outs 7261600 7973688 7975320 7986120 Swap Ins 31694 0 0 0 Swap Outs 98179 0 0 0 Direct pages scanned 53494 57731 34406 113015 Kswapd pages scanned 6271173 1287481 1278174 1219095 Kswapd pages reclaimed 2029240 1281025 1260708 1201583 Direct pages reclaimed 1468 14564 16649 92456 Kswapd efficiency 32% 99% 98% 98% Kswapd velocity 5398.133 1117.130 1102.302 1049.641 Direct efficiency 2% 25% 48% 81% Direct velocity 46.047 50.092 29.672 97.306 Percentage direct scans 0% 4% 2% 8% Page writes by reclaim 1616049 0 0 0 Page writes file 1517870 0 0 0 Page writes anon 98179 0 0 0 Page reclaim immediate 103778 27339 9796 17831 Page rescued immediate 0 0 0 0 Slabs scanned 1096704 986112 980992 998400 Direct inode steals 223 215040 216736 247881 Kswapd inode steals 175331 61548 68444 63066 Kswapd skipped wait 21991 0 1 0 THP fault alloc 1 135 125 134 THP collapse alloc 393 311 228 236 THP splits 25 13 7 8 THP fault fallback 0 0 0 0 THP collapse fail 3 5 7 7 Compaction stalls 865 1270 1422 1518 Compaction success 370 401 353 383 Compaction failures 495 869 1069 1135 Compaction pages moved 870155 3828868 4036106 4423626 Compaction move failure 26429 23865 29742 27514 Success rates are completely hosed for 3.4-rc2 which is almost certainly due to commit fe2c2a106663 ("vmscan: reclaim at order 0 when compaction is enabled"). I expected this would happen for kswapd and impair allocation success rates (https://lkml.org/lkml/2012/1/25/166) but I did not anticipate this much a difference: 80% less scanning, 37% less reclaim by kswapd In comparison, reclaim/compaction is not aggressive and gives up easily which is the intended behaviour. hugetlbfs uses __GFP_REPEAT and would be much more aggressive about reclaim/compaction than THP allocations are. The stress test above is allocating like neither THP or hugetlbfs but is much closer to THP. Mainline is now impaired in terms of high order allocation under heavy load although I do not know to what degree as I did not test with __GFP_REPEAT. Keep this in mind for bugs related to hugepage pool resizing, THP allocation and high order atomic allocation failures from network devices. In terms of congestion throttling, I see the following for this test FTrace Reclaim Statistics: congestion_wait Direct number congest waited 3 0 0 0 Direct time congest waited 0ms 0ms 0ms 0ms Direct full congest waited 0 0 0 0 Direct number conditional waited 957 512 1081 1075 Direct time conditional waited 0ms 0ms 0ms 0ms Direct full conditional waited 0 0 0 0 KSwapd number congest waited 36 4 3 5 KSwapd time congest waited 3148ms 400ms 300ms 500ms KSwapd full congest waited 30 4 3 5 KSwapd number conditional waited 88514 197 332 542 KSwapd time conditional waited 4980ms 0ms 0ms 0ms KSwapd full conditional waited 49 0 0 0 The "conditional waited" times are the most interesting as this is directly impacted by the number of dirty pages encountered during scan. As lumpy reclaim is no longer scanning contiguous ranges, it is finding fewer dirty pages. This brings wait times from about 5 seconds to 0. kswapd itself is still calling congestion_wait() so it'll still stall but it's a lot less. In terms of the type of IO we were doing, I see this FTrace Reclaim Statistics: mm_vmscan_writepage Direct writes anon sync 0 0 0 0 Direct writes anon async 0 0 0 0 Direct writes file sync 0 0 0 0 Direct writes file async 0 0 0 0 Direct writes mixed sync 0 0 0 0 Direct writes mixed async 0 0 0 0 KSwapd writes anon sync 0 0 0 0 KSwapd writes anon async 91682 0 0 0 KSwapd writes file sync 0 0 0 0 KSwapd writes file async 822629 0 0 0 KSwapd writes mixed sync 0 0 0 0 KSwapd writes mixed async 0 0 0 0 In 3.2, kswapd was doing a bunch of async writes of pages but reclaim/compaction was never reaching a point where it was doing sync IO. This does not guarantee that reclaim/compaction was not calling wait_on_page_writeback() but I would consider it unlikely. It indicates that merging patches 2 and 3 to stop reclaim/compaction calling wait_on_page_writeback() should be safe. This patch: Lumpy reclaim had a purpose but in the mind of some, it was to kick the system so hard it trashed. For others the purpose was to complicate vmscan.c. Over time it was giving softer shoes and a nicer attitude but memory compaction needs to step up and replace it so this patch sends lumpy reclaim to the farm. The tracepoint format changes for isolating LRU pages with this patch applied. Furthermore reclaim/compaction can no longer queue dirty pages in pageout() if the underlying BDI is congested. Lumpy reclaim used this logic and reclaim/compaction was using it in error. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Hugh Dickins <hughd@google.com> Cc: Ying Han <yinghan@google.com> Cc: Andy Whitcroft <apw@shadowen.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-30 06:06:19 +08:00
/* Do not give back unevictable pages for compaction */
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
if (PageUnevictable(page))
return ret;
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
ret = -EBUSY;
memcg: synchronized LRU A big patch for changing memcg's LRU semantics. Now, - page_cgroup is linked to mem_cgroup's its own LRU (per zone). - LRU of page_cgroup is not synchronous with global LRU. - page and page_cgroup is one-to-one and statically allocated. - To find page_cgroup is on what LRU, you have to check pc->mem_cgroup as - lru = page_cgroup_zoneinfo(pc, nid_of_pc, zid_of_pc); - SwapCache is handled. And, when we handle LRU list of page_cgroup, we do following. pc = lookup_page_cgroup(page); lock_page_cgroup(pc); .....................(1) mz = page_cgroup_zoneinfo(pc); spin_lock(&mz->lru_lock); .....add to LRU spin_unlock(&mz->lru_lock); unlock_page_cgroup(pc); But (1) is spin_lock and we have to be afraid of dead-lock with zone->lru_lock. So, trylock() is used at (1), now. Without (1), we can't trust "mz" is correct. This is a trial to remove this dirty nesting of locks. This patch changes mz->lru_lock to be zone->lru_lock. Then, above sequence will be written as spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU mem_cgroup_add/remove/etc_lru() { pc = lookup_page_cgroup(page); mz = page_cgroup_zoneinfo(pc); if (PageCgroupUsed(pc)) { ....add to LRU } spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU This is much simpler. (*) We're safe even if we don't take lock_page_cgroup(pc). Because.. 1. When pc->mem_cgroup can be modified. - at charge. - at account_move(). 2. at charge the PCG_USED bit is not set before pc->mem_cgroup is fixed. 3. at account_move() the page is isolated and not on LRU. Pros. - easy for maintenance. - memcg can make use of laziness of pagevec. - we don't have to duplicated LRU/Active/Unevictable bit in page_cgroup. - LRU status of memcg will be synchronized with global LRU's one. - # of locks are reduced. - account_move() is simplified very much. Cons. - may increase cost of LRU rotation. (no impact if memcg is not configured.) Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 10:08:01 +08:00
/*
* To minimise LRU disruption, the caller can indicate that it only
* wants to isolate pages it will be able to operate on without
* blocking - clean pages for the most part.
*
* ISOLATE_CLEAN means that only clean pages should be isolated. This
* is used by reclaim when it is cannot write to backing storage
*
* ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
* that it is possible to migrate without blocking
*/
if (mode & (ISOLATE_CLEAN|ISOLATE_ASYNC_MIGRATE)) {
/* All the caller can do on PageWriteback is block */
if (PageWriteback(page))
return ret;
if (PageDirty(page)) {
struct address_space *mapping;
/* ISOLATE_CLEAN means only clean pages */
if (mode & ISOLATE_CLEAN)
return ret;
/*
* Only pages without mappings or that have a
* ->migratepage callback are possible to migrate
* without blocking
*/
mapping = page_mapping(page);
if (mapping && !mapping->a_ops->migratepage)
return ret;
}
}
if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
return ret;
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
if (likely(get_page_unless_zero(page))) {
/*
* Be careful not to clear PageLRU until after we're
* sure the page is not being freed elsewhere -- the
* page release code relies on it.
*/
ClearPageLRU(page);
ret = 0;
}
return ret;
}
/*
* zone->lru_lock is heavily contended. Some of the functions that
* shrink the lists perform better by taking out a batch of pages
* and working on them outside the LRU lock.
*
* For pagecache intensive workloads, this function is the hottest
* spot in the kernel (apart from copy_*_user functions).
*
* Appropriate locks must be held before calling this function.
*
* @nr_to_scan: The number of pages to look through on the list.
* @lruvec: The LRU vector to pull pages from.
* @dst: The temp list to put pages on to.
* @nr_scanned: The number of pages that were scanned.
* @sc: The scan_control struct for this reclaim session
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
* @mode: One of the LRU isolation modes
* @lru: LRU list id for isolating
*
* returns how many pages were moved onto *@dst.
*/
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
struct lruvec *lruvec, struct list_head *dst,
unsigned long *nr_scanned, struct scan_control *sc,
isolate_mode_t mode, enum lru_list lru)
{
struct list_head *src = &lruvec->lists[lru];
unsigned long nr_taken = 0;
unsigned long scan;
for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
struct page *page;
int nr_pages;
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
page = lru_to_page(src);
prefetchw_prev_lru_page(page, src, flags);
VM_BUG_ON(!PageLRU(page));
switch (__isolate_lru_page(page, mode)) {
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
case 0:
nr_pages = hpage_nr_pages(page);
mem_cgroup_update_lru_size(lruvec, lru, -nr_pages);
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
list_move(&page->lru, dst);
nr_taken += nr_pages;
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
break;
case -EBUSY:
/* else it is being freed elsewhere */
list_move(&page->lru, src);
continue;
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
default:
BUG();
}
}
*nr_scanned = scan;
trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
nr_taken, mode, is_file_lru(lru));
return nr_taken;
}
vmscan: move isolate_lru_page() to vmscan.c On large memory systems, the VM can spend way too much time scanning through pages that it cannot (or should not) evict from memory. Not only does it use up CPU time, but it also provokes lock contention and can leave large systems under memory presure in a catatonic state. This patch series improves VM scalability by: 1) putting filesystem backed, swap backed and unevictable pages onto their own LRUs, so the system only scans the pages that it can/should evict from memory 2) switching to two handed clock replacement for the anonymous LRUs, so the number of pages that need to be scanned when the system starts swapping is bound to a reasonable number 3) keeping unevictable pages off the LRU completely, so the VM does not waste CPU time scanning them. ramfs, ramdisk, SHM_LOCKED shared memory segments and mlock()ed VMA pages are keept on the unevictable list. This patch: isolate_lru_page logically belongs to be in vmscan.c than migrate.c. It is tough, because we don't need that function without memory migration so there is a valid argument to have it in migrate.c. However a subsequent patch needs to make use of it in the core mm, so we can happily move it to vmscan.c. Also, make the function a little more generic by not requiring that it adds an isolated page to a given list. Callers can do that. Note that we now have '__isolate_lru_page()', that does something quite different, visible outside of vmscan.c for use with memory controller. Methinks we need to rationalize these names/purposes. --lts [akpm@linux-foundation.org: fix mm/memory_hotplug.c build] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:09 +08:00
/**
* isolate_lru_page - tries to isolate a page from its LRU list
* @page: page to isolate from its LRU list
*
* Isolates a @page from an LRU list, clears PageLRU and adjusts the
* vmstat statistic corresponding to whatever LRU list the page was on.
*
* Returns 0 if the page was removed from an LRU list.
* Returns -EBUSY if the page was not on an LRU list.
*
* The returned page will have PageLRU() cleared. If it was found on
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
* the active list, it will have PageActive set. If it was found on
* the unevictable list, it will have the PageUnevictable bit set. That flag
* may need to be cleared by the caller before letting the page go.
vmscan: move isolate_lru_page() to vmscan.c On large memory systems, the VM can spend way too much time scanning through pages that it cannot (or should not) evict from memory. Not only does it use up CPU time, but it also provokes lock contention and can leave large systems under memory presure in a catatonic state. This patch series improves VM scalability by: 1) putting filesystem backed, swap backed and unevictable pages onto their own LRUs, so the system only scans the pages that it can/should evict from memory 2) switching to two handed clock replacement for the anonymous LRUs, so the number of pages that need to be scanned when the system starts swapping is bound to a reasonable number 3) keeping unevictable pages off the LRU completely, so the VM does not waste CPU time scanning them. ramfs, ramdisk, SHM_LOCKED shared memory segments and mlock()ed VMA pages are keept on the unevictable list. This patch: isolate_lru_page logically belongs to be in vmscan.c than migrate.c. It is tough, because we don't need that function without memory migration so there is a valid argument to have it in migrate.c. However a subsequent patch needs to make use of it in the core mm, so we can happily move it to vmscan.c. Also, make the function a little more generic by not requiring that it adds an isolated page to a given list. Callers can do that. Note that we now have '__isolate_lru_page()', that does something quite different, visible outside of vmscan.c for use with memory controller. Methinks we need to rationalize these names/purposes. --lts [akpm@linux-foundation.org: fix mm/memory_hotplug.c build] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:09 +08:00
*
* The vmstat statistic corresponding to the list on which the page was
* found will be decremented.
*
* Restrictions:
* (1) Must be called with an elevated refcount on the page. This is a
* fundamentnal difference from isolate_lru_pages (which is called
* without a stable reference).
* (2) the lru_lock must not be held.
* (3) interrupts must be enabled.
*/
int isolate_lru_page(struct page *page)
{
int ret = -EBUSY;
mm: strictly require elevated page refcount in isolate_lru_page() isolate_lru_page() must be called only with stable reference to the page, this is what is written in the comment above it, this is reasonable. current isolate_lru_page() users and its page extra reference sources: mm/huge_memory.c: __collapse_huge_page_isolate() - reference from pte mm/memcontrol.c: mem_cgroup_move_parent() - get_page_unless_zero() mem_cgroup_move_charge_pte_range() - reference from pte mm/memory-failure.c: soft_offline_page() - fixed, reference from get_any_page() delete_from_lru_cache() - reference from caller or get_page_unless_zero() [ seems like there bug, because __memory_failure() can call page_action() for hpages tail, but it is ok for isolate_lru_page(), tail getted and not in lru] mm/memory_hotplug.c: do_migrate_range() - fixed, get_page_unless_zero() mm/mempolicy.c: migrate_page_add() - reference from pte mm/migrate.c: do_move_page_to_node_array() - reference from follow_page() mlock.c: - various external references mm/vmscan.c: putback_lru_page() - reference from isolate_lru_page() It seems that all isolate_lru_page() users are ready now for this restriction. So, let's replace redundant get_page_unless_zero() with get_page() and add page initial reference count check with VM_BUG_ON() Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 08:12:21 +08:00
VM_BUG_ON(!page_count(page));
vmscan: move isolate_lru_page() to vmscan.c On large memory systems, the VM can spend way too much time scanning through pages that it cannot (or should not) evict from memory. Not only does it use up CPU time, but it also provokes lock contention and can leave large systems under memory presure in a catatonic state. This patch series improves VM scalability by: 1) putting filesystem backed, swap backed and unevictable pages onto their own LRUs, so the system only scans the pages that it can/should evict from memory 2) switching to two handed clock replacement for the anonymous LRUs, so the number of pages that need to be scanned when the system starts swapping is bound to a reasonable number 3) keeping unevictable pages off the LRU completely, so the VM does not waste CPU time scanning them. ramfs, ramdisk, SHM_LOCKED shared memory segments and mlock()ed VMA pages are keept on the unevictable list. This patch: isolate_lru_page logically belongs to be in vmscan.c than migrate.c. It is tough, because we don't need that function without memory migration so there is a valid argument to have it in migrate.c. However a subsequent patch needs to make use of it in the core mm, so we can happily move it to vmscan.c. Also, make the function a little more generic by not requiring that it adds an isolated page to a given list. Callers can do that. Note that we now have '__isolate_lru_page()', that does something quite different, visible outside of vmscan.c for use with memory controller. Methinks we need to rationalize these names/purposes. --lts [akpm@linux-foundation.org: fix mm/memory_hotplug.c build] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:09 +08:00
if (PageLRU(page)) {
struct zone *zone = page_zone(page);
struct lruvec *lruvec;
vmscan: move isolate_lru_page() to vmscan.c On large memory systems, the VM can spend way too much time scanning through pages that it cannot (or should not) evict from memory. Not only does it use up CPU time, but it also provokes lock contention and can leave large systems under memory presure in a catatonic state. This patch series improves VM scalability by: 1) putting filesystem backed, swap backed and unevictable pages onto their own LRUs, so the system only scans the pages that it can/should evict from memory 2) switching to two handed clock replacement for the anonymous LRUs, so the number of pages that need to be scanned when the system starts swapping is bound to a reasonable number 3) keeping unevictable pages off the LRU completely, so the VM does not waste CPU time scanning them. ramfs, ramdisk, SHM_LOCKED shared memory segments and mlock()ed VMA pages are keept on the unevictable list. This patch: isolate_lru_page logically belongs to be in vmscan.c than migrate.c. It is tough, because we don't need that function without memory migration so there is a valid argument to have it in migrate.c. However a subsequent patch needs to make use of it in the core mm, so we can happily move it to vmscan.c. Also, make the function a little more generic by not requiring that it adds an isolated page to a given list. Callers can do that. Note that we now have '__isolate_lru_page()', that does something quite different, visible outside of vmscan.c for use with memory controller. Methinks we need to rationalize these names/purposes. --lts [akpm@linux-foundation.org: fix mm/memory_hotplug.c build] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:09 +08:00
spin_lock_irq(&zone->lru_lock);
lruvec = mem_cgroup_page_lruvec(page, zone);
mm: strictly require elevated page refcount in isolate_lru_page() isolate_lru_page() must be called only with stable reference to the page, this is what is written in the comment above it, this is reasonable. current isolate_lru_page() users and its page extra reference sources: mm/huge_memory.c: __collapse_huge_page_isolate() - reference from pte mm/memcontrol.c: mem_cgroup_move_parent() - get_page_unless_zero() mem_cgroup_move_charge_pte_range() - reference from pte mm/memory-failure.c: soft_offline_page() - fixed, reference from get_any_page() delete_from_lru_cache() - reference from caller or get_page_unless_zero() [ seems like there bug, because __memory_failure() can call page_action() for hpages tail, but it is ok for isolate_lru_page(), tail getted and not in lru] mm/memory_hotplug.c: do_migrate_range() - fixed, get_page_unless_zero() mm/mempolicy.c: migrate_page_add() - reference from pte mm/migrate.c: do_move_page_to_node_array() - reference from follow_page() mlock.c: - various external references mm/vmscan.c: putback_lru_page() - reference from isolate_lru_page() It seems that all isolate_lru_page() users are ready now for this restriction. So, let's replace redundant get_page_unless_zero() with get_page() and add page initial reference count check with VM_BUG_ON() Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 08:12:21 +08:00
if (PageLRU(page)) {
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
int lru = page_lru(page);
mm: strictly require elevated page refcount in isolate_lru_page() isolate_lru_page() must be called only with stable reference to the page, this is what is written in the comment above it, this is reasonable. current isolate_lru_page() users and its page extra reference sources: mm/huge_memory.c: __collapse_huge_page_isolate() - reference from pte mm/memcontrol.c: mem_cgroup_move_parent() - get_page_unless_zero() mem_cgroup_move_charge_pte_range() - reference from pte mm/memory-failure.c: soft_offline_page() - fixed, reference from get_any_page() delete_from_lru_cache() - reference from caller or get_page_unless_zero() [ seems like there bug, because __memory_failure() can call page_action() for hpages tail, but it is ok for isolate_lru_page(), tail getted and not in lru] mm/memory_hotplug.c: do_migrate_range() - fixed, get_page_unless_zero() mm/mempolicy.c: migrate_page_add() - reference from pte mm/migrate.c: do_move_page_to_node_array() - reference from follow_page() mlock.c: - various external references mm/vmscan.c: putback_lru_page() - reference from isolate_lru_page() It seems that all isolate_lru_page() users are ready now for this restriction. So, let's replace redundant get_page_unless_zero() with get_page() and add page initial reference count check with VM_BUG_ON() Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 08:12:21 +08:00
get_page(page);
vmscan: move isolate_lru_page() to vmscan.c On large memory systems, the VM can spend way too much time scanning through pages that it cannot (or should not) evict from memory. Not only does it use up CPU time, but it also provokes lock contention and can leave large systems under memory presure in a catatonic state. This patch series improves VM scalability by: 1) putting filesystem backed, swap backed and unevictable pages onto their own LRUs, so the system only scans the pages that it can/should evict from memory 2) switching to two handed clock replacement for the anonymous LRUs, so the number of pages that need to be scanned when the system starts swapping is bound to a reasonable number 3) keeping unevictable pages off the LRU completely, so the VM does not waste CPU time scanning them. ramfs, ramdisk, SHM_LOCKED shared memory segments and mlock()ed VMA pages are keept on the unevictable list. This patch: isolate_lru_page logically belongs to be in vmscan.c than migrate.c. It is tough, because we don't need that function without memory migration so there is a valid argument to have it in migrate.c. However a subsequent patch needs to make use of it in the core mm, so we can happily move it to vmscan.c. Also, make the function a little more generic by not requiring that it adds an isolated page to a given list. Callers can do that. Note that we now have '__isolate_lru_page()', that does something quite different, visible outside of vmscan.c for use with memory controller. Methinks we need to rationalize these names/purposes. --lts [akpm@linux-foundation.org: fix mm/memory_hotplug.c build] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:09 +08:00
ClearPageLRU(page);
del_page_from_lru_list(page, lruvec, lru);
ret = 0;
vmscan: move isolate_lru_page() to vmscan.c On large memory systems, the VM can spend way too much time scanning through pages that it cannot (or should not) evict from memory. Not only does it use up CPU time, but it also provokes lock contention and can leave large systems under memory presure in a catatonic state. This patch series improves VM scalability by: 1) putting filesystem backed, swap backed and unevictable pages onto their own LRUs, so the system only scans the pages that it can/should evict from memory 2) switching to two handed clock replacement for the anonymous LRUs, so the number of pages that need to be scanned when the system starts swapping is bound to a reasonable number 3) keeping unevictable pages off the LRU completely, so the VM does not waste CPU time scanning them. ramfs, ramdisk, SHM_LOCKED shared memory segments and mlock()ed VMA pages are keept on the unevictable list. This patch: isolate_lru_page logically belongs to be in vmscan.c than migrate.c. It is tough, because we don't need that function without memory migration so there is a valid argument to have it in migrate.c. However a subsequent patch needs to make use of it in the core mm, so we can happily move it to vmscan.c. Also, make the function a little more generic by not requiring that it adds an isolated page to a given list. Callers can do that. Note that we now have '__isolate_lru_page()', that does something quite different, visible outside of vmscan.c for use with memory controller. Methinks we need to rationalize these names/purposes. --lts [akpm@linux-foundation.org: fix mm/memory_hotplug.c build] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:09 +08:00
}
spin_unlock_irq(&zone->lru_lock);
}
return ret;
}
/*
* Are there way too many processes in the direct reclaim path already?
*/
static int too_many_isolated(struct zone *zone, int file,
struct scan_control *sc)
{
unsigned long inactive, isolated;
if (current_is_kswapd())
return 0;
if (!global_reclaim(sc))
return 0;
if (file) {
inactive = zone_page_state(zone, NR_INACTIVE_FILE);
isolated = zone_page_state(zone, NR_ISOLATED_FILE);
} else {
inactive = zone_page_state(zone, NR_INACTIVE_ANON);
isolated = zone_page_state(zone, NR_ISOLATED_ANON);
}
return isolated > inactive;
}
static noinline_for_stack void
putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
{
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
struct zone *zone = lruvec_zone(lruvec);
LIST_HEAD(pages_to_free);
/*
* Put back any unfreeable pages.
*/
while (!list_empty(page_list)) {
struct page *page = lru_to_page(page_list);
int lru;
VM_BUG_ON(PageLRU(page));
list_del(&page->lru);
if (unlikely(!page_evictable(page, NULL))) {
spin_unlock_irq(&zone->lru_lock);
putback_lru_page(page);
spin_lock_irq(&zone->lru_lock);
continue;
}
lruvec = mem_cgroup_page_lruvec(page, zone);
SetPageLRU(page);
lru = page_lru(page);
add_page_to_lru_list(page, lruvec, lru);
if (is_active_lru(lru)) {
int file = is_file_lru(lru);
int numpages = hpage_nr_pages(page);
reclaim_stat->recent_rotated[file] += numpages;
}
mm: take pagevecs off reclaim stack Replace pagevecs in putback_lru_pages() and move_active_pages_to_lru() by lists of pages_to_free: then apply Konstantin Khlebnikov's free_hot_cold_page_list() to them instead of pagevec_release(). Which simplifies the flow (no need to drop and retake lock whenever pagevec fills up) and reduces stale addresses in stack backtraces (which often showed through the pagevecs); but more importantly, removes another 120 bytes from the deepest stacks in page reclaim. Although I've not recently seen an actual stack overflow here with a vanilla kernel, move_active_pages_to_lru() has often featured in deep backtraces. However, free_hot_cold_page_list() does not handle compound pages (nor need it: a Transparent HugePage would have been split by the time it reaches the call in shrink_page_list()), but it is possible for putback_lru_pages() or move_active_pages_to_lru() to be left holding the last reference on a THP, so must exclude the unlikely compound case before putting on pages_to_free. Remove pagevec_strip(), its work now done in move_active_pages_to_lru(). The pagevec in scan_mapping_unevictable_pages() remains in mm/vmscan.c, but that is never on the reclaim path, and cannot be replaced by a list. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 09:19:56 +08:00
if (put_page_testzero(page)) {
__ClearPageLRU(page);
__ClearPageActive(page);
del_page_from_lru_list(page, lruvec, lru);
mm: take pagevecs off reclaim stack Replace pagevecs in putback_lru_pages() and move_active_pages_to_lru() by lists of pages_to_free: then apply Konstantin Khlebnikov's free_hot_cold_page_list() to them instead of pagevec_release(). Which simplifies the flow (no need to drop and retake lock whenever pagevec fills up) and reduces stale addresses in stack backtraces (which often showed through the pagevecs); but more importantly, removes another 120 bytes from the deepest stacks in page reclaim. Although I've not recently seen an actual stack overflow here with a vanilla kernel, move_active_pages_to_lru() has often featured in deep backtraces. However, free_hot_cold_page_list() does not handle compound pages (nor need it: a Transparent HugePage would have been split by the time it reaches the call in shrink_page_list()), but it is possible for putback_lru_pages() or move_active_pages_to_lru() to be left holding the last reference on a THP, so must exclude the unlikely compound case before putting on pages_to_free. Remove pagevec_strip(), its work now done in move_active_pages_to_lru(). The pagevec in scan_mapping_unevictable_pages() remains in mm/vmscan.c, but that is never on the reclaim path, and cannot be replaced by a list. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 09:19:56 +08:00
if (unlikely(PageCompound(page))) {
spin_unlock_irq(&zone->lru_lock);
(*get_compound_page_dtor(page))(page);
spin_lock_irq(&zone->lru_lock);
} else
list_add(&page->lru, &pages_to_free);
}
}
/*
* To save our caller's stack, now use input list for pages to free.
*/
list_splice(&pages_to_free, page_list);
}
/*
* shrink_inactive_list() is a helper for shrink_zone(). It returns the number
* of reclaimed pages
*/
static noinline_for_stack unsigned long
shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
struct scan_control *sc, enum lru_list lru)
{
LIST_HEAD(page_list);
unsigned long nr_scanned;
unsigned long nr_reclaimed = 0;
unsigned long nr_taken;
mm: vmscan: throttle reclaim if encountering too many dirty pages under writeback Workloads that are allocating frequently and writing files place a large number of dirty pages on the LRU. With use-once logic, it is possible for them to reach the end of the LRU quickly requiring the reclaimer to scan more to find clean pages. Ordinarily, processes that are dirtying memory will get throttled by dirty balancing but this is a global heuristic and does not take into account that LRUs are maintained on a per-zone basis. This can lead to a situation whereby reclaim is scanning heavily, skipping over a large number of pages under writeback and recycling them around the LRU consuming CPU. This patch checks how many of the number of pages isolated from the LRU were dirty and under writeback. If a percentage of them under writeback, the process will be throttled if a backing device or the zone is congested. Note that this applies whether it is anonymous or file-backed pages that are under writeback meaning that swapping is potentially throttled. This is intentional due to the fact if the swap device is congested, scanning more pages and dispatching more IO is not going to help matters. The percentage that must be in writeback depends on the priority. At default priority, all of them must be dirty. At DEF_PRIORITY-1, 50% of them must be, DEF_PRIORITY-2, 25% etc. i.e. as pressure increases the greater the likelihood the process will get throttled to allow the flusher threads to make some progress. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Johannes Weiner <jweiner@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Alex Elder <aelder@sgi.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 08:07:56 +08:00
unsigned long nr_dirty = 0;
unsigned long nr_writeback = 0;
isolate_mode_t isolate_mode = 0;
int file = is_file_lru(lru);
struct zone *zone = lruvec_zone(lruvec);
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
vmscan: low order lumpy reclaim also should use PAGEOUT_IO_SYNC Commit 33c120ed2843090e2bd316de1588b8bf8b96cbde ("more aggressively use lumpy reclaim") increased how aggressive lumpy reclaim was by isolating both active and inactive pages for asynchronous lumpy reclaim on costly-high-order pages and for cheap-high-order when memory pressure is high. However, if the system is under heavy pressure and there are dirty pages, asynchronous IO may not be sufficient to reclaim a suitable page in time. This patch causes the caller to enter synchronous lumpy reclaim for costly-high-order pages and for cheap-high-order pages when under memory pressure. Minchan.kim@gmail.com said: Andy added synchronous lumpy reclaim with c661b078fd62abe06fd11fab4ac5e4eeafe26b6d. At that time, lumpy reclaim is not agressive. His intension is just for high-order users.(above PAGE_ALLOC_COSTLY_ORDER). After some time, Rik added aggressive lumpy reclaim with 33c120ed2843090e2bd316de1588b8bf8b96cbde. His intention was to do lumpy reclaim when high-order users and trouble getting a small set of contiguous pages. So we also have to add synchronous pageout for small set of contiguous pages. Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Minchan Kim <Minchan.kim@gmail.com> Reviewed-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:31:40 +08:00
while (unlikely(too_many_isolated(zone, file, sc))) {
congestion_wait(BLK_RW_ASYNC, HZ/10);
/* We are about to die and free our memory. Return now. */
if (fatal_signal_pending(current))
return SWAP_CLUSTER_MAX;
}
lru_add_drain();
if (!sc->may_unmap)
isolate_mode |= ISOLATE_UNMAPPED;
if (!sc->may_writepage)
isolate_mode |= ISOLATE_CLEAN;
spin_lock_irq(&zone->lru_lock);
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
&nr_scanned, sc, isolate_mode, lru);
__mod_zone_page_state(zone, NR_LRU_BASE + lru, -nr_taken);
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
if (global_reclaim(sc)) {
zone->pages_scanned += nr_scanned;
if (current_is_kswapd())
__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned);
else
__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned);
}
spin_unlock_irq(&zone->lru_lock);
if (nr_taken == 0)
return 0;
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
nr_reclaimed = shrink_page_list(&page_list, zone, sc,
mm: vmscan: throttle reclaim if encountering too many dirty pages under writeback Workloads that are allocating frequently and writing files place a large number of dirty pages on the LRU. With use-once logic, it is possible for them to reach the end of the LRU quickly requiring the reclaimer to scan more to find clean pages. Ordinarily, processes that are dirtying memory will get throttled by dirty balancing but this is a global heuristic and does not take into account that LRUs are maintained on a per-zone basis. This can lead to a situation whereby reclaim is scanning heavily, skipping over a large number of pages under writeback and recycling them around the LRU consuming CPU. This patch checks how many of the number of pages isolated from the LRU were dirty and under writeback. If a percentage of them under writeback, the process will be throttled if a backing device or the zone is congested. Note that this applies whether it is anonymous or file-backed pages that are under writeback meaning that swapping is potentially throttled. This is intentional due to the fact if the swap device is congested, scanning more pages and dispatching more IO is not going to help matters. The percentage that must be in writeback depends on the priority. At default priority, all of them must be dirty. At DEF_PRIORITY-1, 50% of them must be, DEF_PRIORITY-2, 25% etc. i.e. as pressure increases the greater the likelihood the process will get throttled to allow the flusher threads to make some progress. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Johannes Weiner <jweiner@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Alex Elder <aelder@sgi.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 08:07:56 +08:00
&nr_dirty, &nr_writeback);
spin_lock_irq(&zone->lru_lock);
reclaim_stat->recent_scanned[file] += nr_taken;
if (global_reclaim(sc)) {
if (current_is_kswapd())
__count_zone_vm_events(PGSTEAL_KSWAPD, zone,
nr_reclaimed);
else
__count_zone_vm_events(PGSTEAL_DIRECT, zone,
nr_reclaimed);
}
putback_inactive_pages(lruvec, &page_list);
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
spin_unlock_irq(&zone->lru_lock);
free_hot_cold_page_list(&page_list, 1);
tracing, vmscan: add trace events for LRU list shrinking There have been numerous reports of stalls that pointed at the problem being somewhere in the VM. There are multiple roots to the problems which means dealing with any of the root problems in isolation is tricky to justify on their own and they would still need integration testing. This patch series puts together two different patch sets which in combination should tackle some of the root causes of latency problems being reported. Patch 1 adds a tracepoint for shrink_inactive_list. For this series, the most important results is being able to calculate the scanning/reclaim ratio as a measure of the amount of work being done by page reclaim. Patch 2 accounts for time spent in congestion_wait. Patches 3-6 were originally developed by Kosaki Motohiro but reworked for this series. It has been noted that lumpy reclaim is far too aggressive and trashes the system somewhat. As SLUB uses high-order allocations, a large cost incurred by lumpy reclaim will be noticeable. It was also reported during transparent hugepage support testing that lumpy reclaim was trashing the system and these patches should mitigate that problem without disabling lumpy reclaim. Patch 7 adds wait_iff_congested() and replaces some callers of congestion_wait(). wait_iff_congested() only sleeps if there is a BDI that is currently congested. Patch 8 notes that any BDI being congested is not necessarily a problem because there could be multiple BDIs of varying speeds and numberous zones. It attempts to track when a zone being reclaimed contains many pages backed by a congested BDI and if so, reclaimers wait on the congestion queue. I ran a number of tests with monitoring on X86, X86-64 and PPC64. Each machine had 3G of RAM and the CPUs were X86: Intel P4 2-core X86-64: AMD Phenom 4-core PPC64: PPC970MP Each used a single disk and the onboard IO controller. Dirty ratio was left at 20. I'm just going to report for X86-64 and PPC64 in a vague attempt to keep this report short. Four kernels were tested each based on v2.6.36-rc4 traceonly-v2r2: Patches 1 and 2 to instrument vmscan reclaims and congestion_wait lowlumpy-v2r3: Patches 1-6 to test if lumpy reclaim is better waitcongest-v2r3: Patches 1-7 to only wait on congestion waitwriteback-v2r4: Patches 1-8 to detect when a zone is congested nocongest-v1r5: Patches 1-3 for testing wait_iff_congestion nodirect-v1r5: Patches 1-10 to disable filesystem writeback for better IO The tests run were as follows kernbench compile-based benchmark. Smoke test performance sysbench OLTP read-only benchmark. Will be re-run in the future as read-write micro-mapped-file-stream This is a micro-benchmark from Johannes Weiner that accesses a large sparse-file through mmap(). It was configured to run in only single-CPU mode but can be indicative of how well page reclaim identifies suitable pages. stress-highalloc Tries to allocate huge pages under heavy load. kernbench, iozone and sysbench did not report any performance regression on any machine. sysbench did pressure the system lightly and there was reclaim activity but there were no difference of major interest between the kernels. X86-64 micro-mapped-file-stream traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3 waitwriteback-v2r4 pgalloc_dma 1639.00 ( 0.00%) 667.00 (-145.73%) 1167.00 ( -40.45%) 578.00 (-183.56%) pgalloc_dma32 2842410.00 ( 0.00%) 2842626.00 ( 0.01%) 2843043.00 ( 0.02%) 2843014.00 ( 0.02%) pgalloc_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgsteal_dma 729.00 ( 0.00%) 85.00 (-757.65%) 609.00 ( -19.70%) 125.00 (-483.20%) pgsteal_dma32 2338721.00 ( 0.00%) 2447354.00 ( 4.44%) 2429536.00 ( 3.74%) 2436772.00 ( 4.02%) pgsteal_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgscan_kswapd_dma 1469.00 ( 0.00%) 532.00 (-176.13%) 1078.00 ( -36.27%) 220.00 (-567.73%) pgscan_kswapd_dma32 4597713.00 ( 0.00%) 4503597.00 ( -2.09%) 4295673.00 ( -7.03%) 3891686.00 ( -18.14%) pgscan_kswapd_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgscan_direct_dma 71.00 ( 0.00%) 134.00 ( 47.01%) 243.00 ( 70.78%) 352.00 ( 79.83%) pgscan_direct_dma32 305820.00 ( 0.00%) 280204.00 ( -9.14%) 600518.00 ( 49.07%) 957485.00 ( 68.06%) pgscan_direct_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pageoutrun 16296.00 ( 0.00%) 21254.00 ( 23.33%) 18447.00 ( 11.66%) 20067.00 ( 18.79%) allocstall 443.00 ( 0.00%) 273.00 ( -62.27%) 513.00 ( 13.65%) 1568.00 ( 71.75%) These are based on the raw figures taken from /proc/vmstat. It's a rough measure of reclaim activity. Note that allocstall counts are higher because we are entering direct reclaim more often as a result of not sleeping in congestion. In itself, it's not necessarily a bad thing. It's easier to get a view of what happened from the vmscan tracepoint report. FTrace Reclaim Statistics: vmscan traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3 waitwriteback-v2r4 Direct reclaims 443 273 513 1568 Direct reclaim pages scanned 305968 280402 600825 957933 Direct reclaim pages reclaimed 43503 19005 30327 117191 Direct reclaim write file async I/O 0 0 0 0 Direct reclaim write anon async I/O 0 3 4 12 Direct reclaim write file sync I/O 0 0 0 0 Direct reclaim write anon sync I/O 0 0 0 0 Wake kswapd requests 187649 132338 191695 267701 Kswapd wakeups 3 1 4 1 Kswapd pages scanned 4599269 4454162 4296815 3891906 Kswapd pages reclaimed 2295947 2428434 2399818 2319706 Kswapd reclaim write file async I/O 1 0 1 1 Kswapd reclaim write anon async I/O 59 187 41 222 Kswapd reclaim write file sync I/O 0 0 0 0 Kswapd reclaim write anon sync I/O 0 0 0 0 Time stalled direct reclaim (seconds) 4.34 2.52 6.63 2.96 Time kswapd awake (seconds) 11.15 10.25 11.01 10.19 Total pages scanned 4905237 4734564 4897640 4849839 Total pages reclaimed 2339450 2447439 2430145 2436897 %age total pages scanned/reclaimed 47.69% 51.69% 49.62% 50.25% %age total pages scanned/written 0.00% 0.00% 0.00% 0.00% %age file pages scanned/written 0.00% 0.00% 0.00% 0.00% Percentage Time Spent Direct Reclaim 29.23% 19.02% 38.48% 20.25% Percentage Time kswapd Awake 78.58% 78.85% 76.83% 79.86% What is interesting here for nocongest in particular is that while direct reclaim scans more pages, the overall number of pages scanned remains the same and the ratio of pages scanned to pages reclaimed is more or less the same. In other words, while we are sleeping less, reclaim is not doing more work and as direct reclaim and kswapd is awake for less time, it would appear to be doing less work. FTrace Reclaim Statistics: congestion_wait Direct number congest waited 87 196 64 0 Direct time congest waited 4604ms 4732ms 5420ms 0ms Direct full congest waited 72 145 53 0 Direct number conditional waited 0 0 324 1315 Direct time conditional waited 0ms 0ms 0ms 0ms Direct full conditional waited 0 0 0 0 KSwapd number congest waited 20 10 15 7 KSwapd time congest waited 1264ms 536ms 884ms 284ms KSwapd full congest waited 10 4 6 2 KSwapd number conditional waited 0 0 0 0 KSwapd time conditional waited 0ms 0ms 0ms 0ms KSwapd full conditional waited 0 0 0 0 The vanilla kernel spent 8 seconds asleep in direct reclaim and no time at all asleep with the patches. MMTests Statistics: duration User/Sys Time Running Test (seconds) 10.51 10.73 10.6 11.66 Total Elapsed Time (seconds) 14.19 13.00 14.33 12.76 Overall, the tests completed faster. It is interesting to note that backing off further when a zone is congested and not just a BDI was more efficient overall. PPC64 micro-mapped-file-stream pgalloc_dma 3024660.00 ( 0.00%) 3027185.00 ( 0.08%) 3025845.00 ( 0.04%) 3026281.00 ( 0.05%) pgalloc_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgsteal_dma 2508073.00 ( 0.00%) 2565351.00 ( 2.23%) 2463577.00 ( -1.81%) 2532263.00 ( 0.96%) pgsteal_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgscan_kswapd_dma 4601307.00 ( 0.00%) 4128076.00 ( -11.46%) 3912317.00 ( -17.61%) 3377165.00 ( -36.25%) pgscan_kswapd_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgscan_direct_dma 629825.00 ( 0.00%) 971622.00 ( 35.18%) 1063938.00 ( 40.80%) 1711935.00 ( 63.21%) pgscan_direct_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pageoutrun 27776.00 ( 0.00%) 20458.00 ( -35.77%) 18763.00 ( -48.04%) 18157.00 ( -52.98%) allocstall 977.00 ( 0.00%) 2751.00 ( 64.49%) 2098.00 ( 53.43%) 5136.00 ( 80.98%) Similar trends to x86-64. allocstalls are up but it's not necessarily bad. FTrace Reclaim Statistics: vmscan Direct reclaims 977 2709 2098 5136 Direct reclaim pages scanned 629825 963814 1063938 1711935 Direct reclaim pages reclaimed 75550 242538 150904 387647 Direct reclaim write file async I/O 0 0 0 2 Direct reclaim write anon async I/O 0 10 0 4 Direct reclaim write file sync I/O 0 0 0 0 Direct reclaim write anon sync I/O 0 0 0 0 Wake kswapd requests 392119 1201712 571935 571921 Kswapd wakeups 3 2 3 3 Kswapd pages scanned 4601307 4128076 3912317 3377165 Kswapd pages reclaimed 2432523 2318797 2312673 2144616 Kswapd reclaim write file async I/O 20 1 1 1 Kswapd reclaim write anon async I/O 57 132 11 121 Kswapd reclaim write file sync I/O 0 0 0 0 Kswapd reclaim write anon sync I/O 0 0 0 0 Time stalled direct reclaim (seconds) 6.19 7.30 13.04 10.88 Time kswapd awake (seconds) 21.73 26.51 25.55 23.90 Total pages scanned 5231132 5091890 4976255 5089100 Total pages reclaimed 2508073 2561335 2463577 2532263 %age total pages scanned/reclaimed 47.95% 50.30% 49.51% 49.76% %age total pages scanned/written 0.00% 0.00% 0.00% 0.00% %age file pages scanned/written 0.00% 0.00% 0.00% 0.00% Percentage Time Spent Direct Reclaim 18.89% 20.65% 32.65% 27.65% Percentage Time kswapd Awake 72.39% 80.68% 78.21% 77.40% Again, a similar trend that the congestion_wait changes mean that direct reclaim scans more pages but the overall number of pages scanned while slightly reduced, are very similar. The ratio of scanning/reclaimed remains roughly similar. The downside is that kswapd and direct reclaim was awake longer and for a larger percentage of the overall workload. It's possible there were big differences in the amount of time spent reclaiming slab pages between the different kernels which is plausible considering that the micro tests runs after fsmark and sysbench. Trace Reclaim Statistics: congestion_wait Direct number congest waited 845 1312 104 0 Direct time congest waited 19416ms 26560ms 7544ms 0ms Direct full congest waited 745 1105 72 0 Direct number conditional waited 0 0 1322 2935 Direct time conditional waited 0ms 0ms 12ms 312ms Direct full conditional waited 0 0 0 3 KSwapd number congest waited 39 102 75 63 KSwapd time congest waited 2484ms 6760ms 5756ms 3716ms KSwapd full congest waited 20 48 46 25 KSwapd number conditional waited 0 0 0 0 KSwapd time conditional waited 0ms 0ms 0ms 0ms KSwapd full conditional waited 0 0 0 0 The vanilla kernel spent 20 seconds asleep in direct reclaim and only 312ms asleep with the patches. The time kswapd spent congest waited was also reduced by a large factor. MMTests Statistics: duration ser/Sys Time Running Test (seconds) 26.58 28.05 26.9 28.47 Total Elapsed Time (seconds) 30.02 32.86 32.67 30.88 With all patches applies, the completion times are very similar. X86-64 STRESS-HIGHALLOC traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3waitwriteback-v2r4 Pass 1 82.00 ( 0.00%) 84.00 ( 2.00%) 85.00 ( 3.00%) 85.00 ( 3.00%) Pass 2 90.00 ( 0.00%) 87.00 (-3.00%) 88.00 (-2.00%) 89.00 (-1.00%) At Rest 92.00 ( 0.00%) 90.00 (-2.00%) 90.00 (-2.00%) 91.00 (-1.00%) Success figures across the board are broadly similar. traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3waitwriteback-v2r4 Direct reclaims 1045 944 886 887 Direct reclaim pages scanned 135091 119604 109382 101019 Direct reclaim pages reclaimed 88599 47535 47863 46671 Direct reclaim write file async I/O 494 283 465 280 Direct reclaim write anon async I/O 29357 13710 16656 13462 Direct reclaim write file sync I/O 154 2 2 3 Direct reclaim write anon sync I/O 14594 571 509 561 Wake kswapd requests 7491 933 872 892 Kswapd wakeups 814 778 731 780 Kswapd pages scanned 7290822 15341158 11916436 13703442 Kswapd pages reclaimed 3587336 3142496 3094392 3187151 Kswapd reclaim write file async I/O 91975 32317 28022 29628 Kswapd reclaim write anon async I/O 1992022 789307 829745 849769 Kswapd reclaim write file sync I/O 0 0 0 0 Kswapd reclaim write anon sync I/O 0 0 0 0 Time stalled direct reclaim (seconds) 4588.93 2467.16 2495.41 2547.07 Time kswapd awake (seconds) 2497.66 1020.16 1098.06 1176.82 Total pages scanned 7425913 15460762 12025818 13804461 Total pages reclaimed 3675935 3190031 3142255 3233822 %age total pages scanned/reclaimed 49.50% 20.63% 26.13% 23.43% %age total pages scanned/written 28.66% 5.41% 7.28% 6.47% %age file pages scanned/written 1.25% 0.21% 0.24% 0.22% Percentage Time Spent Direct Reclaim 57.33% 42.15% 42.41% 42.99% Percentage Time kswapd Awake 43.56% 27.87% 29.76% 31.25% Scanned/reclaimed ratios again look good with big improvements in efficiency. The Scanned/written ratios also look much improved. With a better scanned/written ration, there is an expectation that IO would be more efficient and indeed, the time spent in direct reclaim is much reduced by the full series and kswapd spends a little less time awake. Overall, indications here are that allocations were happening much faster and this can be seen with a graph of the latency figures as the allocations were taking place http://www.csn.ul.ie/~mel/postings/vmscanreduce-20101509/highalloc-interlatency-hydra-mean.ps FTrace Reclaim Statistics: congestion_wait Direct number congest waited 1333 204 169 4 Direct time congest waited 78896ms 8288ms 7260ms 200ms Direct full congest waited 756 92 69 2 Direct number conditional waited 0 0 26 186 Direct time conditional waited 0ms 0ms 0ms 2504ms Direct full conditional waited 0 0 0 25 KSwapd number congest waited 4 395 227 282 KSwapd time congest waited 384ms 25136ms 10508ms 18380ms KSwapd full congest waited 3 232 98 176 KSwapd number conditional waited 0 0 0 0 KSwapd time conditional waited 0ms 0ms 0ms 0ms KSwapd full conditional waited 0 0 0 0 KSwapd full conditional waited 318 0 312 9 Overall, the time spent speeping is reduced. kswapd is still hitting congestion_wait() but that is because there are callers remaining where it wasn't clear in advance if they should be changed to wait_iff_congested() or not. Overall the sleep imes are reduced though - from 79ish seconds to about 19. MMTests Statistics: duration User/Sys Time Running Test (seconds) 3415.43 3386.65 3388.39 3377.5 Total Elapsed Time (seconds) 5733.48 3660.33 3689.41 3765.39 With the full series, the time to complete the tests are reduced by 30% PPC64 STRESS-HIGHALLOC traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3waitwriteback-v2r4 Pass 1 17.00 ( 0.00%) 34.00 (17.00%) 38.00 (21.00%) 43.00 (26.00%) Pass 2 25.00 ( 0.00%) 37.00 (12.00%) 42.00 (17.00%) 46.00 (21.00%) At Rest 49.00 ( 0.00%) 43.00 (-6.00%) 45.00 (-4.00%) 51.00 ( 2.00%) Success rates there are *way* up particularly considering that the 16MB huge pages on PPC64 mean that it's always much harder to allocate them. FTrace Reclaim Statistics: vmscan stress-highalloc stress-highalloc stress-highalloc stress-highalloc traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3waitwriteback-v2r4 Direct reclaims 499 505 564 509 Direct reclaim pages scanned 223478 41898 51818 45605 Direct reclaim pages reclaimed 137730 21148 27161 23455 Direct reclaim write file async I/O 399 136 162 136 Direct reclaim write anon async I/O 46977 2865 4686 3998 Direct reclaim write file sync I/O 29 0 1 3 Direct reclaim write anon sync I/O 31023 159 237 239 Wake kswapd requests 420 351 360 326 Kswapd wakeups 185 294 249 277 Kswapd pages scanned 15703488 16392500 17821724 17598737 Kswapd pages reclaimed 5808466 2908858 3139386 3145435 Kswapd reclaim write file async I/O 159938 18400 18717 13473 Kswapd reclaim write anon async I/O 3467554 228957 322799 234278 Kswapd reclaim write file sync I/O 0 0 0 0 Kswapd reclaim write anon sync I/O 0 0 0 0 Time stalled direct reclaim (seconds) 9665.35 1707.81 2374.32 1871.23 Time kswapd awake (seconds) 9401.21 1367.86 1951.75 1328.88 Total pages scanned 15926966 16434398 17873542 17644342 Total pages reclaimed 5946196 2930006 3166547 3168890 %age total pages scanned/reclaimed 37.33% 17.83% 17.72% 17.96% %age total pages scanned/written 23.27% 1.52% 1.94% 1.43% %age file pages scanned/written 1.01% 0.11% 0.11% 0.08% Percentage Time Spent Direct Reclaim 44.55% 35.10% 41.42% 36.91% Percentage Time kswapd Awake 86.71% 43.58% 52.67% 41.14% While the scanning rates are slightly up, the scanned/reclaimed and scanned/written figures are much improved. The time spent in direct reclaim and with kswapd are massively reduced, mostly by the lowlumpy patches. FTrace Reclaim Statistics: congestion_wait Direct number congest waited 725 303 126 3 Direct time congest waited 45524ms 9180ms 5936ms 300ms Direct full congest waited 487 190 52 3 Direct number conditional waited 0 0 200 301 Direct time conditional waited 0ms 0ms 0ms 1904ms Direct full conditional waited 0 0 0 19 KSwapd number congest waited 0 2 23 4 KSwapd time congest waited 0ms 200ms 420ms 404ms KSwapd full congest waited 0 2 2 4 KSwapd number conditional waited 0 0 0 0 KSwapd time conditional waited 0ms 0ms 0ms 0ms KSwapd full conditional waited 0 0 0 0 Not as dramatic a story here but the time spent asleep is reduced and we can still see what wait_iff_congested is going to sleep when necessary. MMTests Statistics: duration User/Sys Time Running Test (seconds) 12028.09 3157.17 3357.79 3199.16 Total Elapsed Time (seconds) 10842.07 3138.72 3705.54 3229.85 The time to complete this test goes way down. With the full series, we are allocating over twice the number of huge pages in 30% of the time and there is a corresponding impact on the allocation latency graph available at. http://www.csn.ul.ie/~mel/postings/vmscanreduce-20101509/highalloc-interlatency-powyah-mean.ps This patch: Add a trace event for shrink_inactive_list() and updates the sample postprocessing script appropriately. It can be used to determine how many pages were reclaimed and for non-lumpy reclaim where exactly the pages were reclaimed from. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:40 +08:00
mm: vmscan: throttle reclaim if encountering too many dirty pages under writeback Workloads that are allocating frequently and writing files place a large number of dirty pages on the LRU. With use-once logic, it is possible for them to reach the end of the LRU quickly requiring the reclaimer to scan more to find clean pages. Ordinarily, processes that are dirtying memory will get throttled by dirty balancing but this is a global heuristic and does not take into account that LRUs are maintained on a per-zone basis. This can lead to a situation whereby reclaim is scanning heavily, skipping over a large number of pages under writeback and recycling them around the LRU consuming CPU. This patch checks how many of the number of pages isolated from the LRU were dirty and under writeback. If a percentage of them under writeback, the process will be throttled if a backing device or the zone is congested. Note that this applies whether it is anonymous or file-backed pages that are under writeback meaning that swapping is potentially throttled. This is intentional due to the fact if the swap device is congested, scanning more pages and dispatching more IO is not going to help matters. The percentage that must be in writeback depends on the priority. At default priority, all of them must be dirty. At DEF_PRIORITY-1, 50% of them must be, DEF_PRIORITY-2, 25% etc. i.e. as pressure increases the greater the likelihood the process will get throttled to allow the flusher threads to make some progress. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Johannes Weiner <jweiner@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Alex Elder <aelder@sgi.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 08:07:56 +08:00
/*
* If reclaim is isolating dirty pages under writeback, it implies
* that the long-lived page allocation rate is exceeding the page
* laundering rate. Either the global limits are not being effective
* at throttling processes due to the page distribution throughout
* zones or there is heavy usage of a slow backing device. The
* only option is to throttle from reclaim context which is not ideal
* as there is no guarantee the dirtying process is throttled in the
* same way balance_dirty_pages() manages.
*
* This scales the number of dirty pages that must be under writeback
* before throttling depending on priority. It is a simple backoff
* function that has the most effect in the range DEF_PRIORITY to
* DEF_PRIORITY-2 which is the priority reclaim is considered to be
* in trouble and reclaim is considered to be in trouble.
*
* DEF_PRIORITY 100% isolated pages must be PageWriteback to throttle
* DEF_PRIORITY-1 50% must be PageWriteback
* DEF_PRIORITY-2 25% must be PageWriteback, kswapd in trouble
* ...
* DEF_PRIORITY-6 For SWAP_CLUSTER_MAX isolated pages, throttle if any
* isolated page is PageWriteback
*/
if (nr_writeback && nr_writeback >=
(nr_taken >> (DEF_PRIORITY - sc->priority)))
mm: vmscan: throttle reclaim if encountering too many dirty pages under writeback Workloads that are allocating frequently and writing files place a large number of dirty pages on the LRU. With use-once logic, it is possible for them to reach the end of the LRU quickly requiring the reclaimer to scan more to find clean pages. Ordinarily, processes that are dirtying memory will get throttled by dirty balancing but this is a global heuristic and does not take into account that LRUs are maintained on a per-zone basis. This can lead to a situation whereby reclaim is scanning heavily, skipping over a large number of pages under writeback and recycling them around the LRU consuming CPU. This patch checks how many of the number of pages isolated from the LRU were dirty and under writeback. If a percentage of them under writeback, the process will be throttled if a backing device or the zone is congested. Note that this applies whether it is anonymous or file-backed pages that are under writeback meaning that swapping is potentially throttled. This is intentional due to the fact if the swap device is congested, scanning more pages and dispatching more IO is not going to help matters. The percentage that must be in writeback depends on the priority. At default priority, all of them must be dirty. At DEF_PRIORITY-1, 50% of them must be, DEF_PRIORITY-2, 25% etc. i.e. as pressure increases the greater the likelihood the process will get throttled to allow the flusher threads to make some progress. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Johannes Weiner <jweiner@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Alex Elder <aelder@sgi.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Chris Mason <chris.mason@oracle.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 08:07:56 +08:00
wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10);
tracing, vmscan: add trace events for LRU list shrinking There have been numerous reports of stalls that pointed at the problem being somewhere in the VM. There are multiple roots to the problems which means dealing with any of the root problems in isolation is tricky to justify on their own and they would still need integration testing. This patch series puts together two different patch sets which in combination should tackle some of the root causes of latency problems being reported. Patch 1 adds a tracepoint for shrink_inactive_list. For this series, the most important results is being able to calculate the scanning/reclaim ratio as a measure of the amount of work being done by page reclaim. Patch 2 accounts for time spent in congestion_wait. Patches 3-6 were originally developed by Kosaki Motohiro but reworked for this series. It has been noted that lumpy reclaim is far too aggressive and trashes the system somewhat. As SLUB uses high-order allocations, a large cost incurred by lumpy reclaim will be noticeable. It was also reported during transparent hugepage support testing that lumpy reclaim was trashing the system and these patches should mitigate that problem without disabling lumpy reclaim. Patch 7 adds wait_iff_congested() and replaces some callers of congestion_wait(). wait_iff_congested() only sleeps if there is a BDI that is currently congested. Patch 8 notes that any BDI being congested is not necessarily a problem because there could be multiple BDIs of varying speeds and numberous zones. It attempts to track when a zone being reclaimed contains many pages backed by a congested BDI and if so, reclaimers wait on the congestion queue. I ran a number of tests with monitoring on X86, X86-64 and PPC64. Each machine had 3G of RAM and the CPUs were X86: Intel P4 2-core X86-64: AMD Phenom 4-core PPC64: PPC970MP Each used a single disk and the onboard IO controller. Dirty ratio was left at 20. I'm just going to report for X86-64 and PPC64 in a vague attempt to keep this report short. Four kernels were tested each based on v2.6.36-rc4 traceonly-v2r2: Patches 1 and 2 to instrument vmscan reclaims and congestion_wait lowlumpy-v2r3: Patches 1-6 to test if lumpy reclaim is better waitcongest-v2r3: Patches 1-7 to only wait on congestion waitwriteback-v2r4: Patches 1-8 to detect when a zone is congested nocongest-v1r5: Patches 1-3 for testing wait_iff_congestion nodirect-v1r5: Patches 1-10 to disable filesystem writeback for better IO The tests run were as follows kernbench compile-based benchmark. Smoke test performance sysbench OLTP read-only benchmark. Will be re-run in the future as read-write micro-mapped-file-stream This is a micro-benchmark from Johannes Weiner that accesses a large sparse-file through mmap(). It was configured to run in only single-CPU mode but can be indicative of how well page reclaim identifies suitable pages. stress-highalloc Tries to allocate huge pages under heavy load. kernbench, iozone and sysbench did not report any performance regression on any machine. sysbench did pressure the system lightly and there was reclaim activity but there were no difference of major interest between the kernels. X86-64 micro-mapped-file-stream traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3 waitwriteback-v2r4 pgalloc_dma 1639.00 ( 0.00%) 667.00 (-145.73%) 1167.00 ( -40.45%) 578.00 (-183.56%) pgalloc_dma32 2842410.00 ( 0.00%) 2842626.00 ( 0.01%) 2843043.00 ( 0.02%) 2843014.00 ( 0.02%) pgalloc_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgsteal_dma 729.00 ( 0.00%) 85.00 (-757.65%) 609.00 ( -19.70%) 125.00 (-483.20%) pgsteal_dma32 2338721.00 ( 0.00%) 2447354.00 ( 4.44%) 2429536.00 ( 3.74%) 2436772.00 ( 4.02%) pgsteal_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgscan_kswapd_dma 1469.00 ( 0.00%) 532.00 (-176.13%) 1078.00 ( -36.27%) 220.00 (-567.73%) pgscan_kswapd_dma32 4597713.00 ( 0.00%) 4503597.00 ( -2.09%) 4295673.00 ( -7.03%) 3891686.00 ( -18.14%) pgscan_kswapd_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgscan_direct_dma 71.00 ( 0.00%) 134.00 ( 47.01%) 243.00 ( 70.78%) 352.00 ( 79.83%) pgscan_direct_dma32 305820.00 ( 0.00%) 280204.00 ( -9.14%) 600518.00 ( 49.07%) 957485.00 ( 68.06%) pgscan_direct_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pageoutrun 16296.00 ( 0.00%) 21254.00 ( 23.33%) 18447.00 ( 11.66%) 20067.00 ( 18.79%) allocstall 443.00 ( 0.00%) 273.00 ( -62.27%) 513.00 ( 13.65%) 1568.00 ( 71.75%) These are based on the raw figures taken from /proc/vmstat. It's a rough measure of reclaim activity. Note that allocstall counts are higher because we are entering direct reclaim more often as a result of not sleeping in congestion. In itself, it's not necessarily a bad thing. It's easier to get a view of what happened from the vmscan tracepoint report. FTrace Reclaim Statistics: vmscan traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3 waitwriteback-v2r4 Direct reclaims 443 273 513 1568 Direct reclaim pages scanned 305968 280402 600825 957933 Direct reclaim pages reclaimed 43503 19005 30327 117191 Direct reclaim write file async I/O 0 0 0 0 Direct reclaim write anon async I/O 0 3 4 12 Direct reclaim write file sync I/O 0 0 0 0 Direct reclaim write anon sync I/O 0 0 0 0 Wake kswapd requests 187649 132338 191695 267701 Kswapd wakeups 3 1 4 1 Kswapd pages scanned 4599269 4454162 4296815 3891906 Kswapd pages reclaimed 2295947 2428434 2399818 2319706 Kswapd reclaim write file async I/O 1 0 1 1 Kswapd reclaim write anon async I/O 59 187 41 222 Kswapd reclaim write file sync I/O 0 0 0 0 Kswapd reclaim write anon sync I/O 0 0 0 0 Time stalled direct reclaim (seconds) 4.34 2.52 6.63 2.96 Time kswapd awake (seconds) 11.15 10.25 11.01 10.19 Total pages scanned 4905237 4734564 4897640 4849839 Total pages reclaimed 2339450 2447439 2430145 2436897 %age total pages scanned/reclaimed 47.69% 51.69% 49.62% 50.25% %age total pages scanned/written 0.00% 0.00% 0.00% 0.00% %age file pages scanned/written 0.00% 0.00% 0.00% 0.00% Percentage Time Spent Direct Reclaim 29.23% 19.02% 38.48% 20.25% Percentage Time kswapd Awake 78.58% 78.85% 76.83% 79.86% What is interesting here for nocongest in particular is that while direct reclaim scans more pages, the overall number of pages scanned remains the same and the ratio of pages scanned to pages reclaimed is more or less the same. In other words, while we are sleeping less, reclaim is not doing more work and as direct reclaim and kswapd is awake for less time, it would appear to be doing less work. FTrace Reclaim Statistics: congestion_wait Direct number congest waited 87 196 64 0 Direct time congest waited 4604ms 4732ms 5420ms 0ms Direct full congest waited 72 145 53 0 Direct number conditional waited 0 0 324 1315 Direct time conditional waited 0ms 0ms 0ms 0ms Direct full conditional waited 0 0 0 0 KSwapd number congest waited 20 10 15 7 KSwapd time congest waited 1264ms 536ms 884ms 284ms KSwapd full congest waited 10 4 6 2 KSwapd number conditional waited 0 0 0 0 KSwapd time conditional waited 0ms 0ms 0ms 0ms KSwapd full conditional waited 0 0 0 0 The vanilla kernel spent 8 seconds asleep in direct reclaim and no time at all asleep with the patches. MMTests Statistics: duration User/Sys Time Running Test (seconds) 10.51 10.73 10.6 11.66 Total Elapsed Time (seconds) 14.19 13.00 14.33 12.76 Overall, the tests completed faster. It is interesting to note that backing off further when a zone is congested and not just a BDI was more efficient overall. PPC64 micro-mapped-file-stream pgalloc_dma 3024660.00 ( 0.00%) 3027185.00 ( 0.08%) 3025845.00 ( 0.04%) 3026281.00 ( 0.05%) pgalloc_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgsteal_dma 2508073.00 ( 0.00%) 2565351.00 ( 2.23%) 2463577.00 ( -1.81%) 2532263.00 ( 0.96%) pgsteal_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgscan_kswapd_dma 4601307.00 ( 0.00%) 4128076.00 ( -11.46%) 3912317.00 ( -17.61%) 3377165.00 ( -36.25%) pgscan_kswapd_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pgscan_direct_dma 629825.00 ( 0.00%) 971622.00 ( 35.18%) 1063938.00 ( 40.80%) 1711935.00 ( 63.21%) pgscan_direct_normal 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) pageoutrun 27776.00 ( 0.00%) 20458.00 ( -35.77%) 18763.00 ( -48.04%) 18157.00 ( -52.98%) allocstall 977.00 ( 0.00%) 2751.00 ( 64.49%) 2098.00 ( 53.43%) 5136.00 ( 80.98%) Similar trends to x86-64. allocstalls are up but it's not necessarily bad. FTrace Reclaim Statistics: vmscan Direct reclaims 977 2709 2098 5136 Direct reclaim pages scanned 629825 963814 1063938 1711935 Direct reclaim pages reclaimed 75550 242538 150904 387647 Direct reclaim write file async I/O 0 0 0 2 Direct reclaim write anon async I/O 0 10 0 4 Direct reclaim write file sync I/O 0 0 0 0 Direct reclaim write anon sync I/O 0 0 0 0 Wake kswapd requests 392119 1201712 571935 571921 Kswapd wakeups 3 2 3 3 Kswapd pages scanned 4601307 4128076 3912317 3377165 Kswapd pages reclaimed 2432523 2318797 2312673 2144616 Kswapd reclaim write file async I/O 20 1 1 1 Kswapd reclaim write anon async I/O 57 132 11 121 Kswapd reclaim write file sync I/O 0 0 0 0 Kswapd reclaim write anon sync I/O 0 0 0 0 Time stalled direct reclaim (seconds) 6.19 7.30 13.04 10.88 Time kswapd awake (seconds) 21.73 26.51 25.55 23.90 Total pages scanned 5231132 5091890 4976255 5089100 Total pages reclaimed 2508073 2561335 2463577 2532263 %age total pages scanned/reclaimed 47.95% 50.30% 49.51% 49.76% %age total pages scanned/written 0.00% 0.00% 0.00% 0.00% %age file pages scanned/written 0.00% 0.00% 0.00% 0.00% Percentage Time Spent Direct Reclaim 18.89% 20.65% 32.65% 27.65% Percentage Time kswapd Awake 72.39% 80.68% 78.21% 77.40% Again, a similar trend that the congestion_wait changes mean that direct reclaim scans more pages but the overall number of pages scanned while slightly reduced, are very similar. The ratio of scanning/reclaimed remains roughly similar. The downside is that kswapd and direct reclaim was awake longer and for a larger percentage of the overall workload. It's possible there were big differences in the amount of time spent reclaiming slab pages between the different kernels which is plausible considering that the micro tests runs after fsmark and sysbench. Trace Reclaim Statistics: congestion_wait Direct number congest waited 845 1312 104 0 Direct time congest waited 19416ms 26560ms 7544ms 0ms Direct full congest waited 745 1105 72 0 Direct number conditional waited 0 0 1322 2935 Direct time conditional waited 0ms 0ms 12ms 312ms Direct full conditional waited 0 0 0 3 KSwapd number congest waited 39 102 75 63 KSwapd time congest waited 2484ms 6760ms 5756ms 3716ms KSwapd full congest waited 20 48 46 25 KSwapd number conditional waited 0 0 0 0 KSwapd time conditional waited 0ms 0ms 0ms 0ms KSwapd full conditional waited 0 0 0 0 The vanilla kernel spent 20 seconds asleep in direct reclaim and only 312ms asleep with the patches. The time kswapd spent congest waited was also reduced by a large factor. MMTests Statistics: duration ser/Sys Time Running Test (seconds) 26.58 28.05 26.9 28.47 Total Elapsed Time (seconds) 30.02 32.86 32.67 30.88 With all patches applies, the completion times are very similar. X86-64 STRESS-HIGHALLOC traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3waitwriteback-v2r4 Pass 1 82.00 ( 0.00%) 84.00 ( 2.00%) 85.00 ( 3.00%) 85.00 ( 3.00%) Pass 2 90.00 ( 0.00%) 87.00 (-3.00%) 88.00 (-2.00%) 89.00 (-1.00%) At Rest 92.00 ( 0.00%) 90.00 (-2.00%) 90.00 (-2.00%) 91.00 (-1.00%) Success figures across the board are broadly similar. traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3waitwriteback-v2r4 Direct reclaims 1045 944 886 887 Direct reclaim pages scanned 135091 119604 109382 101019 Direct reclaim pages reclaimed 88599 47535 47863 46671 Direct reclaim write file async I/O 494 283 465 280 Direct reclaim write anon async I/O 29357 13710 16656 13462 Direct reclaim write file sync I/O 154 2 2 3 Direct reclaim write anon sync I/O 14594 571 509 561 Wake kswapd requests 7491 933 872 892 Kswapd wakeups 814 778 731 780 Kswapd pages scanned 7290822 15341158 11916436 13703442 Kswapd pages reclaimed 3587336 3142496 3094392 3187151 Kswapd reclaim write file async I/O 91975 32317 28022 29628 Kswapd reclaim write anon async I/O 1992022 789307 829745 849769 Kswapd reclaim write file sync I/O 0 0 0 0 Kswapd reclaim write anon sync I/O 0 0 0 0 Time stalled direct reclaim (seconds) 4588.93 2467.16 2495.41 2547.07 Time kswapd awake (seconds) 2497.66 1020.16 1098.06 1176.82 Total pages scanned 7425913 15460762 12025818 13804461 Total pages reclaimed 3675935 3190031 3142255 3233822 %age total pages scanned/reclaimed 49.50% 20.63% 26.13% 23.43% %age total pages scanned/written 28.66% 5.41% 7.28% 6.47% %age file pages scanned/written 1.25% 0.21% 0.24% 0.22% Percentage Time Spent Direct Reclaim 57.33% 42.15% 42.41% 42.99% Percentage Time kswapd Awake 43.56% 27.87% 29.76% 31.25% Scanned/reclaimed ratios again look good with big improvements in efficiency. The Scanned/written ratios also look much improved. With a better scanned/written ration, there is an expectation that IO would be more efficient and indeed, the time spent in direct reclaim is much reduced by the full series and kswapd spends a little less time awake. Overall, indications here are that allocations were happening much faster and this can be seen with a graph of the latency figures as the allocations were taking place http://www.csn.ul.ie/~mel/postings/vmscanreduce-20101509/highalloc-interlatency-hydra-mean.ps FTrace Reclaim Statistics: congestion_wait Direct number congest waited 1333 204 169 4 Direct time congest waited 78896ms 8288ms 7260ms 200ms Direct full congest waited 756 92 69 2 Direct number conditional waited 0 0 26 186 Direct time conditional waited 0ms 0ms 0ms 2504ms Direct full conditional waited 0 0 0 25 KSwapd number congest waited 4 395 227 282 KSwapd time congest waited 384ms 25136ms 10508ms 18380ms KSwapd full congest waited 3 232 98 176 KSwapd number conditional waited 0 0 0 0 KSwapd time conditional waited 0ms 0ms 0ms 0ms KSwapd full conditional waited 0 0 0 0 KSwapd full conditional waited 318 0 312 9 Overall, the time spent speeping is reduced. kswapd is still hitting congestion_wait() but that is because there are callers remaining where it wasn't clear in advance if they should be changed to wait_iff_congested() or not. Overall the sleep imes are reduced though - from 79ish seconds to about 19. MMTests Statistics: duration User/Sys Time Running Test (seconds) 3415.43 3386.65 3388.39 3377.5 Total Elapsed Time (seconds) 5733.48 3660.33 3689.41 3765.39 With the full series, the time to complete the tests are reduced by 30% PPC64 STRESS-HIGHALLOC traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3waitwriteback-v2r4 Pass 1 17.00 ( 0.00%) 34.00 (17.00%) 38.00 (21.00%) 43.00 (26.00%) Pass 2 25.00 ( 0.00%) 37.00 (12.00%) 42.00 (17.00%) 46.00 (21.00%) At Rest 49.00 ( 0.00%) 43.00 (-6.00%) 45.00 (-4.00%) 51.00 ( 2.00%) Success rates there are *way* up particularly considering that the 16MB huge pages on PPC64 mean that it's always much harder to allocate them. FTrace Reclaim Statistics: vmscan stress-highalloc stress-highalloc stress-highalloc stress-highalloc traceonly-v2r2 lowlumpy-v2r3 waitcongest-v2r3waitwriteback-v2r4 Direct reclaims 499 505 564 509 Direct reclaim pages scanned 223478 41898 51818 45605 Direct reclaim pages reclaimed 137730 21148 27161 23455 Direct reclaim write file async I/O 399 136 162 136 Direct reclaim write anon async I/O 46977 2865 4686 3998 Direct reclaim write file sync I/O 29 0 1 3 Direct reclaim write anon sync I/O 31023 159 237 239 Wake kswapd requests 420 351 360 326 Kswapd wakeups 185 294 249 277 Kswapd pages scanned 15703488 16392500 17821724 17598737 Kswapd pages reclaimed 5808466 2908858 3139386 3145435 Kswapd reclaim write file async I/O 159938 18400 18717 13473 Kswapd reclaim write anon async I/O 3467554 228957 322799 234278 Kswapd reclaim write file sync I/O 0 0 0 0 Kswapd reclaim write anon sync I/O 0 0 0 0 Time stalled direct reclaim (seconds) 9665.35 1707.81 2374.32 1871.23 Time kswapd awake (seconds) 9401.21 1367.86 1951.75 1328.88 Total pages scanned 15926966 16434398 17873542 17644342 Total pages reclaimed 5946196 2930006 3166547 3168890 %age total pages scanned/reclaimed 37.33% 17.83% 17.72% 17.96% %age total pages scanned/written 23.27% 1.52% 1.94% 1.43% %age file pages scanned/written 1.01% 0.11% 0.11% 0.08% Percentage Time Spent Direct Reclaim 44.55% 35.10% 41.42% 36.91% Percentage Time kswapd Awake 86.71% 43.58% 52.67% 41.14% While the scanning rates are slightly up, the scanned/reclaimed and scanned/written figures are much improved. The time spent in direct reclaim and with kswapd are massively reduced, mostly by the lowlumpy patches. FTrace Reclaim Statistics: congestion_wait Direct number congest waited 725 303 126 3 Direct time congest waited 45524ms 9180ms 5936ms 300ms Direct full congest waited 487 190 52 3 Direct number conditional waited 0 0 200 301 Direct time conditional waited 0ms 0ms 0ms 1904ms Direct full conditional waited 0 0 0 19 KSwapd number congest waited 0 2 23 4 KSwapd time congest waited 0ms 200ms 420ms 404ms KSwapd full congest waited 0 2 2 4 KSwapd number conditional waited 0 0 0 0 KSwapd time conditional waited 0ms 0ms 0ms 0ms KSwapd full conditional waited 0 0 0 0 Not as dramatic a story here but the time spent asleep is reduced and we can still see what wait_iff_congested is going to sleep when necessary. MMTests Statistics: duration User/Sys Time Running Test (seconds) 12028.09 3157.17 3357.79 3199.16 Total Elapsed Time (seconds) 10842.07 3138.72 3705.54 3229.85 The time to complete this test goes way down. With the full series, we are allocating over twice the number of huge pages in 30% of the time and there is a corresponding impact on the allocation latency graph available at. http://www.csn.ul.ie/~mel/postings/vmscanreduce-20101509/highalloc-interlatency-powyah-mean.ps This patch: Add a trace event for shrink_inactive_list() and updates the sample postprocessing script appropriately. It can be used to determine how many pages were reclaimed and for non-lumpy reclaim where exactly the pages were reclaimed from. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:40 +08:00
trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id,
zone_idx(zone),
nr_scanned, nr_reclaimed,
sc->priority,
trace_shrink_flags(file));
return nr_reclaimed;
}
/*
* This moves pages from the active list to the inactive list.
*
* We move them the other way if the page is referenced by one or more
* processes, from rmap.
*
* If the pages are mostly unmapped, the processing is fast and it is
* appropriate to hold zone->lru_lock across the whole operation. But if
* the pages are mapped, the processing is slow (page_referenced()) so we
* should drop zone->lru_lock around each page. It's impossible to balance
* this, so instead we remove the pages from the LRU while processing them.
* It is safe to rely on PG_active against the non-LRU pages in here because
* nobody will play with that bit on a non-LRU page.
*
* The downside is that we have to touch page->_count against each page.
* But we had to alter page->flags anyway.
*/
per-zone and reclaim enhancements for memory controller: modifies vmscan.c for isolate globa/cgroup lru activity When using memory controller, there are 2 levels of memory reclaim. 1. zone memory reclaim because of system/zone memory shortage. 2. memory cgroup memory reclaim because of hitting limit. These two can be distinguished by sc->mem_cgroup parameter. (scan_global_lru() macro) This patch tries to make memory cgroup reclaim routine avoid affecting system/zone memory reclaim. This patch inserts if (scan_global_lru()) and hook to memory_cgroup reclaim support functions. This patch can be a help for isolating system lru activity and group lru activity and shows what additional functions are necessary. * mem_cgroup_calc_mapped_ratio() ... calculate mapped ratio for cgroup. * mem_cgroup_reclaim_imbalance() ... calculate active/inactive balance in cgroup. * mem_cgroup_calc_reclaim_active() ... calculate the number of active pages to be scanned in this priority in mem_cgroup. * mem_cgroup_calc_reclaim_inactive() ... calculate the number of inactive pages to be scanned in this priority in mem_cgroup. * mem_cgroup_all_unreclaimable() .. checks cgroup's page is all unreclaimable or not. * mem_cgroup_get_reclaim_priority() ... * mem_cgroup_note_reclaim_priority() ... record reclaim priority (temporal) * mem_cgroup_remember_reclaim_priority() .... record reclaim priority as zone->prev_priority. This value is used for calc reclaim_mapped. [akpm@linux-foundation.org: fix unused var warning] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: David Rientjes <rientjes@google.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:37 +08:00
static void move_active_pages_to_lru(struct lruvec *lruvec,
struct list_head *list,
mm: take pagevecs off reclaim stack Replace pagevecs in putback_lru_pages() and move_active_pages_to_lru() by lists of pages_to_free: then apply Konstantin Khlebnikov's free_hot_cold_page_list() to them instead of pagevec_release(). Which simplifies the flow (no need to drop and retake lock whenever pagevec fills up) and reduces stale addresses in stack backtraces (which often showed through the pagevecs); but more importantly, removes another 120 bytes from the deepest stacks in page reclaim. Although I've not recently seen an actual stack overflow here with a vanilla kernel, move_active_pages_to_lru() has often featured in deep backtraces. However, free_hot_cold_page_list() does not handle compound pages (nor need it: a Transparent HugePage would have been split by the time it reaches the call in shrink_page_list()), but it is possible for putback_lru_pages() or move_active_pages_to_lru() to be left holding the last reference on a THP, so must exclude the unlikely compound case before putting on pages_to_free. Remove pagevec_strip(), its work now done in move_active_pages_to_lru(). The pagevec in scan_mapping_unevictable_pages() remains in mm/vmscan.c, but that is never on the reclaim path, and cannot be replaced by a list. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 09:19:56 +08:00
struct list_head *pages_to_free,
enum lru_list lru)
{
struct zone *zone = lruvec_zone(lruvec);
unsigned long pgmoved = 0;
struct page *page;
int nr_pages;
while (!list_empty(list)) {
page = lru_to_page(list);
lruvec = mem_cgroup_page_lruvec(page, zone);
VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
nr_pages = hpage_nr_pages(page);
mem_cgroup_update_lru_size(lruvec, lru, nr_pages);
list_move(&page->lru, &lruvec->lists[lru]);
pgmoved += nr_pages;
mm: take pagevecs off reclaim stack Replace pagevecs in putback_lru_pages() and move_active_pages_to_lru() by lists of pages_to_free: then apply Konstantin Khlebnikov's free_hot_cold_page_list() to them instead of pagevec_release(). Which simplifies the flow (no need to drop and retake lock whenever pagevec fills up) and reduces stale addresses in stack backtraces (which often showed through the pagevecs); but more importantly, removes another 120 bytes from the deepest stacks in page reclaim. Although I've not recently seen an actual stack overflow here with a vanilla kernel, move_active_pages_to_lru() has often featured in deep backtraces. However, free_hot_cold_page_list() does not handle compound pages (nor need it: a Transparent HugePage would have been split by the time it reaches the call in shrink_page_list()), but it is possible for putback_lru_pages() or move_active_pages_to_lru() to be left holding the last reference on a THP, so must exclude the unlikely compound case before putting on pages_to_free. Remove pagevec_strip(), its work now done in move_active_pages_to_lru(). The pagevec in scan_mapping_unevictable_pages() remains in mm/vmscan.c, but that is never on the reclaim path, and cannot be replaced by a list. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 09:19:56 +08:00
if (put_page_testzero(page)) {
__ClearPageLRU(page);
__ClearPageActive(page);
del_page_from_lru_list(page, lruvec, lru);
mm: take pagevecs off reclaim stack Replace pagevecs in putback_lru_pages() and move_active_pages_to_lru() by lists of pages_to_free: then apply Konstantin Khlebnikov's free_hot_cold_page_list() to them instead of pagevec_release(). Which simplifies the flow (no need to drop and retake lock whenever pagevec fills up) and reduces stale addresses in stack backtraces (which often showed through the pagevecs); but more importantly, removes another 120 bytes from the deepest stacks in page reclaim. Although I've not recently seen an actual stack overflow here with a vanilla kernel, move_active_pages_to_lru() has often featured in deep backtraces. However, free_hot_cold_page_list() does not handle compound pages (nor need it: a Transparent HugePage would have been split by the time it reaches the call in shrink_page_list()), but it is possible for putback_lru_pages() or move_active_pages_to_lru() to be left holding the last reference on a THP, so must exclude the unlikely compound case before putting on pages_to_free. Remove pagevec_strip(), its work now done in move_active_pages_to_lru(). The pagevec in scan_mapping_unevictable_pages() remains in mm/vmscan.c, but that is never on the reclaim path, and cannot be replaced by a list. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 09:19:56 +08:00
if (unlikely(PageCompound(page))) {
spin_unlock_irq(&zone->lru_lock);
(*get_compound_page_dtor(page))(page);
spin_lock_irq(&zone->lru_lock);
} else
list_add(&page->lru, pages_to_free);
}
}
__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
if (!is_active_lru(lru))
__count_vm_events(PGDEACTIVATE, pgmoved);
}
per-zone and reclaim enhancements for memory controller: modifies vmscan.c for isolate globa/cgroup lru activity When using memory controller, there are 2 levels of memory reclaim. 1. zone memory reclaim because of system/zone memory shortage. 2. memory cgroup memory reclaim because of hitting limit. These two can be distinguished by sc->mem_cgroup parameter. (scan_global_lru() macro) This patch tries to make memory cgroup reclaim routine avoid affecting system/zone memory reclaim. This patch inserts if (scan_global_lru()) and hook to memory_cgroup reclaim support functions. This patch can be a help for isolating system lru activity and group lru activity and shows what additional functions are necessary. * mem_cgroup_calc_mapped_ratio() ... calculate mapped ratio for cgroup. * mem_cgroup_reclaim_imbalance() ... calculate active/inactive balance in cgroup. * mem_cgroup_calc_reclaim_active() ... calculate the number of active pages to be scanned in this priority in mem_cgroup. * mem_cgroup_calc_reclaim_inactive() ... calculate the number of inactive pages to be scanned in this priority in mem_cgroup. * mem_cgroup_all_unreclaimable() .. checks cgroup's page is all unreclaimable or not. * mem_cgroup_get_reclaim_priority() ... * mem_cgroup_note_reclaim_priority() ... record reclaim priority (temporal) * mem_cgroup_remember_reclaim_priority() .... record reclaim priority as zone->prev_priority. This value is used for calc reclaim_mapped. [akpm@linux-foundation.org: fix unused var warning] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: David Rientjes <rientjes@google.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:37 +08:00
static void shrink_active_list(unsigned long nr_to_scan,
struct lruvec *lruvec,
struct scan_control *sc,
enum lru_list lru)
{
unsigned long nr_taken;
unsigned long nr_scanned;
unsigned long vm_flags;
LIST_HEAD(l_hold); /* The pages which were snipped off */
vmscan: make mapped executable pages the first class citizen Protect referenced PROT_EXEC mapped pages from being deactivated. PROT_EXEC(or its internal presentation VM_EXEC) pages normally belong to some currently running executables and their linked libraries, they shall really be cached aggressively to provide good user experiences. Thanks to Johannes Weiner for the advice to reuse the VMA walk in page_referenced() to get the PROT_EXEC bit. [more details] ( The consequences of this patch will have to be discussed together with Rik van Riel's recent patch "vmscan: evict use-once pages first". ) ( Some of the good points and insights are taken into this changelog. Thanks to all the involved people for the great LKML discussions. ) the problem =========== For a typical desktop, the most precious working set is composed of *actively accessed* (1) memory mapped executables (2) and their anonymous pages (3) and other files (4) and the dcache/icache/.. slabs while the least important data are (5) infrequently used or use-once files For a typical desktop, one major problem is busty and large amount of (5) use-once files flushing out the working set. Inside the working set, (4) dcache/icache have already been too sticky ;-) So we only have to care (2) anonymous and (1)(3) file pages. anonymous pages =============== Anonymous pages are effectively immune to the streaming IO attack, because we now have separate file/anon LRU lists. When the use-once files crowd into the file LRU, the list's "quality" is significantly lowered. Therefore the scan balance policy in get_scan_ratio() will choose to scan the (low quality) file LRU much more frequently than the anon LRU. file pages ========== Rik proposed to *not* scan the active file LRU when the inactive list grows larger than active list. This guarantees that when there are use-once streaming IO, and the working set is not too large(so that active_size < inactive_size), the active file LRU will *not* be scanned at all. So the not-too-large working set can be well protected. But there are also situations where the file working set is a bit large so that (active_size >= inactive_size), or the streaming IOs are not purely use-once. In these cases, the active list will be scanned slowly. Because the current shrink_active_list() policy is to deactivate active pages regardless of their referenced bits. The deactivated pages become susceptible to the streaming IO attack: the inactive list could be scanned fast (500MB / 50MBps = 10s) so that the deactivated pages don't have enough time to get re-referenced. Because a user tend to switch between windows in intervals from seconds to minutes. This patch holds mapped executable pages in the active list as long as they are referenced during each full scan of the active list. Because the active list is normally scanned much slower, they get longer grace time (eg. 100s) for further references, which better matches the pace of user operations. Therefore this patch greatly prolongs the in-cache time of executable code, when there are moderate memory pressures. before patch: guaranteed to be cached if reference intervals < I after patch: guaranteed to be cached if reference intervals < I+A (except when randomly reclaimed by the lumpy reclaim) where A = time to fully scan the active file LRU I = time to fully scan the inactive file LRU Note that normally A >> I. side effects ============ This patch is safe in general, it restores the pre-2.6.28 mmap() behavior but in a much smaller and well targeted scope. One may worry about some one to abuse the PROT_EXEC heuristic. But as Andrew Morton stated, there are other tricks to getting that sort of boost. Another concern is the PROT_EXEC mapped pages growing large in rare cases, and therefore hurting reclaim efficiency. But a sane application targeted for large audience will never use PROT_EXEC for data mappings. If some home made application tries to abuse that bit, it shall be aware of the consequences. If it is abused to scale of 2/3 total memory, it gains nothing but overheads. benchmarks ========== 1) memory tight desktop 1.1) brief summary - clock time and major faults are reduced by 50%; - pswpin numbers are reduced to ~1/3. That means X desktop responsiveness is doubled under high memory/swap pressure. 1.2) test scenario - nfsroot gnome desktop with 512M physical memory - run some programs, and switch between the existing windows after starting each new program. 1.3) progress timing (seconds) before after programs 0.02 0.02 N xeyes 0.75 0.76 N firefox 2.02 1.88 N nautilus 3.36 3.17 N nautilus --browser 5.26 4.89 N gthumb 7.12 6.47 N gedit 9.22 8.16 N xpdf /usr/share/doc/shared-mime-info/shared-mime-info-spec.pdf 13.58 12.55 N xterm 15.87 14.57 N mlterm 18.63 17.06 N gnome-terminal 21.16 18.90 N urxvt 26.24 23.48 N gnome-system-monitor 28.72 26.52 N gnome-help 32.15 29.65 N gnome-dictionary 39.66 36.12 N /usr/games/sol 43.16 39.27 N /usr/games/gnometris 48.65 42.56 N /usr/games/gnect 53.31 47.03 N /usr/games/gtali 58.60 52.05 N /usr/games/iagno 65.77 55.42 N /usr/games/gnotravex 70.76 61.47 N /usr/games/mahjongg 76.15 67.11 N /usr/games/gnome-sudoku 86.32 75.15 N /usr/games/glines 92.21 79.70 N /usr/games/glchess 103.79 88.48 N /usr/games/gnomine 113.84 96.51 N /usr/games/gnotski 124.40 102.19 N /usr/games/gnibbles 137.41 114.93 N /usr/games/gnobots2 155.53 125.02 N /usr/games/blackjack 179.85 135.11 N /usr/games/same-gnome 224.49 154.50 N /usr/bin/gnome-window-properties 248.44 162.09 N /usr/bin/gnome-default-applications-properties 282.62 173.29 N /usr/bin/gnome-at-properties 323.72 188.21 N /usr/bin/gnome-typing-monitor 363.99 199.93 N /usr/bin/gnome-at-visual 394.21 206.95 N /usr/bin/gnome-sound-properties 435.14 224.49 N /usr/bin/gnome-at-mobility 463.05 234.11 N /usr/bin/gnome-keybinding-properties 503.75 248.59 N /usr/bin/gnome-about-me 554.00 276.27 N /usr/bin/gnome-display-properties 615.48 304.39 N /usr/bin/gnome-network-preferences 693.03 342.01 N /usr/bin/gnome-mouse-properties 759.90 388.58 N /usr/bin/gnome-appearance-properties 937.90 508.47 N /usr/bin/gnome-control-center 1109.75 587.57 N /usr/bin/gnome-keyboard-properties 1399.05 758.16 N : oocalc 1524.64 830.03 N : oodraw 1684.31 900.03 N : ooimpress 1874.04 993.91 N : oomath 2115.12 1081.89 N : ooweb 2369.02 1161.99 N : oowriter Note that the last ": oo*" commands are actually commented out. 1.4) vmstat numbers (some relevant ones are marked with *) before after nr_free_pages 1293 3898 nr_inactive_anon 59956 53460 nr_active_anon 26815 30026 nr_inactive_file 2657 3218 nr_active_file 2019 2806 nr_unevictable 4 4 nr_mlock 4 4 nr_anon_pages 26706 27859 *nr_mapped 3542 4469 nr_file_pages 72232 67681 nr_dirty 1 0 nr_writeback 123 19 nr_slab_reclaimable 3375 3534 nr_slab_unreclaimable 11405 10665 nr_page_table_pages 8106 7864 nr_unstable 0 0 nr_bounce 0 0 *nr_vmscan_write 394776 230839 nr_writeback_temp 0 0 numa_hit 6843353 3318676 numa_miss 0 0 numa_foreign 0 0 numa_interleave 1719 1719 numa_local 6843353 3318676 numa_other 0 0 *pgpgin 5954683 2057175 *pgpgout 1578276 922744 *pswpin 1486615 512238 *pswpout 394568 230685 pgalloc_dma 277432 56602 pgalloc_dma32 6769477 3310348 pgalloc_normal 0 0 pgalloc_movable 0 0 pgfree 7048396 3371118 pgactivate 2036343 1471492 pgdeactivate 2189691 1612829 pgfault 3702176 3100702 *pgmajfault 452116 201343 pgrefill_dma 12185 7127 pgrefill_dma32 334384 653703 pgrefill_normal 0 0 pgrefill_movable 0 0 pgsteal_dma 74214 22179 pgsteal_dma32 3334164 1638029 pgsteal_normal 0 0 pgsteal_movable 0 0 pgscan_kswapd_dma 1081421 1216199 pgscan_kswapd_dma32 58979118 46002810 pgscan_kswapd_normal 0 0 pgscan_kswapd_movable 0 0 pgscan_direct_dma 2015438 1086109 pgscan_direct_dma32 55787823 36101597 pgscan_direct_normal 0 0 pgscan_direct_movable 0 0 pginodesteal 3461 7281 slabs_scanned 564864 527616 kswapd_steal 2889797 1448082 kswapd_inodesteal 14827 14835 pageoutrun 43459 21562 allocstall 9653 4032 pgrotated 384216 228631 1.5) free numbers at the end of the tests before patch: total used free shared buffers cached Mem: 474 467 7 0 0 236 -/+ buffers/cache: 230 243 Swap: 1023 418 605 after patch: total used free shared buffers cached Mem: 474 457 16 0 0 236 -/+ buffers/cache: 221 253 Swap: 1023 404 619 2) memory flushing in a file server 2.1) brief summary The number of major faults from 50 to 3 during 10% cache hot reads. That means this patch successfully stops major faults when the active file list is slowly scanned when there are partially cache hot streaming IO. 2.2) test scenario Do 100000 pread(size=110 pages, offset=(i*100) pages), where 10% of the pages will be activated: for i in `seq 0 100 10000000`; do echo $i 110; done > pattern-hot-10 iotrace.rb --load pattern-hot-10 --play /b/sparse vmmon nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree and monitor /proc/vmstat during the time. The test box has 2G memory. I carried out tests on fresh booted console as well as X desktop, and fetched the vmstat numbers on (1) begin: shortly after the big read IO starts; (2) end: just before the big read IO stops; (3) restore: the big read IO stops and the zsh working set restored (4) restore X: after IO, switch back and forth between the urxvt and firefox windows to restore their working set. 2.3) console mode results nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree 2.6.29 VM_EXEC protection ON: begin: 2481 2237 8694 630 0 574299 end: 275 231976 233914 633 776271 20933042 restore: 370 232154 234524 691 777183 20958453 2.6.29 VM_EXEC protection ON (second run): begin: 2434 2237 8493 629 0 574195 end: 284 231970 233536 632 771918 20896129 restore: 399 232218 234789 690 774526 20957909 2.6.30-rc4-mm VM_EXEC protection OFF: begin: 2479 2344 9659 210 0 579643 end: 284 232010 234142 260 772776 20917184 restore: 379 232159 234371 301 774888 20967849 The above console numbers show that - The startup pgmajfault of 2.6.30-rc4-mm is merely 1/3 that of 2.6.29. I'd attribute that improvement to the mmap readahead improvements :-) - The pgmajfault increment during the file copy is 633-630=3 vs 260-210=50. That's a huge improvement - which means with the VM_EXEC protection logic, active mmap pages is pretty safe even under partially cache hot streaming IO. - when active:inactive file lru size reaches 1:1, their scan rates is 1:20.8 under 10% cache hot IO. (computed with formula Dpgdeactivate:Dpgfree) That roughly means the active mmap pages get 20.8 more chances to get re-referenced to stay in memory. - The absolute nr_mapped drops considerably to 1/9 during the big IO, and the dropped pages are mostly inactive ones. The patch has almost no impact in this aspect, that means it won't unnecessarily increase memory pressure. (In contrast, your 20% mmap protection ratio will keep them all, and therefore eliminate the extra 41 major faults to restore working set of zsh etc.) The iotrace.rb read throughput is 151.194384MB/s 284.198252s 100001x 450560b --load pattern-hot-10 --play /b/sparse which means the inactive list is rotated at the speed of 250MB/s, so a full scan of which takes about 3.5 seconds, while a full scan of active file list takes about 77 seconds. 2.4) X mode results We can reach roughly the same conclusions for X desktop: nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree 2.6.30-rc4-mm VM_EXEC protection ON: begin: 9740 8920 64075 561 0 678360 end: 768 218254 220029 565 798953 21057006 restore: 857 218543 220987 606 799462 21075710 restore X: 2414 218560 225344 797 799462 21080795 2.6.30-rc4-mm VM_EXEC protection OFF: begin: 9368 5035 26389 554 0 633391 end: 770 218449 221230 661 646472 17832500 restore: 1113 218466 220978 710 649881 17905235 restore X: 2687 218650 225484 947 802700 21083584 - the absolute nr_mapped drops considerably (to 1/13 of the original size) during the streaming IO. - the delta of pgmajfault is 3 vs 107 during IO, or 236 vs 393 during the whole process. Cc: Elladan <elladan@eskimo.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Andi Kleen <andi@firstfloor.org> Cc: Christoph Lameter <cl@linux-foundation.org> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:12 +08:00
LIST_HEAD(l_active);
LIST_HEAD(l_inactive);
struct page *page;
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
unsigned long nr_rotated = 0;
isolate_mode_t isolate_mode = 0;
int file = is_file_lru(lru);
struct zone *zone = lruvec_zone(lruvec);
lru_add_drain();
if (!sc->may_unmap)
isolate_mode |= ISOLATE_UNMAPPED;
if (!sc->may_writepage)
isolate_mode |= ISOLATE_CLEAN;
spin_lock_irq(&zone->lru_lock);
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
&nr_scanned, sc, isolate_mode, lru);
if (global_reclaim(sc))
zone->pages_scanned += nr_scanned;
reclaim_stat->recent_scanned[file] += nr_taken;
per-zone and reclaim enhancements for memory controller: modifies vmscan.c for isolate globa/cgroup lru activity When using memory controller, there are 2 levels of memory reclaim. 1. zone memory reclaim because of system/zone memory shortage. 2. memory cgroup memory reclaim because of hitting limit. These two can be distinguished by sc->mem_cgroup parameter. (scan_global_lru() macro) This patch tries to make memory cgroup reclaim routine avoid affecting system/zone memory reclaim. This patch inserts if (scan_global_lru()) and hook to memory_cgroup reclaim support functions. This patch can be a help for isolating system lru activity and group lru activity and shows what additional functions are necessary. * mem_cgroup_calc_mapped_ratio() ... calculate mapped ratio for cgroup. * mem_cgroup_reclaim_imbalance() ... calculate active/inactive balance in cgroup. * mem_cgroup_calc_reclaim_active() ... calculate the number of active pages to be scanned in this priority in mem_cgroup. * mem_cgroup_calc_reclaim_inactive() ... calculate the number of inactive pages to be scanned in this priority in mem_cgroup. * mem_cgroup_all_unreclaimable() .. checks cgroup's page is all unreclaimable or not. * mem_cgroup_get_reclaim_priority() ... * mem_cgroup_note_reclaim_priority() ... record reclaim priority (temporal) * mem_cgroup_remember_reclaim_priority() .... record reclaim priority as zone->prev_priority. This value is used for calc reclaim_mapped. [akpm@linux-foundation.org: fix unused var warning] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: David Rientjes <rientjes@google.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:37 +08:00
__count_zone_vm_events(PGREFILL, zone, nr_scanned);
__mod_zone_page_state(zone, NR_LRU_BASE + lru, -nr_taken);
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
spin_unlock_irq(&zone->lru_lock);
while (!list_empty(&l_hold)) {
cond_resched();
page = lru_to_page(&l_hold);
list_del(&page->lru);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
if (unlikely(!page_evictable(page, NULL))) {
putback_lru_page(page);
continue;
}
mm: vmscan: forcibly scan highmem if there are too many buffer_heads pinning highmem Stuart Foster reported on bugzilla that copying large amounts of data from NTFS caused an OOM kill on 32-bit X86 with 16G of memory. Andrew Morton correctly identified that the problem was NTFS was using 512 blocks meaning each page had 8 buffer_heads in low memory pinning it. In the past, direct reclaim used to scan highmem even if the allocating process did not specify __GFP_HIGHMEM but not any more. kswapd no longer will reclaim from zones that are above the high watermark. The intention in both cases was to minimise unnecessary reclaim. The downside is on machines with large amounts of highmem that lowmem can be fully consumed by buffer_heads with nothing trying to free them. The following patch is based on a suggestion by Andrew Morton to extend the buffer_heads_over_limit case to force kswapd and direct reclaim to scan the highmem zone regardless of the allocation request or watermarks. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=42578 [hughd@google.com: move buffer_heads_over_limit check up] [akpm@linux-foundation.org: buffer_heads_over_limit is unlikely] Reported-by: Stuart Foster <smf.linux@ntlworld.com> Tested-by: Stuart Foster <smf.linux@ntlworld.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Cc: Christoph Lameter <cl@linux.com> Cc: stable <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 07:34:00 +08:00
if (unlikely(buffer_heads_over_limit)) {
if (page_has_private(page) && trylock_page(page)) {
if (page_has_private(page))
try_to_release_page(page, 0);
unlock_page(page);
}
}
mm: memcg: count pte references from every member of the reclaimed hierarchy The rmap walker checking page table references has historically ignored references from VMAs that were not part of the memcg that was being reclaimed during memcg hard limit reclaim. When transitioning global reclaim to memcg hierarchy reclaim, I missed that bit and now references from outside a memcg are ignored even during global reclaim. Reverting back to traditional behaviour - count all references during global reclaim and only mind references of the memcg being reclaimed during limit reclaim would be one option. However, the more generic idea is to ignore references exactly then when they are outside the hierarchy that is currently under reclaim; because only then will their reclamation be of any use to help the pressure situation. It makes no sense to ignore references from a sibling memcg and then evict a page that will be immediately refaulted by that sibling which contributes to the same usage of the common ancestor under reclaim. The solution: make the rmap walker ignore references from VMAs that are not part of the hierarchy that is being reclaimed. Flat limit reclaim will stay the same, hierarchical limit reclaim will mind the references only to pages that the hierarchy owns. Global reclaim, since it reclaims from all memcgs, will be fixed to regard all references. [akpm@linux-foundation.org: name the args in the declaration] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Acked-by: Konstantin Khlebnikov<khlebnikov@openvz.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-30 06:06:25 +08:00
if (page_referenced(page, 0, sc->target_mem_cgroup,
&vm_flags)) {
nr_rotated += hpage_nr_pages(page);
vmscan: make mapped executable pages the first class citizen Protect referenced PROT_EXEC mapped pages from being deactivated. PROT_EXEC(or its internal presentation VM_EXEC) pages normally belong to some currently running executables and their linked libraries, they shall really be cached aggressively to provide good user experiences. Thanks to Johannes Weiner for the advice to reuse the VMA walk in page_referenced() to get the PROT_EXEC bit. [more details] ( The consequences of this patch will have to be discussed together with Rik van Riel's recent patch "vmscan: evict use-once pages first". ) ( Some of the good points and insights are taken into this changelog. Thanks to all the involved people for the great LKML discussions. ) the problem =========== For a typical desktop, the most precious working set is composed of *actively accessed* (1) memory mapped executables (2) and their anonymous pages (3) and other files (4) and the dcache/icache/.. slabs while the least important data are (5) infrequently used or use-once files For a typical desktop, one major problem is busty and large amount of (5) use-once files flushing out the working set. Inside the working set, (4) dcache/icache have already been too sticky ;-) So we only have to care (2) anonymous and (1)(3) file pages. anonymous pages =============== Anonymous pages are effectively immune to the streaming IO attack, because we now have separate file/anon LRU lists. When the use-once files crowd into the file LRU, the list's "quality" is significantly lowered. Therefore the scan balance policy in get_scan_ratio() will choose to scan the (low quality) file LRU much more frequently than the anon LRU. file pages ========== Rik proposed to *not* scan the active file LRU when the inactive list grows larger than active list. This guarantees that when there are use-once streaming IO, and the working set is not too large(so that active_size < inactive_size), the active file LRU will *not* be scanned at all. So the not-too-large working set can be well protected. But there are also situations where the file working set is a bit large so that (active_size >= inactive_size), or the streaming IOs are not purely use-once. In these cases, the active list will be scanned slowly. Because the current shrink_active_list() policy is to deactivate active pages regardless of their referenced bits. The deactivated pages become susceptible to the streaming IO attack: the inactive list could be scanned fast (500MB / 50MBps = 10s) so that the deactivated pages don't have enough time to get re-referenced. Because a user tend to switch between windows in intervals from seconds to minutes. This patch holds mapped executable pages in the active list as long as they are referenced during each full scan of the active list. Because the active list is normally scanned much slower, they get longer grace time (eg. 100s) for further references, which better matches the pace of user operations. Therefore this patch greatly prolongs the in-cache time of executable code, when there are moderate memory pressures. before patch: guaranteed to be cached if reference intervals < I after patch: guaranteed to be cached if reference intervals < I+A (except when randomly reclaimed by the lumpy reclaim) where A = time to fully scan the active file LRU I = time to fully scan the inactive file LRU Note that normally A >> I. side effects ============ This patch is safe in general, it restores the pre-2.6.28 mmap() behavior but in a much smaller and well targeted scope. One may worry about some one to abuse the PROT_EXEC heuristic. But as Andrew Morton stated, there are other tricks to getting that sort of boost. Another concern is the PROT_EXEC mapped pages growing large in rare cases, and therefore hurting reclaim efficiency. But a sane application targeted for large audience will never use PROT_EXEC for data mappings. If some home made application tries to abuse that bit, it shall be aware of the consequences. If it is abused to scale of 2/3 total memory, it gains nothing but overheads. benchmarks ========== 1) memory tight desktop 1.1) brief summary - clock time and major faults are reduced by 50%; - pswpin numbers are reduced to ~1/3. That means X desktop responsiveness is doubled under high memory/swap pressure. 1.2) test scenario - nfsroot gnome desktop with 512M physical memory - run some programs, and switch between the existing windows after starting each new program. 1.3) progress timing (seconds) before after programs 0.02 0.02 N xeyes 0.75 0.76 N firefox 2.02 1.88 N nautilus 3.36 3.17 N nautilus --browser 5.26 4.89 N gthumb 7.12 6.47 N gedit 9.22 8.16 N xpdf /usr/share/doc/shared-mime-info/shared-mime-info-spec.pdf 13.58 12.55 N xterm 15.87 14.57 N mlterm 18.63 17.06 N gnome-terminal 21.16 18.90 N urxvt 26.24 23.48 N gnome-system-monitor 28.72 26.52 N gnome-help 32.15 29.65 N gnome-dictionary 39.66 36.12 N /usr/games/sol 43.16 39.27 N /usr/games/gnometris 48.65 42.56 N /usr/games/gnect 53.31 47.03 N /usr/games/gtali 58.60 52.05 N /usr/games/iagno 65.77 55.42 N /usr/games/gnotravex 70.76 61.47 N /usr/games/mahjongg 76.15 67.11 N /usr/games/gnome-sudoku 86.32 75.15 N /usr/games/glines 92.21 79.70 N /usr/games/glchess 103.79 88.48 N /usr/games/gnomine 113.84 96.51 N /usr/games/gnotski 124.40 102.19 N /usr/games/gnibbles 137.41 114.93 N /usr/games/gnobots2 155.53 125.02 N /usr/games/blackjack 179.85 135.11 N /usr/games/same-gnome 224.49 154.50 N /usr/bin/gnome-window-properties 248.44 162.09 N /usr/bin/gnome-default-applications-properties 282.62 173.29 N /usr/bin/gnome-at-properties 323.72 188.21 N /usr/bin/gnome-typing-monitor 363.99 199.93 N /usr/bin/gnome-at-visual 394.21 206.95 N /usr/bin/gnome-sound-properties 435.14 224.49 N /usr/bin/gnome-at-mobility 463.05 234.11 N /usr/bin/gnome-keybinding-properties 503.75 248.59 N /usr/bin/gnome-about-me 554.00 276.27 N /usr/bin/gnome-display-properties 615.48 304.39 N /usr/bin/gnome-network-preferences 693.03 342.01 N /usr/bin/gnome-mouse-properties 759.90 388.58 N /usr/bin/gnome-appearance-properties 937.90 508.47 N /usr/bin/gnome-control-center 1109.75 587.57 N /usr/bin/gnome-keyboard-properties 1399.05 758.16 N : oocalc 1524.64 830.03 N : oodraw 1684.31 900.03 N : ooimpress 1874.04 993.91 N : oomath 2115.12 1081.89 N : ooweb 2369.02 1161.99 N : oowriter Note that the last ": oo*" commands are actually commented out. 1.4) vmstat numbers (some relevant ones are marked with *) before after nr_free_pages 1293 3898 nr_inactive_anon 59956 53460 nr_active_anon 26815 30026 nr_inactive_file 2657 3218 nr_active_file 2019 2806 nr_unevictable 4 4 nr_mlock 4 4 nr_anon_pages 26706 27859 *nr_mapped 3542 4469 nr_file_pages 72232 67681 nr_dirty 1 0 nr_writeback 123 19 nr_slab_reclaimable 3375 3534 nr_slab_unreclaimable 11405 10665 nr_page_table_pages 8106 7864 nr_unstable 0 0 nr_bounce 0 0 *nr_vmscan_write 394776 230839 nr_writeback_temp 0 0 numa_hit 6843353 3318676 numa_miss 0 0 numa_foreign 0 0 numa_interleave 1719 1719 numa_local 6843353 3318676 numa_other 0 0 *pgpgin 5954683 2057175 *pgpgout 1578276 922744 *pswpin 1486615 512238 *pswpout 394568 230685 pgalloc_dma 277432 56602 pgalloc_dma32 6769477 3310348 pgalloc_normal 0 0 pgalloc_movable 0 0 pgfree 7048396 3371118 pgactivate 2036343 1471492 pgdeactivate 2189691 1612829 pgfault 3702176 3100702 *pgmajfault 452116 201343 pgrefill_dma 12185 7127 pgrefill_dma32 334384 653703 pgrefill_normal 0 0 pgrefill_movable 0 0 pgsteal_dma 74214 22179 pgsteal_dma32 3334164 1638029 pgsteal_normal 0 0 pgsteal_movable 0 0 pgscan_kswapd_dma 1081421 1216199 pgscan_kswapd_dma32 58979118 46002810 pgscan_kswapd_normal 0 0 pgscan_kswapd_movable 0 0 pgscan_direct_dma 2015438 1086109 pgscan_direct_dma32 55787823 36101597 pgscan_direct_normal 0 0 pgscan_direct_movable 0 0 pginodesteal 3461 7281 slabs_scanned 564864 527616 kswapd_steal 2889797 1448082 kswapd_inodesteal 14827 14835 pageoutrun 43459 21562 allocstall 9653 4032 pgrotated 384216 228631 1.5) free numbers at the end of the tests before patch: total used free shared buffers cached Mem: 474 467 7 0 0 236 -/+ buffers/cache: 230 243 Swap: 1023 418 605 after patch: total used free shared buffers cached Mem: 474 457 16 0 0 236 -/+ buffers/cache: 221 253 Swap: 1023 404 619 2) memory flushing in a file server 2.1) brief summary The number of major faults from 50 to 3 during 10% cache hot reads. That means this patch successfully stops major faults when the active file list is slowly scanned when there are partially cache hot streaming IO. 2.2) test scenario Do 100000 pread(size=110 pages, offset=(i*100) pages), where 10% of the pages will be activated: for i in `seq 0 100 10000000`; do echo $i 110; done > pattern-hot-10 iotrace.rb --load pattern-hot-10 --play /b/sparse vmmon nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree and monitor /proc/vmstat during the time. The test box has 2G memory. I carried out tests on fresh booted console as well as X desktop, and fetched the vmstat numbers on (1) begin: shortly after the big read IO starts; (2) end: just before the big read IO stops; (3) restore: the big read IO stops and the zsh working set restored (4) restore X: after IO, switch back and forth between the urxvt and firefox windows to restore their working set. 2.3) console mode results nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree 2.6.29 VM_EXEC protection ON: begin: 2481 2237 8694 630 0 574299 end: 275 231976 233914 633 776271 20933042 restore: 370 232154 234524 691 777183 20958453 2.6.29 VM_EXEC protection ON (second run): begin: 2434 2237 8493 629 0 574195 end: 284 231970 233536 632 771918 20896129 restore: 399 232218 234789 690 774526 20957909 2.6.30-rc4-mm VM_EXEC protection OFF: begin: 2479 2344 9659 210 0 579643 end: 284 232010 234142 260 772776 20917184 restore: 379 232159 234371 301 774888 20967849 The above console numbers show that - The startup pgmajfault of 2.6.30-rc4-mm is merely 1/3 that of 2.6.29. I'd attribute that improvement to the mmap readahead improvements :-) - The pgmajfault increment during the file copy is 633-630=3 vs 260-210=50. That's a huge improvement - which means with the VM_EXEC protection logic, active mmap pages is pretty safe even under partially cache hot streaming IO. - when active:inactive file lru size reaches 1:1, their scan rates is 1:20.8 under 10% cache hot IO. (computed with formula Dpgdeactivate:Dpgfree) That roughly means the active mmap pages get 20.8 more chances to get re-referenced to stay in memory. - The absolute nr_mapped drops considerably to 1/9 during the big IO, and the dropped pages are mostly inactive ones. The patch has almost no impact in this aspect, that means it won't unnecessarily increase memory pressure. (In contrast, your 20% mmap protection ratio will keep them all, and therefore eliminate the extra 41 major faults to restore working set of zsh etc.) The iotrace.rb read throughput is 151.194384MB/s 284.198252s 100001x 450560b --load pattern-hot-10 --play /b/sparse which means the inactive list is rotated at the speed of 250MB/s, so a full scan of which takes about 3.5 seconds, while a full scan of active file list takes about 77 seconds. 2.4) X mode results We can reach roughly the same conclusions for X desktop: nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree 2.6.30-rc4-mm VM_EXEC protection ON: begin: 9740 8920 64075 561 0 678360 end: 768 218254 220029 565 798953 21057006 restore: 857 218543 220987 606 799462 21075710 restore X: 2414 218560 225344 797 799462 21080795 2.6.30-rc4-mm VM_EXEC protection OFF: begin: 9368 5035 26389 554 0 633391 end: 770 218449 221230 661 646472 17832500 restore: 1113 218466 220978 710 649881 17905235 restore X: 2687 218650 225484 947 802700 21083584 - the absolute nr_mapped drops considerably (to 1/13 of the original size) during the streaming IO. - the delta of pgmajfault is 3 vs 107 during IO, or 236 vs 393 during the whole process. Cc: Elladan <elladan@eskimo.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Andi Kleen <andi@firstfloor.org> Cc: Christoph Lameter <cl@linux-foundation.org> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:12 +08:00
/*
* Identify referenced, file-backed active pages and
* give them one more trip around the active list. So
* that executable code get better chances to stay in
* memory under moderate memory pressure. Anon pages
* are not likely to be evicted by use-once streaming
* IO, plus JVM can create lots of anon VM_EXEC pages,
* so we ignore them here.
*/
if ((vm_flags & VM_EXEC) && page_is_file_cache(page)) {
vmscan: make mapped executable pages the first class citizen Protect referenced PROT_EXEC mapped pages from being deactivated. PROT_EXEC(or its internal presentation VM_EXEC) pages normally belong to some currently running executables and their linked libraries, they shall really be cached aggressively to provide good user experiences. Thanks to Johannes Weiner for the advice to reuse the VMA walk in page_referenced() to get the PROT_EXEC bit. [more details] ( The consequences of this patch will have to be discussed together with Rik van Riel's recent patch "vmscan: evict use-once pages first". ) ( Some of the good points and insights are taken into this changelog. Thanks to all the involved people for the great LKML discussions. ) the problem =========== For a typical desktop, the most precious working set is composed of *actively accessed* (1) memory mapped executables (2) and their anonymous pages (3) and other files (4) and the dcache/icache/.. slabs while the least important data are (5) infrequently used or use-once files For a typical desktop, one major problem is busty and large amount of (5) use-once files flushing out the working set. Inside the working set, (4) dcache/icache have already been too sticky ;-) So we only have to care (2) anonymous and (1)(3) file pages. anonymous pages =============== Anonymous pages are effectively immune to the streaming IO attack, because we now have separate file/anon LRU lists. When the use-once files crowd into the file LRU, the list's "quality" is significantly lowered. Therefore the scan balance policy in get_scan_ratio() will choose to scan the (low quality) file LRU much more frequently than the anon LRU. file pages ========== Rik proposed to *not* scan the active file LRU when the inactive list grows larger than active list. This guarantees that when there are use-once streaming IO, and the working set is not too large(so that active_size < inactive_size), the active file LRU will *not* be scanned at all. So the not-too-large working set can be well protected. But there are also situations where the file working set is a bit large so that (active_size >= inactive_size), or the streaming IOs are not purely use-once. In these cases, the active list will be scanned slowly. Because the current shrink_active_list() policy is to deactivate active pages regardless of their referenced bits. The deactivated pages become susceptible to the streaming IO attack: the inactive list could be scanned fast (500MB / 50MBps = 10s) so that the deactivated pages don't have enough time to get re-referenced. Because a user tend to switch between windows in intervals from seconds to minutes. This patch holds mapped executable pages in the active list as long as they are referenced during each full scan of the active list. Because the active list is normally scanned much slower, they get longer grace time (eg. 100s) for further references, which better matches the pace of user operations. Therefore this patch greatly prolongs the in-cache time of executable code, when there are moderate memory pressures. before patch: guaranteed to be cached if reference intervals < I after patch: guaranteed to be cached if reference intervals < I+A (except when randomly reclaimed by the lumpy reclaim) where A = time to fully scan the active file LRU I = time to fully scan the inactive file LRU Note that normally A >> I. side effects ============ This patch is safe in general, it restores the pre-2.6.28 mmap() behavior but in a much smaller and well targeted scope. One may worry about some one to abuse the PROT_EXEC heuristic. But as Andrew Morton stated, there are other tricks to getting that sort of boost. Another concern is the PROT_EXEC mapped pages growing large in rare cases, and therefore hurting reclaim efficiency. But a sane application targeted for large audience will never use PROT_EXEC for data mappings. If some home made application tries to abuse that bit, it shall be aware of the consequences. If it is abused to scale of 2/3 total memory, it gains nothing but overheads. benchmarks ========== 1) memory tight desktop 1.1) brief summary - clock time and major faults are reduced by 50%; - pswpin numbers are reduced to ~1/3. That means X desktop responsiveness is doubled under high memory/swap pressure. 1.2) test scenario - nfsroot gnome desktop with 512M physical memory - run some programs, and switch between the existing windows after starting each new program. 1.3) progress timing (seconds) before after programs 0.02 0.02 N xeyes 0.75 0.76 N firefox 2.02 1.88 N nautilus 3.36 3.17 N nautilus --browser 5.26 4.89 N gthumb 7.12 6.47 N gedit 9.22 8.16 N xpdf /usr/share/doc/shared-mime-info/shared-mime-info-spec.pdf 13.58 12.55 N xterm 15.87 14.57 N mlterm 18.63 17.06 N gnome-terminal 21.16 18.90 N urxvt 26.24 23.48 N gnome-system-monitor 28.72 26.52 N gnome-help 32.15 29.65 N gnome-dictionary 39.66 36.12 N /usr/games/sol 43.16 39.27 N /usr/games/gnometris 48.65 42.56 N /usr/games/gnect 53.31 47.03 N /usr/games/gtali 58.60 52.05 N /usr/games/iagno 65.77 55.42 N /usr/games/gnotravex 70.76 61.47 N /usr/games/mahjongg 76.15 67.11 N /usr/games/gnome-sudoku 86.32 75.15 N /usr/games/glines 92.21 79.70 N /usr/games/glchess 103.79 88.48 N /usr/games/gnomine 113.84 96.51 N /usr/games/gnotski 124.40 102.19 N /usr/games/gnibbles 137.41 114.93 N /usr/games/gnobots2 155.53 125.02 N /usr/games/blackjack 179.85 135.11 N /usr/games/same-gnome 224.49 154.50 N /usr/bin/gnome-window-properties 248.44 162.09 N /usr/bin/gnome-default-applications-properties 282.62 173.29 N /usr/bin/gnome-at-properties 323.72 188.21 N /usr/bin/gnome-typing-monitor 363.99 199.93 N /usr/bin/gnome-at-visual 394.21 206.95 N /usr/bin/gnome-sound-properties 435.14 224.49 N /usr/bin/gnome-at-mobility 463.05 234.11 N /usr/bin/gnome-keybinding-properties 503.75 248.59 N /usr/bin/gnome-about-me 554.00 276.27 N /usr/bin/gnome-display-properties 615.48 304.39 N /usr/bin/gnome-network-preferences 693.03 342.01 N /usr/bin/gnome-mouse-properties 759.90 388.58 N /usr/bin/gnome-appearance-properties 937.90 508.47 N /usr/bin/gnome-control-center 1109.75 587.57 N /usr/bin/gnome-keyboard-properties 1399.05 758.16 N : oocalc 1524.64 830.03 N : oodraw 1684.31 900.03 N : ooimpress 1874.04 993.91 N : oomath 2115.12 1081.89 N : ooweb 2369.02 1161.99 N : oowriter Note that the last ": oo*" commands are actually commented out. 1.4) vmstat numbers (some relevant ones are marked with *) before after nr_free_pages 1293 3898 nr_inactive_anon 59956 53460 nr_active_anon 26815 30026 nr_inactive_file 2657 3218 nr_active_file 2019 2806 nr_unevictable 4 4 nr_mlock 4 4 nr_anon_pages 26706 27859 *nr_mapped 3542 4469 nr_file_pages 72232 67681 nr_dirty 1 0 nr_writeback 123 19 nr_slab_reclaimable 3375 3534 nr_slab_unreclaimable 11405 10665 nr_page_table_pages 8106 7864 nr_unstable 0 0 nr_bounce 0 0 *nr_vmscan_write 394776 230839 nr_writeback_temp 0 0 numa_hit 6843353 3318676 numa_miss 0 0 numa_foreign 0 0 numa_interleave 1719 1719 numa_local 6843353 3318676 numa_other 0 0 *pgpgin 5954683 2057175 *pgpgout 1578276 922744 *pswpin 1486615 512238 *pswpout 394568 230685 pgalloc_dma 277432 56602 pgalloc_dma32 6769477 3310348 pgalloc_normal 0 0 pgalloc_movable 0 0 pgfree 7048396 3371118 pgactivate 2036343 1471492 pgdeactivate 2189691 1612829 pgfault 3702176 3100702 *pgmajfault 452116 201343 pgrefill_dma 12185 7127 pgrefill_dma32 334384 653703 pgrefill_normal 0 0 pgrefill_movable 0 0 pgsteal_dma 74214 22179 pgsteal_dma32 3334164 1638029 pgsteal_normal 0 0 pgsteal_movable 0 0 pgscan_kswapd_dma 1081421 1216199 pgscan_kswapd_dma32 58979118 46002810 pgscan_kswapd_normal 0 0 pgscan_kswapd_movable 0 0 pgscan_direct_dma 2015438 1086109 pgscan_direct_dma32 55787823 36101597 pgscan_direct_normal 0 0 pgscan_direct_movable 0 0 pginodesteal 3461 7281 slabs_scanned 564864 527616 kswapd_steal 2889797 1448082 kswapd_inodesteal 14827 14835 pageoutrun 43459 21562 allocstall 9653 4032 pgrotated 384216 228631 1.5) free numbers at the end of the tests before patch: total used free shared buffers cached Mem: 474 467 7 0 0 236 -/+ buffers/cache: 230 243 Swap: 1023 418 605 after patch: total used free shared buffers cached Mem: 474 457 16 0 0 236 -/+ buffers/cache: 221 253 Swap: 1023 404 619 2) memory flushing in a file server 2.1) brief summary The number of major faults from 50 to 3 during 10% cache hot reads. That means this patch successfully stops major faults when the active file list is slowly scanned when there are partially cache hot streaming IO. 2.2) test scenario Do 100000 pread(size=110 pages, offset=(i*100) pages), where 10% of the pages will be activated: for i in `seq 0 100 10000000`; do echo $i 110; done > pattern-hot-10 iotrace.rb --load pattern-hot-10 --play /b/sparse vmmon nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree and monitor /proc/vmstat during the time. The test box has 2G memory. I carried out tests on fresh booted console as well as X desktop, and fetched the vmstat numbers on (1) begin: shortly after the big read IO starts; (2) end: just before the big read IO stops; (3) restore: the big read IO stops and the zsh working set restored (4) restore X: after IO, switch back and forth between the urxvt and firefox windows to restore their working set. 2.3) console mode results nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree 2.6.29 VM_EXEC protection ON: begin: 2481 2237 8694 630 0 574299 end: 275 231976 233914 633 776271 20933042 restore: 370 232154 234524 691 777183 20958453 2.6.29 VM_EXEC protection ON (second run): begin: 2434 2237 8493 629 0 574195 end: 284 231970 233536 632 771918 20896129 restore: 399 232218 234789 690 774526 20957909 2.6.30-rc4-mm VM_EXEC protection OFF: begin: 2479 2344 9659 210 0 579643 end: 284 232010 234142 260 772776 20917184 restore: 379 232159 234371 301 774888 20967849 The above console numbers show that - The startup pgmajfault of 2.6.30-rc4-mm is merely 1/3 that of 2.6.29. I'd attribute that improvement to the mmap readahead improvements :-) - The pgmajfault increment during the file copy is 633-630=3 vs 260-210=50. That's a huge improvement - which means with the VM_EXEC protection logic, active mmap pages is pretty safe even under partially cache hot streaming IO. - when active:inactive file lru size reaches 1:1, their scan rates is 1:20.8 under 10% cache hot IO. (computed with formula Dpgdeactivate:Dpgfree) That roughly means the active mmap pages get 20.8 more chances to get re-referenced to stay in memory. - The absolute nr_mapped drops considerably to 1/9 during the big IO, and the dropped pages are mostly inactive ones. The patch has almost no impact in this aspect, that means it won't unnecessarily increase memory pressure. (In contrast, your 20% mmap protection ratio will keep them all, and therefore eliminate the extra 41 major faults to restore working set of zsh etc.) The iotrace.rb read throughput is 151.194384MB/s 284.198252s 100001x 450560b --load pattern-hot-10 --play /b/sparse which means the inactive list is rotated at the speed of 250MB/s, so a full scan of which takes about 3.5 seconds, while a full scan of active file list takes about 77 seconds. 2.4) X mode results We can reach roughly the same conclusions for X desktop: nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree 2.6.30-rc4-mm VM_EXEC protection ON: begin: 9740 8920 64075 561 0 678360 end: 768 218254 220029 565 798953 21057006 restore: 857 218543 220987 606 799462 21075710 restore X: 2414 218560 225344 797 799462 21080795 2.6.30-rc4-mm VM_EXEC protection OFF: begin: 9368 5035 26389 554 0 633391 end: 770 218449 221230 661 646472 17832500 restore: 1113 218466 220978 710 649881 17905235 restore X: 2687 218650 225484 947 802700 21083584 - the absolute nr_mapped drops considerably (to 1/13 of the original size) during the streaming IO. - the delta of pgmajfault is 3 vs 107 during IO, or 236 vs 393 during the whole process. Cc: Elladan <elladan@eskimo.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Andi Kleen <andi@firstfloor.org> Cc: Christoph Lameter <cl@linux-foundation.org> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:12 +08:00
list_add(&page->lru, &l_active);
continue;
}
}
ClearPageActive(page); /* we are de-activating */
list_add(&page->lru, &l_inactive);
}
/*
vmscan: make mapped executable pages the first class citizen Protect referenced PROT_EXEC mapped pages from being deactivated. PROT_EXEC(or its internal presentation VM_EXEC) pages normally belong to some currently running executables and their linked libraries, they shall really be cached aggressively to provide good user experiences. Thanks to Johannes Weiner for the advice to reuse the VMA walk in page_referenced() to get the PROT_EXEC bit. [more details] ( The consequences of this patch will have to be discussed together with Rik van Riel's recent patch "vmscan: evict use-once pages first". ) ( Some of the good points and insights are taken into this changelog. Thanks to all the involved people for the great LKML discussions. ) the problem =========== For a typical desktop, the most precious working set is composed of *actively accessed* (1) memory mapped executables (2) and their anonymous pages (3) and other files (4) and the dcache/icache/.. slabs while the least important data are (5) infrequently used or use-once files For a typical desktop, one major problem is busty and large amount of (5) use-once files flushing out the working set. Inside the working set, (4) dcache/icache have already been too sticky ;-) So we only have to care (2) anonymous and (1)(3) file pages. anonymous pages =============== Anonymous pages are effectively immune to the streaming IO attack, because we now have separate file/anon LRU lists. When the use-once files crowd into the file LRU, the list's "quality" is significantly lowered. Therefore the scan balance policy in get_scan_ratio() will choose to scan the (low quality) file LRU much more frequently than the anon LRU. file pages ========== Rik proposed to *not* scan the active file LRU when the inactive list grows larger than active list. This guarantees that when there are use-once streaming IO, and the working set is not too large(so that active_size < inactive_size), the active file LRU will *not* be scanned at all. So the not-too-large working set can be well protected. But there are also situations where the file working set is a bit large so that (active_size >= inactive_size), or the streaming IOs are not purely use-once. In these cases, the active list will be scanned slowly. Because the current shrink_active_list() policy is to deactivate active pages regardless of their referenced bits. The deactivated pages become susceptible to the streaming IO attack: the inactive list could be scanned fast (500MB / 50MBps = 10s) so that the deactivated pages don't have enough time to get re-referenced. Because a user tend to switch between windows in intervals from seconds to minutes. This patch holds mapped executable pages in the active list as long as they are referenced during each full scan of the active list. Because the active list is normally scanned much slower, they get longer grace time (eg. 100s) for further references, which better matches the pace of user operations. Therefore this patch greatly prolongs the in-cache time of executable code, when there are moderate memory pressures. before patch: guaranteed to be cached if reference intervals < I after patch: guaranteed to be cached if reference intervals < I+A (except when randomly reclaimed by the lumpy reclaim) where A = time to fully scan the active file LRU I = time to fully scan the inactive file LRU Note that normally A >> I. side effects ============ This patch is safe in general, it restores the pre-2.6.28 mmap() behavior but in a much smaller and well targeted scope. One may worry about some one to abuse the PROT_EXEC heuristic. But as Andrew Morton stated, there are other tricks to getting that sort of boost. Another concern is the PROT_EXEC mapped pages growing large in rare cases, and therefore hurting reclaim efficiency. But a sane application targeted for large audience will never use PROT_EXEC for data mappings. If some home made application tries to abuse that bit, it shall be aware of the consequences. If it is abused to scale of 2/3 total memory, it gains nothing but overheads. benchmarks ========== 1) memory tight desktop 1.1) brief summary - clock time and major faults are reduced by 50%; - pswpin numbers are reduced to ~1/3. That means X desktop responsiveness is doubled under high memory/swap pressure. 1.2) test scenario - nfsroot gnome desktop with 512M physical memory - run some programs, and switch between the existing windows after starting each new program. 1.3) progress timing (seconds) before after programs 0.02 0.02 N xeyes 0.75 0.76 N firefox 2.02 1.88 N nautilus 3.36 3.17 N nautilus --browser 5.26 4.89 N gthumb 7.12 6.47 N gedit 9.22 8.16 N xpdf /usr/share/doc/shared-mime-info/shared-mime-info-spec.pdf 13.58 12.55 N xterm 15.87 14.57 N mlterm 18.63 17.06 N gnome-terminal 21.16 18.90 N urxvt 26.24 23.48 N gnome-system-monitor 28.72 26.52 N gnome-help 32.15 29.65 N gnome-dictionary 39.66 36.12 N /usr/games/sol 43.16 39.27 N /usr/games/gnometris 48.65 42.56 N /usr/games/gnect 53.31 47.03 N /usr/games/gtali 58.60 52.05 N /usr/games/iagno 65.77 55.42 N /usr/games/gnotravex 70.76 61.47 N /usr/games/mahjongg 76.15 67.11 N /usr/games/gnome-sudoku 86.32 75.15 N /usr/games/glines 92.21 79.70 N /usr/games/glchess 103.79 88.48 N /usr/games/gnomine 113.84 96.51 N /usr/games/gnotski 124.40 102.19 N /usr/games/gnibbles 137.41 114.93 N /usr/games/gnobots2 155.53 125.02 N /usr/games/blackjack 179.85 135.11 N /usr/games/same-gnome 224.49 154.50 N /usr/bin/gnome-window-properties 248.44 162.09 N /usr/bin/gnome-default-applications-properties 282.62 173.29 N /usr/bin/gnome-at-properties 323.72 188.21 N /usr/bin/gnome-typing-monitor 363.99 199.93 N /usr/bin/gnome-at-visual 394.21 206.95 N /usr/bin/gnome-sound-properties 435.14 224.49 N /usr/bin/gnome-at-mobility 463.05 234.11 N /usr/bin/gnome-keybinding-properties 503.75 248.59 N /usr/bin/gnome-about-me 554.00 276.27 N /usr/bin/gnome-display-properties 615.48 304.39 N /usr/bin/gnome-network-preferences 693.03 342.01 N /usr/bin/gnome-mouse-properties 759.90 388.58 N /usr/bin/gnome-appearance-properties 937.90 508.47 N /usr/bin/gnome-control-center 1109.75 587.57 N /usr/bin/gnome-keyboard-properties 1399.05 758.16 N : oocalc 1524.64 830.03 N : oodraw 1684.31 900.03 N : ooimpress 1874.04 993.91 N : oomath 2115.12 1081.89 N : ooweb 2369.02 1161.99 N : oowriter Note that the last ": oo*" commands are actually commented out. 1.4) vmstat numbers (some relevant ones are marked with *) before after nr_free_pages 1293 3898 nr_inactive_anon 59956 53460 nr_active_anon 26815 30026 nr_inactive_file 2657 3218 nr_active_file 2019 2806 nr_unevictable 4 4 nr_mlock 4 4 nr_anon_pages 26706 27859 *nr_mapped 3542 4469 nr_file_pages 72232 67681 nr_dirty 1 0 nr_writeback 123 19 nr_slab_reclaimable 3375 3534 nr_slab_unreclaimable 11405 10665 nr_page_table_pages 8106 7864 nr_unstable 0 0 nr_bounce 0 0 *nr_vmscan_write 394776 230839 nr_writeback_temp 0 0 numa_hit 6843353 3318676 numa_miss 0 0 numa_foreign 0 0 numa_interleave 1719 1719 numa_local 6843353 3318676 numa_other 0 0 *pgpgin 5954683 2057175 *pgpgout 1578276 922744 *pswpin 1486615 512238 *pswpout 394568 230685 pgalloc_dma 277432 56602 pgalloc_dma32 6769477 3310348 pgalloc_normal 0 0 pgalloc_movable 0 0 pgfree 7048396 3371118 pgactivate 2036343 1471492 pgdeactivate 2189691 1612829 pgfault 3702176 3100702 *pgmajfault 452116 201343 pgrefill_dma 12185 7127 pgrefill_dma32 334384 653703 pgrefill_normal 0 0 pgrefill_movable 0 0 pgsteal_dma 74214 22179 pgsteal_dma32 3334164 1638029 pgsteal_normal 0 0 pgsteal_movable 0 0 pgscan_kswapd_dma 1081421 1216199 pgscan_kswapd_dma32 58979118 46002810 pgscan_kswapd_normal 0 0 pgscan_kswapd_movable 0 0 pgscan_direct_dma 2015438 1086109 pgscan_direct_dma32 55787823 36101597 pgscan_direct_normal 0 0 pgscan_direct_movable 0 0 pginodesteal 3461 7281 slabs_scanned 564864 527616 kswapd_steal 2889797 1448082 kswapd_inodesteal 14827 14835 pageoutrun 43459 21562 allocstall 9653 4032 pgrotated 384216 228631 1.5) free numbers at the end of the tests before patch: total used free shared buffers cached Mem: 474 467 7 0 0 236 -/+ buffers/cache: 230 243 Swap: 1023 418 605 after patch: total used free shared buffers cached Mem: 474 457 16 0 0 236 -/+ buffers/cache: 221 253 Swap: 1023 404 619 2) memory flushing in a file server 2.1) brief summary The number of major faults from 50 to 3 during 10% cache hot reads. That means this patch successfully stops major faults when the active file list is slowly scanned when there are partially cache hot streaming IO. 2.2) test scenario Do 100000 pread(size=110 pages, offset=(i*100) pages), where 10% of the pages will be activated: for i in `seq 0 100 10000000`; do echo $i 110; done > pattern-hot-10 iotrace.rb --load pattern-hot-10 --play /b/sparse vmmon nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree and monitor /proc/vmstat during the time. The test box has 2G memory. I carried out tests on fresh booted console as well as X desktop, and fetched the vmstat numbers on (1) begin: shortly after the big read IO starts; (2) end: just before the big read IO stops; (3) restore: the big read IO stops and the zsh working set restored (4) restore X: after IO, switch back and forth between the urxvt and firefox windows to restore their working set. 2.3) console mode results nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree 2.6.29 VM_EXEC protection ON: begin: 2481 2237 8694 630 0 574299 end: 275 231976 233914 633 776271 20933042 restore: 370 232154 234524 691 777183 20958453 2.6.29 VM_EXEC protection ON (second run): begin: 2434 2237 8493 629 0 574195 end: 284 231970 233536 632 771918 20896129 restore: 399 232218 234789 690 774526 20957909 2.6.30-rc4-mm VM_EXEC protection OFF: begin: 2479 2344 9659 210 0 579643 end: 284 232010 234142 260 772776 20917184 restore: 379 232159 234371 301 774888 20967849 The above console numbers show that - The startup pgmajfault of 2.6.30-rc4-mm is merely 1/3 that of 2.6.29. I'd attribute that improvement to the mmap readahead improvements :-) - The pgmajfault increment during the file copy is 633-630=3 vs 260-210=50. That's a huge improvement - which means with the VM_EXEC protection logic, active mmap pages is pretty safe even under partially cache hot streaming IO. - when active:inactive file lru size reaches 1:1, their scan rates is 1:20.8 under 10% cache hot IO. (computed with formula Dpgdeactivate:Dpgfree) That roughly means the active mmap pages get 20.8 more chances to get re-referenced to stay in memory. - The absolute nr_mapped drops considerably to 1/9 during the big IO, and the dropped pages are mostly inactive ones. The patch has almost no impact in this aspect, that means it won't unnecessarily increase memory pressure. (In contrast, your 20% mmap protection ratio will keep them all, and therefore eliminate the extra 41 major faults to restore working set of zsh etc.) The iotrace.rb read throughput is 151.194384MB/s 284.198252s 100001x 450560b --load pattern-hot-10 --play /b/sparse which means the inactive list is rotated at the speed of 250MB/s, so a full scan of which takes about 3.5 seconds, while a full scan of active file list takes about 77 seconds. 2.4) X mode results We can reach roughly the same conclusions for X desktop: nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree 2.6.30-rc4-mm VM_EXEC protection ON: begin: 9740 8920 64075 561 0 678360 end: 768 218254 220029 565 798953 21057006 restore: 857 218543 220987 606 799462 21075710 restore X: 2414 218560 225344 797 799462 21080795 2.6.30-rc4-mm VM_EXEC protection OFF: begin: 9368 5035 26389 554 0 633391 end: 770 218449 221230 661 646472 17832500 restore: 1113 218466 220978 710 649881 17905235 restore X: 2687 218650 225484 947 802700 21083584 - the absolute nr_mapped drops considerably (to 1/13 of the original size) during the streaming IO. - the delta of pgmajfault is 3 vs 107 during IO, or 236 vs 393 during the whole process. Cc: Elladan <elladan@eskimo.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Andi Kleen <andi@firstfloor.org> Cc: Christoph Lameter <cl@linux-foundation.org> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:12 +08:00
* Move pages back to the lru list.
*/
spin_lock_irq(&zone->lru_lock);
/*
vmscan: make mapped executable pages the first class citizen Protect referenced PROT_EXEC mapped pages from being deactivated. PROT_EXEC(or its internal presentation VM_EXEC) pages normally belong to some currently running executables and their linked libraries, they shall really be cached aggressively to provide good user experiences. Thanks to Johannes Weiner for the advice to reuse the VMA walk in page_referenced() to get the PROT_EXEC bit. [more details] ( The consequences of this patch will have to be discussed together with Rik van Riel's recent patch "vmscan: evict use-once pages first". ) ( Some of the good points and insights are taken into this changelog. Thanks to all the involved people for the great LKML discussions. ) the problem =========== For a typical desktop, the most precious working set is composed of *actively accessed* (1) memory mapped executables (2) and their anonymous pages (3) and other files (4) and the dcache/icache/.. slabs while the least important data are (5) infrequently used or use-once files For a typical desktop, one major problem is busty and large amount of (5) use-once files flushing out the working set. Inside the working set, (4) dcache/icache have already been too sticky ;-) So we only have to care (2) anonymous and (1)(3) file pages. anonymous pages =============== Anonymous pages are effectively immune to the streaming IO attack, because we now have separate file/anon LRU lists. When the use-once files crowd into the file LRU, the list's "quality" is significantly lowered. Therefore the scan balance policy in get_scan_ratio() will choose to scan the (low quality) file LRU much more frequently than the anon LRU. file pages ========== Rik proposed to *not* scan the active file LRU when the inactive list grows larger than active list. This guarantees that when there are use-once streaming IO, and the working set is not too large(so that active_size < inactive_size), the active file LRU will *not* be scanned at all. So the not-too-large working set can be well protected. But there are also situations where the file working set is a bit large so that (active_size >= inactive_size), or the streaming IOs are not purely use-once. In these cases, the active list will be scanned slowly. Because the current shrink_active_list() policy is to deactivate active pages regardless of their referenced bits. The deactivated pages become susceptible to the streaming IO attack: the inactive list could be scanned fast (500MB / 50MBps = 10s) so that the deactivated pages don't have enough time to get re-referenced. Because a user tend to switch between windows in intervals from seconds to minutes. This patch holds mapped executable pages in the active list as long as they are referenced during each full scan of the active list. Because the active list is normally scanned much slower, they get longer grace time (eg. 100s) for further references, which better matches the pace of user operations. Therefore this patch greatly prolongs the in-cache time of executable code, when there are moderate memory pressures. before patch: guaranteed to be cached if reference intervals < I after patch: guaranteed to be cached if reference intervals < I+A (except when randomly reclaimed by the lumpy reclaim) where A = time to fully scan the active file LRU I = time to fully scan the inactive file LRU Note that normally A >> I. side effects ============ This patch is safe in general, it restores the pre-2.6.28 mmap() behavior but in a much smaller and well targeted scope. One may worry about some one to abuse the PROT_EXEC heuristic. But as Andrew Morton stated, there are other tricks to getting that sort of boost. Another concern is the PROT_EXEC mapped pages growing large in rare cases, and therefore hurting reclaim efficiency. But a sane application targeted for large audience will never use PROT_EXEC for data mappings. If some home made application tries to abuse that bit, it shall be aware of the consequences. If it is abused to scale of 2/3 total memory, it gains nothing but overheads. benchmarks ========== 1) memory tight desktop 1.1) brief summary - clock time and major faults are reduced by 50%; - pswpin numbers are reduced to ~1/3. That means X desktop responsiveness is doubled under high memory/swap pressure. 1.2) test scenario - nfsroot gnome desktop with 512M physical memory - run some programs, and switch between the existing windows after starting each new program. 1.3) progress timing (seconds) before after programs 0.02 0.02 N xeyes 0.75 0.76 N firefox 2.02 1.88 N nautilus 3.36 3.17 N nautilus --browser 5.26 4.89 N gthumb 7.12 6.47 N gedit 9.22 8.16 N xpdf /usr/share/doc/shared-mime-info/shared-mime-info-spec.pdf 13.58 12.55 N xterm 15.87 14.57 N mlterm 18.63 17.06 N gnome-terminal 21.16 18.90 N urxvt 26.24 23.48 N gnome-system-monitor 28.72 26.52 N gnome-help 32.15 29.65 N gnome-dictionary 39.66 36.12 N /usr/games/sol 43.16 39.27 N /usr/games/gnometris 48.65 42.56 N /usr/games/gnect 53.31 47.03 N /usr/games/gtali 58.60 52.05 N /usr/games/iagno 65.77 55.42 N /usr/games/gnotravex 70.76 61.47 N /usr/games/mahjongg 76.15 67.11 N /usr/games/gnome-sudoku 86.32 75.15 N /usr/games/glines 92.21 79.70 N /usr/games/glchess 103.79 88.48 N /usr/games/gnomine 113.84 96.51 N /usr/games/gnotski 124.40 102.19 N /usr/games/gnibbles 137.41 114.93 N /usr/games/gnobots2 155.53 125.02 N /usr/games/blackjack 179.85 135.11 N /usr/games/same-gnome 224.49 154.50 N /usr/bin/gnome-window-properties 248.44 162.09 N /usr/bin/gnome-default-applications-properties 282.62 173.29 N /usr/bin/gnome-at-properties 323.72 188.21 N /usr/bin/gnome-typing-monitor 363.99 199.93 N /usr/bin/gnome-at-visual 394.21 206.95 N /usr/bin/gnome-sound-properties 435.14 224.49 N /usr/bin/gnome-at-mobility 463.05 234.11 N /usr/bin/gnome-keybinding-properties 503.75 248.59 N /usr/bin/gnome-about-me 554.00 276.27 N /usr/bin/gnome-display-properties 615.48 304.39 N /usr/bin/gnome-network-preferences 693.03 342.01 N /usr/bin/gnome-mouse-properties 759.90 388.58 N /usr/bin/gnome-appearance-properties 937.90 508.47 N /usr/bin/gnome-control-center 1109.75 587.57 N /usr/bin/gnome-keyboard-properties 1399.05 758.16 N : oocalc 1524.64 830.03 N : oodraw 1684.31 900.03 N : ooimpress 1874.04 993.91 N : oomath 2115.12 1081.89 N : ooweb 2369.02 1161.99 N : oowriter Note that the last ": oo*" commands are actually commented out. 1.4) vmstat numbers (some relevant ones are marked with *) before after nr_free_pages 1293 3898 nr_inactive_anon 59956 53460 nr_active_anon 26815 30026 nr_inactive_file 2657 3218 nr_active_file 2019 2806 nr_unevictable 4 4 nr_mlock 4 4 nr_anon_pages 26706 27859 *nr_mapped 3542 4469 nr_file_pages 72232 67681 nr_dirty 1 0 nr_writeback 123 19 nr_slab_reclaimable 3375 3534 nr_slab_unreclaimable 11405 10665 nr_page_table_pages 8106 7864 nr_unstable 0 0 nr_bounce 0 0 *nr_vmscan_write 394776 230839 nr_writeback_temp 0 0 numa_hit 6843353 3318676 numa_miss 0 0 numa_foreign 0 0 numa_interleave 1719 1719 numa_local 6843353 3318676 numa_other 0 0 *pgpgin 5954683 2057175 *pgpgout 1578276 922744 *pswpin 1486615 512238 *pswpout 394568 230685 pgalloc_dma 277432 56602 pgalloc_dma32 6769477 3310348 pgalloc_normal 0 0 pgalloc_movable 0 0 pgfree 7048396 3371118 pgactivate 2036343 1471492 pgdeactivate 2189691 1612829 pgfault 3702176 3100702 *pgmajfault 452116 201343 pgrefill_dma 12185 7127 pgrefill_dma32 334384 653703 pgrefill_normal 0 0 pgrefill_movable 0 0 pgsteal_dma 74214 22179 pgsteal_dma32 3334164 1638029 pgsteal_normal 0 0 pgsteal_movable 0 0 pgscan_kswapd_dma 1081421 1216199 pgscan_kswapd_dma32 58979118 46002810 pgscan_kswapd_normal 0 0 pgscan_kswapd_movable 0 0 pgscan_direct_dma 2015438 1086109 pgscan_direct_dma32 55787823 36101597 pgscan_direct_normal 0 0 pgscan_direct_movable 0 0 pginodesteal 3461 7281 slabs_scanned 564864 527616 kswapd_steal 2889797 1448082 kswapd_inodesteal 14827 14835 pageoutrun 43459 21562 allocstall 9653 4032 pgrotated 384216 228631 1.5) free numbers at the end of the tests before patch: total used free shared buffers cached Mem: 474 467 7 0 0 236 -/+ buffers/cache: 230 243 Swap: 1023 418 605 after patch: total used free shared buffers cached Mem: 474 457 16 0 0 236 -/+ buffers/cache: 221 253 Swap: 1023 404 619 2) memory flushing in a file server 2.1) brief summary The number of major faults from 50 to 3 during 10% cache hot reads. That means this patch successfully stops major faults when the active file list is slowly scanned when there are partially cache hot streaming IO. 2.2) test scenario Do 100000 pread(size=110 pages, offset=(i*100) pages), where 10% of the pages will be activated: for i in `seq 0 100 10000000`; do echo $i 110; done > pattern-hot-10 iotrace.rb --load pattern-hot-10 --play /b/sparse vmmon nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree and monitor /proc/vmstat during the time. The test box has 2G memory. I carried out tests on fresh booted console as well as X desktop, and fetched the vmstat numbers on (1) begin: shortly after the big read IO starts; (2) end: just before the big read IO stops; (3) restore: the big read IO stops and the zsh working set restored (4) restore X: after IO, switch back and forth between the urxvt and firefox windows to restore their working set. 2.3) console mode results nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree 2.6.29 VM_EXEC protection ON: begin: 2481 2237 8694 630 0 574299 end: 275 231976 233914 633 776271 20933042 restore: 370 232154 234524 691 777183 20958453 2.6.29 VM_EXEC protection ON (second run): begin: 2434 2237 8493 629 0 574195 end: 284 231970 233536 632 771918 20896129 restore: 399 232218 234789 690 774526 20957909 2.6.30-rc4-mm VM_EXEC protection OFF: begin: 2479 2344 9659 210 0 579643 end: 284 232010 234142 260 772776 20917184 restore: 379 232159 234371 301 774888 20967849 The above console numbers show that - The startup pgmajfault of 2.6.30-rc4-mm is merely 1/3 that of 2.6.29. I'd attribute that improvement to the mmap readahead improvements :-) - The pgmajfault increment during the file copy is 633-630=3 vs 260-210=50. That's a huge improvement - which means with the VM_EXEC protection logic, active mmap pages is pretty safe even under partially cache hot streaming IO. - when active:inactive file lru size reaches 1:1, their scan rates is 1:20.8 under 10% cache hot IO. (computed with formula Dpgdeactivate:Dpgfree) That roughly means the active mmap pages get 20.8 more chances to get re-referenced to stay in memory. - The absolute nr_mapped drops considerably to 1/9 during the big IO, and the dropped pages are mostly inactive ones. The patch has almost no impact in this aspect, that means it won't unnecessarily increase memory pressure. (In contrast, your 20% mmap protection ratio will keep them all, and therefore eliminate the extra 41 major faults to restore working set of zsh etc.) The iotrace.rb read throughput is 151.194384MB/s 284.198252s 100001x 450560b --load pattern-hot-10 --play /b/sparse which means the inactive list is rotated at the speed of 250MB/s, so a full scan of which takes about 3.5 seconds, while a full scan of active file list takes about 77 seconds. 2.4) X mode results We can reach roughly the same conclusions for X desktop: nr_mapped nr_active_file nr_inactive_file pgmajfault pgdeactivate pgfree 2.6.30-rc4-mm VM_EXEC protection ON: begin: 9740 8920 64075 561 0 678360 end: 768 218254 220029 565 798953 21057006 restore: 857 218543 220987 606 799462 21075710 restore X: 2414 218560 225344 797 799462 21080795 2.6.30-rc4-mm VM_EXEC protection OFF: begin: 9368 5035 26389 554 0 633391 end: 770 218449 221230 661 646472 17832500 restore: 1113 218466 220978 710 649881 17905235 restore X: 2687 218650 225484 947 802700 21083584 - the absolute nr_mapped drops considerably (to 1/13 of the original size) during the streaming IO. - the delta of pgmajfault is 3 vs 107 during IO, or 236 vs 393 during the whole process. Cc: Elladan <elladan@eskimo.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Andi Kleen <andi@firstfloor.org> Cc: Christoph Lameter <cl@linux-foundation.org> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:12 +08:00
* Count referenced pages from currently used mappings as rotated,
* even though only some of them are actually re-activated. This
* helps balance scan pressure between file and anonymous pages in
* get_scan_ratio.
*/
reclaim_stat->recent_rotated[file] += nr_rotated;
move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
[PATCH] Light weight event counters The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 16:55:45 +08:00
spin_unlock_irq(&zone->lru_lock);
mm: take pagevecs off reclaim stack Replace pagevecs in putback_lru_pages() and move_active_pages_to_lru() by lists of pages_to_free: then apply Konstantin Khlebnikov's free_hot_cold_page_list() to them instead of pagevec_release(). Which simplifies the flow (no need to drop and retake lock whenever pagevec fills up) and reduces stale addresses in stack backtraces (which often showed through the pagevecs); but more importantly, removes another 120 bytes from the deepest stacks in page reclaim. Although I've not recently seen an actual stack overflow here with a vanilla kernel, move_active_pages_to_lru() has often featured in deep backtraces. However, free_hot_cold_page_list() does not handle compound pages (nor need it: a Transparent HugePage would have been split by the time it reaches the call in shrink_page_list()), but it is possible for putback_lru_pages() or move_active_pages_to_lru() to be left holding the last reference on a THP, so must exclude the unlikely compound case before putting on pages_to_free. Remove pagevec_strip(), its work now done in move_active_pages_to_lru(). The pagevec in scan_mapping_unevictable_pages() remains in mm/vmscan.c, but that is never on the reclaim path, and cannot be replaced by a list. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 09:19:56 +08:00
free_hot_cold_page_list(&l_hold, 1);
}
vmscan: prevent background aging of anon page in no swap system Ying Han reported that backing aging of anon pages in no swap system causes unnecessary TLB flush. When I sent a patch(69c8548175), I wanted this patch but Rik pointed out and allowed aging of anon pages to give a chance to promote from inactive to active LRU. It has a two problem. 1) non-swap system Never make sense to age anon pages. 2) swap configured but still doesn't swapon It doesn't make sense to age anon pages until swap-on time. But it's arguable. If we have aged anon pages by swapon, VM have moved anon pages from active to inactive. And in the time swapon by admin, the VM can't reclaim hot pages so we can protect hot pages swapout. But let's think about it. When does swap-on happen? It depends on admin. we can't expect it. Nonetheless, we have done aging of anon pages to protect hot pages swapout. It means we lost run time overhead when below high watermark but gain hot page swap-[in/out] overhead when VM decide swapout. Is it true? Let's think more detail. We don't promote anon pages in case of non-swap system. So even though VM does aging of anon pages, the pages would be in inactive LRU for a long time. It means many of pages in there would mark access bit again. So access bit hot/code separation would be pointless. This patch prevents unnecessary anon pages demotion in not-yet-swapon and non-configured swap system. Even, in non-configuared swap system inactive_anon_is_low can be compiled out. It could make side effect that hot anon pages could swap out when admin does swap on. But I think sooner or later it would be steady state. So it's not a big problem. We could lose someting but gain more thing(TLB flush and unnecessary function call to demote anon pages). Signed-off-by: Ying Han <yinghan@google.com> Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:31 +08:00
#ifdef CONFIG_SWAP
static int inactive_anon_is_low_global(struct zone *zone)
{
unsigned long active, inactive;
active = zone_page_state(zone, NR_ACTIVE_ANON);
inactive = zone_page_state(zone, NR_INACTIVE_ANON);
if (inactive * zone->inactive_ratio < active)
return 1;
return 0;
}
/**
* inactive_anon_is_low - check if anonymous pages need to be deactivated
* @lruvec: LRU vector to check
*
* Returns true if the zone does not have enough inactive anon pages,
* meaning some active anon pages need to be deactivated.
*/
static int inactive_anon_is_low(struct lruvec *lruvec)
{
vmscan: prevent background aging of anon page in no swap system Ying Han reported that backing aging of anon pages in no swap system causes unnecessary TLB flush. When I sent a patch(69c8548175), I wanted this patch but Rik pointed out and allowed aging of anon pages to give a chance to promote from inactive to active LRU. It has a two problem. 1) non-swap system Never make sense to age anon pages. 2) swap configured but still doesn't swapon It doesn't make sense to age anon pages until swap-on time. But it's arguable. If we have aged anon pages by swapon, VM have moved anon pages from active to inactive. And in the time swapon by admin, the VM can't reclaim hot pages so we can protect hot pages swapout. But let's think about it. When does swap-on happen? It depends on admin. we can't expect it. Nonetheless, we have done aging of anon pages to protect hot pages swapout. It means we lost run time overhead when below high watermark but gain hot page swap-[in/out] overhead when VM decide swapout. Is it true? Let's think more detail. We don't promote anon pages in case of non-swap system. So even though VM does aging of anon pages, the pages would be in inactive LRU for a long time. It means many of pages in there would mark access bit again. So access bit hot/code separation would be pointless. This patch prevents unnecessary anon pages demotion in not-yet-swapon and non-configured swap system. Even, in non-configuared swap system inactive_anon_is_low can be compiled out. It could make side effect that hot anon pages could swap out when admin does swap on. But I think sooner or later it would be steady state. So it's not a big problem. We could lose someting but gain more thing(TLB flush and unnecessary function call to demote anon pages). Signed-off-by: Ying Han <yinghan@google.com> Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:31 +08:00
/*
* If we don't have swap space, anonymous page deactivation
* is pointless.
*/
if (!total_swap_pages)
return 0;
if (!mem_cgroup_disabled())
return mem_cgroup_inactive_anon_is_low(lruvec);
return inactive_anon_is_low_global(lruvec_zone(lruvec));
}
vmscan: prevent background aging of anon page in no swap system Ying Han reported that backing aging of anon pages in no swap system causes unnecessary TLB flush. When I sent a patch(69c8548175), I wanted this patch but Rik pointed out and allowed aging of anon pages to give a chance to promote from inactive to active LRU. It has a two problem. 1) non-swap system Never make sense to age anon pages. 2) swap configured but still doesn't swapon It doesn't make sense to age anon pages until swap-on time. But it's arguable. If we have aged anon pages by swapon, VM have moved anon pages from active to inactive. And in the time swapon by admin, the VM can't reclaim hot pages so we can protect hot pages swapout. But let's think about it. When does swap-on happen? It depends on admin. we can't expect it. Nonetheless, we have done aging of anon pages to protect hot pages swapout. It means we lost run time overhead when below high watermark but gain hot page swap-[in/out] overhead when VM decide swapout. Is it true? Let's think more detail. We don't promote anon pages in case of non-swap system. So even though VM does aging of anon pages, the pages would be in inactive LRU for a long time. It means many of pages in there would mark access bit again. So access bit hot/code separation would be pointless. This patch prevents unnecessary anon pages demotion in not-yet-swapon and non-configured swap system. Even, in non-configuared swap system inactive_anon_is_low can be compiled out. It could make side effect that hot anon pages could swap out when admin does swap on. But I think sooner or later it would be steady state. So it's not a big problem. We could lose someting but gain more thing(TLB flush and unnecessary function call to demote anon pages). Signed-off-by: Ying Han <yinghan@google.com> Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:31 +08:00
#else
static inline int inactive_anon_is_low(struct lruvec *lruvec)
vmscan: prevent background aging of anon page in no swap system Ying Han reported that backing aging of anon pages in no swap system causes unnecessary TLB flush. When I sent a patch(69c8548175), I wanted this patch but Rik pointed out and allowed aging of anon pages to give a chance to promote from inactive to active LRU. It has a two problem. 1) non-swap system Never make sense to age anon pages. 2) swap configured but still doesn't swapon It doesn't make sense to age anon pages until swap-on time. But it's arguable. If we have aged anon pages by swapon, VM have moved anon pages from active to inactive. And in the time swapon by admin, the VM can't reclaim hot pages so we can protect hot pages swapout. But let's think about it. When does swap-on happen? It depends on admin. we can't expect it. Nonetheless, we have done aging of anon pages to protect hot pages swapout. It means we lost run time overhead when below high watermark but gain hot page swap-[in/out] overhead when VM decide swapout. Is it true? Let's think more detail. We don't promote anon pages in case of non-swap system. So even though VM does aging of anon pages, the pages would be in inactive LRU for a long time. It means many of pages in there would mark access bit again. So access bit hot/code separation would be pointless. This patch prevents unnecessary anon pages demotion in not-yet-swapon and non-configured swap system. Even, in non-configuared swap system inactive_anon_is_low can be compiled out. It could make side effect that hot anon pages could swap out when admin does swap on. But I think sooner or later it would be steady state. So it's not a big problem. We could lose someting but gain more thing(TLB flush and unnecessary function call to demote anon pages). Signed-off-by: Ying Han <yinghan@google.com> Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 05:21:31 +08:00
{
return 0;
}
#endif
static int inactive_file_is_low_global(struct zone *zone)
{
unsigned long active, inactive;
active = zone_page_state(zone, NR_ACTIVE_FILE);
inactive = zone_page_state(zone, NR_INACTIVE_FILE);
return (active > inactive);
}
/**
* inactive_file_is_low - check if file pages need to be deactivated
* @lruvec: LRU vector to check
*
* When the system is doing streaming IO, memory pressure here
* ensures that active file pages get deactivated, until more
* than half of the file pages are on the inactive list.
*
* Once we get to that situation, protect the system's working
* set from being evicted by disabling active file page aging.
*
* This uses a different ratio than the anonymous pages, because
* the page cache uses a use-once replacement algorithm.
*/
static int inactive_file_is_low(struct lruvec *lruvec)
{
if (!mem_cgroup_disabled())
return mem_cgroup_inactive_file_is_low(lruvec);
return inactive_file_is_low_global(lruvec_zone(lruvec));
}
static int inactive_list_is_low(struct lruvec *lruvec, enum lru_list lru)
{
if (is_file_lru(lru))
return inactive_file_is_low(lruvec);
else
return inactive_anon_is_low(lruvec);
}
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
struct lruvec *lruvec, struct scan_control *sc)
{
if (is_active_lru(lru)) {
if (inactive_list_is_low(lruvec, lru))
shrink_active_list(nr_to_scan, lruvec, sc, lru);
return 0;
}
return shrink_inactive_list(nr_to_scan, lruvec, sc, lru);
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
}
static int vmscan_swappiness(struct scan_control *sc)
{
if (global_reclaim(sc))
return vm_swappiness;
return mem_cgroup_swappiness(sc->target_mem_cgroup);
}
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
/*
* Determine how aggressively the anon and file LRU lists should be
* scanned. The relative value of each set of LRU lists is determined
* by looking at the fraction of the pages scanned we did rotate back
* onto the active list instead of evict.
*
* nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan
* nr[2] = file inactive pages to scan; nr[3] = file active pages to scan
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
*/
static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
unsigned long *nr)
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
{
unsigned long anon, file, free;
unsigned long anon_prio, file_prio;
unsigned long ap, fp;
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
vmscan: prevent get_scan_ratio() rounding errors get_scan_ratio() calculates percentage and if the percentage is < 1%, it will round percentage down to 0% and cause we completely ignore scanning anon/file pages to reclaim memory even the total anon/file pages are very big. To avoid underflow, we don't use percentage, instead we directly calculate how many pages should be scaned. In this way, we should get several scanned pages for < 1% percent. This has some benefits: 1. increase our calculation precision 2. making our scan more smoothly. Without this, if percent[x] is underflow, shrink_zone() doesn't scan any pages and suddenly it scans all pages when priority is zero. With this, even priority isn't zero, shrink_zone() gets chance to scan some pages. Note, this patch doesn't really change logics, but just increase precision. For system with a lot of memory, this might slightly changes behavior. For example, in a sequential file read workload, without the patch, we don't swap any anon pages. With it, if anon memory size is bigger than 16G, we will see one anon page swapped. The 16G is calculated as PAGE_SIZE * priority(4096) * (fp/ap). fp/ap is assumed to be 1024 which is common in this workload. So the impact sounds not a big deal. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:36 +08:00
u64 fraction[2], denominator;
enum lru_list lru;
vmscan: prevent get_scan_ratio() rounding errors get_scan_ratio() calculates percentage and if the percentage is < 1%, it will round percentage down to 0% and cause we completely ignore scanning anon/file pages to reclaim memory even the total anon/file pages are very big. To avoid underflow, we don't use percentage, instead we directly calculate how many pages should be scaned. In this way, we should get several scanned pages for < 1% percent. This has some benefits: 1. increase our calculation precision 2. making our scan more smoothly. Without this, if percent[x] is underflow, shrink_zone() doesn't scan any pages and suddenly it scans all pages when priority is zero. With this, even priority isn't zero, shrink_zone() gets chance to scan some pages. Note, this patch doesn't really change logics, but just increase precision. For system with a lot of memory, this might slightly changes behavior. For example, in a sequential file read workload, without the patch, we don't swap any anon pages. With it, if anon memory size is bigger than 16G, we will see one anon page swapped. The 16G is calculated as PAGE_SIZE * priority(4096) * (fp/ap). fp/ap is assumed to be 1024 which is common in this workload. So the impact sounds not a big deal. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:36 +08:00
int noswap = 0;
bool force_scan = false;
struct zone *zone = lruvec_zone(lruvec);
memcg: fix get_scan_count() for small targets During memory reclaim we determine the number of pages to be scanned per zone as (anon + file) >> priority. Assume scan = (anon + file) >> priority. If scan < SWAP_CLUSTER_MAX, the scan will be skipped for this time and priority gets higher. This has some problems. 1. This increases priority as 1 without any scan. To do scan in this priority, amount of pages should be larger than 512M. If pages>>priority < SWAP_CLUSTER_MAX, it's recorded and scan will be batched, later. (But we lose 1 priority.) If memory size is below 16M, pages >> priority is 0 and no scan in DEF_PRIORITY forever. 2. If zone->all_unreclaimabe==true, it's scanned only when priority==0. So, x86's ZONE_DMA will never be recoverred until the user of pages frees memory by itself. 3. With memcg, the limit of memory can be small. When using small memcg, it gets priority < DEF_PRIORITY-2 very easily and need to call wait_iff_congested(). For doing scan before priorty=9, 64MB of memory should be used. Then, this patch tries to scan SWAP_CLUSTER_MAX of pages in force...when 1. the target is enough small. 2. it's kswapd or memcg reclaim. Then we can avoid rapid priority drop and may be able to recover all_unreclaimable in a small zones. And this patch removes nr_saved_scan. This will allow scanning in this priority even when pages >> priority is very small. Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Ying Han <yinghan@google.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-27 07:25:34 +08:00
/*
* If the zone or memcg is small, nr[l] can be 0. This
* results in no scanning on this priority and a potential
* priority drop. Global direct reclaim can go to the next
* zone and tends to have no problems. Global kswapd is for
* zone balancing and it needs to scan a minimum amount. When
* reclaiming for a memcg, a priority drop can cause high
* latencies, so it's better to scan a minimum amount there as
* well.
*/
if (current_is_kswapd() && zone->all_unreclaimable)
force_scan = true;
if (!global_reclaim(sc))
force_scan = true;
vmscan: prevent get_scan_ratio() rounding errors get_scan_ratio() calculates percentage and if the percentage is < 1%, it will round percentage down to 0% and cause we completely ignore scanning anon/file pages to reclaim memory even the total anon/file pages are very big. To avoid underflow, we don't use percentage, instead we directly calculate how many pages should be scaned. In this way, we should get several scanned pages for < 1% percent. This has some benefits: 1. increase our calculation precision 2. making our scan more smoothly. Without this, if percent[x] is underflow, shrink_zone() doesn't scan any pages and suddenly it scans all pages when priority is zero. With this, even priority isn't zero, shrink_zone() gets chance to scan some pages. Note, this patch doesn't really change logics, but just increase precision. For system with a lot of memory, this might slightly changes behavior. For example, in a sequential file read workload, without the patch, we don't swap any anon pages. With it, if anon memory size is bigger than 16G, we will see one anon page swapped. The 16G is calculated as PAGE_SIZE * priority(4096) * (fp/ap). fp/ap is assumed to be 1024 which is common in this workload. So the impact sounds not a big deal. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:36 +08:00
/* If we have no swap space, do not bother scanning anon pages. */
if (!sc->may_swap || (nr_swap_pages <= 0)) {
noswap = 1;
fraction[0] = 0;
fraction[1] = 1;
denominator = 1;
goto out;
}
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) +
get_lru_size(lruvec, LRU_INACTIVE_ANON);
file = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
get_lru_size(lruvec, LRU_INACTIVE_FILE);
if (global_reclaim(sc)) {
free = zone_page_state(zone, NR_FREE_PAGES);
/* If we have very few page cache pages,
force-scan anon pages. */
if (unlikely(file + free <= high_wmark_pages(zone))) {
vmscan: prevent get_scan_ratio() rounding errors get_scan_ratio() calculates percentage and if the percentage is < 1%, it will round percentage down to 0% and cause we completely ignore scanning anon/file pages to reclaim memory even the total anon/file pages are very big. To avoid underflow, we don't use percentage, instead we directly calculate how many pages should be scaned. In this way, we should get several scanned pages for < 1% percent. This has some benefits: 1. increase our calculation precision 2. making our scan more smoothly. Without this, if percent[x] is underflow, shrink_zone() doesn't scan any pages and suddenly it scans all pages when priority is zero. With this, even priority isn't zero, shrink_zone() gets chance to scan some pages. Note, this patch doesn't really change logics, but just increase precision. For system with a lot of memory, this might slightly changes behavior. For example, in a sequential file read workload, without the patch, we don't swap any anon pages. With it, if anon memory size is bigger than 16G, we will see one anon page swapped. The 16G is calculated as PAGE_SIZE * priority(4096) * (fp/ap). fp/ap is assumed to be 1024 which is common in this workload. So the impact sounds not a big deal. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:36 +08:00
fraction[0] = 1;
fraction[1] = 0;
denominator = 1;
goto out;
}
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
}
/*
* With swappiness at 100, anonymous and file have the same priority.
* This scanning priority is essentially the inverse of IO cost.
*/
anon_prio = vmscan_swappiness(sc);
file_prio = 200 - anon_prio;
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
/*
* OK, so we have swap space and a fair amount of page cache
* pages. We use the recently rotated / recently scanned
* ratios to determine how valuable each cache is.
*
* Because workloads change over time (and to avoid overflow)
* we keep these statistics as a floating average, which ends
* up weighing recent references more than old ones.
*
* anon in [0], file in [1]
*/
spin_lock_irq(&zone->lru_lock);
if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
reclaim_stat->recent_scanned[0] /= 2;
reclaim_stat->recent_rotated[0] /= 2;
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
}
if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
reclaim_stat->recent_scanned[1] /= 2;
reclaim_stat->recent_rotated[1] /= 2;
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
}
/*
* The amount of pressure on anon vs file pages is inversely
* proportional to the fraction of recently scanned pages on
* each list that were recently referenced and in active use.
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
*/
ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1);
ap /= reclaim_stat->recent_rotated[0] + 1;
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
fp /= reclaim_stat->recent_rotated[1] + 1;
spin_unlock_irq(&zone->lru_lock);
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
vmscan: prevent get_scan_ratio() rounding errors get_scan_ratio() calculates percentage and if the percentage is < 1%, it will round percentage down to 0% and cause we completely ignore scanning anon/file pages to reclaim memory even the total anon/file pages are very big. To avoid underflow, we don't use percentage, instead we directly calculate how many pages should be scaned. In this way, we should get several scanned pages for < 1% percent. This has some benefits: 1. increase our calculation precision 2. making our scan more smoothly. Without this, if percent[x] is underflow, shrink_zone() doesn't scan any pages and suddenly it scans all pages when priority is zero. With this, even priority isn't zero, shrink_zone() gets chance to scan some pages. Note, this patch doesn't really change logics, but just increase precision. For system with a lot of memory, this might slightly changes behavior. For example, in a sequential file read workload, without the patch, we don't swap any anon pages. With it, if anon memory size is bigger than 16G, we will see one anon page swapped. The 16G is calculated as PAGE_SIZE * priority(4096) * (fp/ap). fp/ap is assumed to be 1024 which is common in this workload. So the impact sounds not a big deal. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:36 +08:00
fraction[0] = ap;
fraction[1] = fp;
denominator = ap + fp + 1;
out:
for_each_evictable_lru(lru) {
int file = is_file_lru(lru);
vmscan: prevent get_scan_ratio() rounding errors get_scan_ratio() calculates percentage and if the percentage is < 1%, it will round percentage down to 0% and cause we completely ignore scanning anon/file pages to reclaim memory even the total anon/file pages are very big. To avoid underflow, we don't use percentage, instead we directly calculate how many pages should be scaned. In this way, we should get several scanned pages for < 1% percent. This has some benefits: 1. increase our calculation precision 2. making our scan more smoothly. Without this, if percent[x] is underflow, shrink_zone() doesn't scan any pages and suddenly it scans all pages when priority is zero. With this, even priority isn't zero, shrink_zone() gets chance to scan some pages. Note, this patch doesn't really change logics, but just increase precision. For system with a lot of memory, this might slightly changes behavior. For example, in a sequential file read workload, without the patch, we don't swap any anon pages. With it, if anon memory size is bigger than 16G, we will see one anon page swapped. The 16G is calculated as PAGE_SIZE * priority(4096) * (fp/ap). fp/ap is assumed to be 1024 which is common in this workload. So the impact sounds not a big deal. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:36 +08:00
unsigned long scan;
scan = get_lru_size(lruvec, lru);
if (sc->priority || noswap || !vmscan_swappiness(sc)) {
scan >>= sc->priority;
if (!scan && force_scan)
scan = SWAP_CLUSTER_MAX;
vmscan: prevent get_scan_ratio() rounding errors get_scan_ratio() calculates percentage and if the percentage is < 1%, it will round percentage down to 0% and cause we completely ignore scanning anon/file pages to reclaim memory even the total anon/file pages are very big. To avoid underflow, we don't use percentage, instead we directly calculate how many pages should be scaned. In this way, we should get several scanned pages for < 1% percent. This has some benefits: 1. increase our calculation precision 2. making our scan more smoothly. Without this, if percent[x] is underflow, shrink_zone() doesn't scan any pages and suddenly it scans all pages when priority is zero. With this, even priority isn't zero, shrink_zone() gets chance to scan some pages. Note, this patch doesn't really change logics, but just increase precision. For system with a lot of memory, this might slightly changes behavior. For example, in a sequential file read workload, without the patch, we don't swap any anon pages. With it, if anon memory size is bigger than 16G, we will see one anon page swapped. The 16G is calculated as PAGE_SIZE * priority(4096) * (fp/ap). fp/ap is assumed to be 1024 which is common in this workload. So the impact sounds not a big deal. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:36 +08:00
scan = div64_u64(scan * fraction[file], denominator);
}
nr[lru] = scan;
vmscan: prevent get_scan_ratio() rounding errors get_scan_ratio() calculates percentage and if the percentage is < 1%, it will round percentage down to 0% and cause we completely ignore scanning anon/file pages to reclaim memory even the total anon/file pages are very big. To avoid underflow, we don't use percentage, instead we directly calculate how many pages should be scaned. In this way, we should get several scanned pages for < 1% percent. This has some benefits: 1. increase our calculation precision 2. making our scan more smoothly. Without this, if percent[x] is underflow, shrink_zone() doesn't scan any pages and suddenly it scans all pages when priority is zero. With this, even priority isn't zero, shrink_zone() gets chance to scan some pages. Note, this patch doesn't really change logics, but just increase precision. For system with a lot of memory, this might slightly changes behavior. For example, in a sequential file read workload, without the patch, we don't swap any anon pages. With it, if anon memory size is bigger than 16G, we will see one anon page swapped. The 16G is calculated as PAGE_SIZE * priority(4096) * (fp/ap). fp/ap is assumed to be 1024 which is common in this workload. So the impact sounds not a big deal. Signed-off-by: Shaohua Li <shaohua.li@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-05-25 05:32:36 +08:00
}
}
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
/* Use reclaim/compaction for costly allocs or under memory pressure */
static bool in_reclaim_compaction(struct scan_control *sc)
{
if (COMPACTION_BUILD && sc->order &&
(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
sc->priority < DEF_PRIORITY - 2))
return true;
return false;
}
/*
* Reclaim/compaction is used for high-order allocation requests. It reclaims
* order-0 pages before compacting the zone. should_continue_reclaim() returns
* true if more pages should be reclaimed such that when the page allocator
* calls try_to_compact_zone() that it will have enough free pages to succeed.
* It will give up earlier than that if there is difficulty reclaiming pages.
*/
static inline bool should_continue_reclaim(struct lruvec *lruvec,
unsigned long nr_reclaimed,
unsigned long nr_scanned,
struct scan_control *sc)
{
unsigned long pages_for_compaction;
unsigned long inactive_lru_pages;
/* If not in reclaim/compaction mode, stop */
if (!in_reclaim_compaction(sc))
return false;
mm: vmscan: stop reclaim/compaction earlier due to insufficient progress if !__GFP_REPEAT should_continue_reclaim() for reclaim/compaction allows scanning to continue even if pages are not being reclaimed until the full list is scanned. In terms of allocation success, this makes sense but potentially it introduces unwanted latency for high-order allocations such as transparent hugepages and network jumbo frames that would prefer to fail the allocation attempt and fallback to order-0 pages. Worse, there is a potential that the full LRU scan will clear all the young bits, distort page aging information and potentially push pages into swap that would have otherwise remained resident. This patch will stop reclaim/compaction if no pages were reclaimed in the last SWAP_CLUSTER_MAX pages that were considered. For allocations such as hugetlbfs that use __GFP_REPEAT and have fewer fallback options, the full LRU list may still be scanned. Order-0 allocation should not be affected because RECLAIM_MODE_COMPACTION is not set so the following avoids the gfp_mask being examined: if (!(sc->reclaim_mode & RECLAIM_MODE_COMPACTION)) return false; A tool was developed based on ftrace that tracked the latency of high-order allocations while transparent hugepage support was enabled and three benchmarks were run. The "fix-infinite" figures are 2.6.38-rc4 with Johannes's patch "vmscan: fix zone shrinking exit when scan work is done" applied. STREAM Highorder Allocation Latency Statistics fix-infinite break-early 1 :: Count 10298 10229 1 :: Min 0.4560 0.4640 1 :: Mean 1.0589 1.0183 1 :: Max 14.5990 11.7510 1 :: Stddev 0.5208 0.4719 2 :: Count 2 1 2 :: Min 1.8610 3.7240 2 :: Mean 3.4325 3.7240 2 :: Max 5.0040 3.7240 2 :: Stddev 1.5715 0.0000 9 :: Count 111696 111694 9 :: Min 0.5230 0.4110 9 :: Mean 10.5831 10.5718 9 :: Max 38.4480 43.2900 9 :: Stddev 1.1147 1.1325 Mean time for order-1 allocations is reduced. order-2 looks increased but with so few allocations, it's not particularly significant. THP mean allocation latency is also reduced. That said, allocation time varies so significantly that the reductions are within noise. Max allocation time is reduced by a significant amount for low-order allocations but reduced for THP allocations which presumably are now breaking before reclaim has done enough work. SysBench Highorder Allocation Latency Statistics fix-infinite break-early 1 :: Count 15745 15677 1 :: Min 0.4250 0.4550 1 :: Mean 1.1023 1.0810 1 :: Max 14.4590 10.8220 1 :: Stddev 0.5117 0.5100 2 :: Count 1 1 2 :: Min 3.0040 2.1530 2 :: Mean 3.0040 2.1530 2 :: Max 3.0040 2.1530 2 :: Stddev 0.0000 0.0000 9 :: Count 2017 1931 9 :: Min 0.4980 0.7480 9 :: Mean 10.4717 10.3840 9 :: Max 24.9460 26.2500 9 :: Stddev 1.1726 1.1966 Again, mean time for order-1 allocations is reduced while order-2 allocations are too few to draw conclusions from. The mean time for THP allocations is also slightly reduced albeit the reductions are within varianes. Once again, our maximum allocation time is significantly reduced for low-order allocations and slightly increased for THP allocations. Anon stream mmap reference Highorder Allocation Latency Statistics 1 :: Count 1376 1790 1 :: Min 0.4940 0.5010 1 :: Mean 1.0289 0.9732 1 :: Max 6.2670 4.2540 1 :: Stddev 0.4142 0.2785 2 :: Count 1 - 2 :: Min 1.9060 - 2 :: Mean 1.9060 - 2 :: Max 1.9060 - 2 :: Stddev 0.0000 - 9 :: Count 11266 11257 9 :: Min 0.4990 0.4940 9 :: Mean 27250.4669 24256.1919 9 :: Max 11439211.0000 6008885.0000 9 :: Stddev 226427.4624 186298.1430 This benchmark creates one thread per CPU which references an amount of anonymous memory 1.5 times the size of physical RAM. This pounds swap quite heavily and is intended to exercise THP a bit. Mean allocation time for order-1 is reduced as before. It's also reduced for THP allocations but the variations here are pretty massive due to swap. As before, maximum allocation times are significantly reduced. Overall, the patch reduces the mean and maximum allocation latencies for the smaller high-order allocations. This was with Slab configured so it would be expected to be more significant with Slub which uses these size allocations more aggressively. The mean allocation times for THP allocations are also slightly reduced. The maximum latency was slightly increased as predicted by the comments due to reclaim/compaction breaking early. However, workloads care more about the latency of lower-order allocations than THP so it's an acceptable trade-off. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Kent Overstreet <kent.overstreet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-26 06:44:20 +08:00
/* Consider stopping depending on scan and reclaim activity */
if (sc->gfp_mask & __GFP_REPEAT) {
/*
* For __GFP_REPEAT allocations, stop reclaiming if the
* full LRU list has been scanned and we are still failing
* to reclaim pages. This full LRU scan is potentially
* expensive but a __GFP_REPEAT caller really wants to succeed
*/
if (!nr_reclaimed && !nr_scanned)
return false;
} else {
/*
* For non-__GFP_REPEAT allocations which can presumably
* fail without consequence, stop if we failed to reclaim
* any pages from the last SWAP_CLUSTER_MAX number of
* pages that were scanned. This will return to the
* caller faster at the risk reclaim/compaction and
* the resulting allocation attempt fails
*/
if (!nr_reclaimed)
return false;
}
/*
* If we have not reclaimed enough pages for compaction and the
* inactive lists are large enough, continue reclaiming
*/
pages_for_compaction = (2UL << sc->order);
inactive_lru_pages = get_lru_size(lruvec, LRU_INACTIVE_FILE);
if (nr_swap_pages > 0)
inactive_lru_pages += get_lru_size(lruvec, LRU_INACTIVE_ANON);
if (sc->nr_reclaimed < pages_for_compaction &&
inactive_lru_pages > pages_for_compaction)
return true;
/* If compaction would go ahead or the allocation would succeed, stop */
switch (compaction_suitable(lruvec_zone(lruvec), sc->order)) {
case COMPACT_PARTIAL:
case COMPACT_CONTINUE:
return false;
default:
return true;
}
}
/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
*/
static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
unsigned long nr[NR_LRU_LISTS];
unsigned long nr_to_scan;
enum lru_list lru;
unsigned long nr_reclaimed, nr_scanned;
unsigned long nr_to_reclaim = sc->nr_to_reclaim;
struct blk_plug plug;
restart:
nr_reclaimed = 0;
nr_scanned = sc->nr_scanned;
get_scan_count(lruvec, sc, nr);
blk_start_plug(&plug);
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
for_each_evictable_lru(lru) {
if (nr[lru]) {
nr_to_scan = min_t(unsigned long,
nr[lru], SWAP_CLUSTER_MAX);
nr[lru] -= nr_to_scan;
nr_reclaimed += shrink_list(lru, nr_to_scan,
lruvec, sc);
}
}
vmscan: bail out of direct reclaim after swap_cluster_max pages When the VM is under pressure, it can happen that several direct reclaim processes are in the pageout code simultaneously. It also happens that the reclaiming processes run into mostly referenced, mapped and dirty pages in the first round. This results in multiple direct reclaim processes having a lower pageout priority, which corresponds to a higher target of pages to scan. This in turn can result in each direct reclaim process freeing many pages. Together, they can end up freeing way too many pages. This kicks useful data out of memory (in some cases more than half of all memory is swapped out). It also impacts performance by keeping tasks stuck in the pageout code for too long. A 30% improvement in hackbench has been observed with this patch. The fix is relatively simple: in shrink_zone() we can check how many pages we have already freed, direct reclaim tasks break out of the scanning loop if they have already freed enough pages and have reached a lower priority level. We do not break out of shrink_zone() when priority == DEF_PRIORITY, to ensure that equal pressure is applied to every zone in the common case. However, in order to do this we do need to know how many pages we already freed, so move nr_reclaimed into scan_control. akpm: a historical interlude... We tried this in 2004: :commit e468e46a9bea3297011d5918663ce6d19094cf87 :Author: akpm <akpm> :Date: Thu Jun 24 15:53:52 2004 +0000 : :[PATCH] vmscan.c: dont reclaim too many pages : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly hit : a large number of reclaimable pages on the LRU. : Change things so we bale out when SWAP_CLUSTER_MAX pages have been reclaimed. And we reverted it in 2006: :commit 210fe530305ee50cd889fe9250168228b2994f32 :Author: Andrew Morton <akpm@osdl.org> :Date: Fri Jan 6 00:11:14 2006 -0800 : : [PATCH] vmscan: balancing fix : : Revert a patch which went into 2.6.8-rc1. The changelog for that patch was: : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly : hit a large number of reclaimable pages on the LRU. : : Change things so we bale out when SWAP_CLUSTER_MAX pages have been : reclaimed. : : Problem is, this change caused significant imbalance in inter-zone scan : balancing by truncating scans of larger zones. : : Suppose, for example, ZONE_HIGHMEM is 10x the size of ZONE_NORMAL. The zone : balancing algorithm would require that if we're scanning 100 pages of : ZONE_HIGHMEM, we should scan 10 pages of ZONE_NORMAL. But this logic will : cause the scanning of ZONE_HIGHMEM to bale out after only 32 pages are : reclaimed. Thus effectively causing smaller zones to be scanned relatively : harder than large ones. : : Now I need to remember what the workload was which caused me to write this : patch originally, then fix it up in a different way... And we haven't demonstrated that whatever problem caused that reversion is not being reintroduced by this change in 2008. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:01 +08:00
/*
* On large memory systems, scan >> priority can become
* really large. This is fine for the starting priority;
* we want to put equal scanning pressure on each zone.
* However, if the VM has a harder time of freeing pages,
* with multiple processes reclaiming pages, the total
* freeing target can get unreasonably large.
*/
if (nr_reclaimed >= nr_to_reclaim &&
sc->priority < DEF_PRIORITY)
vmscan: bail out of direct reclaim after swap_cluster_max pages When the VM is under pressure, it can happen that several direct reclaim processes are in the pageout code simultaneously. It also happens that the reclaiming processes run into mostly referenced, mapped and dirty pages in the first round. This results in multiple direct reclaim processes having a lower pageout priority, which corresponds to a higher target of pages to scan. This in turn can result in each direct reclaim process freeing many pages. Together, they can end up freeing way too many pages. This kicks useful data out of memory (in some cases more than half of all memory is swapped out). It also impacts performance by keeping tasks stuck in the pageout code for too long. A 30% improvement in hackbench has been observed with this patch. The fix is relatively simple: in shrink_zone() we can check how many pages we have already freed, direct reclaim tasks break out of the scanning loop if they have already freed enough pages and have reached a lower priority level. We do not break out of shrink_zone() when priority == DEF_PRIORITY, to ensure that equal pressure is applied to every zone in the common case. However, in order to do this we do need to know how many pages we already freed, so move nr_reclaimed into scan_control. akpm: a historical interlude... We tried this in 2004: :commit e468e46a9bea3297011d5918663ce6d19094cf87 :Author: akpm <akpm> :Date: Thu Jun 24 15:53:52 2004 +0000 : :[PATCH] vmscan.c: dont reclaim too many pages : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly hit : a large number of reclaimable pages on the LRU. : Change things so we bale out when SWAP_CLUSTER_MAX pages have been reclaimed. And we reverted it in 2006: :commit 210fe530305ee50cd889fe9250168228b2994f32 :Author: Andrew Morton <akpm@osdl.org> :Date: Fri Jan 6 00:11:14 2006 -0800 : : [PATCH] vmscan: balancing fix : : Revert a patch which went into 2.6.8-rc1. The changelog for that patch was: : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly : hit a large number of reclaimable pages on the LRU. : : Change things so we bale out when SWAP_CLUSTER_MAX pages have been : reclaimed. : : Problem is, this change caused significant imbalance in inter-zone scan : balancing by truncating scans of larger zones. : : Suppose, for example, ZONE_HIGHMEM is 10x the size of ZONE_NORMAL. The zone : balancing algorithm would require that if we're scanning 100 pages of : ZONE_HIGHMEM, we should scan 10 pages of ZONE_NORMAL. But this logic will : cause the scanning of ZONE_HIGHMEM to bale out after only 32 pages are : reclaimed. Thus effectively causing smaller zones to be scanned relatively : harder than large ones. : : Now I need to remember what the workload was which caused me to write this : patch originally, then fix it up in a different way... And we haven't demonstrated that whatever problem caused that reversion is not being reintroduced by this change in 2008. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:01 +08:00
break;
}
blk_finish_plug(&plug);
sc->nr_reclaimed += nr_reclaimed;
vmscan: improve reclaim throughput to bail out patch The vmscan bail out patch move nr_reclaimed variable to struct scan_control. Unfortunately, indirect access can easily happen cache miss. if heavy memory pressure happend, that's ok. cache miss already plenty. it is not observable. but, if memory pressure is lite, performance degression is obserbable. I compared following three pattern (it was mesured 10 times each) hackbench 125 process 3000 hackbench 130 process 3000 hackbench 135 process 3000 2.6.28-rc6 bail-out 125 130 135 125 130 135 ============================================================== 71.866 75.86 81.274 93.414 73.254 193.382 74.145 78.295 77.27 74.897 75.021 80.17 70.305 77.643 75.855 70.134 77.571 79.896 74.288 73.986 75.955 77.222 78.48 80.619 72.029 79.947 78.312 75.128 82.172 79.708 71.499 77.615 77.042 74.177 76.532 77.306 76.188 74.471 83.562 73.839 72.43 79.833 73.236 75.606 78.743 76.001 76.557 82.726 69.427 77.271 76.691 76.236 79.371 103.189 72.473 76.978 80.643 69.128 78.932 75.736 avg 72.545 76.767 78.534 76.017 77.03 93.256 std 1.89 1.71 2.41 6.29 2.79 34.16 min 69.427 73.986 75.855 69.128 72.43 75.736 max 76.188 79.947 83.562 93.414 82.172 193.382 about 4-5% degression. Then, this patch introduces a temporary local variable. result: 2.6.28-rc6 this patch num 125 130 135 125 130 135 ============================================================== 71.866 75.86 81.274 67.302 68.269 77.161 74.145 78.295 77.27 72.616 72.712 79.06 70.305 77.643 75.855 72.475 75.712 77.735 74.288 73.986 75.955 69.229 73.062 78.814 72.029 79.947 78.312 71.551 74.392 78.564 71.499 77.615 77.042 69.227 74.31 78.837 76.188 74.471 83.562 70.759 75.256 76.6 73.236 75.606 78.743 69.966 76.001 78.464 69.427 77.271 76.691 69.068 75.218 80.321 72.473 76.978 80.643 72.057 77.151 79.068 avg 72.545 76.767 78.534 70.425 74.2083 78.462 std 1.89 1.71 2.41 1.66 2.34 1.00 min 69.427 73.986 75.855 67.302 68.269 76.6 max 76.188 79.947 83.562 72.616 77.151 80.321 OK. the degression is disappeared. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:02 +08:00
/*
* Even if we did not try to evict anon pages at all, we want to
* rebalance the anon lru active/inactive ratio.
*/
if (inactive_anon_is_low(lruvec))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
/* reclaim/compaction might need reclaim to continue */
if (should_continue_reclaim(lruvec, nr_reclaimed,
sc->nr_scanned - nr_scanned, sc))
goto restart;
throttle_vm_writeout(sc->gfp_mask);
}
static void shrink_zone(struct zone *zone, struct scan_control *sc)
{
struct mem_cgroup *root = sc->target_mem_cgroup;
struct mem_cgroup_reclaim_cookie reclaim = {
.zone = zone,
.priority = sc->priority,
};
struct mem_cgroup *memcg;
memcg = mem_cgroup_iter(root, NULL, &reclaim);
do {
struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
shrink_lruvec(lruvec, sc);
/*
* Limit reclaim has historically picked one memcg and
* scanned it with decreasing priority levels until
* nr_to_reclaim had been reclaimed. This priority
* cycle is thus over after a single memcg.
*
* Direct reclaim and kswapd, on the other hand, have
* to scan all memory cgroups to fulfill the overall
* scan target for the zone.
*/
if (!global_reclaim(sc)) {
mem_cgroup_iter_break(root, memcg);
break;
}
memcg = mem_cgroup_iter(root, memcg, &reclaim);
} while (memcg);
}
mm: vmscan: when reclaiming for compaction, ensure there are sufficient free pages available In commit e0887c19 ("vmscan: limit direct reclaim for higher order allocations"), Rik noted that reclaim was too aggressive when THP was enabled. In his initial patch he used the number of free pages to decide if reclaim should abort for compaction. My feedback was that reclaim and compaction should be using the same logic when deciding if reclaim should be aborted. Unfortunately, this had the effect of reducing THP success rates when the workload included something like streaming reads that continually allocated pages. The window during which compaction could run and return a THP was too small. This patch combines Rik's two patches together. compaction_suitable() is still used to decide if reclaim should be aborted to allow compaction is used. However, it will also ensure that there is a reasonable buffer of free pages available. This improves upon the THP allocation success rates but bounds the number of pages that are freed for compaction. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel<riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Dave Jones <davej@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Andy Isaacson <adi@hexapodia.org> Cc: Nai Xia <nai.xia@gmail.com> Cc: Johannes Weiner <jweiner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 09:19:45 +08:00
/* Returns true if compaction should go ahead for a high-order request */
static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
{
unsigned long balance_gap, watermark;
bool watermark_ok;
/* Do not consider compaction for orders reclaim is meant to satisfy */
if (sc->order <= PAGE_ALLOC_COSTLY_ORDER)
return false;
/*
* Compaction takes time to run and there are potentially other
* callers using the pages just freed. Continue reclaiming until
* there is a buffer of free pages available to give compaction
* a reasonable chance of completing and allocating the page
*/
balance_gap = min(low_wmark_pages(zone),
(zone->present_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
KSWAPD_ZONE_BALANCE_GAP_RATIO);
watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order);
watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0);
/*
* If compaction is deferred, reclaim up to a point where
* compaction will have a chance of success when re-enabled
*/
if (compaction_deferred(zone, sc->order))
mm: vmscan: when reclaiming for compaction, ensure there are sufficient free pages available In commit e0887c19 ("vmscan: limit direct reclaim for higher order allocations"), Rik noted that reclaim was too aggressive when THP was enabled. In his initial patch he used the number of free pages to decide if reclaim should abort for compaction. My feedback was that reclaim and compaction should be using the same logic when deciding if reclaim should be aborted. Unfortunately, this had the effect of reducing THP success rates when the workload included something like streaming reads that continually allocated pages. The window during which compaction could run and return a THP was too small. This patch combines Rik's two patches together. compaction_suitable() is still used to decide if reclaim should be aborted to allow compaction is used. However, it will also ensure that there is a reasonable buffer of free pages available. This improves upon the THP allocation success rates but bounds the number of pages that are freed for compaction. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel<riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Dave Jones <davej@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Andy Isaacson <adi@hexapodia.org> Cc: Nai Xia <nai.xia@gmail.com> Cc: Johannes Weiner <jweiner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 09:19:45 +08:00
return watermark_ok;
/* If compaction is not ready to start, keep reclaiming */
if (!compaction_suitable(zone, sc->order))
return false;
return watermark_ok;
}
/*
* This is the direct reclaim path, for page-allocating processes. We only
* try to reclaim pages from zones which will satisfy the caller's allocation
* request.
*
* We reclaim from a zone even if that zone is over high_wmark_pages(zone).
* Because:
* a) The caller may be trying to free *extra* pages to satisfy a higher-order
* allocation or
* b) The target zone may be at high_wmark_pages(zone) but the lower zones
* must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
* zone defense algorithm.
*
* If a zone is deemed to be full of pinned pages then just give it a light
* scan then give up on it.
*
* This function returns true if a zone is being reclaimed for a costly
mm: vmscan: when reclaiming for compaction, ensure there are sufficient free pages available In commit e0887c19 ("vmscan: limit direct reclaim for higher order allocations"), Rik noted that reclaim was too aggressive when THP was enabled. In his initial patch he used the number of free pages to decide if reclaim should abort for compaction. My feedback was that reclaim and compaction should be using the same logic when deciding if reclaim should be aborted. Unfortunately, this had the effect of reducing THP success rates when the workload included something like streaming reads that continually allocated pages. The window during which compaction could run and return a THP was too small. This patch combines Rik's two patches together. compaction_suitable() is still used to decide if reclaim should be aborted to allow compaction is used. However, it will also ensure that there is a reasonable buffer of free pages available. This improves upon the THP allocation success rates but bounds the number of pages that are freed for compaction. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel<riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Dave Jones <davej@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Andy Isaacson <adi@hexapodia.org> Cc: Nai Xia <nai.xia@gmail.com> Cc: Johannes Weiner <jweiner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 09:19:45 +08:00
* high-order allocation and compaction is ready to begin. This indicates to
* the caller that it should consider retrying the allocation instead of
* further reclaim.
*/
static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
{
mm: have zonelist contains structs with both a zone pointer and zone_idx Filtering zonelists requires very frequent use of zone_idx(). This is costly as it involves a lookup of another structure and a substraction operation. As the zone_idx is often required, it should be quickly accessible. The node idx could also be stored here if it was found that accessing zone->node is significant which may be the case on workloads where nodemasks are heavily used. This patch introduces a struct zoneref to store a zone pointer and a zone index. The zonelist then consists of an array of these struct zonerefs which are looked up as necessary. Helpers are given for accessing the zone index as well as the node index. [kamezawa.hiroyu@jp.fujitsu.com: Suggested struct zoneref instead of embedding information in pointers] [hugh@veritas.com: mm-have-zonelist: fix memcg ooms] [hugh@veritas.com: just return do_try_to_free_pages] [hugh@veritas.com: do_try_to_free_pages gfp_mask redundant] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Christoph Lameter <clameter@sgi.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <clameter@sgi.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:17 +08:00
struct zoneref *z;
struct zone *zone;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
bool aborted_reclaim = false;
per-zone and reclaim enhancements for memory controller: modifies vmscan.c for isolate globa/cgroup lru activity When using memory controller, there are 2 levels of memory reclaim. 1. zone memory reclaim because of system/zone memory shortage. 2. memory cgroup memory reclaim because of hitting limit. These two can be distinguished by sc->mem_cgroup parameter. (scan_global_lru() macro) This patch tries to make memory cgroup reclaim routine avoid affecting system/zone memory reclaim. This patch inserts if (scan_global_lru()) and hook to memory_cgroup reclaim support functions. This patch can be a help for isolating system lru activity and group lru activity and shows what additional functions are necessary. * mem_cgroup_calc_mapped_ratio() ... calculate mapped ratio for cgroup. * mem_cgroup_reclaim_imbalance() ... calculate active/inactive balance in cgroup. * mem_cgroup_calc_reclaim_active() ... calculate the number of active pages to be scanned in this priority in mem_cgroup. * mem_cgroup_calc_reclaim_inactive() ... calculate the number of inactive pages to be scanned in this priority in mem_cgroup. * mem_cgroup_all_unreclaimable() .. checks cgroup's page is all unreclaimable or not. * mem_cgroup_get_reclaim_priority() ... * mem_cgroup_note_reclaim_priority() ... record reclaim priority (temporal) * mem_cgroup_remember_reclaim_priority() .... record reclaim priority as zone->prev_priority. This value is used for calc reclaim_mapped. [akpm@linux-foundation.org: fix unused var warning] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: David Rientjes <rientjes@google.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:37 +08:00
mm: vmscan: forcibly scan highmem if there are too many buffer_heads pinning highmem Stuart Foster reported on bugzilla that copying large amounts of data from NTFS caused an OOM kill on 32-bit X86 with 16G of memory. Andrew Morton correctly identified that the problem was NTFS was using 512 blocks meaning each page had 8 buffer_heads in low memory pinning it. In the past, direct reclaim used to scan highmem even if the allocating process did not specify __GFP_HIGHMEM but not any more. kswapd no longer will reclaim from zones that are above the high watermark. The intention in both cases was to minimise unnecessary reclaim. The downside is on machines with large amounts of highmem that lowmem can be fully consumed by buffer_heads with nothing trying to free them. The following patch is based on a suggestion by Andrew Morton to extend the buffer_heads_over_limit case to force kswapd and direct reclaim to scan the highmem zone regardless of the allocation request or watermarks. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=42578 [hughd@google.com: move buffer_heads_over_limit check up] [akpm@linux-foundation.org: buffer_heads_over_limit is unlikely] Reported-by: Stuart Foster <smf.linux@ntlworld.com> Tested-by: Stuart Foster <smf.linux@ntlworld.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Cc: Christoph Lameter <cl@linux.com> Cc: stable <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 07:34:00 +08:00
/*
* If the number of buffer_heads in the machine exceeds the maximum
* allowed level, force direct reclaim to scan the highmem zone as
* highmem pages could be pinning lowmem pages storing buffer_heads
*/
if (buffer_heads_over_limit)
sc->gfp_mask |= __GFP_HIGHMEM;
for_each_zone_zonelist_nodemask(zone, z, zonelist,
gfp_zone(sc->gfp_mask), sc->nodemask) {
if (!populated_zone(zone))
continue;
per-zone and reclaim enhancements for memory controller: modifies vmscan.c for isolate globa/cgroup lru activity When using memory controller, there are 2 levels of memory reclaim. 1. zone memory reclaim because of system/zone memory shortage. 2. memory cgroup memory reclaim because of hitting limit. These two can be distinguished by sc->mem_cgroup parameter. (scan_global_lru() macro) This patch tries to make memory cgroup reclaim routine avoid affecting system/zone memory reclaim. This patch inserts if (scan_global_lru()) and hook to memory_cgroup reclaim support functions. This patch can be a help for isolating system lru activity and group lru activity and shows what additional functions are necessary. * mem_cgroup_calc_mapped_ratio() ... calculate mapped ratio for cgroup. * mem_cgroup_reclaim_imbalance() ... calculate active/inactive balance in cgroup. * mem_cgroup_calc_reclaim_active() ... calculate the number of active pages to be scanned in this priority in mem_cgroup. * mem_cgroup_calc_reclaim_inactive() ... calculate the number of inactive pages to be scanned in this priority in mem_cgroup. * mem_cgroup_all_unreclaimable() .. checks cgroup's page is all unreclaimable or not. * mem_cgroup_get_reclaim_priority() ... * mem_cgroup_note_reclaim_priority() ... record reclaim priority (temporal) * mem_cgroup_remember_reclaim_priority() .... record reclaim priority as zone->prev_priority. This value is used for calc reclaim_mapped. [akpm@linux-foundation.org: fix unused var warning] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: David Rientjes <rientjes@google.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:37 +08:00
/*
* Take care memory controller reclaiming has small influence
* to global LRU.
*/
if (global_reclaim(sc)) {
per-zone and reclaim enhancements for memory controller: modifies vmscan.c for isolate globa/cgroup lru activity When using memory controller, there are 2 levels of memory reclaim. 1. zone memory reclaim because of system/zone memory shortage. 2. memory cgroup memory reclaim because of hitting limit. These two can be distinguished by sc->mem_cgroup parameter. (scan_global_lru() macro) This patch tries to make memory cgroup reclaim routine avoid affecting system/zone memory reclaim. This patch inserts if (scan_global_lru()) and hook to memory_cgroup reclaim support functions. This patch can be a help for isolating system lru activity and group lru activity and shows what additional functions are necessary. * mem_cgroup_calc_mapped_ratio() ... calculate mapped ratio for cgroup. * mem_cgroup_reclaim_imbalance() ... calculate active/inactive balance in cgroup. * mem_cgroup_calc_reclaim_active() ... calculate the number of active pages to be scanned in this priority in mem_cgroup. * mem_cgroup_calc_reclaim_inactive() ... calculate the number of inactive pages to be scanned in this priority in mem_cgroup. * mem_cgroup_all_unreclaimable() .. checks cgroup's page is all unreclaimable or not. * mem_cgroup_get_reclaim_priority() ... * mem_cgroup_note_reclaim_priority() ... record reclaim priority (temporal) * mem_cgroup_remember_reclaim_priority() .... record reclaim priority as zone->prev_priority. This value is used for calc reclaim_mapped. [akpm@linux-foundation.org: fix unused var warning] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: David Rientjes <rientjes@google.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:37 +08:00
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
if (zone->all_unreclaimable &&
sc->priority != DEF_PRIORITY)
per-zone and reclaim enhancements for memory controller: modifies vmscan.c for isolate globa/cgroup lru activity When using memory controller, there are 2 levels of memory reclaim. 1. zone memory reclaim because of system/zone memory shortage. 2. memory cgroup memory reclaim because of hitting limit. These two can be distinguished by sc->mem_cgroup parameter. (scan_global_lru() macro) This patch tries to make memory cgroup reclaim routine avoid affecting system/zone memory reclaim. This patch inserts if (scan_global_lru()) and hook to memory_cgroup reclaim support functions. This patch can be a help for isolating system lru activity and group lru activity and shows what additional functions are necessary. * mem_cgroup_calc_mapped_ratio() ... calculate mapped ratio for cgroup. * mem_cgroup_reclaim_imbalance() ... calculate active/inactive balance in cgroup. * mem_cgroup_calc_reclaim_active() ... calculate the number of active pages to be scanned in this priority in mem_cgroup. * mem_cgroup_calc_reclaim_inactive() ... calculate the number of inactive pages to be scanned in this priority in mem_cgroup. * mem_cgroup_all_unreclaimable() .. checks cgroup's page is all unreclaimable or not. * mem_cgroup_get_reclaim_priority() ... * mem_cgroup_note_reclaim_priority() ... record reclaim priority (temporal) * mem_cgroup_remember_reclaim_priority() .... record reclaim priority as zone->prev_priority. This value is used for calc reclaim_mapped. [akpm@linux-foundation.org: fix unused var warning] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: David Rientjes <rientjes@google.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:37 +08:00
continue; /* Let kswapd poll it */
if (COMPACTION_BUILD) {
/*
* If we already have plenty of memory free for
* compaction in this zone, don't free any more.
* Even though compaction is invoked for any
* non-zero order, only frequent costly order
* reclamation is disruptive enough to become a
* noticeable problem, like transparent huge
* page allocations.
*/
mm: vmscan: when reclaiming for compaction, ensure there are sufficient free pages available In commit e0887c19 ("vmscan: limit direct reclaim for higher order allocations"), Rik noted that reclaim was too aggressive when THP was enabled. In his initial patch he used the number of free pages to decide if reclaim should abort for compaction. My feedback was that reclaim and compaction should be using the same logic when deciding if reclaim should be aborted. Unfortunately, this had the effect of reducing THP success rates when the workload included something like streaming reads that continually allocated pages. The window during which compaction could run and return a THP was too small. This patch combines Rik's two patches together. compaction_suitable() is still used to decide if reclaim should be aborted to allow compaction is used. However, it will also ensure that there is a reasonable buffer of free pages available. This improves upon the THP allocation success rates but bounds the number of pages that are freed for compaction. Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel<riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Dave Jones <davej@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Andy Isaacson <adi@hexapodia.org> Cc: Nai Xia <nai.xia@gmail.com> Cc: Johannes Weiner <jweiner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 09:19:45 +08:00
if (compaction_ready(zone, sc)) {
aborted_reclaim = true;
continue;
}
}
/*
* This steals pages from memory cgroups over softlimit
* and returns the number of reclaimed pages and
* scanned pages. This works for global memory pressure
* and balancing, not for a memcg's limit.
*/
nr_soft_scanned = 0;
nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
sc->order, sc->gfp_mask,
&nr_soft_scanned);
sc->nr_reclaimed += nr_soft_reclaimed;
sc->nr_scanned += nr_soft_scanned;
/* need some check for avoid more shrink_zone() */
per-zone and reclaim enhancements for memory controller: modifies vmscan.c for isolate globa/cgroup lru activity When using memory controller, there are 2 levels of memory reclaim. 1. zone memory reclaim because of system/zone memory shortage. 2. memory cgroup memory reclaim because of hitting limit. These two can be distinguished by sc->mem_cgroup parameter. (scan_global_lru() macro) This patch tries to make memory cgroup reclaim routine avoid affecting system/zone memory reclaim. This patch inserts if (scan_global_lru()) and hook to memory_cgroup reclaim support functions. This patch can be a help for isolating system lru activity and group lru activity and shows what additional functions are necessary. * mem_cgroup_calc_mapped_ratio() ... calculate mapped ratio for cgroup. * mem_cgroup_reclaim_imbalance() ... calculate active/inactive balance in cgroup. * mem_cgroup_calc_reclaim_active() ... calculate the number of active pages to be scanned in this priority in mem_cgroup. * mem_cgroup_calc_reclaim_inactive() ... calculate the number of inactive pages to be scanned in this priority in mem_cgroup. * mem_cgroup_all_unreclaimable() .. checks cgroup's page is all unreclaimable or not. * mem_cgroup_get_reclaim_priority() ... * mem_cgroup_note_reclaim_priority() ... record reclaim priority (temporal) * mem_cgroup_remember_reclaim_priority() .... record reclaim priority as zone->prev_priority. This value is used for calc reclaim_mapped. [akpm@linux-foundation.org: fix unused var warning] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: David Rientjes <rientjes@google.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:37 +08:00
}
shrink_zone(zone, sc);
}
return aborted_reclaim;
vmscan: check all_unreclaimable in direct reclaim path M. Vefa Bicakci reported 2.6.35 kernel hang up when hibernation on his 32bit 3GB mem machine. (https://bugzilla.kernel.org/show_bug.cgi?id=16771). Also he bisected the regression to commit bb21c7ce18eff8e6e7877ca1d06c6db719376e3c Author: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Date: Fri Jun 4 14:15:05 2010 -0700 vmscan: fix do_try_to_free_pages() return value when priority==0 reclaim failure At first impression, this seemed very strange because the above commit only chenged function return value and hibernate_preallocate_memory() ignore return value of shrink_all_memory(). But it's related. Now, page allocation from hibernation code may enter infinite loop if the system has highmem. The reasons are that vmscan don't care enough OOM case when oom_killer_disabled. The problem sequence is following as. 1. hibernation 2. oom_disable 3. alloc_pages 4. do_try_to_free_pages if (scanning_global_lru(sc) && !all_unreclaimable) return 1; If kswapd is not freozen, it would set zone->all_unreclaimable to 1 and then shrink_zones maybe return true(ie, all_unreclaimable is true). So at last, alloc_pages could go to _nopage_. If it is, it should have no problem. This patch adds all_unreclaimable check to protect in direct reclaim path, too. It can care of hibernation OOM case and help bailout all_unreclaimable case slightly. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reported-by: M. Vefa Bicakci <bicave@superonline.com> Reported-by: <caiqian@redhat.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Tested-by: <caiqian@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-09-23 04:05:01 +08:00
}
static bool zone_reclaimable(struct zone *zone)
{
return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
}
vmscan: all_unreclaimable() use zone->all_unreclaimable as a name all_unreclaimable check in direct reclaim has been introduced at 2.6.19 by following commit. 2006 Sep 25; commit 408d8544; oom: use unreclaimable info And it went through strange history. firstly, following commit broke the logic unintentionally. 2008 Apr 29; commit a41f24ea; page allocator: smarter retry of costly-order allocations Two years later, I've found obvious meaningless code fragment and restored original intention by following commit. 2010 Jun 04; commit bb21c7ce; vmscan: fix do_try_to_free_pages() return value when priority==0 But, the logic didn't works when 32bit highmem system goes hibernation and Minchan slightly changed the algorithm and fixed it . 2010 Sep 22: commit d1908362: vmscan: check all_unreclaimable in direct reclaim path But, recently, Andrey Vagin found the new corner case. Look, struct zone { .. int all_unreclaimable; .. unsigned long pages_scanned; .. } zone->all_unreclaimable and zone->pages_scanned are neigher atomic variables nor protected by lock. Therefore zones can become a state of zone->page_scanned=0 and zone->all_unreclaimable=1. In this case, current all_unreclaimable() return false even though zone->all_unreclaimabe=1. This resulted in the kernel hanging up when executing a loop of the form 1. fork 2. mmap 3. touch memory 4. read memory 5. munmmap as described in http://www.gossamer-threads.com/lists/linux/kernel/1348725#1348725 Is this ignorable minor issue? No. Unfortunately, x86 has very small dma zone and it become zone->all_unreclamble=1 easily. and if it become all_unreclaimable=1, it never restore all_unreclaimable=0. Why? if all_unreclaimable=1, vmscan only try DEF_PRIORITY reclaim and a-few-lru-pages>>DEF_PRIORITY always makes 0. that mean no page scan at all! Eventually, oom-killer never works on such systems. That said, we can't use zone->pages_scanned for this purpose. This patch restore all_unreclaimable() use zone->all_unreclaimable as old. and in addition, to add oom_killer_disabled check to avoid reintroduce the issue of commit d1908362 ("vmscan: check all_unreclaimable in direct reclaim path"). Reported-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: David Rientjes <rientjes@google.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-15 06:22:12 +08:00
/* All zones in zonelist are unreclaimable? */
vmscan: check all_unreclaimable in direct reclaim path M. Vefa Bicakci reported 2.6.35 kernel hang up when hibernation on his 32bit 3GB mem machine. (https://bugzilla.kernel.org/show_bug.cgi?id=16771). Also he bisected the regression to commit bb21c7ce18eff8e6e7877ca1d06c6db719376e3c Author: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Date: Fri Jun 4 14:15:05 2010 -0700 vmscan: fix do_try_to_free_pages() return value when priority==0 reclaim failure At first impression, this seemed very strange because the above commit only chenged function return value and hibernate_preallocate_memory() ignore return value of shrink_all_memory(). But it's related. Now, page allocation from hibernation code may enter infinite loop if the system has highmem. The reasons are that vmscan don't care enough OOM case when oom_killer_disabled. The problem sequence is following as. 1. hibernation 2. oom_disable 3. alloc_pages 4. do_try_to_free_pages if (scanning_global_lru(sc) && !all_unreclaimable) return 1; If kswapd is not freozen, it would set zone->all_unreclaimable to 1 and then shrink_zones maybe return true(ie, all_unreclaimable is true). So at last, alloc_pages could go to _nopage_. If it is, it should have no problem. This patch adds all_unreclaimable check to protect in direct reclaim path, too. It can care of hibernation OOM case and help bailout all_unreclaimable case slightly. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reported-by: M. Vefa Bicakci <bicave@superonline.com> Reported-by: <caiqian@redhat.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Tested-by: <caiqian@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-09-23 04:05:01 +08:00
static bool all_unreclaimable(struct zonelist *zonelist,
struct scan_control *sc)
{
struct zoneref *z;
struct zone *zone;
for_each_zone_zonelist_nodemask(zone, z, zonelist,
gfp_zone(sc->gfp_mask), sc->nodemask) {
if (!populated_zone(zone))
continue;
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
vmscan: all_unreclaimable() use zone->all_unreclaimable as a name all_unreclaimable check in direct reclaim has been introduced at 2.6.19 by following commit. 2006 Sep 25; commit 408d8544; oom: use unreclaimable info And it went through strange history. firstly, following commit broke the logic unintentionally. 2008 Apr 29; commit a41f24ea; page allocator: smarter retry of costly-order allocations Two years later, I've found obvious meaningless code fragment and restored original intention by following commit. 2010 Jun 04; commit bb21c7ce; vmscan: fix do_try_to_free_pages() return value when priority==0 But, the logic didn't works when 32bit highmem system goes hibernation and Minchan slightly changed the algorithm and fixed it . 2010 Sep 22: commit d1908362: vmscan: check all_unreclaimable in direct reclaim path But, recently, Andrey Vagin found the new corner case. Look, struct zone { .. int all_unreclaimable; .. unsigned long pages_scanned; .. } zone->all_unreclaimable and zone->pages_scanned are neigher atomic variables nor protected by lock. Therefore zones can become a state of zone->page_scanned=0 and zone->all_unreclaimable=1. In this case, current all_unreclaimable() return false even though zone->all_unreclaimabe=1. This resulted in the kernel hanging up when executing a loop of the form 1. fork 2. mmap 3. touch memory 4. read memory 5. munmmap as described in http://www.gossamer-threads.com/lists/linux/kernel/1348725#1348725 Is this ignorable minor issue? No. Unfortunately, x86 has very small dma zone and it become zone->all_unreclamble=1 easily. and if it become all_unreclaimable=1, it never restore all_unreclaimable=0. Why? if all_unreclaimable=1, vmscan only try DEF_PRIORITY reclaim and a-few-lru-pages>>DEF_PRIORITY always makes 0. that mean no page scan at all! Eventually, oom-killer never works on such systems. That said, we can't use zone->pages_scanned for this purpose. This patch restore all_unreclaimable() use zone->all_unreclaimable as old. and in addition, to add oom_killer_disabled check to avoid reintroduce the issue of commit d1908362 ("vmscan: check all_unreclaimable in direct reclaim path"). Reported-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: David Rientjes <rientjes@google.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-15 06:22:12 +08:00
if (!zone->all_unreclaimable)
return false;
vmscan: check all_unreclaimable in direct reclaim path M. Vefa Bicakci reported 2.6.35 kernel hang up when hibernation on his 32bit 3GB mem machine. (https://bugzilla.kernel.org/show_bug.cgi?id=16771). Also he bisected the regression to commit bb21c7ce18eff8e6e7877ca1d06c6db719376e3c Author: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Date: Fri Jun 4 14:15:05 2010 -0700 vmscan: fix do_try_to_free_pages() return value when priority==0 reclaim failure At first impression, this seemed very strange because the above commit only chenged function return value and hibernate_preallocate_memory() ignore return value of shrink_all_memory(). But it's related. Now, page allocation from hibernation code may enter infinite loop if the system has highmem. The reasons are that vmscan don't care enough OOM case when oom_killer_disabled. The problem sequence is following as. 1. hibernation 2. oom_disable 3. alloc_pages 4. do_try_to_free_pages if (scanning_global_lru(sc) && !all_unreclaimable) return 1; If kswapd is not freozen, it would set zone->all_unreclaimable to 1 and then shrink_zones maybe return true(ie, all_unreclaimable is true). So at last, alloc_pages could go to _nopage_. If it is, it should have no problem. This patch adds all_unreclaimable check to protect in direct reclaim path, too. It can care of hibernation OOM case and help bailout all_unreclaimable case slightly. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reported-by: M. Vefa Bicakci <bicave@superonline.com> Reported-by: <caiqian@redhat.com> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Tested-by: <caiqian@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-09-23 04:05:01 +08:00
}
vmscan: all_unreclaimable() use zone->all_unreclaimable as a name all_unreclaimable check in direct reclaim has been introduced at 2.6.19 by following commit. 2006 Sep 25; commit 408d8544; oom: use unreclaimable info And it went through strange history. firstly, following commit broke the logic unintentionally. 2008 Apr 29; commit a41f24ea; page allocator: smarter retry of costly-order allocations Two years later, I've found obvious meaningless code fragment and restored original intention by following commit. 2010 Jun 04; commit bb21c7ce; vmscan: fix do_try_to_free_pages() return value when priority==0 But, the logic didn't works when 32bit highmem system goes hibernation and Minchan slightly changed the algorithm and fixed it . 2010 Sep 22: commit d1908362: vmscan: check all_unreclaimable in direct reclaim path But, recently, Andrey Vagin found the new corner case. Look, struct zone { .. int all_unreclaimable; .. unsigned long pages_scanned; .. } zone->all_unreclaimable and zone->pages_scanned are neigher atomic variables nor protected by lock. Therefore zones can become a state of zone->page_scanned=0 and zone->all_unreclaimable=1. In this case, current all_unreclaimable() return false even though zone->all_unreclaimabe=1. This resulted in the kernel hanging up when executing a loop of the form 1. fork 2. mmap 3. touch memory 4. read memory 5. munmmap as described in http://www.gossamer-threads.com/lists/linux/kernel/1348725#1348725 Is this ignorable minor issue? No. Unfortunately, x86 has very small dma zone and it become zone->all_unreclamble=1 easily. and if it become all_unreclaimable=1, it never restore all_unreclaimable=0. Why? if all_unreclaimable=1, vmscan only try DEF_PRIORITY reclaim and a-few-lru-pages>>DEF_PRIORITY always makes 0. that mean no page scan at all! Eventually, oom-killer never works on such systems. That said, we can't use zone->pages_scanned for this purpose. This patch restore all_unreclaimable() use zone->all_unreclaimable as old. and in addition, to add oom_killer_disabled check to avoid reintroduce the issue of commit d1908362 ("vmscan: check all_unreclaimable in direct reclaim path"). Reported-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: David Rientjes <rientjes@google.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-15 06:22:12 +08:00
return true;
}
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
/*
* This is the main entry point to direct page reclaim.
*
* If a full scan of the inactive list fails to free enough memory then we
* are "out of memory" and something needs to be killed.
*
* If the caller is !__GFP_FS then the probability of a failure is reasonably
* high - the zone may be full of dirty or under-writeback pages, which this
* caller can't do much about. We kick the writeback threads and take explicit
* naps in the hope that some of these pages can be written. But if the
* allocating task holds filesystem locks which prevent writeout this might not
* work, and the allocation attempt will fail.
page allocator: smarter retry of costly-order allocations Because of page order checks in __alloc_pages(), hugepage (and similarly large order) allocations will not retry unless explicitly marked __GFP_REPEAT. However, the current retry logic is nearly an infinite loop (or until reclaim does no progress whatsoever). For these costly allocations, that seems like overkill and could potentially never terminate. Mel observed that allowing current __GFP_REPEAT semantics for hugepage allocations essentially killed the system. I believe this is because we may continue to reclaim small orders of pages all over, but never have enough to satisfy the hugepage allocation request. This is clearly only a problem for large order allocations, of which hugepages are the most obvious (to me). Modify try_to_free_pages() to indicate how many pages were reclaimed. Use that information in __alloc_pages() to eventually fail a large __GFP_REPEAT allocation when we've reclaimed an order of pages equal to or greater than the allocation's order. This relies on lumpy reclaim functioning as advertised. Due to fragmentation, lumpy reclaim may not be able to free up the order needed in one invocation, so multiple iterations may be requred. In other words, the more fragmented memory is, the more retry attempts __GFP_REPEAT will make (particularly for higher order allocations). This changes the semantics of __GFP_REPEAT subtly, but *only* for allocations > PAGE_ALLOC_COSTLY_ORDER. With this patch, for those size allocations, we will try up to some point (at least 1<<order reclaimed pages), rather than forever (which is the case for allocations <= PAGE_ALLOC_COSTLY_ORDER). This change improves the /proc/sys/vm/nr_hugepages interface with a follow-on patch that makes pool allocations use __GFP_REPEAT. Rather than administrators repeatedly echo'ing a particular value into the sysctl, and forcing reclaim into action manually, this change allows for the sysctl to attempt a reasonable effort itself. Similarly, dynamic pool growth should be more successful under load, as lumpy reclaim can try to free up pages, rather than failing right away. Choosing to reclaim only up to the order of the requested allocation strikes a balance between not failing hugepage allocations and returning to the caller when it's unlikely to every succeed. Because of lumpy reclaim, if we have freed the order requested, hopefully it has been in big chunks and those chunks will allow our allocation to succeed. If that isn't the case after freeing up the current order, I don't think it is likely to succeed in the future, although it is possible given a particular fragmentation pattern. Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com> Cc: Andy Whitcroft <apw@shadowen.org> Tested-by: Mel Gorman <mel@csn.ul.ie> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 15:58:25 +08:00
*
* returns: 0, if no pages reclaimed
* else, the number of pages reclaimed
*/
mm: use zonelists instead of zones when direct reclaiming pages The following patches replace multiple zonelists per node with two zonelists that are filtered based on the GFP flags. The patches as a set fix a bug with regard to the use of MPOL_BIND and ZONE_MOVABLE. With this patchset, the MPOL_BIND will apply to the two highest zones when the highest zone is ZONE_MOVABLE. This should be considered as an alternative fix for the MPOL_BIND+ZONE_MOVABLE in 2.6.23 to the previously discussed hack that filters only custom zonelists. The first patch cleans up an inconsistency where direct reclaim uses zonelist->zones where other places use zonelist. The second patch introduces a helper function node_zonelist() for looking up the appropriate zonelist for a GFP mask which simplifies patches later in the set. The third patch defines/remembers the "preferred zone" for numa statistics, as it is no longer always the first zone in a zonelist. The forth patch replaces multiple zonelists with two zonelists that are filtered. The two zonelists are due to the fact that the memoryless patchset introduces a second set of zonelists for __GFP_THISNODE. The fifth patch introduces helper macros for retrieving the zone and node indices of entries in a zonelist. The final patch introduces filtering of the zonelists based on a nodemask. Two zonelists exist per node, one for normal allocations and one for __GFP_THISNODE. Performance results varied depending on the machine configuration. In real workloads the gain/loss will depend on how much the userspace portion of the benchmark benefits from having more cache available due to reduced referencing of zonelists. These are the range of performance losses/gains when running against 2.6.24-rc4-mm1. The set and these machines are a mix of i386, x86_64 and ppc64 both NUMA and non-NUMA. loss to gain Total CPU time on Kernbench: -0.86% to 1.13% Elapsed time on Kernbench: -0.79% to 0.76% page_test from aim9: -4.37% to 0.79% brk_test from aim9: -0.71% to 4.07% fork_test from aim9: -1.84% to 4.60% exec_test from aim9: -0.71% to 1.08% This patch: The allocator deals with zonelists which indicate the order in which zones should be targeted for an allocation. Similarly, direct reclaim of pages iterates over an array of zones. For consistency, this patch converts direct reclaim to use a zonelist. No functionality is changed by this patch. This simplifies zonelist iterators in the next patch. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <clameter@sgi.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:12 +08:00
static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
struct scan_control *sc,
struct shrink_control *shrink)
{
unsigned long total_scanned = 0;
struct reclaim_state *reclaim_state = current->reclaim_state;
mm: have zonelist contains structs with both a zone pointer and zone_idx Filtering zonelists requires very frequent use of zone_idx(). This is costly as it involves a lookup of another structure and a substraction operation. As the zone_idx is often required, it should be quickly accessible. The node idx could also be stored here if it was found that accessing zone->node is significant which may be the case on workloads where nodemasks are heavily used. This patch introduces a struct zoneref to store a zone pointer and a zone index. The zonelist then consists of an array of these struct zonerefs which are looked up as necessary. Helpers are given for accessing the zone index as well as the node index. [kamezawa.hiroyu@jp.fujitsu.com: Suggested struct zoneref instead of embedding information in pointers] [hugh@veritas.com: mm-have-zonelist: fix memcg ooms] [hugh@veritas.com: just return do_try_to_free_pages] [hugh@veritas.com: do_try_to_free_pages gfp_mask redundant] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Christoph Lameter <clameter@sgi.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <clameter@sgi.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:17 +08:00
struct zoneref *z;
struct zone *zone;
unsigned long writeback_threshold;
bool aborted_reclaim;
per-task-delay-accounting: add memory reclaim delay Sometimes, application responses become bad under heavy memory load. Applications take a bit time to reclaim memory. The statistics, how long memory reclaim takes, will be useful to measure memory usage. This patch adds accounting memory reclaim to per-task-delay-accounting for accounting the time of do_try_to_free_pages(). <i.e> - When System is under low memory load, memory reclaim may not occur. $ free total used free shared buffers cached Mem: 8197800 1577300 6620500 0 4808 1516724 -/+ buffers/cache: 55768 8142032 Swap: 16386292 0 16386292 $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 0 5069748 10612 3014060 0 0 0 0 3 26 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 4 22 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 3 18 0 0 100 0 Measure the time of tar command. $ ls -s test.dat 1501472 test.dat $ time tar cvf test.tar test.dat real 0m13.388s user 0m0.116s sys 0m5.304s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 428 5528345500 5477116080 62749891 IO count delay total 338 8078977189 SWAP count delay total 0 0 RECLAIM count delay total 0 0 - When system is under heavy memory load memory reclaim may occur. $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 7159032 49724 1812 3012 0 0 0 0 3 24 0 0 100 0 0 0 7159032 49724 1812 3012 0 0 0 0 4 24 0 0 100 0 0 0 7159032 49848 1812 3012 0 0 0 0 3 22 0 0 100 0 In this case, one process uses more 8G memory by execution of malloc() and memset(). $ time tar cvf test.tar test.dat real 1m38.563s <- increased by 85 sec user 0m0.140s sys 0m7.060s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 9021 7140446250 7315277975 923201824 IO count delay total 8965 90466349669 SWAP count delay total 3 21036367 RECLAIM count delay total 740 61011951153 In the later case, the value of RECLAIM is increasing. So, taskstats can show how much memory reclaim influences TAT. Signed-off-by: Keika Kobayashi <kobayashi.kk@ncos.nec.co.jp> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujistu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 16:48:52 +08:00
delayacct_freepages_start();
if (global_reclaim(sc))
per-zone and reclaim enhancements for memory controller: modifies vmscan.c for isolate globa/cgroup lru activity When using memory controller, there are 2 levels of memory reclaim. 1. zone memory reclaim because of system/zone memory shortage. 2. memory cgroup memory reclaim because of hitting limit. These two can be distinguished by sc->mem_cgroup parameter. (scan_global_lru() macro) This patch tries to make memory cgroup reclaim routine avoid affecting system/zone memory reclaim. This patch inserts if (scan_global_lru()) and hook to memory_cgroup reclaim support functions. This patch can be a help for isolating system lru activity and group lru activity and shows what additional functions are necessary. * mem_cgroup_calc_mapped_ratio() ... calculate mapped ratio for cgroup. * mem_cgroup_reclaim_imbalance() ... calculate active/inactive balance in cgroup. * mem_cgroup_calc_reclaim_active() ... calculate the number of active pages to be scanned in this priority in mem_cgroup. * mem_cgroup_calc_reclaim_inactive() ... calculate the number of inactive pages to be scanned in this priority in mem_cgroup. * mem_cgroup_all_unreclaimable() .. checks cgroup's page is all unreclaimable or not. * mem_cgroup_get_reclaim_priority() ... * mem_cgroup_note_reclaim_priority() ... record reclaim priority (temporal) * mem_cgroup_remember_reclaim_priority() .... record reclaim priority as zone->prev_priority. This value is used for calc reclaim_mapped. [akpm@linux-foundation.org: fix unused var warning] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: David Rientjes <rientjes@google.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Paul Menage <menage@google.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 16:14:37 +08:00
count_vm_event(ALLOCSTALL);
do {
sc->nr_scanned = 0;
aborted_reclaim = shrink_zones(zonelist, sc);
/*
* Don't shrink slabs when reclaiming memory from
* over limit cgroups
*/
if (global_reclaim(sc)) {
unsigned long lru_pages = 0;
for_each_zone_zonelist(zone, z, zonelist,
gfp_zone(sc->gfp_mask)) {
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
lru_pages += zone_reclaimable_pages(zone);
}
shrink_slab(shrink, sc->nr_scanned, lru_pages);
if (reclaim_state) {
vmscan: bail out of direct reclaim after swap_cluster_max pages When the VM is under pressure, it can happen that several direct reclaim processes are in the pageout code simultaneously. It also happens that the reclaiming processes run into mostly referenced, mapped and dirty pages in the first round. This results in multiple direct reclaim processes having a lower pageout priority, which corresponds to a higher target of pages to scan. This in turn can result in each direct reclaim process freeing many pages. Together, they can end up freeing way too many pages. This kicks useful data out of memory (in some cases more than half of all memory is swapped out). It also impacts performance by keeping tasks stuck in the pageout code for too long. A 30% improvement in hackbench has been observed with this patch. The fix is relatively simple: in shrink_zone() we can check how many pages we have already freed, direct reclaim tasks break out of the scanning loop if they have already freed enough pages and have reached a lower priority level. We do not break out of shrink_zone() when priority == DEF_PRIORITY, to ensure that equal pressure is applied to every zone in the common case. However, in order to do this we do need to know how many pages we already freed, so move nr_reclaimed into scan_control. akpm: a historical interlude... We tried this in 2004: :commit e468e46a9bea3297011d5918663ce6d19094cf87 :Author: akpm <akpm> :Date: Thu Jun 24 15:53:52 2004 +0000 : :[PATCH] vmscan.c: dont reclaim too many pages : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly hit : a large number of reclaimable pages on the LRU. : Change things so we bale out when SWAP_CLUSTER_MAX pages have been reclaimed. And we reverted it in 2006: :commit 210fe530305ee50cd889fe9250168228b2994f32 :Author: Andrew Morton <akpm@osdl.org> :Date: Fri Jan 6 00:11:14 2006 -0800 : : [PATCH] vmscan: balancing fix : : Revert a patch which went into 2.6.8-rc1. The changelog for that patch was: : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly : hit a large number of reclaimable pages on the LRU. : : Change things so we bale out when SWAP_CLUSTER_MAX pages have been : reclaimed. : : Problem is, this change caused significant imbalance in inter-zone scan : balancing by truncating scans of larger zones. : : Suppose, for example, ZONE_HIGHMEM is 10x the size of ZONE_NORMAL. The zone : balancing algorithm would require that if we're scanning 100 pages of : ZONE_HIGHMEM, we should scan 10 pages of ZONE_NORMAL. But this logic will : cause the scanning of ZONE_HIGHMEM to bale out after only 32 pages are : reclaimed. Thus effectively causing smaller zones to be scanned relatively : harder than large ones. : : Now I need to remember what the workload was which caused me to write this : patch originally, then fix it up in a different way... And we haven't demonstrated that whatever problem caused that reversion is not being reintroduced by this change in 2008. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:01 +08:00
sc->nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
}
}
total_scanned += sc->nr_scanned;
vmscan: fix do_try_to_free_pages() return value when priority==0 reclaim failure Greg Thelen reported recent Johannes's stack diet patch makes kernel hang. His test is following. mount -t cgroup none /cgroups -o memory mkdir /cgroups/cg1 echo $$ > /cgroups/cg1/tasks dd bs=1024 count=1024 if=/dev/null of=/data/foo echo $$ > /cgroups/tasks echo 1 > /cgroups/cg1/memory.force_empty Actually, This OOM hard to try logic have been corrupted since following two years old patch. commit a41f24ea9fd6169b147c53c2392e2887cc1d9247 Author: Nishanth Aravamudan <nacc@us.ibm.com> Date: Tue Apr 29 00:58:25 2008 -0700 page allocator: smarter retry of costly-order allocations Original intention was "return success if the system have shrinkable zones though priority==0 reclaim was failure". But the above patch changed to "return nr_reclaimed if .....". Oh, That forgot nr_reclaimed may be 0 if priority==0 reclaim failure. And Johannes's patch 0aeb2339e54e ("vmscan: remove all_unreclaimable scan control") made it more corrupt. Originally, priority==0 reclaim failure on memcg return 0, but this patch changed to return 1. It totally confused memcg. This patch fixes it completely. Reported-by: Greg Thelen <gthelen@google.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Tested-by: Greg Thelen <gthelen@google.com> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-06-05 05:15:05 +08:00
if (sc->nr_reclaimed >= sc->nr_to_reclaim)
goto out;
/*
* Try to write back as many pages as we just scanned. This
* tends to cause slow streaming writers to write data to the
* disk smoothly, at the dirtying rate, which is nice. But
* that's undesirable in laptop mode, where we *want* lumpy
* writeout. So in laptop mode, write out the whole world.
*/
writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
if (total_scanned > writeback_threshold) {
wakeup_flusher_threads(laptop_mode ? 0 : total_scanned,
WB_REASON_TRY_TO_FREE_PAGES);
sc->may_writepage = 1;
}
/* Take a nap, wait for some writeback to complete */
vmscan: kill hibernation specific reclaim logic and unify it shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing memory for suspend). commit a06fe4d307 said Without the patch: Freed 14600 pages in 1749 jiffies = 32.61 MB/s (Anomolous!) Freed 88563 pages in 14719 jiffies = 23.50 MB/s Freed 205734 pages in 32389 jiffies = 24.81 MB/s With the patch: Freed 68252 pages in 496 jiffies = 537.52 MB/s Freed 116464 pages in 569 jiffies = 798.54 MB/s Freed 209699 pages in 705 jiffies = 1161.89 MB/s At that time, their patch was pretty worth. However, Modern Hardware trend and recent VM improvement broke its worth. From several reason, I think we should remove shrink_all_zones() at all. detail: 1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle at no i/o congestion. but current shrink_zone() is sane, not slow. 2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works fine on numa system. example) System has 4GB memory and each node have 2GB. and hibernate need 1GB. optimal) steal 500MB from each node. shrink_all_zones) steal 1GB from node-0. Oh, Cache balancing logic was broken. ;) Unfortunately, Desktop system moved ahead NUMA at nowadays. (Side note, if hibernate require 2GB, shrink_all_zones() never success on above machine) 3) if the node has several I/O flighting pages, shrink_all_zones() makes pretty bad result. schenario) hibernate need 1GB 1) shrink_all_zones() try to reclaim 1GB from Node-0 2) but it only reclaimed 990MB 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1 4) it reclaimed 990MB Oh, well. it reclaimed twice much than required. In the other hand, current shrink_zone() has sane baling out logic. then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk. 4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal. Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages(). it bring good reviewability and debuggability, and solve above problems. side note: Reclaim logic unificication makes two good side effect. - Fix recursive reclaim bug on shrink_all_memory(). it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock. - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 09:59:12 +08:00
if (!sc->hibernation_mode && sc->nr_scanned &&
sc->priority < DEF_PRIORITY - 2) {
struct zone *preferred_zone;
first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask),
mm: fix deferred congestion timeout if preferred zone is not allowed Before 0e093d99763e ("writeback: do not sleep on the congestion queue if there are no congested BDIs or if significant congestion is not being encountered in the current zone"), preferred_zone was only used for NUMA statistics, to determine the zoneidx from which to allocate from given the type requested, and whether to utilize memory compaction. wait_iff_congested(), though, uses preferred_zone to determine if the congestion wait should be deferred because its dirty pages are backed by a congested bdi. This incorrectly defers the timeout and busy loops in the page allocator with various cond_resched() calls if preferred_zone is not allowed in the current context, usually consuming 100% of a cpu. This patch ensures preferred_zone is an allowed zone in the fastpath depending on whether current is constrained by its cpuset or nodes in its mempolicy (when the nodemask passed is non-NULL). This is correct since the fastpath allocation always passes ALLOC_CPUSET when trying to allocate memory. In the slowpath, this patch resets preferred_zone to the first zone of the allowed type when the allocation is not constrained by current's cpuset, i.e. it does not pass ALLOC_CPUSET. This patch also ensures preferred_zone is from the set of allowed nodes when called from within direct reclaim since allocations are always constrained by cpusets in this context (it is blockable). Both of these uses of cpuset_current_mems_allowed are protected by get_mems_allowed(). Signed-off-by: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-26 07:07:20 +08:00
&cpuset_current_mems_allowed,
&preferred_zone);
wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10);
}
} while (--sc->priority >= 0);
vmscan: fix do_try_to_free_pages() return value when priority==0 reclaim failure Greg Thelen reported recent Johannes's stack diet patch makes kernel hang. His test is following. mount -t cgroup none /cgroups -o memory mkdir /cgroups/cg1 echo $$ > /cgroups/cg1/tasks dd bs=1024 count=1024 if=/dev/null of=/data/foo echo $$ > /cgroups/tasks echo 1 > /cgroups/cg1/memory.force_empty Actually, This OOM hard to try logic have been corrupted since following two years old patch. commit a41f24ea9fd6169b147c53c2392e2887cc1d9247 Author: Nishanth Aravamudan <nacc@us.ibm.com> Date: Tue Apr 29 00:58:25 2008 -0700 page allocator: smarter retry of costly-order allocations Original intention was "return success if the system have shrinkable zones though priority==0 reclaim was failure". But the above patch changed to "return nr_reclaimed if .....". Oh, That forgot nr_reclaimed may be 0 if priority==0 reclaim failure. And Johannes's patch 0aeb2339e54e ("vmscan: remove all_unreclaimable scan control") made it more corrupt. Originally, priority==0 reclaim failure on memcg return 0, but this patch changed to return 1. It totally confused memcg. This patch fixes it completely. Reported-by: Greg Thelen <gthelen@google.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Tested-by: Greg Thelen <gthelen@google.com> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-06-05 05:15:05 +08:00
out:
per-task-delay-accounting: add memory reclaim delay Sometimes, application responses become bad under heavy memory load. Applications take a bit time to reclaim memory. The statistics, how long memory reclaim takes, will be useful to measure memory usage. This patch adds accounting memory reclaim to per-task-delay-accounting for accounting the time of do_try_to_free_pages(). <i.e> - When System is under low memory load, memory reclaim may not occur. $ free total used free shared buffers cached Mem: 8197800 1577300 6620500 0 4808 1516724 -/+ buffers/cache: 55768 8142032 Swap: 16386292 0 16386292 $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 0 5069748 10612 3014060 0 0 0 0 3 26 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 4 22 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 3 18 0 0 100 0 Measure the time of tar command. $ ls -s test.dat 1501472 test.dat $ time tar cvf test.tar test.dat real 0m13.388s user 0m0.116s sys 0m5.304s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 428 5528345500 5477116080 62749891 IO count delay total 338 8078977189 SWAP count delay total 0 0 RECLAIM count delay total 0 0 - When system is under heavy memory load memory reclaim may occur. $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 7159032 49724 1812 3012 0 0 0 0 3 24 0 0 100 0 0 0 7159032 49724 1812 3012 0 0 0 0 4 24 0 0 100 0 0 0 7159032 49848 1812 3012 0 0 0 0 3 22 0 0 100 0 In this case, one process uses more 8G memory by execution of malloc() and memset(). $ time tar cvf test.tar test.dat real 1m38.563s <- increased by 85 sec user 0m0.140s sys 0m7.060s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 9021 7140446250 7315277975 923201824 IO count delay total 8965 90466349669 SWAP count delay total 3 21036367 RECLAIM count delay total 740 61011951153 In the later case, the value of RECLAIM is increasing. So, taskstats can show how much memory reclaim influences TAT. Signed-off-by: Keika Kobayashi <kobayashi.kk@ncos.nec.co.jp> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujistu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 16:48:52 +08:00
delayacct_freepages_end();
vmscan: fix do_try_to_free_pages() return value when priority==0 reclaim failure Greg Thelen reported recent Johannes's stack diet patch makes kernel hang. His test is following. mount -t cgroup none /cgroups -o memory mkdir /cgroups/cg1 echo $$ > /cgroups/cg1/tasks dd bs=1024 count=1024 if=/dev/null of=/data/foo echo $$ > /cgroups/tasks echo 1 > /cgroups/cg1/memory.force_empty Actually, This OOM hard to try logic have been corrupted since following two years old patch. commit a41f24ea9fd6169b147c53c2392e2887cc1d9247 Author: Nishanth Aravamudan <nacc@us.ibm.com> Date: Tue Apr 29 00:58:25 2008 -0700 page allocator: smarter retry of costly-order allocations Original intention was "return success if the system have shrinkable zones though priority==0 reclaim was failure". But the above patch changed to "return nr_reclaimed if .....". Oh, That forgot nr_reclaimed may be 0 if priority==0 reclaim failure. And Johannes's patch 0aeb2339e54e ("vmscan: remove all_unreclaimable scan control") made it more corrupt. Originally, priority==0 reclaim failure on memcg return 0, but this patch changed to return 1. It totally confused memcg. This patch fixes it completely. Reported-by: Greg Thelen <gthelen@google.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Tested-by: Greg Thelen <gthelen@google.com> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-06-05 05:15:05 +08:00
if (sc->nr_reclaimed)
return sc->nr_reclaimed;
vmscan: all_unreclaimable() use zone->all_unreclaimable as a name all_unreclaimable check in direct reclaim has been introduced at 2.6.19 by following commit. 2006 Sep 25; commit 408d8544; oom: use unreclaimable info And it went through strange history. firstly, following commit broke the logic unintentionally. 2008 Apr 29; commit a41f24ea; page allocator: smarter retry of costly-order allocations Two years later, I've found obvious meaningless code fragment and restored original intention by following commit. 2010 Jun 04; commit bb21c7ce; vmscan: fix do_try_to_free_pages() return value when priority==0 But, the logic didn't works when 32bit highmem system goes hibernation and Minchan slightly changed the algorithm and fixed it . 2010 Sep 22: commit d1908362: vmscan: check all_unreclaimable in direct reclaim path But, recently, Andrey Vagin found the new corner case. Look, struct zone { .. int all_unreclaimable; .. unsigned long pages_scanned; .. } zone->all_unreclaimable and zone->pages_scanned are neigher atomic variables nor protected by lock. Therefore zones can become a state of zone->page_scanned=0 and zone->all_unreclaimable=1. In this case, current all_unreclaimable() return false even though zone->all_unreclaimabe=1. This resulted in the kernel hanging up when executing a loop of the form 1. fork 2. mmap 3. touch memory 4. read memory 5. munmmap as described in http://www.gossamer-threads.com/lists/linux/kernel/1348725#1348725 Is this ignorable minor issue? No. Unfortunately, x86 has very small dma zone and it become zone->all_unreclamble=1 easily. and if it become all_unreclaimable=1, it never restore all_unreclaimable=0. Why? if all_unreclaimable=1, vmscan only try DEF_PRIORITY reclaim and a-few-lru-pages>>DEF_PRIORITY always makes 0. that mean no page scan at all! Eventually, oom-killer never works on such systems. That said, we can't use zone->pages_scanned for this purpose. This patch restore all_unreclaimable() use zone->all_unreclaimable as old. and in addition, to add oom_killer_disabled check to avoid reintroduce the issue of commit d1908362 ("vmscan: check all_unreclaimable in direct reclaim path"). Reported-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: David Rientjes <rientjes@google.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-15 06:22:12 +08:00
/*
* As hibernation is going on, kswapd is freezed so that it can't mark
* the zone into all_unreclaimable. Thus bypassing all_unreclaimable
* check.
*/
if (oom_killer_disabled)
return 0;
/* Aborted reclaim to try compaction? don't OOM, then */
if (aborted_reclaim)
return 1;
vmscan: fix do_try_to_free_pages() return value when priority==0 reclaim failure Greg Thelen reported recent Johannes's stack diet patch makes kernel hang. His test is following. mount -t cgroup none /cgroups -o memory mkdir /cgroups/cg1 echo $$ > /cgroups/cg1/tasks dd bs=1024 count=1024 if=/dev/null of=/data/foo echo $$ > /cgroups/tasks echo 1 > /cgroups/cg1/memory.force_empty Actually, This OOM hard to try logic have been corrupted since following two years old patch. commit a41f24ea9fd6169b147c53c2392e2887cc1d9247 Author: Nishanth Aravamudan <nacc@us.ibm.com> Date: Tue Apr 29 00:58:25 2008 -0700 page allocator: smarter retry of costly-order allocations Original intention was "return success if the system have shrinkable zones though priority==0 reclaim was failure". But the above patch changed to "return nr_reclaimed if .....". Oh, That forgot nr_reclaimed may be 0 if priority==0 reclaim failure. And Johannes's patch 0aeb2339e54e ("vmscan: remove all_unreclaimable scan control") made it more corrupt. Originally, priority==0 reclaim failure on memcg return 0, but this patch changed to return 1. It totally confused memcg. This patch fixes it completely. Reported-by: Greg Thelen <gthelen@google.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Tested-by: Greg Thelen <gthelen@google.com> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-06-05 05:15:05 +08:00
/* top priority shrink_zones still had more to do? don't OOM, then */
if (global_reclaim(sc) && !all_unreclaimable(zonelist, sc))
vmscan: fix do_try_to_free_pages() return value when priority==0 reclaim failure Greg Thelen reported recent Johannes's stack diet patch makes kernel hang. His test is following. mount -t cgroup none /cgroups -o memory mkdir /cgroups/cg1 echo $$ > /cgroups/cg1/tasks dd bs=1024 count=1024 if=/dev/null of=/data/foo echo $$ > /cgroups/tasks echo 1 > /cgroups/cg1/memory.force_empty Actually, This OOM hard to try logic have been corrupted since following two years old patch. commit a41f24ea9fd6169b147c53c2392e2887cc1d9247 Author: Nishanth Aravamudan <nacc@us.ibm.com> Date: Tue Apr 29 00:58:25 2008 -0700 page allocator: smarter retry of costly-order allocations Original intention was "return success if the system have shrinkable zones though priority==0 reclaim was failure". But the above patch changed to "return nr_reclaimed if .....". Oh, That forgot nr_reclaimed may be 0 if priority==0 reclaim failure. And Johannes's patch 0aeb2339e54e ("vmscan: remove all_unreclaimable scan control") made it more corrupt. Originally, priority==0 reclaim failure on memcg return 0, but this patch changed to return 1. It totally confused memcg. This patch fixes it completely. Reported-by: Greg Thelen <gthelen@google.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Tested-by: Greg Thelen <gthelen@google.com> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-06-05 05:15:05 +08:00
return 1;
return 0;
}
static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
{
struct zone *zone;
unsigned long pfmemalloc_reserve = 0;
unsigned long free_pages = 0;
int i;
bool wmark_ok;
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
pfmemalloc_reserve += min_wmark_pages(zone);
free_pages += zone_page_state(zone, NR_FREE_PAGES);
}
wmark_ok = free_pages > pfmemalloc_reserve / 2;
/* kswapd must be awake if processes are being throttled */
if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
pgdat->classzone_idx = min(pgdat->classzone_idx,
(enum zone_type)ZONE_NORMAL);
wake_up_interruptible(&pgdat->kswapd_wait);
}
return wmark_ok;
}
/*
* Throttle direct reclaimers if backing storage is backed by the network
* and the PFMEMALLOC reserve for the preferred node is getting dangerously
* depleted. kswapd will continue to make progress and wake the processes
* when the low watermark is reached
*/
static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
nodemask_t *nodemask)
{
struct zone *zone;
int high_zoneidx = gfp_zone(gfp_mask);
pg_data_t *pgdat;
/*
* Kernel threads should not be throttled as they may be indirectly
* responsible for cleaning pages necessary for reclaim to make forward
* progress. kjournald for example may enter direct reclaim while
* committing a transaction where throttling it could forcing other
* processes to block on log_wait_commit().
*/
if (current->flags & PF_KTHREAD)
return;
/* Check if the pfmemalloc reserves are ok */
first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
pgdat = zone->zone_pgdat;
if (pfmemalloc_watermark_ok(pgdat))
return;
/* Account for the throttling */
count_vm_event(PGSCAN_DIRECT_THROTTLE);
/*
* If the caller cannot enter the filesystem, it's possible that it
* is due to the caller holding an FS lock or performing a journal
* transaction in the case of a filesystem like ext[3|4]. In this case,
* it is not safe to block on pfmemalloc_wait as kswapd could be
* blocked waiting on the same lock. Instead, throttle for up to a
* second before continuing.
*/
if (!(gfp_mask & __GFP_FS)) {
wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
pfmemalloc_watermark_ok(pgdat), HZ);
return;
}
/* Throttle until kswapd wakes the process */
wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
pfmemalloc_watermark_ok(pgdat));
}
mm: use zonelists instead of zones when direct reclaiming pages The following patches replace multiple zonelists per node with two zonelists that are filtered based on the GFP flags. The patches as a set fix a bug with regard to the use of MPOL_BIND and ZONE_MOVABLE. With this patchset, the MPOL_BIND will apply to the two highest zones when the highest zone is ZONE_MOVABLE. This should be considered as an alternative fix for the MPOL_BIND+ZONE_MOVABLE in 2.6.23 to the previously discussed hack that filters only custom zonelists. The first patch cleans up an inconsistency where direct reclaim uses zonelist->zones where other places use zonelist. The second patch introduces a helper function node_zonelist() for looking up the appropriate zonelist for a GFP mask which simplifies patches later in the set. The third patch defines/remembers the "preferred zone" for numa statistics, as it is no longer always the first zone in a zonelist. The forth patch replaces multiple zonelists with two zonelists that are filtered. The two zonelists are due to the fact that the memoryless patchset introduces a second set of zonelists for __GFP_THISNODE. The fifth patch introduces helper macros for retrieving the zone and node indices of entries in a zonelist. The final patch introduces filtering of the zonelists based on a nodemask. Two zonelists exist per node, one for normal allocations and one for __GFP_THISNODE. Performance results varied depending on the machine configuration. In real workloads the gain/loss will depend on how much the userspace portion of the benchmark benefits from having more cache available due to reduced referencing of zonelists. These are the range of performance losses/gains when running against 2.6.24-rc4-mm1. The set and these machines are a mix of i386, x86_64 and ppc64 both NUMA and non-NUMA. loss to gain Total CPU time on Kernbench: -0.86% to 1.13% Elapsed time on Kernbench: -0.79% to 0.76% page_test from aim9: -4.37% to 0.79% brk_test from aim9: -0.71% to 4.07% fork_test from aim9: -1.84% to 4.60% exec_test from aim9: -0.71% to 1.08% This patch: The allocator deals with zonelists which indicate the order in which zones should be targeted for an allocation. Similarly, direct reclaim of pages iterates over an array of zones. For consistency, this patch converts direct reclaim to use a zonelist. No functionality is changed by this patch. This simplifies zonelist iterators in the next patch. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <clameter@sgi.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:12 +08:00
unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *nodemask)
{
unsigned long nr_reclaimed;
struct scan_control sc = {
.gfp_mask = gfp_mask,
.may_writepage = !laptop_mode,
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.may_unmap = 1,
.may_swap = 1,
.order = order,
.priority = DEF_PRIORITY,
.target_mem_cgroup = NULL,
.nodemask = nodemask,
};
struct shrink_control shrink = {
.gfp_mask = sc.gfp_mask,
};
throttle_direct_reclaim(gfp_mask, zonelist, nodemask);
/*
* Do not enter reclaim if fatal signal is pending. 1 is returned so
* that the page allocator does not consider triggering OOM
*/
if (fatal_signal_pending(current))
return 1;
trace_mm_vmscan_direct_reclaim_begin(order,
sc.may_writepage,
gfp_mask);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
return nr_reclaimed;
}
#ifdef CONFIG_MEMCG
unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
2009-09-24 06:56:39 +08:00
gfp_t gfp_mask, bool noswap,
memcg: count the soft_limit reclaim in global background reclaim The global kswapd scans per-zone LRU and reclaims pages regardless of the cgroup. It breaks memory isolation since one cgroup can end up reclaiming pages from another cgroup. Instead we should rely on memcg-aware target reclaim including per-memcg kswapd and soft_limit hierarchical reclaim under memory pressure. In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. This patch is the first step to skip shrink_zone() if soft_limit reclaim does enough work. This is part of the effort which tries to reduce reclaiming pages in global LRU in memcg. The per-memcg background reclaim patchset further enhances the per-cgroup targetting reclaim, which I should have V4 posted shortly. Try running multiple memory intensive workloads within seperate memcgs. Watch the counters of soft_steal in memory.stat. $ cat /dev/cgroup/A/memory.stat | grep 'soft' soft_steal 240000 soft_scan 240000 total_soft_steal 240000 total_soft_scan 240000 This patch: In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. We would like to skip shrink_zone() if soft_limit reclaim does enough work. Also, we need to make the memory pressure balanced across per-memcg zones, like the logic vm-core. This patch is the first step where we start with counting the nr_scanned and nr_reclaimed from soft_limit reclaim into the global scan_control. Signed-off-by: Ying Han <yinghan@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-27 07:25:25 +08:00
struct zone *zone,
unsigned long *nr_scanned)
2009-09-24 06:56:39 +08:00
{
struct scan_control sc = {
memcg: count the soft_limit reclaim in global background reclaim The global kswapd scans per-zone LRU and reclaims pages regardless of the cgroup. It breaks memory isolation since one cgroup can end up reclaiming pages from another cgroup. Instead we should rely on memcg-aware target reclaim including per-memcg kswapd and soft_limit hierarchical reclaim under memory pressure. In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. This patch is the first step to skip shrink_zone() if soft_limit reclaim does enough work. This is part of the effort which tries to reduce reclaiming pages in global LRU in memcg. The per-memcg background reclaim patchset further enhances the per-cgroup targetting reclaim, which I should have V4 posted shortly. Try running multiple memory intensive workloads within seperate memcgs. Watch the counters of soft_steal in memory.stat. $ cat /dev/cgroup/A/memory.stat | grep 'soft' soft_steal 240000 soft_scan 240000 total_soft_steal 240000 total_soft_scan 240000 This patch: In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. We would like to skip shrink_zone() if soft_limit reclaim does enough work. Also, we need to make the memory pressure balanced across per-memcg zones, like the logic vm-core. This patch is the first step where we start with counting the nr_scanned and nr_reclaimed from soft_limit reclaim into the global scan_control. Signed-off-by: Ying Han <yinghan@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-27 07:25:25 +08:00
.nr_scanned = 0,
.nr_to_reclaim = SWAP_CLUSTER_MAX,
2009-09-24 06:56:39 +08:00
.may_writepage = !laptop_mode,
.may_unmap = 1,
.may_swap = !noswap,
.order = 0,
.priority = 0,
.target_mem_cgroup = memcg,
2009-09-24 06:56:39 +08:00
};
struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
memcg: count the soft_limit reclaim in global background reclaim The global kswapd scans per-zone LRU and reclaims pages regardless of the cgroup. It breaks memory isolation since one cgroup can end up reclaiming pages from another cgroup. Instead we should rely on memcg-aware target reclaim including per-memcg kswapd and soft_limit hierarchical reclaim under memory pressure. In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. This patch is the first step to skip shrink_zone() if soft_limit reclaim does enough work. This is part of the effort which tries to reduce reclaiming pages in global LRU in memcg. The per-memcg background reclaim patchset further enhances the per-cgroup targetting reclaim, which I should have V4 posted shortly. Try running multiple memory intensive workloads within seperate memcgs. Watch the counters of soft_steal in memory.stat. $ cat /dev/cgroup/A/memory.stat | grep 'soft' soft_steal 240000 soft_scan 240000 total_soft_steal 240000 total_soft_scan 240000 This patch: In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. We would like to skip shrink_zone() if soft_limit reclaim does enough work. Also, we need to make the memory pressure balanced across per-memcg zones, like the logic vm-core. This patch is the first step where we start with counting the nr_scanned and nr_reclaimed from soft_limit reclaim into the global scan_control. Signed-off-by: Ying Han <yinghan@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-27 07:25:25 +08:00
2009-09-24 06:56:39 +08:00
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
sc.may_writepage,
sc.gfp_mask);
2009-09-24 06:56:39 +08:00
/*
* NOTE: Although we can get the priority field, using it
* here is not a good idea, since it limits the pages we can scan.
* if we don't reclaim here, the shrink_zone from balance_pgdat
* will pick up pages from other mem cgroup's as well. We hack
* the priority and make it zero.
*/
shrink_lruvec(lruvec, &sc);
trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
memcg: count the soft_limit reclaim in global background reclaim The global kswapd scans per-zone LRU and reclaims pages regardless of the cgroup. It breaks memory isolation since one cgroup can end up reclaiming pages from another cgroup. Instead we should rely on memcg-aware target reclaim including per-memcg kswapd and soft_limit hierarchical reclaim under memory pressure. In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. This patch is the first step to skip shrink_zone() if soft_limit reclaim does enough work. This is part of the effort which tries to reduce reclaiming pages in global LRU in memcg. The per-memcg background reclaim patchset further enhances the per-cgroup targetting reclaim, which I should have V4 posted shortly. Try running multiple memory intensive workloads within seperate memcgs. Watch the counters of soft_steal in memory.stat. $ cat /dev/cgroup/A/memory.stat | grep 'soft' soft_steal 240000 soft_scan 240000 total_soft_steal 240000 total_soft_scan 240000 This patch: In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. We would like to skip shrink_zone() if soft_limit reclaim does enough work. Also, we need to make the memory pressure balanced across per-memcg zones, like the logic vm-core. This patch is the first step where we start with counting the nr_scanned and nr_reclaimed from soft_limit reclaim into the global scan_control. Signed-off-by: Ying Han <yinghan@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-27 07:25:25 +08:00
*nr_scanned = sc.nr_scanned;
2009-09-24 06:56:39 +08:00
return sc.nr_reclaimed;
}
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
gfp_t gfp_mask,
bool noswap)
{
2009-09-24 06:56:39 +08:00
struct zonelist *zonelist;
unsigned long nr_reclaimed;
int nid;
struct scan_control sc = {
.may_writepage = !laptop_mode,
.may_unmap = 1,
.may_swap = !noswap,
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.order = 0,
.priority = DEF_PRIORITY,
.target_mem_cgroup = memcg,
.nodemask = NULL, /* we don't care the placement */
.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
};
struct shrink_control shrink = {
.gfp_mask = sc.gfp_mask,
};
/*
* Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
* take care of from where we get pages. So the node where we start the
* scan does not need to be the current node.
*/
nid = mem_cgroup_select_victim_node(memcg);
zonelist = NODE_DATA(nid)->node_zonelists;
trace_mm_vmscan_memcg_reclaim_begin(0,
sc.may_writepage,
sc.gfp_mask);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
return nr_reclaimed;
}
#endif
static void age_active_anon(struct zone *zone, struct scan_control *sc)
{
struct mem_cgroup *memcg;
if (!total_swap_pages)
return;
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
if (inactive_anon_is_low(lruvec))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
memcg = mem_cgroup_iter(NULL, memcg, NULL);
} while (memcg);
}
/*
* pgdat_balanced is used when checking if a node is balanced for high-order
* allocations. Only zones that meet watermarks and are in a zone allowed
* by the callers classzone_idx are added to balanced_pages. The total of
* balanced pages must be at least 25% of the zones allowed by classzone_idx
* for the node to be considered balanced. Forcing all zones to be balanced
* for high orders can cause excessive reclaim when there are imbalanced zones.
* The choice of 25% is due to
* o a 16M DMA zone that is balanced will not balance a zone on any
* reasonable sized machine
* o On all other machines, the top zone must be at least a reasonable
* percentage of the middle zones. For example, on 32-bit x86, highmem
* would need to be at least 256M for it to be balance a whole node.
* Similarly, on x86-64 the Normal zone would need to be at least 1G
* to balance a node on its own. These seemed like reasonable ratios.
*/
static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages,
int classzone_idx)
{
unsigned long present_pages = 0;
int i;
for (i = 0; i <= classzone_idx; i++)
present_pages += pgdat->node_zones[i].present_pages;
/* A special case here: if zone has no page, we think it's balanced */
return balanced_pages >= (present_pages >> 2);
}
/*
* Prepare kswapd for sleeping. This verifies that there are no processes
* waiting in throttle_direct_reclaim() and that watermarks have been met.
*
* Returns true if kswapd is ready to sleep
*/
static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
int classzone_idx)
{
int i;
unsigned long balanced = 0;
bool all_zones_ok = true;
/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
if (remaining)
return false;
/*
* There is a potential race between when kswapd checks its watermarks
* and a process gets throttled. There is also a potential race if
* processes get throttled, kswapd wakes, a large process exits therby
* balancing the zones that causes kswapd to miss a wakeup. If kswapd
* is going to sleep, no process should be sleeping on pfmemalloc_wait
* so wake them now if necessary. If necessary, processes will wake
* kswapd and get throttled again
*/
if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
wake_up(&pgdat->pfmemalloc_wait);
return false;
}
/* Check the watermark levels */
mm: vmscan: correct check for kswapd sleeping in sleeping_prematurely During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. This seems to happen most with recent sandybridge laptops but it's probably a co-incidence as some of these laptops just happen to have a small Normal zone. The reproduction case is almost always during copying large files that kswapd pegs at 100% CPU until the file is deleted or cache is dropped. The problem is mostly down to sleeping_prematurely() keeping kswapd awake when the highest zone is small and unreclaimable and compounded by the fact we shrink slabs even when not shrinking zones causing a lot of time to be spent in shrinkers and a lot of memory to be reclaimed. Patch 1 corrects sleeping_prematurely to check the zones matching the classzone_idx instead of all zones. Patch 2 avoids shrinking slab when we are not shrinking a zone. Patch 3 notes that sleeping_prematurely is checking lower zones against a high classzone which is not what allocators or balance_pgdat() is doing leading to an artifical belief that kswapd should be still awake. Patch 4 notes that when balance_pgdat() gives up on a high zone that the decision is not communicated to sleeping_prematurely() This problem affects 2.6.38.8 for certain and is expected to affect 2.6.39 and 3.0-rc4 as well. If accepted, they need to go to -stable to be picked up by distros and this series is against 3.0-rc4. I've cc'd people that reported similar problems recently to see if they still suffer from the problem and if this fixes it. This patch: correct the check for kswapd sleeping in sleeping_prematurely() During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. A problem occurs if the highest zone is small. balance_pgdat() only considers unreclaimable zones when priority is DEF_PRIORITY but sleeping_prematurely considers all zones. It's possible for this sequence to occur 1. kswapd wakes up and enters balance_pgdat() 2. At DEF_PRIORITY, marks highest zone unreclaimable 3. At DEF_PRIORITY-1, ignores highest zone setting end_zone 4. At DEF_PRIORITY-1, calls shrink_slab freeing memory from highest zone, clearing all_unreclaimable. Highest zone is still unbalanced 5. kswapd returns and calls sleeping_prematurely 6. sleeping_prematurely looks at *all* zones, not just the ones being considered by balance_pgdat. The highest small zone has all_unreclaimable cleared but the zone is not balanced. all_zones_ok is false so kswapd stays awake This patch corrects the behaviour of sleeping_prematurely to check the zones balance_pgdat() checked. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Pádraig Brady <P@draigBrady.com> Tested-by: Pádraig Brady <P@draigBrady.com> Tested-by: Andrew Lutomirski <luto@mit.edu> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-09 06:39:36 +08:00
for (i = 0; i <= classzone_idx; i++) {
struct zone *zone = pgdat->node_zones + i;
if (!populated_zone(zone))
continue;
/*
* balance_pgdat() skips over all_unreclaimable after
* DEF_PRIORITY. Effectively, it considers them balanced so
* they must be considered balanced here as well if kswapd
* is to sleep
*/
if (zone->all_unreclaimable) {
balanced += zone->present_pages;
continue;
}
mm: page allocator: adjust the per-cpu counter threshold when memory is low Commit aa45484 ("calculate a better estimate of NR_FREE_PAGES when memory is low") noted that watermarks were based on the vmstat NR_FREE_PAGES. To avoid synchronization overhead, these counters are maintained on a per-cpu basis and drained both periodically and when a threshold is above a threshold. On large CPU systems, the difference between the estimate and real value of NR_FREE_PAGES can be very high. The system can get into a case where pages are allocated far below the min watermark potentially causing livelock issues. The commit solved the problem by taking a better reading of NR_FREE_PAGES when memory was low. Unfortately, as reported by Shaohua Li this accurate reading can consume a large amount of CPU time on systems with many sockets due to cache line bouncing. This patch takes a different approach. For large machines where counter drift might be unsafe and while kswapd is awake, the per-cpu thresholds for the target pgdat are reduced to limit the level of drift to what should be a safe level. This incurs a performance penalty in heavy memory pressure by a factor that depends on the workload and the machine but the machine should function correctly without accidentally exhausting all memory on a node. There is an additional cost when kswapd wakes and sleeps but the event is not expected to be frequent - in Shaohua's test case, there was one recorded sleep and wake event at least. To ensure that kswapd wakes up, a safe version of zone_watermark_ok() is introduced that takes a more accurate reading of NR_FREE_PAGES when called from wakeup_kswapd, when deciding whether it is really safe to go back to sleep in sleeping_prematurely() and when deciding if a zone is really balanced or not in balance_pgdat(). We are still using an expensive function but limiting how often it is called. When the test case is reproduced, the time spent in the watermark functions is reduced. The following report is on the percentage of time spent cumulatively spent in the functions zone_nr_free_pages(), zone_watermark_ok(), __zone_watermark_ok(), zone_watermark_ok_safe(), zone_page_state_snapshot(), zone_page_state(). vanilla 11.6615% disable-threshold 0.2584% David said: : We had to pull aa454840 "mm: page allocator: calculate a better estimate : of NR_FREE_PAGES when memory is low and kswapd is awake" from 2.6.36 : internally because tests showed that it would cause the machine to stall : as the result of heavy kswapd activity. I merged it back with this fix as : it is pending in the -mm tree and it solves the issue we were seeing, so I : definitely think this should be pushed to -stable (and I would seriously : consider it for 2.6.37 inclusion even at this late date). Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reported-by: Shaohua Li <shaohua.li@intel.com> Reviewed-by: Christoph Lameter <cl@linux.com> Tested-by: Nicolas Bareil <nico@chdir.org> Cc: David Rientjes <rientjes@google.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: <stable@kernel.org> [2.6.37.1, 2.6.36.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:45:41 +08:00
if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone),
i, 0))
all_zones_ok = false;
else
balanced += zone->present_pages;
}
/*
* For high-order requests, the balanced zones must contain at least
* 25% of the nodes pages for kswapd to sleep. For order-0, all zones
* must be balanced
*/
if (order)
return pgdat_balanced(pgdat, balanced, classzone_idx);
else
return all_zones_ok;
}
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
* they are all at high_wmark_pages(zone).
*
* Returns the final order kswapd was reclaiming at
*
* There is special handling here for zones which are full of pinned pages.
* This can happen if the pages are all mlocked, or if they are all used by
* device drivers (say, ZONE_DMA). Or if they are all in use by hugetlb.
* What we do is to detect the case where all pages in the zone have been
* scanned twice and there has been zero successful reclaim. Mark the zone as
* dead and from now on, only perform a short scan. Basically we're polling
* the zone for when the problem goes away.
*
* kswapd scans the zones in the highmem->normal->dma direction. It skips
* zones which have free_pages > high_wmark_pages(zone), but once a zone is
* found to have free_pages <= high_wmark_pages(zone), we scan that zone and the
* lower zones regardless of the number of free pages in the lower zones. This
* interoperates with the page allocator fallback scheme to ensure that aging
* of pages is balanced across the zones.
*/
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
int *classzone_idx)
{
int all_zones_ok;
unsigned long balanced;
int i;
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */
unsigned long total_scanned;
struct reclaim_state *reclaim_state = current->reclaim_state;
memcg: count the soft_limit reclaim in global background reclaim The global kswapd scans per-zone LRU and reclaims pages regardless of the cgroup. It breaks memory isolation since one cgroup can end up reclaiming pages from another cgroup. Instead we should rely on memcg-aware target reclaim including per-memcg kswapd and soft_limit hierarchical reclaim under memory pressure. In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. This patch is the first step to skip shrink_zone() if soft_limit reclaim does enough work. This is part of the effort which tries to reduce reclaiming pages in global LRU in memcg. The per-memcg background reclaim patchset further enhances the per-cgroup targetting reclaim, which I should have V4 posted shortly. Try running multiple memory intensive workloads within seperate memcgs. Watch the counters of soft_steal in memory.stat. $ cat /dev/cgroup/A/memory.stat | grep 'soft' soft_steal 240000 soft_scan 240000 total_soft_steal 240000 total_soft_scan 240000 This patch: In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. We would like to skip shrink_zone() if soft_limit reclaim does enough work. Also, we need to make the memory pressure balanced across per-memcg zones, like the logic vm-core. This patch is the first step where we start with counting the nr_scanned and nr_reclaimed from soft_limit reclaim into the global scan_control. Signed-off-by: Ying Han <yinghan@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-27 07:25:25 +08:00
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_unmap = 1,
.may_swap = 1,
/*
* kswapd doesn't want to be bailed out while reclaim. because
* we want to put equal scanning pressure on each zone.
*/
.nr_to_reclaim = ULONG_MAX,
Lumpy Reclaim V4 When we are out of memory of a suitable size we enter reclaim. The current reclaim algorithm targets pages in LRU order, which is great for fairness at order-0 but highly unsuitable if you desire pages at higher orders. To get pages of higher order we must shoot down a very high proportion of memory; >95% in a lot of cases. This patch set adds a lumpy reclaim algorithm to the allocator. It targets groups of pages at the specified order anchored at the end of the active and inactive lists. This encourages groups of pages at the requested orders to move from active to inactive, and active to free lists. This behaviour is only triggered out of direct reclaim when higher order pages have been requested. This patch set is particularly effective when utilised with an anti-fragmentation scheme which groups pages of similar reclaimability together. This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms the foundation. Credit to Mel Gorman for sanitity checking. Mel said: The patches have an application with hugepage pool resizing. When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can be resized with greater reliability. Testing on a desktop machine with 2GB of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own was very slow as the success rate was quite low. Without lumpy-reclaim, each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages. With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical. [akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup] [bunk@stusta.de: static declarations for internal functions] [a.p.zijlstra@chello.nl: initial lumpy V2 implementation] Signed-off-by: Andy Whitcroft <apw@shadowen.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:16 +08:00
.order = order,
.target_mem_cgroup = NULL,
};
struct shrink_control shrink = {
.gfp_mask = sc.gfp_mask,
};
loop_again:
total_scanned = 0;
sc.priority = DEF_PRIORITY;
vmscan: bail out of direct reclaim after swap_cluster_max pages When the VM is under pressure, it can happen that several direct reclaim processes are in the pageout code simultaneously. It also happens that the reclaiming processes run into mostly referenced, mapped and dirty pages in the first round. This results in multiple direct reclaim processes having a lower pageout priority, which corresponds to a higher target of pages to scan. This in turn can result in each direct reclaim process freeing many pages. Together, they can end up freeing way too many pages. This kicks useful data out of memory (in some cases more than half of all memory is swapped out). It also impacts performance by keeping tasks stuck in the pageout code for too long. A 30% improvement in hackbench has been observed with this patch. The fix is relatively simple: in shrink_zone() we can check how many pages we have already freed, direct reclaim tasks break out of the scanning loop if they have already freed enough pages and have reached a lower priority level. We do not break out of shrink_zone() when priority == DEF_PRIORITY, to ensure that equal pressure is applied to every zone in the common case. However, in order to do this we do need to know how many pages we already freed, so move nr_reclaimed into scan_control. akpm: a historical interlude... We tried this in 2004: :commit e468e46a9bea3297011d5918663ce6d19094cf87 :Author: akpm <akpm> :Date: Thu Jun 24 15:53:52 2004 +0000 : :[PATCH] vmscan.c: dont reclaim too many pages : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly hit : a large number of reclaimable pages on the LRU. : Change things so we bale out when SWAP_CLUSTER_MAX pages have been reclaimed. And we reverted it in 2006: :commit 210fe530305ee50cd889fe9250168228b2994f32 :Author: Andrew Morton <akpm@osdl.org> :Date: Fri Jan 6 00:11:14 2006 -0800 : : [PATCH] vmscan: balancing fix : : Revert a patch which went into 2.6.8-rc1. The changelog for that patch was: : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly : hit a large number of reclaimable pages on the LRU. : : Change things so we bale out when SWAP_CLUSTER_MAX pages have been : reclaimed. : : Problem is, this change caused significant imbalance in inter-zone scan : balancing by truncating scans of larger zones. : : Suppose, for example, ZONE_HIGHMEM is 10x the size of ZONE_NORMAL. The zone : balancing algorithm would require that if we're scanning 100 pages of : ZONE_HIGHMEM, we should scan 10 pages of ZONE_NORMAL. But this logic will : cause the scanning of ZONE_HIGHMEM to bale out after only 32 pages are : reclaimed. Thus effectively causing smaller zones to be scanned relatively : harder than large ones. : : Now I need to remember what the workload was which caused me to write this : patch originally, then fix it up in a different way... And we haven't demonstrated that whatever problem caused that reversion is not being reintroduced by this change in 2008. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:01 +08:00
sc.nr_reclaimed = 0;
sc.may_writepage = !laptop_mode;
[PATCH] Light weight event counters The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 16:55:45 +08:00
count_vm_event(PAGEOUTRUN);
do {
unsigned long lru_pages = 0;
int has_under_min_watermark_zone = 0;
all_zones_ok = 1;
balanced = 0;
/*
* Scan in the highmem->dma direction for the highest
* zone which needs scanning
*/
for (i = pgdat->nr_zones - 1; i >= 0; i--) {
struct zone *zone = pgdat->node_zones + i;
if (!populated_zone(zone))
continue;
if (zone->all_unreclaimable &&
sc.priority != DEF_PRIORITY)
continue;
/*
* Do some background aging of the anon list, to give
* pages a chance to be referenced before reclaiming.
*/
age_active_anon(zone, &sc);
mm: vmscan: forcibly scan highmem if there are too many buffer_heads pinning highmem Stuart Foster reported on bugzilla that copying large amounts of data from NTFS caused an OOM kill on 32-bit X86 with 16G of memory. Andrew Morton correctly identified that the problem was NTFS was using 512 blocks meaning each page had 8 buffer_heads in low memory pinning it. In the past, direct reclaim used to scan highmem even if the allocating process did not specify __GFP_HIGHMEM but not any more. kswapd no longer will reclaim from zones that are above the high watermark. The intention in both cases was to minimise unnecessary reclaim. The downside is on machines with large amounts of highmem that lowmem can be fully consumed by buffer_heads with nothing trying to free them. The following patch is based on a suggestion by Andrew Morton to extend the buffer_heads_over_limit case to force kswapd and direct reclaim to scan the highmem zone regardless of the allocation request or watermarks. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=42578 [hughd@google.com: move buffer_heads_over_limit check up] [akpm@linux-foundation.org: buffer_heads_over_limit is unlikely] Reported-by: Stuart Foster <smf.linux@ntlworld.com> Tested-by: Stuart Foster <smf.linux@ntlworld.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Cc: Christoph Lameter <cl@linux.com> Cc: stable <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 07:34:00 +08:00
/*
* If the number of buffer_heads in the machine
* exceeds the maximum allowed level and this node
* has a highmem zone, force kswapd to reclaim from
* it to relieve lowmem pressure.
*/
if (buffer_heads_over_limit && is_highmem_idx(i)) {
end_zone = i;
break;
}
mm: page allocator: adjust the per-cpu counter threshold when memory is low Commit aa45484 ("calculate a better estimate of NR_FREE_PAGES when memory is low") noted that watermarks were based on the vmstat NR_FREE_PAGES. To avoid synchronization overhead, these counters are maintained on a per-cpu basis and drained both periodically and when a threshold is above a threshold. On large CPU systems, the difference between the estimate and real value of NR_FREE_PAGES can be very high. The system can get into a case where pages are allocated far below the min watermark potentially causing livelock issues. The commit solved the problem by taking a better reading of NR_FREE_PAGES when memory was low. Unfortately, as reported by Shaohua Li this accurate reading can consume a large amount of CPU time on systems with many sockets due to cache line bouncing. This patch takes a different approach. For large machines where counter drift might be unsafe and while kswapd is awake, the per-cpu thresholds for the target pgdat are reduced to limit the level of drift to what should be a safe level. This incurs a performance penalty in heavy memory pressure by a factor that depends on the workload and the machine but the machine should function correctly without accidentally exhausting all memory on a node. There is an additional cost when kswapd wakes and sleeps but the event is not expected to be frequent - in Shaohua's test case, there was one recorded sleep and wake event at least. To ensure that kswapd wakes up, a safe version of zone_watermark_ok() is introduced that takes a more accurate reading of NR_FREE_PAGES when called from wakeup_kswapd, when deciding whether it is really safe to go back to sleep in sleeping_prematurely() and when deciding if a zone is really balanced or not in balance_pgdat(). We are still using an expensive function but limiting how often it is called. When the test case is reproduced, the time spent in the watermark functions is reduced. The following report is on the percentage of time spent cumulatively spent in the functions zone_nr_free_pages(), zone_watermark_ok(), __zone_watermark_ok(), zone_watermark_ok_safe(), zone_page_state_snapshot(), zone_page_state(). vanilla 11.6615% disable-threshold 0.2584% David said: : We had to pull aa454840 "mm: page allocator: calculate a better estimate : of NR_FREE_PAGES when memory is low and kswapd is awake" from 2.6.36 : internally because tests showed that it would cause the machine to stall : as the result of heavy kswapd activity. I merged it back with this fix as : it is pending in the -mm tree and it solves the issue we were seeing, so I : definitely think this should be pushed to -stable (and I would seriously : consider it for 2.6.37 inclusion even at this late date). Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reported-by: Shaohua Li <shaohua.li@intel.com> Reviewed-by: Christoph Lameter <cl@linux.com> Tested-by: Nicolas Bareil <nico@chdir.org> Cc: David Rientjes <rientjes@google.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: <stable@kernel.org> [2.6.37.1, 2.6.36.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:45:41 +08:00
if (!zone_watermark_ok_safe(zone, order,
high_wmark_pages(zone), 0, 0)) {
end_zone = i;
break;
} else {
/* If balanced, clear the congested flag */
zone_clear_flag(zone, ZONE_CONGESTED);
}
}
if (i < 0)
goto out;
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
lru_pages += zone_reclaimable_pages(zone);
}
/*
* Now scan the zone in the dma->highmem direction, stopping
* at the last zone which needs scanning.
*
* We do this because the page allocator works in the opposite
* direction. This prevents the page allocator from allocating
* pages behind kswapd's direction of progress, which would
* cause too much scanning of the lower zones.
*/
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
int nr_slab, testorder;
mm: vmscan: kswapd should not free an excessive number of pages when balancing small zones When reclaiming for order-0 pages, kswapd requires that all zones be balanced. Each cycle through balance_pgdat() does background ageing on all zones if necessary and applies equal pressure on the inactive zone unless a lot of pages are free already. A "lot of free pages" is defined as a "balance gap" above the high watermark which is currently 7*high_watermark. Historically this was reasonable as min_free_kbytes was small. However, on systems using huge pages, it is recommended that min_free_kbytes is higher and it is tuned with hugeadm --set-recommended-min_free_kbytes. With the introduction of transparent huge page support, this recommended value is also applied. On X86-64 with 4G of memory, min_free_kbytes becomes 67584 so one would expect around 68M of memory to be free. The Normal zone is approximately 35000 pages so under even normal memory pressure such as copying a large file, it gets exhausted quickly. As it is getting exhausted, kswapd applies pressure equally to all zones, including the DMA32 zone. DMA32 is approximately 700,000 pages with a high watermark of around 23,000 pages. In this situation, kswapd will reclaim around (23000*8 where 8 is the high watermark + balance gap of 7 * high watermark) pages or 718M of pages before the zone is ignored. What the user sees is that free memory far higher than it should be. To avoid an excessive number of pages being reclaimed from the larger zones, explicitely defines the "balance gap" to be either 1% of the zone or the low watermark for the zone, whichever is smaller. While kswapd will check all zones to apply pressure, it'll ignore zones that meets the (high_wmark + balance_gap) watermark. To test this, 80G were copied from a partition and the amount of memory being used was recorded. A comparison of a patch and unpatched kernel can be seen at http://www.csn.ul.ie/~mel/postings/minfree-20110222/memory-usage-hydra.ps and shows that kswapd is not reclaiming as much memory with the patch applied. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: "Chen, Tim C" <tim.c.chen@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:04 +08:00
unsigned long balance_gap;
if (!populated_zone(zone))
continue;
if (zone->all_unreclaimable &&
sc.priority != DEF_PRIORITY)
continue;
sc.nr_scanned = 0;
2009-09-24 06:56:39 +08:00
memcg: count the soft_limit reclaim in global background reclaim The global kswapd scans per-zone LRU and reclaims pages regardless of the cgroup. It breaks memory isolation since one cgroup can end up reclaiming pages from another cgroup. Instead we should rely on memcg-aware target reclaim including per-memcg kswapd and soft_limit hierarchical reclaim under memory pressure. In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. This patch is the first step to skip shrink_zone() if soft_limit reclaim does enough work. This is part of the effort which tries to reduce reclaiming pages in global LRU in memcg. The per-memcg background reclaim patchset further enhances the per-cgroup targetting reclaim, which I should have V4 posted shortly. Try running multiple memory intensive workloads within seperate memcgs. Watch the counters of soft_steal in memory.stat. $ cat /dev/cgroup/A/memory.stat | grep 'soft' soft_steal 240000 soft_scan 240000 total_soft_steal 240000 total_soft_scan 240000 This patch: In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. We would like to skip shrink_zone() if soft_limit reclaim does enough work. Also, we need to make the memory pressure balanced across per-memcg zones, like the logic vm-core. This patch is the first step where we start with counting the nr_scanned and nr_reclaimed from soft_limit reclaim into the global scan_control. Signed-off-by: Ying Han <yinghan@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-27 07:25:25 +08:00
nr_soft_scanned = 0;
2009-09-24 06:56:39 +08:00
/*
* Call soft limit reclaim before calling shrink_zone.
*/
memcg: count the soft_limit reclaim in global background reclaim The global kswapd scans per-zone LRU and reclaims pages regardless of the cgroup. It breaks memory isolation since one cgroup can end up reclaiming pages from another cgroup. Instead we should rely on memcg-aware target reclaim including per-memcg kswapd and soft_limit hierarchical reclaim under memory pressure. In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. This patch is the first step to skip shrink_zone() if soft_limit reclaim does enough work. This is part of the effort which tries to reduce reclaiming pages in global LRU in memcg. The per-memcg background reclaim patchset further enhances the per-cgroup targetting reclaim, which I should have V4 posted shortly. Try running multiple memory intensive workloads within seperate memcgs. Watch the counters of soft_steal in memory.stat. $ cat /dev/cgroup/A/memory.stat | grep 'soft' soft_steal 240000 soft_scan 240000 total_soft_steal 240000 total_soft_scan 240000 This patch: In the global background reclaim, we do soft reclaim before scanning the per-zone LRU. However, the return value is ignored. We would like to skip shrink_zone() if soft_limit reclaim does enough work. Also, we need to make the memory pressure balanced across per-memcg zones, like the logic vm-core. This patch is the first step where we start with counting the nr_scanned and nr_reclaimed from soft_limit reclaim into the global scan_control. Signed-off-by: Ying Han <yinghan@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-27 07:25:25 +08:00
nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
order, sc.gfp_mask,
&nr_soft_scanned);
sc.nr_reclaimed += nr_soft_reclaimed;
total_scanned += nr_soft_scanned;
/*
mm: vmscan: kswapd should not free an excessive number of pages when balancing small zones When reclaiming for order-0 pages, kswapd requires that all zones be balanced. Each cycle through balance_pgdat() does background ageing on all zones if necessary and applies equal pressure on the inactive zone unless a lot of pages are free already. A "lot of free pages" is defined as a "balance gap" above the high watermark which is currently 7*high_watermark. Historically this was reasonable as min_free_kbytes was small. However, on systems using huge pages, it is recommended that min_free_kbytes is higher and it is tuned with hugeadm --set-recommended-min_free_kbytes. With the introduction of transparent huge page support, this recommended value is also applied. On X86-64 with 4G of memory, min_free_kbytes becomes 67584 so one would expect around 68M of memory to be free. The Normal zone is approximately 35000 pages so under even normal memory pressure such as copying a large file, it gets exhausted quickly. As it is getting exhausted, kswapd applies pressure equally to all zones, including the DMA32 zone. DMA32 is approximately 700,000 pages with a high watermark of around 23,000 pages. In this situation, kswapd will reclaim around (23000*8 where 8 is the high watermark + balance gap of 7 * high watermark) pages or 718M of pages before the zone is ignored. What the user sees is that free memory far higher than it should be. To avoid an excessive number of pages being reclaimed from the larger zones, explicitely defines the "balance gap" to be either 1% of the zone or the low watermark for the zone, whichever is smaller. While kswapd will check all zones to apply pressure, it'll ignore zones that meets the (high_wmark + balance_gap) watermark. To test this, 80G were copied from a partition and the amount of memory being used was recorded. A comparison of a patch and unpatched kernel can be seen at http://www.csn.ul.ie/~mel/postings/minfree-20110222/memory-usage-hydra.ps and shows that kswapd is not reclaiming as much memory with the patch applied. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: "Chen, Tim C" <tim.c.chen@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:04 +08:00
* We put equal pressure on every zone, unless
* one zone has way too many pages free
* already. The "too many pages" is defined
* as the high wmark plus a "gap" where the
* gap is either the low watermark or 1%
* of the zone, whichever is smaller.
*/
mm: vmscan: kswapd should not free an excessive number of pages when balancing small zones When reclaiming for order-0 pages, kswapd requires that all zones be balanced. Each cycle through balance_pgdat() does background ageing on all zones if necessary and applies equal pressure on the inactive zone unless a lot of pages are free already. A "lot of free pages" is defined as a "balance gap" above the high watermark which is currently 7*high_watermark. Historically this was reasonable as min_free_kbytes was small. However, on systems using huge pages, it is recommended that min_free_kbytes is higher and it is tuned with hugeadm --set-recommended-min_free_kbytes. With the introduction of transparent huge page support, this recommended value is also applied. On X86-64 with 4G of memory, min_free_kbytes becomes 67584 so one would expect around 68M of memory to be free. The Normal zone is approximately 35000 pages so under even normal memory pressure such as copying a large file, it gets exhausted quickly. As it is getting exhausted, kswapd applies pressure equally to all zones, including the DMA32 zone. DMA32 is approximately 700,000 pages with a high watermark of around 23,000 pages. In this situation, kswapd will reclaim around (23000*8 where 8 is the high watermark + balance gap of 7 * high watermark) pages or 718M of pages before the zone is ignored. What the user sees is that free memory far higher than it should be. To avoid an excessive number of pages being reclaimed from the larger zones, explicitely defines the "balance gap" to be either 1% of the zone or the low watermark for the zone, whichever is smaller. While kswapd will check all zones to apply pressure, it'll ignore zones that meets the (high_wmark + balance_gap) watermark. To test this, 80G were copied from a partition and the amount of memory being used was recorded. A comparison of a patch and unpatched kernel can be seen at http://www.csn.ul.ie/~mel/postings/minfree-20110222/memory-usage-hydra.ps and shows that kswapd is not reclaiming as much memory with the patch applied. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: "Chen, Tim C" <tim.c.chen@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:04 +08:00
balance_gap = min(low_wmark_pages(zone),
(zone->present_pages +
KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
KSWAPD_ZONE_BALANCE_GAP_RATIO);
/*
* Kswapd reclaims only single pages with compaction
* enabled. Trying too hard to reclaim until contiguous
* free pages have become available can hurt performance
* by evicting too much useful data from memory.
* Do not reclaim more than needed for compaction.
*/
testorder = order;
if (COMPACTION_BUILD && order &&
compaction_suitable(zone, order) !=
COMPACT_SKIPPED)
testorder = 0;
mm: vmscan: forcibly scan highmem if there are too many buffer_heads pinning highmem Stuart Foster reported on bugzilla that copying large amounts of data from NTFS caused an OOM kill on 32-bit X86 with 16G of memory. Andrew Morton correctly identified that the problem was NTFS was using 512 blocks meaning each page had 8 buffer_heads in low memory pinning it. In the past, direct reclaim used to scan highmem even if the allocating process did not specify __GFP_HIGHMEM but not any more. kswapd no longer will reclaim from zones that are above the high watermark. The intention in both cases was to minimise unnecessary reclaim. The downside is on machines with large amounts of highmem that lowmem can be fully consumed by buffer_heads with nothing trying to free them. The following patch is based on a suggestion by Andrew Morton to extend the buffer_heads_over_limit case to force kswapd and direct reclaim to scan the highmem zone regardless of the allocation request or watermarks. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=42578 [hughd@google.com: move buffer_heads_over_limit check up] [akpm@linux-foundation.org: buffer_heads_over_limit is unlikely] Reported-by: Stuart Foster <smf.linux@ntlworld.com> Tested-by: Stuart Foster <smf.linux@ntlworld.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Cc: Christoph Lameter <cl@linux.com> Cc: stable <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 07:34:00 +08:00
if ((buffer_heads_over_limit && is_highmem_idx(i)) ||
!zone_watermark_ok_safe(zone, testorder,
mm: vmscan: kswapd should not free an excessive number of pages when balancing small zones When reclaiming for order-0 pages, kswapd requires that all zones be balanced. Each cycle through balance_pgdat() does background ageing on all zones if necessary and applies equal pressure on the inactive zone unless a lot of pages are free already. A "lot of free pages" is defined as a "balance gap" above the high watermark which is currently 7*high_watermark. Historically this was reasonable as min_free_kbytes was small. However, on systems using huge pages, it is recommended that min_free_kbytes is higher and it is tuned with hugeadm --set-recommended-min_free_kbytes. With the introduction of transparent huge page support, this recommended value is also applied. On X86-64 with 4G of memory, min_free_kbytes becomes 67584 so one would expect around 68M of memory to be free. The Normal zone is approximately 35000 pages so under even normal memory pressure such as copying a large file, it gets exhausted quickly. As it is getting exhausted, kswapd applies pressure equally to all zones, including the DMA32 zone. DMA32 is approximately 700,000 pages with a high watermark of around 23,000 pages. In this situation, kswapd will reclaim around (23000*8 where 8 is the high watermark + balance gap of 7 * high watermark) pages or 718M of pages before the zone is ignored. What the user sees is that free memory far higher than it should be. To avoid an excessive number of pages being reclaimed from the larger zones, explicitely defines the "balance gap" to be either 1% of the zone or the low watermark for the zone, whichever is smaller. While kswapd will check all zones to apply pressure, it'll ignore zones that meets the (high_wmark + balance_gap) watermark. To test this, 80G were copied from a partition and the amount of memory being used was recorded. A comparison of a patch and unpatched kernel can be seen at http://www.csn.ul.ie/~mel/postings/minfree-20110222/memory-usage-hydra.ps and shows that kswapd is not reclaiming as much memory with the patch applied. Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: "Chen, Tim C" <tim.c.chen@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:04 +08:00
high_wmark_pages(zone) + balance_gap,
end_zone, 0)) {
shrink_zone(zone, &sc);
reclaim_state->reclaimed_slab = 0;
nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages);
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
total_scanned += sc.nr_scanned;
if (nr_slab == 0 && !zone_reclaimable(zone))
zone->all_unreclaimable = 1;
}
/*
* If we've done a decent amount of scanning and
* the reclaim ratio is low, start doing writepage
* even in laptop mode
*/
if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
vmscan: bail out of direct reclaim after swap_cluster_max pages When the VM is under pressure, it can happen that several direct reclaim processes are in the pageout code simultaneously. It also happens that the reclaiming processes run into mostly referenced, mapped and dirty pages in the first round. This results in multiple direct reclaim processes having a lower pageout priority, which corresponds to a higher target of pages to scan. This in turn can result in each direct reclaim process freeing many pages. Together, they can end up freeing way too many pages. This kicks useful data out of memory (in some cases more than half of all memory is swapped out). It also impacts performance by keeping tasks stuck in the pageout code for too long. A 30% improvement in hackbench has been observed with this patch. The fix is relatively simple: in shrink_zone() we can check how many pages we have already freed, direct reclaim tasks break out of the scanning loop if they have already freed enough pages and have reached a lower priority level. We do not break out of shrink_zone() when priority == DEF_PRIORITY, to ensure that equal pressure is applied to every zone in the common case. However, in order to do this we do need to know how many pages we already freed, so move nr_reclaimed into scan_control. akpm: a historical interlude... We tried this in 2004: :commit e468e46a9bea3297011d5918663ce6d19094cf87 :Author: akpm <akpm> :Date: Thu Jun 24 15:53:52 2004 +0000 : :[PATCH] vmscan.c: dont reclaim too many pages : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly hit : a large number of reclaimable pages on the LRU. : Change things so we bale out when SWAP_CLUSTER_MAX pages have been reclaimed. And we reverted it in 2006: :commit 210fe530305ee50cd889fe9250168228b2994f32 :Author: Andrew Morton <akpm@osdl.org> :Date: Fri Jan 6 00:11:14 2006 -0800 : : [PATCH] vmscan: balancing fix : : Revert a patch which went into 2.6.8-rc1. The changelog for that patch was: : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly : hit a large number of reclaimable pages on the LRU. : : Change things so we bale out when SWAP_CLUSTER_MAX pages have been : reclaimed. : : Problem is, this change caused significant imbalance in inter-zone scan : balancing by truncating scans of larger zones. : : Suppose, for example, ZONE_HIGHMEM is 10x the size of ZONE_NORMAL. The zone : balancing algorithm would require that if we're scanning 100 pages of : ZONE_HIGHMEM, we should scan 10 pages of ZONE_NORMAL. But this logic will : cause the scanning of ZONE_HIGHMEM to bale out after only 32 pages are : reclaimed. Thus effectively causing smaller zones to be scanned relatively : harder than large ones. : : Now I need to remember what the workload was which caused me to write this : patch originally, then fix it up in a different way... And we haven't demonstrated that whatever problem caused that reversion is not being reintroduced by this change in 2008. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:01 +08:00
total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
sc.may_writepage = 1;
mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. When balance_pgdat() returns, it may be at a lower classzone_idx than it started because the highest zone was unreclaimable. Before checking if it should go to sleep though, it checks pgdat->classzone_idx which when there is no other activity will be MAX_NR_ZONES-1. It interprets this as it has been woken up while reclaiming, skips scheduling and reclaims again. As there is no useful reclaim work to do, it enters into a loop of shrinking slab consuming loads of CPU until the highest zone becomes reclaimable for a long period of time. There are two problems here. 1) If the returned classzone or order is lower, it'll continue reclaiming without scheduling. 2) if the highest zone was marked unreclaimable but balance_pgdat() returns immediately at DEF_PRIORITY, the new lower classzone is not communicated back to kswapd() for sleeping. This patch does two things that are related. If the end_zone is unreclaimable, this information is communicated back. Second, if the classzone or order was reduced due to failing to reclaim, new information is not read from pgdat and instead an attempt is made to go to sleep. Due to this, it is also necessary that pgdat->classzone_idx be initialised each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as wakeups. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Pádraig Brady <P@draigBrady.com> Tested-by: Pádraig Brady <P@draigBrady.com> Tested-by: Andrew Lutomirski <luto@mit.edu> Acked-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-09 06:39:40 +08:00
if (zone->all_unreclaimable) {
if (end_zone && end_zone == i)
end_zone--;
continue;
mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. When balance_pgdat() returns, it may be at a lower classzone_idx than it started because the highest zone was unreclaimable. Before checking if it should go to sleep though, it checks pgdat->classzone_idx which when there is no other activity will be MAX_NR_ZONES-1. It interprets this as it has been woken up while reclaiming, skips scheduling and reclaims again. As there is no useful reclaim work to do, it enters into a loop of shrinking slab consuming loads of CPU until the highest zone becomes reclaimable for a long period of time. There are two problems here. 1) If the returned classzone or order is lower, it'll continue reclaiming without scheduling. 2) if the highest zone was marked unreclaimable but balance_pgdat() returns immediately at DEF_PRIORITY, the new lower classzone is not communicated back to kswapd() for sleeping. This patch does two things that are related. If the end_zone is unreclaimable, this information is communicated back. Second, if the classzone or order was reduced due to failing to reclaim, new information is not read from pgdat and instead an attempt is made to go to sleep. Due to this, it is also necessary that pgdat->classzone_idx be initialised each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as wakeups. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Pádraig Brady <P@draigBrady.com> Tested-by: Pádraig Brady <P@draigBrady.com> Tested-by: Andrew Lutomirski <luto@mit.edu> Acked-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-09 06:39:40 +08:00
}
if (!zone_watermark_ok_safe(zone, testorder,
high_wmark_pages(zone), end_zone, 0)) {
all_zones_ok = 0;
/*
* We are still under min water mark. This
* means that we have a GFP_ATOMIC allocation
* failure risk. Hurry up!
*/
mm: page allocator: adjust the per-cpu counter threshold when memory is low Commit aa45484 ("calculate a better estimate of NR_FREE_PAGES when memory is low") noted that watermarks were based on the vmstat NR_FREE_PAGES. To avoid synchronization overhead, these counters are maintained on a per-cpu basis and drained both periodically and when a threshold is above a threshold. On large CPU systems, the difference between the estimate and real value of NR_FREE_PAGES can be very high. The system can get into a case where pages are allocated far below the min watermark potentially causing livelock issues. The commit solved the problem by taking a better reading of NR_FREE_PAGES when memory was low. Unfortately, as reported by Shaohua Li this accurate reading can consume a large amount of CPU time on systems with many sockets due to cache line bouncing. This patch takes a different approach. For large machines where counter drift might be unsafe and while kswapd is awake, the per-cpu thresholds for the target pgdat are reduced to limit the level of drift to what should be a safe level. This incurs a performance penalty in heavy memory pressure by a factor that depends on the workload and the machine but the machine should function correctly without accidentally exhausting all memory on a node. There is an additional cost when kswapd wakes and sleeps but the event is not expected to be frequent - in Shaohua's test case, there was one recorded sleep and wake event at least. To ensure that kswapd wakes up, a safe version of zone_watermark_ok() is introduced that takes a more accurate reading of NR_FREE_PAGES when called from wakeup_kswapd, when deciding whether it is really safe to go back to sleep in sleeping_prematurely() and when deciding if a zone is really balanced or not in balance_pgdat(). We are still using an expensive function but limiting how often it is called. When the test case is reproduced, the time spent in the watermark functions is reduced. The following report is on the percentage of time spent cumulatively spent in the functions zone_nr_free_pages(), zone_watermark_ok(), __zone_watermark_ok(), zone_watermark_ok_safe(), zone_page_state_snapshot(), zone_page_state(). vanilla 11.6615% disable-threshold 0.2584% David said: : We had to pull aa454840 "mm: page allocator: calculate a better estimate : of NR_FREE_PAGES when memory is low and kswapd is awake" from 2.6.36 : internally because tests showed that it would cause the machine to stall : as the result of heavy kswapd activity. I merged it back with this fix as : it is pending in the -mm tree and it solves the issue we were seeing, so I : definitely think this should be pushed to -stable (and I would seriously : consider it for 2.6.37 inclusion even at this late date). Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reported-by: Shaohua Li <shaohua.li@intel.com> Reviewed-by: Christoph Lameter <cl@linux.com> Tested-by: Nicolas Bareil <nico@chdir.org> Cc: David Rientjes <rientjes@google.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: <stable@kernel.org> [2.6.37.1, 2.6.36.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:45:41 +08:00
if (!zone_watermark_ok_safe(zone, order,
min_wmark_pages(zone), end_zone, 0))
has_under_min_watermark_zone = 1;
} else {
/*
* If a zone reaches its high watermark,
* consider it to be no longer congested. It's
* possible there are dirty pages backed by
* congested BDIs but as pressure is relieved,
* speculatively avoid congestion waits
*/
zone_clear_flag(zone, ZONE_CONGESTED);
if (i <= *classzone_idx)
balanced += zone->present_pages;
}
}
/*
* If the low watermark is met there is no need for processes
* to be throttled on pfmemalloc_wait as they should not be
* able to safely make forward progress. Wake them
*/
if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
pfmemalloc_watermark_ok(pgdat))
wake_up(&pgdat->pfmemalloc_wait);
if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))
break; /* kswapd: all done */
/*
* OK, kswapd is getting into trouble. Take a nap, then take
* another pass across the zones.
*/
if (total_scanned && (sc.priority < DEF_PRIORITY - 2)) {
if (has_under_min_watermark_zone)
count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT);
else
congestion_wait(BLK_RW_ASYNC, HZ/10);
}
/*
* We do this so kswapd doesn't build up large priorities for
* example when it is freeing in parallel with allocators. It
* matches the direct reclaim path behaviour in terms of impact
* on zone->*_priority.
*/
vmscan: bail out of direct reclaim after swap_cluster_max pages When the VM is under pressure, it can happen that several direct reclaim processes are in the pageout code simultaneously. It also happens that the reclaiming processes run into mostly referenced, mapped and dirty pages in the first round. This results in multiple direct reclaim processes having a lower pageout priority, which corresponds to a higher target of pages to scan. This in turn can result in each direct reclaim process freeing many pages. Together, they can end up freeing way too many pages. This kicks useful data out of memory (in some cases more than half of all memory is swapped out). It also impacts performance by keeping tasks stuck in the pageout code for too long. A 30% improvement in hackbench has been observed with this patch. The fix is relatively simple: in shrink_zone() we can check how many pages we have already freed, direct reclaim tasks break out of the scanning loop if they have already freed enough pages and have reached a lower priority level. We do not break out of shrink_zone() when priority == DEF_PRIORITY, to ensure that equal pressure is applied to every zone in the common case. However, in order to do this we do need to know how many pages we already freed, so move nr_reclaimed into scan_control. akpm: a historical interlude... We tried this in 2004: :commit e468e46a9bea3297011d5918663ce6d19094cf87 :Author: akpm <akpm> :Date: Thu Jun 24 15:53:52 2004 +0000 : :[PATCH] vmscan.c: dont reclaim too many pages : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly hit : a large number of reclaimable pages on the LRU. : Change things so we bale out when SWAP_CLUSTER_MAX pages have been reclaimed. And we reverted it in 2006: :commit 210fe530305ee50cd889fe9250168228b2994f32 :Author: Andrew Morton <akpm@osdl.org> :Date: Fri Jan 6 00:11:14 2006 -0800 : : [PATCH] vmscan: balancing fix : : Revert a patch which went into 2.6.8-rc1. The changelog for that patch was: : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly : hit a large number of reclaimable pages on the LRU. : : Change things so we bale out when SWAP_CLUSTER_MAX pages have been : reclaimed. : : Problem is, this change caused significant imbalance in inter-zone scan : balancing by truncating scans of larger zones. : : Suppose, for example, ZONE_HIGHMEM is 10x the size of ZONE_NORMAL. The zone : balancing algorithm would require that if we're scanning 100 pages of : ZONE_HIGHMEM, we should scan 10 pages of ZONE_NORMAL. But this logic will : cause the scanning of ZONE_HIGHMEM to bale out after only 32 pages are : reclaimed. Thus effectively causing smaller zones to be scanned relatively : harder than large ones. : : Now I need to remember what the workload was which caused me to write this : patch originally, then fix it up in a different way... And we haven't demonstrated that whatever problem caused that reversion is not being reintroduced by this change in 2008. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:01 +08:00
if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX)
break;
} while (--sc.priority >= 0);
out:
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
/*
* order-0: All zones must meet high watermark for a balanced node
* high-order: Balanced zones must make up at least 25% of the node
* for the node to be balanced
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
*/
if (!(all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))) {
cond_resched();
[PATCH] swsusp: Improve handling of highmem Currently swsusp saves the contents of highmem pages by copying them to the normal zone which is quite inefficient (eg. it requires two normal pages to be used for saving one highmem page). This may be improved by using highmem for saving the contents of saveable highmem pages. Namely, during the suspend phase of the suspend-resume cycle we try to allocate as many free highmem pages as there are saveable highmem pages. If there are not enough highmem image pages to store the contents of all of the saveable highmem pages, some of them will be stored in the "normal" memory. Next, we allocate as many free "normal" pages as needed to store the (remaining) image data. We use a memory bitmap to mark the allocated free pages (ie. highmem as well as "normal" image pages). Now, we use another memory bitmap to mark all of the saveable pages (highmem as well as "normal") and the contents of the saveable pages are copied into the image pages. Then, the second bitmap is used to save the pfns corresponding to the saveable pages and the first one is used to save their data. During the resume phase the pfns of the pages that were saveable during the suspend are loaded from the image and used to mark the "unsafe" page frames. Next, we try to allocate as many free highmem page frames as to load all of the image data that had been in the highmem before the suspend and we allocate so many free "normal" page frames that the total number of allocated free pages (highmem and "normal") is equal to the size of the image. While doing this we have to make sure that there will be some extra free "normal" and "safe" page frames for two lists of PBEs constructed later. Now, the image data are loaded, if possible, into their "original" page frames. The image data that cannot be written into their "original" page frames are loaded into "safe" page frames and their "original" kernel virtual addresses, as well as the addresses of the "safe" pages containing their copies, are stored in one of two lists of PBEs. One list of PBEs is for the copies of "normal" suspend pages (ie. "normal" pages that were saveable during the suspend) and it is used in the same way as previously (ie. by the architecture-dependent parts of swsusp). The other list of PBEs is for the copies of highmem suspend pages. The pages in this list are restored (in a reversible way) right before the arch-dependent code is called. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 12:34:18 +08:00
try_to_freeze();
/*
* Fragmentation may mean that the system cannot be
* rebalanced for high-order allocations in all zones.
* At this point, if nr_reclaimed < SWAP_CLUSTER_MAX,
* it means the zones have been fully scanned and are still
* not balanced. For high-order allocations, there is
* little point trying all over again as kswapd may
* infinite loop.
*
* Instead, recheck all watermarks at order-0 as they
* are the most important. If watermarks are ok, kswapd will go
* back to sleep. High-order users can still perform direct
* reclaim if they wish.
*/
if (sc.nr_reclaimed < SWAP_CLUSTER_MAX)
order = sc.order = 0;
goto loop_again;
}
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
/*
* If kswapd was reclaiming at a higher order, it has the option of
* sleeping without all zones being balanced. Before it does, it must
* ensure that the watermarks for order-0 on *all* zones are met and
* that the congestion flags are cleared. The congestion flag must
* be cleared as kswapd is the only mechanism that clears the flag
* and it is potentially going to sleep here.
*/
if (order) {
int zones_need_compaction = 1;
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
if (!populated_zone(zone))
continue;
if (zone->all_unreclaimable &&
sc.priority != DEF_PRIORITY)
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
continue;
/* Would compaction fail due to lack of free memory? */
if (COMPACTION_BUILD &&
compaction_suitable(zone, order) == COMPACT_SKIPPED)
goto loop_again;
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
/* Confirm the zone is balanced for order-0 */
if (!zone_watermark_ok(zone, 0,
high_wmark_pages(zone), 0, 0)) {
order = sc.order = 0;
goto loop_again;
}
/* Check if the memory needs to be defragmented. */
if (zone_watermark_ok(zone, order,
low_wmark_pages(zone), *classzone_idx, 0))
zones_need_compaction = 0;
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
/* If balanced, clear the congested flag */
zone_clear_flag(zone, ZONE_CONGESTED);
}
if (zones_need_compaction)
compact_pgdat(pgdat, order);
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
}
/*
* Return the order we were reclaiming at so prepare_kswapd_sleep()
* makes a decision on the order we were last reclaiming at. However,
* if another caller entered the allocator slow path while kswapd
* was awake, order will remain at the higher level
*/
*classzone_idx = end_zone;
return order;
}
static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
{
long remaining = 0;
DEFINE_WAIT(wait);
if (freezing(current) || kthread_should_stop())
return;
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
/* Try to sleep for a short interval */
if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
remaining = schedule_timeout(HZ/10);
finish_wait(&pgdat->kswapd_wait, &wait);
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
}
/*
* After a short sleep, check if it was a premature sleep. If not, then
* go fully to sleep until explicitly woken up.
*/
if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
/*
* vmstat counters are not perfectly accurate and the estimated
* value for counters such as NR_FREE_PAGES can deviate from the
* true value by nr_online_cpus * threshold. To avoid the zone
* watermarks being breached while under pressure, we reduce the
* per-cpu vmstat threshold while kswapd is awake and restore
* them before going back to sleep.
*/
set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
if (!kthread_should_stop())
schedule();
set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
} else {
if (remaining)
count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
else
count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
}
finish_wait(&pgdat->kswapd_wait, &wait);
}
/*
* The background pageout daemon, started as a kernel thread
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
* from the init process.
*
* This basically trickles out pages so that we have _some_
* free memory available even if there is no other activity
* that frees anything up. This is needed for things like routing
* etc, where we otherwise might have all activity going on in
* asynchronous contexts that cannot page things out.
*
* If there are applications that are active memory-allocators
* (most normal use), this basically shouldn't matter.
*/
static int kswapd(void *p)
{
mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. When balance_pgdat() returns, it may be at a lower classzone_idx than it started because the highest zone was unreclaimable. Before checking if it should go to sleep though, it checks pgdat->classzone_idx which when there is no other activity will be MAX_NR_ZONES-1. It interprets this as it has been woken up while reclaiming, skips scheduling and reclaims again. As there is no useful reclaim work to do, it enters into a loop of shrinking slab consuming loads of CPU until the highest zone becomes reclaimable for a long period of time. There are two problems here. 1) If the returned classzone or order is lower, it'll continue reclaiming without scheduling. 2) if the highest zone was marked unreclaimable but balance_pgdat() returns immediately at DEF_PRIORITY, the new lower classzone is not communicated back to kswapd() for sleeping. This patch does two things that are related. If the end_zone is unreclaimable, this information is communicated back. Second, if the classzone or order was reduced due to failing to reclaim, new information is not read from pgdat and instead an attempt is made to go to sleep. Due to this, it is also necessary that pgdat->classzone_idx be initialised each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as wakeups. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Pádraig Brady <P@draigBrady.com> Tested-by: Pádraig Brady <P@draigBrady.com> Tested-by: Andrew Lutomirski <luto@mit.edu> Acked-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-09 06:39:40 +08:00
unsigned long order, new_order;
unsigned balanced_order;
mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. When balance_pgdat() returns, it may be at a lower classzone_idx than it started because the highest zone was unreclaimable. Before checking if it should go to sleep though, it checks pgdat->classzone_idx which when there is no other activity will be MAX_NR_ZONES-1. It interprets this as it has been woken up while reclaiming, skips scheduling and reclaims again. As there is no useful reclaim work to do, it enters into a loop of shrinking slab consuming loads of CPU until the highest zone becomes reclaimable for a long period of time. There are two problems here. 1) If the returned classzone or order is lower, it'll continue reclaiming without scheduling. 2) if the highest zone was marked unreclaimable but balance_pgdat() returns immediately at DEF_PRIORITY, the new lower classzone is not communicated back to kswapd() for sleeping. This patch does two things that are related. If the end_zone is unreclaimable, this information is communicated back. Second, if the classzone or order was reduced due to failing to reclaim, new information is not read from pgdat and instead an attempt is made to go to sleep. Due to this, it is also necessary that pgdat->classzone_idx be initialised each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as wakeups. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Pádraig Brady <P@draigBrady.com> Tested-by: Pádraig Brady <P@draigBrady.com> Tested-by: Andrew Lutomirski <luto@mit.edu> Acked-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-09 06:39:40 +08:00
int classzone_idx, new_classzone_idx;
int balanced_classzone_idx;
pg_data_t *pgdat = (pg_data_t*)p;
struct task_struct *tsk = current;
struct reclaim_state reclaim_state = {
.reclaimed_slab = 0,
};
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
lockdep: annotate reclaim context (__GFP_NOFS) Here is another version, with the incremental patch rolled up, and added reclaim context annotation to kswapd, and allocation tracing to slab allocators (which may only ever reach the page allocator in rare cases, so it is good to put annotations here too). Haven't tested this version as such, but it should be getting closer to merge worthy ;) -- After noticing some code in mm/filemap.c accidentally perform a __GFP_FS allocation when it should not have been, I thought it might be a good idea to try to catch this kind of thing with lockdep. I coded up a little idea that seems to work. Unfortunately the system has to actually be in __GFP_FS page reclaim, then take the lock, before it will mark it. But at least that might still be some orders of magnitude more common (and more debuggable) than an actual deadlock condition, so we have some improvement I hope (the concept is no less complete than discovery of a lock's interrupt contexts). I guess we could even do the same thing with __GFP_IO (normal reclaim), and even GFP_NOIO locks too... but filesystems will have the most locks and fiddly code paths, so let's start there and see how it goes. It *seems* to work. I did a quick test. ================================= [ INFO: inconsistent lock state ] 2.6.28-rc6-00007-ged31348-dirty #26 --------------------------------- inconsistent {in-reclaim-W} -> {ov-reclaim-W} usage. modprobe/8526 [HC0[0]:SC0[0]:HE1:SE1] takes: (testlock){--..}, at: [<ffffffffa0020055>] brd_init+0x55/0x216 [brd] {in-reclaim-W} state was registered at: [<ffffffff80267bdb>] __lock_acquire+0x75b/0x1a60 [<ffffffff80268f71>] lock_acquire+0x91/0xc0 [<ffffffff8070f0e1>] mutex_lock_nested+0xb1/0x310 [<ffffffffa002002b>] brd_init+0x2b/0x216 [brd] [<ffffffff8020903b>] _stext+0x3b/0x170 [<ffffffff80272ebf>] sys_init_module+0xaf/0x1e0 [<ffffffff8020c3fb>] system_call_fastpath+0x16/0x1b [<ffffffffffffffff>] 0xffffffffffffffff irq event stamp: 3929 hardirqs last enabled at (3929): [<ffffffff8070f2b5>] mutex_lock_nested+0x285/0x310 hardirqs last disabled at (3928): [<ffffffff8070f089>] mutex_lock_nested+0x59/0x310 softirqs last enabled at (3732): [<ffffffff8061f623>] sk_filter+0x83/0xe0 softirqs last disabled at (3730): [<ffffffff8061f5b6>] sk_filter+0x16/0xe0 other info that might help us debug this: 1 lock held by modprobe/8526: #0: (testlock){--..}, at: [<ffffffffa0020055>] brd_init+0x55/0x216 [brd] stack backtrace: Pid: 8526, comm: modprobe Not tainted 2.6.28-rc6-00007-ged31348-dirty #26 Call Trace: [<ffffffff80265483>] print_usage_bug+0x193/0x1d0 [<ffffffff80266530>] mark_lock+0xaf0/0xca0 [<ffffffff80266735>] mark_held_locks+0x55/0xc0 [<ffffffffa0020000>] ? brd_init+0x0/0x216 [brd] [<ffffffff802667ca>] trace_reclaim_fs+0x2a/0x60 [<ffffffff80285005>] __alloc_pages_internal+0x475/0x580 [<ffffffff8070f29e>] ? mutex_lock_nested+0x26e/0x310 [<ffffffffa0020000>] ? brd_init+0x0/0x216 [brd] [<ffffffffa002006a>] brd_init+0x6a/0x216 [brd] [<ffffffffa0020000>] ? brd_init+0x0/0x216 [brd] [<ffffffff8020903b>] _stext+0x3b/0x170 [<ffffffff8070f8b9>] ? mutex_unlock+0x9/0x10 [<ffffffff8070f83d>] ? __mutex_unlock_slowpath+0x10d/0x180 [<ffffffff802669ec>] ? trace_hardirqs_on_caller+0x12c/0x190 [<ffffffff80272ebf>] sys_init_module+0xaf/0x1e0 [<ffffffff8020c3fb>] system_call_fastpath+0x16/0x1b Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-21 15:12:39 +08:00
lockdep_set_current_reclaim_state(GFP_KERNEL);
if (!cpumask_empty(cpumask))
set_cpus_allowed_ptr(tsk, cpumask);
current->reclaim_state = &reclaim_state;
/*
* Tell the memory management that we're a "memory allocator",
* and that if we need more memory we should get access to it
* regardless (see "__alloc_pages()"). "kswapd" should
* never get caught in the normal page freeing logic.
*
* (Kswapd normally doesn't need memory anyway, but sometimes
* you need a small amount of memory in order to be able to
* page out something else, and this flag essentially protects
* us from recursively trying to free more memory as we're
* trying to free the first piece of memory in the first place).
*/
tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
set_freezable();
mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. When balance_pgdat() returns, it may be at a lower classzone_idx than it started because the highest zone was unreclaimable. Before checking if it should go to sleep though, it checks pgdat->classzone_idx which when there is no other activity will be MAX_NR_ZONES-1. It interprets this as it has been woken up while reclaiming, skips scheduling and reclaims again. As there is no useful reclaim work to do, it enters into a loop of shrinking slab consuming loads of CPU until the highest zone becomes reclaimable for a long period of time. There are two problems here. 1) If the returned classzone or order is lower, it'll continue reclaiming without scheduling. 2) if the highest zone was marked unreclaimable but balance_pgdat() returns immediately at DEF_PRIORITY, the new lower classzone is not communicated back to kswapd() for sleeping. This patch does two things that are related. If the end_zone is unreclaimable, this information is communicated back. Second, if the classzone or order was reduced due to failing to reclaim, new information is not read from pgdat and instead an attempt is made to go to sleep. Due to this, it is also necessary that pgdat->classzone_idx be initialised each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as wakeups. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Pádraig Brady <P@draigBrady.com> Tested-by: Pádraig Brady <P@draigBrady.com> Tested-by: Andrew Lutomirski <luto@mit.edu> Acked-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-09 06:39:40 +08:00
order = new_order = 0;
balanced_order = 0;
mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. When balance_pgdat() returns, it may be at a lower classzone_idx than it started because the highest zone was unreclaimable. Before checking if it should go to sleep though, it checks pgdat->classzone_idx which when there is no other activity will be MAX_NR_ZONES-1. It interprets this as it has been woken up while reclaiming, skips scheduling and reclaims again. As there is no useful reclaim work to do, it enters into a loop of shrinking slab consuming loads of CPU until the highest zone becomes reclaimable for a long period of time. There are two problems here. 1) If the returned classzone or order is lower, it'll continue reclaiming without scheduling. 2) if the highest zone was marked unreclaimable but balance_pgdat() returns immediately at DEF_PRIORITY, the new lower classzone is not communicated back to kswapd() for sleeping. This patch does two things that are related. If the end_zone is unreclaimable, this information is communicated back. Second, if the classzone or order was reduced due to failing to reclaim, new information is not read from pgdat and instead an attempt is made to go to sleep. Due to this, it is also necessary that pgdat->classzone_idx be initialised each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as wakeups. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Pádraig Brady <P@draigBrady.com> Tested-by: Pádraig Brady <P@draigBrady.com> Tested-by: Andrew Lutomirski <luto@mit.edu> Acked-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-09 06:39:40 +08:00
classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
balanced_classzone_idx = classzone_idx;
for ( ; ; ) {
int ret;
mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. When balance_pgdat() returns, it may be at a lower classzone_idx than it started because the highest zone was unreclaimable. Before checking if it should go to sleep though, it checks pgdat->classzone_idx which when there is no other activity will be MAX_NR_ZONES-1. It interprets this as it has been woken up while reclaiming, skips scheduling and reclaims again. As there is no useful reclaim work to do, it enters into a loop of shrinking slab consuming loads of CPU until the highest zone becomes reclaimable for a long period of time. There are two problems here. 1) If the returned classzone or order is lower, it'll continue reclaiming without scheduling. 2) if the highest zone was marked unreclaimable but balance_pgdat() returns immediately at DEF_PRIORITY, the new lower classzone is not communicated back to kswapd() for sleeping. This patch does two things that are related. If the end_zone is unreclaimable, this information is communicated back. Second, if the classzone or order was reduced due to failing to reclaim, new information is not read from pgdat and instead an attempt is made to go to sleep. Due to this, it is also necessary that pgdat->classzone_idx be initialised each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as wakeups. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Pádraig Brady <P@draigBrady.com> Tested-by: Pádraig Brady <P@draigBrady.com> Tested-by: Andrew Lutomirski <luto@mit.edu> Acked-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-09 06:39:40 +08:00
/*
* If the last balance_pgdat was unsuccessful it's unlikely a
* new request of a similar or harder type will succeed soon
* so consider going to sleep on the basis we reclaimed at
*/
if (balanced_classzone_idx >= new_classzone_idx &&
balanced_order == new_order) {
mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. When balance_pgdat() returns, it may be at a lower classzone_idx than it started because the highest zone was unreclaimable. Before checking if it should go to sleep though, it checks pgdat->classzone_idx which when there is no other activity will be MAX_NR_ZONES-1. It interprets this as it has been woken up while reclaiming, skips scheduling and reclaims again. As there is no useful reclaim work to do, it enters into a loop of shrinking slab consuming loads of CPU until the highest zone becomes reclaimable for a long period of time. There are two problems here. 1) If the returned classzone or order is lower, it'll continue reclaiming without scheduling. 2) if the highest zone was marked unreclaimable but balance_pgdat() returns immediately at DEF_PRIORITY, the new lower classzone is not communicated back to kswapd() for sleeping. This patch does two things that are related. If the end_zone is unreclaimable, this information is communicated back. Second, if the classzone or order was reduced due to failing to reclaim, new information is not read from pgdat and instead an attempt is made to go to sleep. Due to this, it is also necessary that pgdat->classzone_idx be initialised each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as wakeups. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Pádraig Brady <P@draigBrady.com> Tested-by: Pádraig Brady <P@draigBrady.com> Tested-by: Andrew Lutomirski <luto@mit.edu> Acked-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-09 06:39:40 +08:00
new_order = pgdat->kswapd_max_order;
new_classzone_idx = pgdat->classzone_idx;
pgdat->kswapd_max_order = 0;
pgdat->classzone_idx = pgdat->nr_zones - 1;
}
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
if (order < new_order || classzone_idx > new_classzone_idx) {
/*
* Don't sleep if someone wants a larger 'order'
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
* allocation or has tigher zone constraints
*/
order = new_order;
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
classzone_idx = new_classzone_idx;
} else {
kswapd_try_to_sleep(pgdat, balanced_order,
balanced_classzone_idx);
order = pgdat->kswapd_max_order;
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
classzone_idx = pgdat->classzone_idx;
new_order = order;
new_classzone_idx = classzone_idx;
pgdat->kswapd_max_order = 0;
mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully During allocator-intensive workloads, kswapd will be woken frequently causing free memory to oscillate between the high and min watermark. This is expected behaviour. Unfortunately, if the highest zone is small, a problem occurs. When balance_pgdat() returns, it may be at a lower classzone_idx than it started because the highest zone was unreclaimable. Before checking if it should go to sleep though, it checks pgdat->classzone_idx which when there is no other activity will be MAX_NR_ZONES-1. It interprets this as it has been woken up while reclaiming, skips scheduling and reclaims again. As there is no useful reclaim work to do, it enters into a loop of shrinking slab consuming loads of CPU until the highest zone becomes reclaimable for a long period of time. There are two problems here. 1) If the returned classzone or order is lower, it'll continue reclaiming without scheduling. 2) if the highest zone was marked unreclaimable but balance_pgdat() returns immediately at DEF_PRIORITY, the new lower classzone is not communicated back to kswapd() for sleeping. This patch does two things that are related. If the end_zone is unreclaimable, this information is communicated back. Second, if the classzone or order was reduced due to failing to reclaim, new information is not read from pgdat and instead an attempt is made to go to sleep. Due to this, it is also necessary that pgdat->classzone_idx be initialised each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as wakeups. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Pádraig Brady <P@draigBrady.com> Tested-by: Pádraig Brady <P@draigBrady.com> Tested-by: Andrew Lutomirski <luto@mit.edu> Acked-by: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-09 06:39:40 +08:00
pgdat->classzone_idx = pgdat->nr_zones - 1;
}
ret = try_to_freeze();
if (kthread_should_stop())
break;
/*
* We can speed up thawing tasks if we don't call balance_pgdat
* after returning from the refrigerator
*/
if (!ret) {
trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
balanced_classzone_idx = classzone_idx;
balanced_order = balance_pgdat(pgdat, order,
&balanced_classzone_idx);
}
}
return 0;
}
/*
* A zone is low on free memory, so wake its kswapd task to service it.
*/
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
{
pg_data_t *pgdat;
if (!populated_zone(zone))
return;
mm: page allocator: adjust the per-cpu counter threshold when memory is low Commit aa45484 ("calculate a better estimate of NR_FREE_PAGES when memory is low") noted that watermarks were based on the vmstat NR_FREE_PAGES. To avoid synchronization overhead, these counters are maintained on a per-cpu basis and drained both periodically and when a threshold is above a threshold. On large CPU systems, the difference between the estimate and real value of NR_FREE_PAGES can be very high. The system can get into a case where pages are allocated far below the min watermark potentially causing livelock issues. The commit solved the problem by taking a better reading of NR_FREE_PAGES when memory was low. Unfortately, as reported by Shaohua Li this accurate reading can consume a large amount of CPU time on systems with many sockets due to cache line bouncing. This patch takes a different approach. For large machines where counter drift might be unsafe and while kswapd is awake, the per-cpu thresholds for the target pgdat are reduced to limit the level of drift to what should be a safe level. This incurs a performance penalty in heavy memory pressure by a factor that depends on the workload and the machine but the machine should function correctly without accidentally exhausting all memory on a node. There is an additional cost when kswapd wakes and sleeps but the event is not expected to be frequent - in Shaohua's test case, there was one recorded sleep and wake event at least. To ensure that kswapd wakes up, a safe version of zone_watermark_ok() is introduced that takes a more accurate reading of NR_FREE_PAGES when called from wakeup_kswapd, when deciding whether it is really safe to go back to sleep in sleeping_prematurely() and when deciding if a zone is really balanced or not in balance_pgdat(). We are still using an expensive function but limiting how often it is called. When the test case is reproduced, the time spent in the watermark functions is reduced. The following report is on the percentage of time spent cumulatively spent in the functions zone_nr_free_pages(), zone_watermark_ok(), __zone_watermark_ok(), zone_watermark_ok_safe(), zone_page_state_snapshot(), zone_page_state(). vanilla 11.6615% disable-threshold 0.2584% David said: : We had to pull aa454840 "mm: page allocator: calculate a better estimate : of NR_FREE_PAGES when memory is low and kswapd is awake" from 2.6.36 : internally because tests showed that it would cause the machine to stall : as the result of heavy kswapd activity. I merged it back with this fix as : it is pending in the -mm tree and it solves the issue we were seeing, so I : definitely think this should be pushed to -stable (and I would seriously : consider it for 2.6.37 inclusion even at this late date). Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reported-by: Shaohua Li <shaohua.li@intel.com> Reviewed-by: Christoph Lameter <cl@linux.com> Tested-by: Nicolas Bareil <nico@chdir.org> Cc: David Rientjes <rientjes@google.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: <stable@kernel.org> [2.6.37.1, 2.6.36.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:45:41 +08:00
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
return;
mm: page allocator: adjust the per-cpu counter threshold when memory is low Commit aa45484 ("calculate a better estimate of NR_FREE_PAGES when memory is low") noted that watermarks were based on the vmstat NR_FREE_PAGES. To avoid synchronization overhead, these counters are maintained on a per-cpu basis and drained both periodically and when a threshold is above a threshold. On large CPU systems, the difference between the estimate and real value of NR_FREE_PAGES can be very high. The system can get into a case where pages are allocated far below the min watermark potentially causing livelock issues. The commit solved the problem by taking a better reading of NR_FREE_PAGES when memory was low. Unfortately, as reported by Shaohua Li this accurate reading can consume a large amount of CPU time on systems with many sockets due to cache line bouncing. This patch takes a different approach. For large machines where counter drift might be unsafe and while kswapd is awake, the per-cpu thresholds for the target pgdat are reduced to limit the level of drift to what should be a safe level. This incurs a performance penalty in heavy memory pressure by a factor that depends on the workload and the machine but the machine should function correctly without accidentally exhausting all memory on a node. There is an additional cost when kswapd wakes and sleeps but the event is not expected to be frequent - in Shaohua's test case, there was one recorded sleep and wake event at least. To ensure that kswapd wakes up, a safe version of zone_watermark_ok() is introduced that takes a more accurate reading of NR_FREE_PAGES when called from wakeup_kswapd, when deciding whether it is really safe to go back to sleep in sleeping_prematurely() and when deciding if a zone is really balanced or not in balance_pgdat(). We are still using an expensive function but limiting how often it is called. When the test case is reproduced, the time spent in the watermark functions is reduced. The following report is on the percentage of time spent cumulatively spent in the functions zone_nr_free_pages(), zone_watermark_ok(), __zone_watermark_ok(), zone_watermark_ok_safe(), zone_page_state_snapshot(), zone_page_state(). vanilla 11.6615% disable-threshold 0.2584% David said: : We had to pull aa454840 "mm: page allocator: calculate a better estimate : of NR_FREE_PAGES when memory is low and kswapd is awake" from 2.6.36 : internally because tests showed that it would cause the machine to stall : as the result of heavy kswapd activity. I merged it back with this fix as : it is pending in the -mm tree and it solves the issue we were seeing, so I : definitely think this should be pushed to -stable (and I would seriously : consider it for 2.6.37 inclusion even at this late date). Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reported-by: Shaohua Li <shaohua.li@intel.com> Reviewed-by: Christoph Lameter <cl@linux.com> Tested-by: Nicolas Bareil <nico@chdir.org> Cc: David Rientjes <rientjes@google.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: <stable@kernel.org> [2.6.37.1, 2.6.36.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:45:41 +08:00
pgdat = zone->zone_pgdat;
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
if (pgdat->kswapd_max_order < order) {
pgdat->kswapd_max_order = order;
mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Eric B Munson <emunson@mgebm.net> Cc: Simon Kirby <sim@hostway.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:20 +08:00
pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
}
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
mm: page allocator: adjust the per-cpu counter threshold when memory is low Commit aa45484 ("calculate a better estimate of NR_FREE_PAGES when memory is low") noted that watermarks were based on the vmstat NR_FREE_PAGES. To avoid synchronization overhead, these counters are maintained on a per-cpu basis and drained both periodically and when a threshold is above a threshold. On large CPU systems, the difference between the estimate and real value of NR_FREE_PAGES can be very high. The system can get into a case where pages are allocated far below the min watermark potentially causing livelock issues. The commit solved the problem by taking a better reading of NR_FREE_PAGES when memory was low. Unfortately, as reported by Shaohua Li this accurate reading can consume a large amount of CPU time on systems with many sockets due to cache line bouncing. This patch takes a different approach. For large machines where counter drift might be unsafe and while kswapd is awake, the per-cpu thresholds for the target pgdat are reduced to limit the level of drift to what should be a safe level. This incurs a performance penalty in heavy memory pressure by a factor that depends on the workload and the machine but the machine should function correctly without accidentally exhausting all memory on a node. There is an additional cost when kswapd wakes and sleeps but the event is not expected to be frequent - in Shaohua's test case, there was one recorded sleep and wake event at least. To ensure that kswapd wakes up, a safe version of zone_watermark_ok() is introduced that takes a more accurate reading of NR_FREE_PAGES when called from wakeup_kswapd, when deciding whether it is really safe to go back to sleep in sleeping_prematurely() and when deciding if a zone is really balanced or not in balance_pgdat(). We are still using an expensive function but limiting how often it is called. When the test case is reproduced, the time spent in the watermark functions is reduced. The following report is on the percentage of time spent cumulatively spent in the functions zone_nr_free_pages(), zone_watermark_ok(), __zone_watermark_ok(), zone_watermark_ok_safe(), zone_page_state_snapshot(), zone_page_state(). vanilla 11.6615% disable-threshold 0.2584% David said: : We had to pull aa454840 "mm: page allocator: calculate a better estimate : of NR_FREE_PAGES when memory is low and kswapd is awake" from 2.6.36 : internally because tests showed that it would cause the machine to stall : as the result of heavy kswapd activity. I merged it back with this fix as : it is pending in the -mm tree and it solves the issue we were seeing, so I : definitely think this should be pushed to -stable (and I would seriously : consider it for 2.6.37 inclusion even at this late date). Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reported-by: Shaohua Li <shaohua.li@intel.com> Reviewed-by: Christoph Lameter <cl@linux.com> Tested-by: Nicolas Bareil <nico@chdir.org> Cc: David Rientjes <rientjes@google.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: <stable@kernel.org> [2.6.37.1, 2.6.36.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:45:41 +08:00
if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0))
return;
trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
wake_up_interruptible(&pgdat->kswapd_wait);
}
/*
* The reclaimable count would be mostly accurate.
* The less reclaimable pages may be
* - mlocked pages, which will be moved to unevictable list when encountered
* - mapped pages, which may require several travels to be reclaimed
* - dirty pages, which is not "instantly" reclaimable
*/
unsigned long global_reclaimable_pages(void)
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
{
int nr;
nr = global_page_state(NR_ACTIVE_FILE) +
global_page_state(NR_INACTIVE_FILE);
if (nr_swap_pages > 0)
nr += global_page_state(NR_ACTIVE_ANON) +
global_page_state(NR_INACTIVE_ANON);
return nr;
}
unsigned long zone_reclaimable_pages(struct zone *zone)
{
int nr;
nr = zone_page_state(zone, NR_ACTIVE_FILE) +
zone_page_state(zone, NR_INACTIVE_FILE);
if (nr_swap_pages > 0)
nr += zone_page_state(zone, NR_ACTIVE_ANON) +
zone_page_state(zone, NR_INACTIVE_ANON);
return nr;
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:32 +08:00
}
#ifdef CONFIG_HIBERNATION
/*
vmscan: kill hibernation specific reclaim logic and unify it shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing memory for suspend). commit a06fe4d307 said Without the patch: Freed 14600 pages in 1749 jiffies = 32.61 MB/s (Anomolous!) Freed 88563 pages in 14719 jiffies = 23.50 MB/s Freed 205734 pages in 32389 jiffies = 24.81 MB/s With the patch: Freed 68252 pages in 496 jiffies = 537.52 MB/s Freed 116464 pages in 569 jiffies = 798.54 MB/s Freed 209699 pages in 705 jiffies = 1161.89 MB/s At that time, their patch was pretty worth. However, Modern Hardware trend and recent VM improvement broke its worth. From several reason, I think we should remove shrink_all_zones() at all. detail: 1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle at no i/o congestion. but current shrink_zone() is sane, not slow. 2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works fine on numa system. example) System has 4GB memory and each node have 2GB. and hibernate need 1GB. optimal) steal 500MB from each node. shrink_all_zones) steal 1GB from node-0. Oh, Cache balancing logic was broken. ;) Unfortunately, Desktop system moved ahead NUMA at nowadays. (Side note, if hibernate require 2GB, shrink_all_zones() never success on above machine) 3) if the node has several I/O flighting pages, shrink_all_zones() makes pretty bad result. schenario) hibernate need 1GB 1) shrink_all_zones() try to reclaim 1GB from Node-0 2) but it only reclaimed 990MB 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1 4) it reclaimed 990MB Oh, well. it reclaimed twice much than required. In the other hand, current shrink_zone() has sane baling out logic. then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk. 4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal. Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages(). it bring good reviewability and debuggability, and solve above problems. side note: Reclaim logic unificication makes two good side effect. - Fix recursive reclaim bug on shrink_all_memory(). it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock. - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 09:59:12 +08:00
* Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
* freed pages.
*
* Rather than trying to age LRUs the aim is to preserve the overall
* LRU order by reclaiming preferentially
* inactive > active > active referenced > active mapped
*/
vmscan: kill hibernation specific reclaim logic and unify it shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing memory for suspend). commit a06fe4d307 said Without the patch: Freed 14600 pages in 1749 jiffies = 32.61 MB/s (Anomolous!) Freed 88563 pages in 14719 jiffies = 23.50 MB/s Freed 205734 pages in 32389 jiffies = 24.81 MB/s With the patch: Freed 68252 pages in 496 jiffies = 537.52 MB/s Freed 116464 pages in 569 jiffies = 798.54 MB/s Freed 209699 pages in 705 jiffies = 1161.89 MB/s At that time, their patch was pretty worth. However, Modern Hardware trend and recent VM improvement broke its worth. From several reason, I think we should remove shrink_all_zones() at all. detail: 1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle at no i/o congestion. but current shrink_zone() is sane, not slow. 2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works fine on numa system. example) System has 4GB memory and each node have 2GB. and hibernate need 1GB. optimal) steal 500MB from each node. shrink_all_zones) steal 1GB from node-0. Oh, Cache balancing logic was broken. ;) Unfortunately, Desktop system moved ahead NUMA at nowadays. (Side note, if hibernate require 2GB, shrink_all_zones() never success on above machine) 3) if the node has several I/O flighting pages, shrink_all_zones() makes pretty bad result. schenario) hibernate need 1GB 1) shrink_all_zones() try to reclaim 1GB from Node-0 2) but it only reclaimed 990MB 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1 4) it reclaimed 990MB Oh, well. it reclaimed twice much than required. In the other hand, current shrink_zone() has sane baling out logic. then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk. 4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal. Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages(). it bring good reviewability and debuggability, and solve above problems. side note: Reclaim logic unificication makes two good side effect. - Fix recursive reclaim bug on shrink_all_memory(). it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock. - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 09:59:12 +08:00
unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
{
struct reclaim_state reclaim_state;
struct scan_control sc = {
vmscan: kill hibernation specific reclaim logic and unify it shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing memory for suspend). commit a06fe4d307 said Without the patch: Freed 14600 pages in 1749 jiffies = 32.61 MB/s (Anomolous!) Freed 88563 pages in 14719 jiffies = 23.50 MB/s Freed 205734 pages in 32389 jiffies = 24.81 MB/s With the patch: Freed 68252 pages in 496 jiffies = 537.52 MB/s Freed 116464 pages in 569 jiffies = 798.54 MB/s Freed 209699 pages in 705 jiffies = 1161.89 MB/s At that time, their patch was pretty worth. However, Modern Hardware trend and recent VM improvement broke its worth. From several reason, I think we should remove shrink_all_zones() at all. detail: 1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle at no i/o congestion. but current shrink_zone() is sane, not slow. 2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works fine on numa system. example) System has 4GB memory and each node have 2GB. and hibernate need 1GB. optimal) steal 500MB from each node. shrink_all_zones) steal 1GB from node-0. Oh, Cache balancing logic was broken. ;) Unfortunately, Desktop system moved ahead NUMA at nowadays. (Side note, if hibernate require 2GB, shrink_all_zones() never success on above machine) 3) if the node has several I/O flighting pages, shrink_all_zones() makes pretty bad result. schenario) hibernate need 1GB 1) shrink_all_zones() try to reclaim 1GB from Node-0 2) but it only reclaimed 990MB 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1 4) it reclaimed 990MB Oh, well. it reclaimed twice much than required. In the other hand, current shrink_zone() has sane baling out logic. then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk. 4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal. Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages(). it bring good reviewability and debuggability, and solve above problems. side note: Reclaim logic unificication makes two good side effect. - Fix recursive reclaim bug on shrink_all_memory(). it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock. - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 09:59:12 +08:00
.gfp_mask = GFP_HIGHUSER_MOVABLE,
.may_swap = 1,
.may_unmap = 1,
.may_writepage = 1,
vmscan: kill hibernation specific reclaim logic and unify it shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing memory for suspend). commit a06fe4d307 said Without the patch: Freed 14600 pages in 1749 jiffies = 32.61 MB/s (Anomolous!) Freed 88563 pages in 14719 jiffies = 23.50 MB/s Freed 205734 pages in 32389 jiffies = 24.81 MB/s With the patch: Freed 68252 pages in 496 jiffies = 537.52 MB/s Freed 116464 pages in 569 jiffies = 798.54 MB/s Freed 209699 pages in 705 jiffies = 1161.89 MB/s At that time, their patch was pretty worth. However, Modern Hardware trend and recent VM improvement broke its worth. From several reason, I think we should remove shrink_all_zones() at all. detail: 1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle at no i/o congestion. but current shrink_zone() is sane, not slow. 2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works fine on numa system. example) System has 4GB memory and each node have 2GB. and hibernate need 1GB. optimal) steal 500MB from each node. shrink_all_zones) steal 1GB from node-0. Oh, Cache balancing logic was broken. ;) Unfortunately, Desktop system moved ahead NUMA at nowadays. (Side note, if hibernate require 2GB, shrink_all_zones() never success on above machine) 3) if the node has several I/O flighting pages, shrink_all_zones() makes pretty bad result. schenario) hibernate need 1GB 1) shrink_all_zones() try to reclaim 1GB from Node-0 2) but it only reclaimed 990MB 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1 4) it reclaimed 990MB Oh, well. it reclaimed twice much than required. In the other hand, current shrink_zone() has sane baling out logic. then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk. 4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal. Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages(). it bring good reviewability and debuggability, and solve above problems. side note: Reclaim logic unificication makes two good side effect. - Fix recursive reclaim bug on shrink_all_memory(). it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock. - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 09:59:12 +08:00
.nr_to_reclaim = nr_to_reclaim,
.hibernation_mode = 1,
.order = 0,
.priority = DEF_PRIORITY,
};
struct shrink_control shrink = {
.gfp_mask = sc.gfp_mask,
};
struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
vmscan: kill hibernation specific reclaim logic and unify it shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing memory for suspend). commit a06fe4d307 said Without the patch: Freed 14600 pages in 1749 jiffies = 32.61 MB/s (Anomolous!) Freed 88563 pages in 14719 jiffies = 23.50 MB/s Freed 205734 pages in 32389 jiffies = 24.81 MB/s With the patch: Freed 68252 pages in 496 jiffies = 537.52 MB/s Freed 116464 pages in 569 jiffies = 798.54 MB/s Freed 209699 pages in 705 jiffies = 1161.89 MB/s At that time, their patch was pretty worth. However, Modern Hardware trend and recent VM improvement broke its worth. From several reason, I think we should remove shrink_all_zones() at all. detail: 1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle at no i/o congestion. but current shrink_zone() is sane, not slow. 2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works fine on numa system. example) System has 4GB memory and each node have 2GB. and hibernate need 1GB. optimal) steal 500MB from each node. shrink_all_zones) steal 1GB from node-0. Oh, Cache balancing logic was broken. ;) Unfortunately, Desktop system moved ahead NUMA at nowadays. (Side note, if hibernate require 2GB, shrink_all_zones() never success on above machine) 3) if the node has several I/O flighting pages, shrink_all_zones() makes pretty bad result. schenario) hibernate need 1GB 1) shrink_all_zones() try to reclaim 1GB from Node-0 2) but it only reclaimed 990MB 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1 4) it reclaimed 990MB Oh, well. it reclaimed twice much than required. In the other hand, current shrink_zone() has sane baling out logic. then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk. 4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal. Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages(). it bring good reviewability and debuggability, and solve above problems. side note: Reclaim logic unificication makes two good side effect. - Fix recursive reclaim bug on shrink_all_memory(). it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock. - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 09:59:12 +08:00
struct task_struct *p = current;
unsigned long nr_reclaimed;
vmscan: kill hibernation specific reclaim logic and unify it shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing memory for suspend). commit a06fe4d307 said Without the patch: Freed 14600 pages in 1749 jiffies = 32.61 MB/s (Anomolous!) Freed 88563 pages in 14719 jiffies = 23.50 MB/s Freed 205734 pages in 32389 jiffies = 24.81 MB/s With the patch: Freed 68252 pages in 496 jiffies = 537.52 MB/s Freed 116464 pages in 569 jiffies = 798.54 MB/s Freed 209699 pages in 705 jiffies = 1161.89 MB/s At that time, their patch was pretty worth. However, Modern Hardware trend and recent VM improvement broke its worth. From several reason, I think we should remove shrink_all_zones() at all. detail: 1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle at no i/o congestion. but current shrink_zone() is sane, not slow. 2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works fine on numa system. example) System has 4GB memory and each node have 2GB. and hibernate need 1GB. optimal) steal 500MB from each node. shrink_all_zones) steal 1GB from node-0. Oh, Cache balancing logic was broken. ;) Unfortunately, Desktop system moved ahead NUMA at nowadays. (Side note, if hibernate require 2GB, shrink_all_zones() never success on above machine) 3) if the node has several I/O flighting pages, shrink_all_zones() makes pretty bad result. schenario) hibernate need 1GB 1) shrink_all_zones() try to reclaim 1GB from Node-0 2) but it only reclaimed 990MB 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1 4) it reclaimed 990MB Oh, well. it reclaimed twice much than required. In the other hand, current shrink_zone() has sane baling out logic. then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk. 4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal. Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages(). it bring good reviewability and debuggability, and solve above problems. side note: Reclaim logic unificication makes two good side effect. - Fix recursive reclaim bug on shrink_all_memory(). it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock. - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 09:59:12 +08:00
p->flags |= PF_MEMALLOC;
lockdep_set_current_reclaim_state(sc.gfp_mask);
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
vmscan: kill hibernation specific reclaim logic and unify it shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing memory for suspend). commit a06fe4d307 said Without the patch: Freed 14600 pages in 1749 jiffies = 32.61 MB/s (Anomolous!) Freed 88563 pages in 14719 jiffies = 23.50 MB/s Freed 205734 pages in 32389 jiffies = 24.81 MB/s With the patch: Freed 68252 pages in 496 jiffies = 537.52 MB/s Freed 116464 pages in 569 jiffies = 798.54 MB/s Freed 209699 pages in 705 jiffies = 1161.89 MB/s At that time, their patch was pretty worth. However, Modern Hardware trend and recent VM improvement broke its worth. From several reason, I think we should remove shrink_all_zones() at all. detail: 1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle at no i/o congestion. but current shrink_zone() is sane, not slow. 2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works fine on numa system. example) System has 4GB memory and each node have 2GB. and hibernate need 1GB. optimal) steal 500MB from each node. shrink_all_zones) steal 1GB from node-0. Oh, Cache balancing logic was broken. ;) Unfortunately, Desktop system moved ahead NUMA at nowadays. (Side note, if hibernate require 2GB, shrink_all_zones() never success on above machine) 3) if the node has several I/O flighting pages, shrink_all_zones() makes pretty bad result. schenario) hibernate need 1GB 1) shrink_all_zones() try to reclaim 1GB from Node-0 2) but it only reclaimed 990MB 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1 4) it reclaimed 990MB Oh, well. it reclaimed twice much than required. In the other hand, current shrink_zone() has sane baling out logic. then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk. 4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal. Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages(). it bring good reviewability and debuggability, and solve above problems. side note: Reclaim logic unificication makes two good side effect. - Fix recursive reclaim bug on shrink_all_memory(). it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock. - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 09:59:12 +08:00
p->reclaim_state = NULL;
lockdep_clear_current_reclaim_state();
p->flags &= ~PF_MEMALLOC;
vmscan: kill hibernation specific reclaim logic and unify it shrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework memory shrinker) for hibernate performance improvement. and sc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing memory for suspend). commit a06fe4d307 said Without the patch: Freed 14600 pages in 1749 jiffies = 32.61 MB/s (Anomolous!) Freed 88563 pages in 14719 jiffies = 23.50 MB/s Freed 205734 pages in 32389 jiffies = 24.81 MB/s With the patch: Freed 68252 pages in 496 jiffies = 537.52 MB/s Freed 116464 pages in 569 jiffies = 798.54 MB/s Freed 209699 pages in 705 jiffies = 1161.89 MB/s At that time, their patch was pretty worth. However, Modern Hardware trend and recent VM improvement broke its worth. From several reason, I think we should remove shrink_all_zones() at all. detail: 1) Old days, shrink_zone()'s slowness was mainly caused by stupid io-throttle at no i/o congestion. but current shrink_zone() is sane, not slow. 2) shrink_all_zone() try to shrink all pages at a time. but it doesn't works fine on numa system. example) System has 4GB memory and each node have 2GB. and hibernate need 1GB. optimal) steal 500MB from each node. shrink_all_zones) steal 1GB from node-0. Oh, Cache balancing logic was broken. ;) Unfortunately, Desktop system moved ahead NUMA at nowadays. (Side note, if hibernate require 2GB, shrink_all_zones() never success on above machine) 3) if the node has several I/O flighting pages, shrink_all_zones() makes pretty bad result. schenario) hibernate need 1GB 1) shrink_all_zones() try to reclaim 1GB from Node-0 2) but it only reclaimed 990MB 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1 4) it reclaimed 990MB Oh, well. it reclaimed twice much than required. In the other hand, current shrink_zone() has sane baling out logic. then, it doesn't make overkill reclaim. then, we lost shrink_zones()'s risk. 4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal. Now, shrink_all_memory() is only the wrapper function of do_try_to_free_pages(). it bring good reviewability and debuggability, and solve above problems. side note: Reclaim logic unificication makes two good side effect. - Fix recursive reclaim bug on shrink_all_memory(). it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock. - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability. Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 09:59:12 +08:00
return nr_reclaimed;
}
#endif /* CONFIG_HIBERNATION */
/* It's optimal to keep kswapds on the same CPUs as their memory, but
not required for correctness. So if the last cpu in a node goes
away, we get changed to run anywhere: as the first one comes back,
restore their cpu bindings. */
static int __devinit cpu_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
int nid;
if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
for_each_node_state(nid, N_HIGH_MEMORY) {
pg_data_t *pgdat = NODE_DATA(nid);
const struct cpumask *mask;
mask = cpumask_of_node(pgdat->node_id);
if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
/* One of our CPUs online: restore mask */
set_cpus_allowed_ptr(pgdat->kswapd, mask);
}
}
return NOTIFY_OK;
}
/*
* This kswapd start function will be called by init and node-hot-add.
* On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
*/
int kswapd_run(int nid)
{
pg_data_t *pgdat = NODE_DATA(nid);
int ret = 0;
if (pgdat->kswapd)
return 0;
pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
if (IS_ERR(pgdat->kswapd)) {
/* failure at boot is fatal */
BUG_ON(system_state == SYSTEM_BOOTING);
printk("Failed to start kswapd on node %d\n",nid);
pgdat->kswapd = NULL;
ret = -1;
}
return ret;
}
/*
memory hotplug: fix invalid memory access caused by stale kswapd pointer kswapd_stop() is called to destroy the kswapd work thread when all memory of a NUMA node has been offlined. But kswapd_stop() only terminates the work thread without resetting NODE_DATA(nid)->kswapd to NULL. The stale pointer will prevent kswapd_run() from creating a new work thread when adding memory to the memory-less NUMA node again. Eventually the stale pointer may cause invalid memory access. An example stack dump as below. It's reproduced with 2.6.32, but latest kernel has the same issue. BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<ffffffff81051a94>] exit_creds+0x12/0x78 PGD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/system/memory/memory391/state CPU 11 Modules linked in: cpufreq_conservative cpufreq_userspace cpufreq_powersave acpi_cpufreq microcode fuse loop dm_mod tpm_tis rtc_cmos i2c_i801 rtc_core tpm serio_raw pcspkr sg tpm_bios igb i2c_core iTCO_wdt rtc_lib mptctl iTCO_vendor_support button dca bnx2 usbhid hid uhci_hcd ehci_hcd usbcore sd_mod crc_t10dif edd ext3 mbcache jbd fan ide_pci_generic ide_core ata_generic ata_piix libata thermal processor thermal_sys hwmon mptsas mptscsih mptbase scsi_transport_sas scsi_mod Pid: 7949, comm: sh Not tainted 2.6.32.12-qiuxishi-5-default #92 Tecal RH2285 RIP: 0010:exit_creds+0x12/0x78 RSP: 0018:ffff8806044f1d78 EFLAGS: 00010202 RAX: 0000000000000000 RBX: ffff880604f22140 RCX: 0000000000019502 RDX: 0000000000000000 RSI: 0000000000000202 RDI: 0000000000000000 RBP: ffff880604f22150 R08: 0000000000000000 R09: ffffffff81a4dc10 R10: 00000000000032a0 R11: ffff880006202500 R12: 0000000000000000 R13: 0000000000c40000 R14: 0000000000008000 R15: 0000000000000001 FS: 00007fbc03d066f0(0000) GS:ffff8800282e0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000000 CR3: 000000060f029000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process sh (pid: 7949, threadinfo ffff8806044f0000, task ffff880603d7c600) Stack: ffff880604f22140 ffffffff8103aac5 ffff880604f22140 ffffffff8104d21e ffff880006202500 0000000000008000 0000000000c38000 ffffffff810bd5b1 0000000000000000 ffff880603d7c600 00000000ffffdd29 0000000000000003 Call Trace: __put_task_struct+0x5d/0x97 kthread_stop+0x50/0x58 offline_pages+0x324/0x3da memory_block_change_state+0x179/0x1db store_mem_state+0x9e/0xbb sysfs_write_file+0xd0/0x107 vfs_write+0xad/0x169 sys_write+0x45/0x6e system_call_fastpath+0x16/0x1b Code: ff 4d 00 0f 94 c0 84 c0 74 08 48 89 ef e8 1f fd ff ff 5b 5d 31 c0 41 5c c3 53 48 8b 87 20 06 00 00 48 89 fb 48 8b bf 18 06 00 00 <8b> 00 48 c7 83 18 06 00 00 00 00 00 00 f0 ff 0f 0f 94 c0 84 c0 RIP exit_creds+0x12/0x78 RSP <ffff8806044f1d78> CR2: 0000000000000000 [akpm@linux-foundation.org: add pglist_data.kswapd locking comments] Signed-off-by: Xishi Qiu <qiuxishi@huawei.com> Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: David Rientjes <rientjes@google.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-12 05:01:52 +08:00
* Called by memory hotplug when all memory in a node is offlined. Caller must
* hold lock_memory_hotplug().
*/
void kswapd_stop(int nid)
{
struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
memory hotplug: fix invalid memory access caused by stale kswapd pointer kswapd_stop() is called to destroy the kswapd work thread when all memory of a NUMA node has been offlined. But kswapd_stop() only terminates the work thread without resetting NODE_DATA(nid)->kswapd to NULL. The stale pointer will prevent kswapd_run() from creating a new work thread when adding memory to the memory-less NUMA node again. Eventually the stale pointer may cause invalid memory access. An example stack dump as below. It's reproduced with 2.6.32, but latest kernel has the same issue. BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<ffffffff81051a94>] exit_creds+0x12/0x78 PGD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/system/memory/memory391/state CPU 11 Modules linked in: cpufreq_conservative cpufreq_userspace cpufreq_powersave acpi_cpufreq microcode fuse loop dm_mod tpm_tis rtc_cmos i2c_i801 rtc_core tpm serio_raw pcspkr sg tpm_bios igb i2c_core iTCO_wdt rtc_lib mptctl iTCO_vendor_support button dca bnx2 usbhid hid uhci_hcd ehci_hcd usbcore sd_mod crc_t10dif edd ext3 mbcache jbd fan ide_pci_generic ide_core ata_generic ata_piix libata thermal processor thermal_sys hwmon mptsas mptscsih mptbase scsi_transport_sas scsi_mod Pid: 7949, comm: sh Not tainted 2.6.32.12-qiuxishi-5-default #92 Tecal RH2285 RIP: 0010:exit_creds+0x12/0x78 RSP: 0018:ffff8806044f1d78 EFLAGS: 00010202 RAX: 0000000000000000 RBX: ffff880604f22140 RCX: 0000000000019502 RDX: 0000000000000000 RSI: 0000000000000202 RDI: 0000000000000000 RBP: ffff880604f22150 R08: 0000000000000000 R09: ffffffff81a4dc10 R10: 00000000000032a0 R11: ffff880006202500 R12: 0000000000000000 R13: 0000000000c40000 R14: 0000000000008000 R15: 0000000000000001 FS: 00007fbc03d066f0(0000) GS:ffff8800282e0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000000 CR3: 000000060f029000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process sh (pid: 7949, threadinfo ffff8806044f0000, task ffff880603d7c600) Stack: ffff880604f22140 ffffffff8103aac5 ffff880604f22140 ffffffff8104d21e ffff880006202500 0000000000008000 0000000000c38000 ffffffff810bd5b1 0000000000000000 ffff880603d7c600 00000000ffffdd29 0000000000000003 Call Trace: __put_task_struct+0x5d/0x97 kthread_stop+0x50/0x58 offline_pages+0x324/0x3da memory_block_change_state+0x179/0x1db store_mem_state+0x9e/0xbb sysfs_write_file+0xd0/0x107 vfs_write+0xad/0x169 sys_write+0x45/0x6e system_call_fastpath+0x16/0x1b Code: ff 4d 00 0f 94 c0 84 c0 74 08 48 89 ef e8 1f fd ff ff 5b 5d 31 c0 41 5c c3 53 48 8b 87 20 06 00 00 48 89 fb 48 8b bf 18 06 00 00 <8b> 00 48 c7 83 18 06 00 00 00 00 00 00 f0 ff 0f 0f 94 c0 84 c0 RIP exit_creds+0x12/0x78 RSP <ffff8806044f1d78> CR2: 0000000000000000 [akpm@linux-foundation.org: add pglist_data.kswapd locking comments] Signed-off-by: Xishi Qiu <qiuxishi@huawei.com> Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: David Rientjes <rientjes@google.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-12 05:01:52 +08:00
if (kswapd) {
kthread_stop(kswapd);
memory hotplug: fix invalid memory access caused by stale kswapd pointer kswapd_stop() is called to destroy the kswapd work thread when all memory of a NUMA node has been offlined. But kswapd_stop() only terminates the work thread without resetting NODE_DATA(nid)->kswapd to NULL. The stale pointer will prevent kswapd_run() from creating a new work thread when adding memory to the memory-less NUMA node again. Eventually the stale pointer may cause invalid memory access. An example stack dump as below. It's reproduced with 2.6.32, but latest kernel has the same issue. BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<ffffffff81051a94>] exit_creds+0x12/0x78 PGD 0 Oops: 0000 [#1] SMP last sysfs file: /sys/devices/system/memory/memory391/state CPU 11 Modules linked in: cpufreq_conservative cpufreq_userspace cpufreq_powersave acpi_cpufreq microcode fuse loop dm_mod tpm_tis rtc_cmos i2c_i801 rtc_core tpm serio_raw pcspkr sg tpm_bios igb i2c_core iTCO_wdt rtc_lib mptctl iTCO_vendor_support button dca bnx2 usbhid hid uhci_hcd ehci_hcd usbcore sd_mod crc_t10dif edd ext3 mbcache jbd fan ide_pci_generic ide_core ata_generic ata_piix libata thermal processor thermal_sys hwmon mptsas mptscsih mptbase scsi_transport_sas scsi_mod Pid: 7949, comm: sh Not tainted 2.6.32.12-qiuxishi-5-default #92 Tecal RH2285 RIP: 0010:exit_creds+0x12/0x78 RSP: 0018:ffff8806044f1d78 EFLAGS: 00010202 RAX: 0000000000000000 RBX: ffff880604f22140 RCX: 0000000000019502 RDX: 0000000000000000 RSI: 0000000000000202 RDI: 0000000000000000 RBP: ffff880604f22150 R08: 0000000000000000 R09: ffffffff81a4dc10 R10: 00000000000032a0 R11: ffff880006202500 R12: 0000000000000000 R13: 0000000000c40000 R14: 0000000000008000 R15: 0000000000000001 FS: 00007fbc03d066f0(0000) GS:ffff8800282e0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000000 CR3: 000000060f029000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process sh (pid: 7949, threadinfo ffff8806044f0000, task ffff880603d7c600) Stack: ffff880604f22140 ffffffff8103aac5 ffff880604f22140 ffffffff8104d21e ffff880006202500 0000000000008000 0000000000c38000 ffffffff810bd5b1 0000000000000000 ffff880603d7c600 00000000ffffdd29 0000000000000003 Call Trace: __put_task_struct+0x5d/0x97 kthread_stop+0x50/0x58 offline_pages+0x324/0x3da memory_block_change_state+0x179/0x1db store_mem_state+0x9e/0xbb sysfs_write_file+0xd0/0x107 vfs_write+0xad/0x169 sys_write+0x45/0x6e system_call_fastpath+0x16/0x1b Code: ff 4d 00 0f 94 c0 84 c0 74 08 48 89 ef e8 1f fd ff ff 5b 5d 31 c0 41 5c c3 53 48 8b 87 20 06 00 00 48 89 fb 48 8b bf 18 06 00 00 <8b> 00 48 c7 83 18 06 00 00 00 00 00 00 f0 ff 0f 0f 94 c0 84 c0 RIP exit_creds+0x12/0x78 RSP <ffff8806044f1d78> CR2: 0000000000000000 [akpm@linux-foundation.org: add pglist_data.kswapd locking comments] Signed-off-by: Xishi Qiu <qiuxishi@huawei.com> Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: David Rientjes <rientjes@google.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-12 05:01:52 +08:00
NODE_DATA(nid)->kswapd = NULL;
}
}
static int __init kswapd_init(void)
{
int nid;
swap_setup();
for_each_node_state(nid, N_HIGH_MEMORY)
kswapd_run(nid);
hotcpu_notifier(cpu_callback, 0);
return 0;
}
module_init(kswapd_init)
#ifdef CONFIG_NUMA
/*
* Zone reclaim mode
*
* If non-zero call zone_reclaim when the number of free pages falls below
* the watermarks.
*/
int zone_reclaim_mode __read_mostly;
#define RECLAIM_OFF 0
#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */
#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
#define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */
/*
* Priority for ZONE_RECLAIM. This determines the fraction of pages
* of a node considered for each zone_reclaim. 4 scans 1/16th of
* a zone.
*/
#define ZONE_RECLAIM_PRIORITY 4
/*
* Percentage of pages in a zone that must be unmapped for zone_reclaim to
* occur.
*/
int sysctl_min_unmapped_ratio = 1;
[PATCH] zone_reclaim: dynamic slab reclaim Currently one can enable slab reclaim by setting an explicit option in /proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final option if the freeing of unmapped file backed pages is not enough to free enough pages to allow a local allocation. However, that means that the slab can grow excessively and that most memory of a node may be used by slabs. We have had a case where a machine with 46GB of memory was using 40-42GB for slab. Zone reclaim was effective in dealing with pagecache pages. However, slab reclaim was only done during global reclaim (which is a bit rare on NUMA systems). This patch implements slab reclaim during zone reclaim. Zone reclaim occurs if there is a danger of an off node allocation. At that point we 1. Shrink the per node page cache if the number of pagecache pages is more than min_unmapped_ratio percent of pages in a zone. 2. Shrink the slab cache if the number of the nodes reclaimable slab pages (patch depends on earlier one that implements that counter) are more than min_slab_ratio (a new /proc/sys/vm tunable). The shrinking of the slab cache is a bit problematic since it is not node specific. So we simply calculate what point in the slab we want to reach (current per node slab use minus the number of pages that neeed to be allocated) and then repeately run the global reclaim until that is unsuccessful or we have reached the limit. I hope we will have zone based slab reclaim at some point which will make that easier. The default for the min_slab_ratio is 5% Also remove the slab option from /proc/sys/vm/zone_reclaim_mode. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 14:31:52 +08:00
/*
* If the number of slab pages in a zone grows beyond this percentage then
* slab reclaim needs to occur.
*/
int sysctl_min_slab_ratio = 5;
vmscan: properly account for the number of page cache pages zone_reclaim() can reclaim A bug was brought to my attention against a distro kernel but it affects mainline and I believe problems like this have been reported in various guises on the mailing lists although I don't have specific examples at the moment. The reported problem was that malloc() stalled for a long time (minutes in some cases) if a large tmpfs mount was occupying a large percentage of memory overall. The pages did not get cleaned or reclaimed by zone_reclaim() because the zone_reclaim_mode was unsuitable, but the lists are uselessly scanned frequencly making the CPU spin at near 100%. This patchset intends to address that bug and bring the behaviour of zone_reclaim() more in line with expectations which were noticed during investigation. It is based on top of mmotm and takes advantage of Kosaki's work with respect to zone_reclaim(). Patch 1 fixes the heuristics that zone_reclaim() uses to determine if the scan should go ahead. The broken heuristic is what was causing the malloc() stall as it uselessly scanned the LRU constantly. Currently, zone_reclaim is assuming zone_reclaim_mode is 1 and historically it could not deal with tmpfs pages at all. This fixes up the heuristic so that an unnecessary scan is more likely to be correctly avoided. Patch 2 notes that zone_reclaim() returning a failure automatically means the zone is marked full. This is not always true. It could have failed because the GFP mask or zone_reclaim_mode were unsuitable. Patch 3 introduces a counter zreclaim_failed that will increment each time the zone_reclaim scan-avoidance heuristics fail. If that counter is rapidly increasing, then zone_reclaim_mode should be set to 0 as a temporarily resolution and a bug reported because the scan-avoidance heuristic is still broken. This patch: On NUMA machines, the administrator can configure zone_reclaim_mode that is a more targetted form of direct reclaim. On machines with large NUMA distances for example, a zone_reclaim_mode defaults to 1 meaning that clean unmapped pages will be reclaimed if the zone watermarks are not being met. There is a heuristic that determines if the scan is worthwhile but the problem is that the heuristic is not being properly applied and is basically assuming zone_reclaim_mode is 1 if it is enabled. The lack of proper detection can manfiest as high CPU usage as the LRU list is scanned uselessly. Historically, once enabled it was depending on NR_FILE_PAGES which may include swapcache pages that the reclaim_mode cannot deal with. Patch vmscan-change-the-number-of-the-unmapped-files-in-zone-reclaim.patch by Kosaki Motohiro noted that zone_page_state(zone, NR_FILE_PAGES) included pages that were not file-backed such as swapcache and made a calculation based on the inactive, active and mapped files. This is far superior when zone_reclaim==1 but if RECLAIM_SWAP is set, then NR_FILE_PAGES is a reasonable starting figure. This patch alters how zone_reclaim() works out how many pages it might be able to reclaim given the current reclaim_mode. If RECLAIM_SWAP is set in the reclaim_mode it will either consider NR_FILE_PAGES as potential candidates or else use NR_{IN}ACTIVE}_PAGES-NR_FILE_MAPPED to discount swapcache and other non-file-backed pages. If RECLAIM_WRITE is not set, then NR_FILE_DIRTY number of pages are not candidates. If RECLAIM_SWAP is not set, then NR_FILE_MAPPED are not. [kosaki.motohiro@jp.fujitsu.com: Estimate unmapped pages minus tmpfs pages] [fengguang.wu@intel.com: Fix underflow problem in Kosaki's estimate] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Christoph Lameter <cl@linux-foundation.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:20 +08:00
static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
{
unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED);
unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) +
zone_page_state(zone, NR_ACTIVE_FILE);
/*
* It's possible for there to be more file mapped pages than
* accounted for by the pages on the file LRU lists because
* tmpfs pages accounted for as ANON can also be FILE_MAPPED
*/
return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0;
}
/* Work out how many page cache pages we can reclaim in this reclaim_mode */
static long zone_pagecache_reclaimable(struct zone *zone)
{
long nr_pagecache_reclaimable;
long delta = 0;
/*
* If RECLAIM_SWAP is set, then all file pages are considered
* potentially reclaimable. Otherwise, we have to worry about
* pages like swapcache and zone_unmapped_file_pages() provides
* a better estimate
*/
if (zone_reclaim_mode & RECLAIM_SWAP)
nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES);
else
nr_pagecache_reclaimable = zone_unmapped_file_pages(zone);
/* If we can't clean pages, remove dirty pages from consideration */
if (!(zone_reclaim_mode & RECLAIM_WRITE))
delta += zone_page_state(zone, NR_FILE_DIRTY);
/* Watch for any possible underflows due to delta */
if (unlikely(delta > nr_pagecache_reclaimable))
delta = nr_pagecache_reclaimable;
return nr_pagecache_reclaimable - delta;
}
/*
* Try to free up some pages from this zone through reclaim.
*/
static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
{
/* Minimum pages needed in order to stay on node */
const unsigned long nr_pages = 1 << order;
struct task_struct *p = current;
struct reclaim_state reclaim_state;
struct scan_control sc = {
.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
.may_swap = 1,
.nr_to_reclaim = max_t(unsigned long, nr_pages,
SWAP_CLUSTER_MAX),
.gfp_mask = gfp_mask,
.order = order,
.priority = ZONE_RECLAIM_PRIORITY,
};
struct shrink_control shrink = {
.gfp_mask = sc.gfp_mask,
};
unsigned long nr_slab_pages0, nr_slab_pages1;
cond_resched();
/*
* We need to be able to allocate from the reserves for RECLAIM_SWAP
* and we also need to be able to write out pages for RECLAIM_WRITE
* and RECLAIM_SWAP.
*/
p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
lockdep_set_current_reclaim_state(gfp_mask);
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
vmscan: properly account for the number of page cache pages zone_reclaim() can reclaim A bug was brought to my attention against a distro kernel but it affects mainline and I believe problems like this have been reported in various guises on the mailing lists although I don't have specific examples at the moment. The reported problem was that malloc() stalled for a long time (minutes in some cases) if a large tmpfs mount was occupying a large percentage of memory overall. The pages did not get cleaned or reclaimed by zone_reclaim() because the zone_reclaim_mode was unsuitable, but the lists are uselessly scanned frequencly making the CPU spin at near 100%. This patchset intends to address that bug and bring the behaviour of zone_reclaim() more in line with expectations which were noticed during investigation. It is based on top of mmotm and takes advantage of Kosaki's work with respect to zone_reclaim(). Patch 1 fixes the heuristics that zone_reclaim() uses to determine if the scan should go ahead. The broken heuristic is what was causing the malloc() stall as it uselessly scanned the LRU constantly. Currently, zone_reclaim is assuming zone_reclaim_mode is 1 and historically it could not deal with tmpfs pages at all. This fixes up the heuristic so that an unnecessary scan is more likely to be correctly avoided. Patch 2 notes that zone_reclaim() returning a failure automatically means the zone is marked full. This is not always true. It could have failed because the GFP mask or zone_reclaim_mode were unsuitable. Patch 3 introduces a counter zreclaim_failed that will increment each time the zone_reclaim scan-avoidance heuristics fail. If that counter is rapidly increasing, then zone_reclaim_mode should be set to 0 as a temporarily resolution and a bug reported because the scan-avoidance heuristic is still broken. This patch: On NUMA machines, the administrator can configure zone_reclaim_mode that is a more targetted form of direct reclaim. On machines with large NUMA distances for example, a zone_reclaim_mode defaults to 1 meaning that clean unmapped pages will be reclaimed if the zone watermarks are not being met. There is a heuristic that determines if the scan is worthwhile but the problem is that the heuristic is not being properly applied and is basically assuming zone_reclaim_mode is 1 if it is enabled. The lack of proper detection can manfiest as high CPU usage as the LRU list is scanned uselessly. Historically, once enabled it was depending on NR_FILE_PAGES which may include swapcache pages that the reclaim_mode cannot deal with. Patch vmscan-change-the-number-of-the-unmapped-files-in-zone-reclaim.patch by Kosaki Motohiro noted that zone_page_state(zone, NR_FILE_PAGES) included pages that were not file-backed such as swapcache and made a calculation based on the inactive, active and mapped files. This is far superior when zone_reclaim==1 but if RECLAIM_SWAP is set, then NR_FILE_PAGES is a reasonable starting figure. This patch alters how zone_reclaim() works out how many pages it might be able to reclaim given the current reclaim_mode. If RECLAIM_SWAP is set in the reclaim_mode it will either consider NR_FILE_PAGES as potential candidates or else use NR_{IN}ACTIVE}_PAGES-NR_FILE_MAPPED to discount swapcache and other non-file-backed pages. If RECLAIM_WRITE is not set, then NR_FILE_DIRTY number of pages are not candidates. If RECLAIM_SWAP is not set, then NR_FILE_MAPPED are not. [kosaki.motohiro@jp.fujitsu.com: Estimate unmapped pages minus tmpfs pages] [fengguang.wu@intel.com: Fix underflow problem in Kosaki's estimate] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Christoph Lameter <cl@linux-foundation.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:20 +08:00
if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) {
[PATCH] zone_reclaim: dynamic slab reclaim Currently one can enable slab reclaim by setting an explicit option in /proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final option if the freeing of unmapped file backed pages is not enough to free enough pages to allow a local allocation. However, that means that the slab can grow excessively and that most memory of a node may be used by slabs. We have had a case where a machine with 46GB of memory was using 40-42GB for slab. Zone reclaim was effective in dealing with pagecache pages. However, slab reclaim was only done during global reclaim (which is a bit rare on NUMA systems). This patch implements slab reclaim during zone reclaim. Zone reclaim occurs if there is a danger of an off node allocation. At that point we 1. Shrink the per node page cache if the number of pagecache pages is more than min_unmapped_ratio percent of pages in a zone. 2. Shrink the slab cache if the number of the nodes reclaimable slab pages (patch depends on earlier one that implements that counter) are more than min_slab_ratio (a new /proc/sys/vm tunable). The shrinking of the slab cache is a bit problematic since it is not node specific. So we simply calculate what point in the slab we want to reach (current per node slab use minus the number of pages that neeed to be allocated) and then repeately run the global reclaim until that is unsuccessful or we have reached the limit. I hope we will have zone based slab reclaim at some point which will make that easier. The default for the min_slab_ratio is 5% Also remove the slab option from /proc/sys/vm/zone_reclaim_mode. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 14:31:52 +08:00
/*
* Free memory by calling shrink zone with increasing
* priorities until we have enough memory freed.
*/
do {
shrink_zone(zone, &sc);
} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
[PATCH] zone_reclaim: dynamic slab reclaim Currently one can enable slab reclaim by setting an explicit option in /proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final option if the freeing of unmapped file backed pages is not enough to free enough pages to allow a local allocation. However, that means that the slab can grow excessively and that most memory of a node may be used by slabs. We have had a case where a machine with 46GB of memory was using 40-42GB for slab. Zone reclaim was effective in dealing with pagecache pages. However, slab reclaim was only done during global reclaim (which is a bit rare on NUMA systems). This patch implements slab reclaim during zone reclaim. Zone reclaim occurs if there is a danger of an off node allocation. At that point we 1. Shrink the per node page cache if the number of pagecache pages is more than min_unmapped_ratio percent of pages in a zone. 2. Shrink the slab cache if the number of the nodes reclaimable slab pages (patch depends on earlier one that implements that counter) are more than min_slab_ratio (a new /proc/sys/vm tunable). The shrinking of the slab cache is a bit problematic since it is not node specific. So we simply calculate what point in the slab we want to reach (current per node slab use minus the number of pages that neeed to be allocated) and then repeately run the global reclaim until that is unsuccessful or we have reached the limit. I hope we will have zone based slab reclaim at some point which will make that easier. The default for the min_slab_ratio is 5% Also remove the slab option from /proc/sys/vm/zone_reclaim_mode. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 14:31:52 +08:00
}
nr_slab_pages0 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
if (nr_slab_pages0 > zone->min_slab_pages) {
/*
* shrink_slab() does not currently allow us to determine how
[PATCH] zone_reclaim: dynamic slab reclaim Currently one can enable slab reclaim by setting an explicit option in /proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final option if the freeing of unmapped file backed pages is not enough to free enough pages to allow a local allocation. However, that means that the slab can grow excessively and that most memory of a node may be used by slabs. We have had a case where a machine with 46GB of memory was using 40-42GB for slab. Zone reclaim was effective in dealing with pagecache pages. However, slab reclaim was only done during global reclaim (which is a bit rare on NUMA systems). This patch implements slab reclaim during zone reclaim. Zone reclaim occurs if there is a danger of an off node allocation. At that point we 1. Shrink the per node page cache if the number of pagecache pages is more than min_unmapped_ratio percent of pages in a zone. 2. Shrink the slab cache if the number of the nodes reclaimable slab pages (patch depends on earlier one that implements that counter) are more than min_slab_ratio (a new /proc/sys/vm tunable). The shrinking of the slab cache is a bit problematic since it is not node specific. So we simply calculate what point in the slab we want to reach (current per node slab use minus the number of pages that neeed to be allocated) and then repeately run the global reclaim until that is unsuccessful or we have reached the limit. I hope we will have zone based slab reclaim at some point which will make that easier. The default for the min_slab_ratio is 5% Also remove the slab option from /proc/sys/vm/zone_reclaim_mode. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 14:31:52 +08:00
* many pages were freed in this zone. So we take the current
* number of slab pages and shake the slab until it is reduced
* by the same nr_pages that we used for reclaiming unmapped
* pages.
*
[PATCH] zone_reclaim: dynamic slab reclaim Currently one can enable slab reclaim by setting an explicit option in /proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final option if the freeing of unmapped file backed pages is not enough to free enough pages to allow a local allocation. However, that means that the slab can grow excessively and that most memory of a node may be used by slabs. We have had a case where a machine with 46GB of memory was using 40-42GB for slab. Zone reclaim was effective in dealing with pagecache pages. However, slab reclaim was only done during global reclaim (which is a bit rare on NUMA systems). This patch implements slab reclaim during zone reclaim. Zone reclaim occurs if there is a danger of an off node allocation. At that point we 1. Shrink the per node page cache if the number of pagecache pages is more than min_unmapped_ratio percent of pages in a zone. 2. Shrink the slab cache if the number of the nodes reclaimable slab pages (patch depends on earlier one that implements that counter) are more than min_slab_ratio (a new /proc/sys/vm tunable). The shrinking of the slab cache is a bit problematic since it is not node specific. So we simply calculate what point in the slab we want to reach (current per node slab use minus the number of pages that neeed to be allocated) and then repeately run the global reclaim until that is unsuccessful or we have reached the limit. I hope we will have zone based slab reclaim at some point which will make that easier. The default for the min_slab_ratio is 5% Also remove the slab option from /proc/sys/vm/zone_reclaim_mode. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 14:31:52 +08:00
* Note that shrink_slab will free memory on all zones and may
* take a long time.
*/
for (;;) {
unsigned long lru_pages = zone_reclaimable_pages(zone);
/* No reclaimable slab or very low memory pressure */
if (!shrink_slab(&shrink, sc.nr_scanned, lru_pages))
break;
/* Freed enough memory */
nr_slab_pages1 = zone_page_state(zone,
NR_SLAB_RECLAIMABLE);
if (nr_slab_pages1 + nr_pages <= nr_slab_pages0)
break;
}
/*
* Update nr_reclaimed by the number of slab pages we
* reclaimed from this zone.
*/
nr_slab_pages1 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
if (nr_slab_pages1 < nr_slab_pages0)
sc.nr_reclaimed += nr_slab_pages0 - nr_slab_pages1;
}
p->reclaim_state = NULL;
current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
lockdep_clear_current_reclaim_state();
vmscan: bail out of direct reclaim after swap_cluster_max pages When the VM is under pressure, it can happen that several direct reclaim processes are in the pageout code simultaneously. It also happens that the reclaiming processes run into mostly referenced, mapped and dirty pages in the first round. This results in multiple direct reclaim processes having a lower pageout priority, which corresponds to a higher target of pages to scan. This in turn can result in each direct reclaim process freeing many pages. Together, they can end up freeing way too many pages. This kicks useful data out of memory (in some cases more than half of all memory is swapped out). It also impacts performance by keeping tasks stuck in the pageout code for too long. A 30% improvement in hackbench has been observed with this patch. The fix is relatively simple: in shrink_zone() we can check how many pages we have already freed, direct reclaim tasks break out of the scanning loop if they have already freed enough pages and have reached a lower priority level. We do not break out of shrink_zone() when priority == DEF_PRIORITY, to ensure that equal pressure is applied to every zone in the common case. However, in order to do this we do need to know how many pages we already freed, so move nr_reclaimed into scan_control. akpm: a historical interlude... We tried this in 2004: :commit e468e46a9bea3297011d5918663ce6d19094cf87 :Author: akpm <akpm> :Date: Thu Jun 24 15:53:52 2004 +0000 : :[PATCH] vmscan.c: dont reclaim too many pages : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly hit : a large number of reclaimable pages on the LRU. : Change things so we bale out when SWAP_CLUSTER_MAX pages have been reclaimed. And we reverted it in 2006: :commit 210fe530305ee50cd889fe9250168228b2994f32 :Author: Andrew Morton <akpm@osdl.org> :Date: Fri Jan 6 00:11:14 2006 -0800 : : [PATCH] vmscan: balancing fix : : Revert a patch which went into 2.6.8-rc1. The changelog for that patch was: : : The shrink_zone() logic can, under some circumstances, cause far too many : pages to be reclaimed. Say, we're scanning at high priority and suddenly : hit a large number of reclaimable pages on the LRU. : : Change things so we bale out when SWAP_CLUSTER_MAX pages have been : reclaimed. : : Problem is, this change caused significant imbalance in inter-zone scan : balancing by truncating scans of larger zones. : : Suppose, for example, ZONE_HIGHMEM is 10x the size of ZONE_NORMAL. The zone : balancing algorithm would require that if we're scanning 100 pages of : ZONE_HIGHMEM, we should scan 10 pages of ZONE_NORMAL. But this logic will : cause the scanning of ZONE_HIGHMEM to bale out after only 32 pages are : reclaimed. Thus effectively causing smaller zones to be scanned relatively : harder than large ones. : : Now I need to remember what the workload was which caused me to write this : patch originally, then fix it up in a different way... And we haven't demonstrated that whatever problem caused that reversion is not being reintroduced by this change in 2008. Signed-off-by: Rik van Riel <riel@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:01 +08:00
return sc.nr_reclaimed >= nr_pages;
}
int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
{
int node_id;
int ret;
/*
[PATCH] zone_reclaim: dynamic slab reclaim Currently one can enable slab reclaim by setting an explicit option in /proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final option if the freeing of unmapped file backed pages is not enough to free enough pages to allow a local allocation. However, that means that the slab can grow excessively and that most memory of a node may be used by slabs. We have had a case where a machine with 46GB of memory was using 40-42GB for slab. Zone reclaim was effective in dealing with pagecache pages. However, slab reclaim was only done during global reclaim (which is a bit rare on NUMA systems). This patch implements slab reclaim during zone reclaim. Zone reclaim occurs if there is a danger of an off node allocation. At that point we 1. Shrink the per node page cache if the number of pagecache pages is more than min_unmapped_ratio percent of pages in a zone. 2. Shrink the slab cache if the number of the nodes reclaimable slab pages (patch depends on earlier one that implements that counter) are more than min_slab_ratio (a new /proc/sys/vm tunable). The shrinking of the slab cache is a bit problematic since it is not node specific. So we simply calculate what point in the slab we want to reach (current per node slab use minus the number of pages that neeed to be allocated) and then repeately run the global reclaim until that is unsuccessful or we have reached the limit. I hope we will have zone based slab reclaim at some point which will make that easier. The default for the min_slab_ratio is 5% Also remove the slab option from /proc/sys/vm/zone_reclaim_mode. [akpm@osdl.org: cleanups] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 14:31:52 +08:00
* Zone reclaim reclaims unmapped file backed pages and
* slab pages if we are over the defined limits.
*
* A small portion of unmapped file backed pages is needed for
* file I/O otherwise pages read by file I/O will be immediately
* thrown out if the zone is overallocated. So we do not reclaim
* if less than a specified percentage of the zone is used by
* unmapped file backed pages.
*/
vmscan: properly account for the number of page cache pages zone_reclaim() can reclaim A bug was brought to my attention against a distro kernel but it affects mainline and I believe problems like this have been reported in various guises on the mailing lists although I don't have specific examples at the moment. The reported problem was that malloc() stalled for a long time (minutes in some cases) if a large tmpfs mount was occupying a large percentage of memory overall. The pages did not get cleaned or reclaimed by zone_reclaim() because the zone_reclaim_mode was unsuitable, but the lists are uselessly scanned frequencly making the CPU spin at near 100%. This patchset intends to address that bug and bring the behaviour of zone_reclaim() more in line with expectations which were noticed during investigation. It is based on top of mmotm and takes advantage of Kosaki's work with respect to zone_reclaim(). Patch 1 fixes the heuristics that zone_reclaim() uses to determine if the scan should go ahead. The broken heuristic is what was causing the malloc() stall as it uselessly scanned the LRU constantly. Currently, zone_reclaim is assuming zone_reclaim_mode is 1 and historically it could not deal with tmpfs pages at all. This fixes up the heuristic so that an unnecessary scan is more likely to be correctly avoided. Patch 2 notes that zone_reclaim() returning a failure automatically means the zone is marked full. This is not always true. It could have failed because the GFP mask or zone_reclaim_mode were unsuitable. Patch 3 introduces a counter zreclaim_failed that will increment each time the zone_reclaim scan-avoidance heuristics fail. If that counter is rapidly increasing, then zone_reclaim_mode should be set to 0 as a temporarily resolution and a bug reported because the scan-avoidance heuristic is still broken. This patch: On NUMA machines, the administrator can configure zone_reclaim_mode that is a more targetted form of direct reclaim. On machines with large NUMA distances for example, a zone_reclaim_mode defaults to 1 meaning that clean unmapped pages will be reclaimed if the zone watermarks are not being met. There is a heuristic that determines if the scan is worthwhile but the problem is that the heuristic is not being properly applied and is basically assuming zone_reclaim_mode is 1 if it is enabled. The lack of proper detection can manfiest as high CPU usage as the LRU list is scanned uselessly. Historically, once enabled it was depending on NR_FILE_PAGES which may include swapcache pages that the reclaim_mode cannot deal with. Patch vmscan-change-the-number-of-the-unmapped-files-in-zone-reclaim.patch by Kosaki Motohiro noted that zone_page_state(zone, NR_FILE_PAGES) included pages that were not file-backed such as swapcache and made a calculation based on the inactive, active and mapped files. This is far superior when zone_reclaim==1 but if RECLAIM_SWAP is set, then NR_FILE_PAGES is a reasonable starting figure. This patch alters how zone_reclaim() works out how many pages it might be able to reclaim given the current reclaim_mode. If RECLAIM_SWAP is set in the reclaim_mode it will either consider NR_FILE_PAGES as potential candidates or else use NR_{IN}ACTIVE}_PAGES-NR_FILE_MAPPED to discount swapcache and other non-file-backed pages. If RECLAIM_WRITE is not set, then NR_FILE_DIRTY number of pages are not candidates. If RECLAIM_SWAP is not set, then NR_FILE_MAPPED are not. [kosaki.motohiro@jp.fujitsu.com: Estimate unmapped pages minus tmpfs pages] [fengguang.wu@intel.com: Fix underflow problem in Kosaki's estimate] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Christoph Lameter <cl@linux-foundation.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:20 +08:00
if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
vmscan: do not unconditionally treat zones that fail zone_reclaim() as full On NUMA machines, the administrator can configure zone_reclaim_mode that is a more targetted form of direct reclaim. On machines with large NUMA distances for example, a zone_reclaim_mode defaults to 1 meaning that clean unmapped pages will be reclaimed if the zone watermarks are not being met. The problem is that zone_reclaim() failing at all means the zone gets marked full. This can cause situations where a zone is usable, but is being skipped because it has been considered full. Take a situation where a large tmpfs mount is occuping a large percentage of memory overall. The pages do not get cleaned or reclaimed by zone_reclaim(), but the zone gets marked full and the zonelist cache considers them not worth trying in the future. This patch makes zone_reclaim() return more fine-grained information about what occured when zone_reclaim() failued. The zone only gets marked full if it really is unreclaimable. If it's a case that the scan did not occur or if enough pages were not reclaimed with the limited reclaim_mode, then the zone is simply skipped. There is a side-effect to this patch. Currently, if zone_reclaim() successfully reclaimed SWAP_CLUSTER_MAX, an allocation attempt would go ahead. With this patch applied, zone watermarks are rechecked after zone_reclaim() does some work. This bug was introduced by commit 9276b1bc96a132f4068fdee00983c532f43d3a26 ("memory page_alloc zonelist caching speedup") way back in 2.6.19 when the zonelist_cache was introduced. It was not intended that zone_reclaim() aggressively consider the zone to be full when it failed as full direct reclaim can still be an option. Due to the age of the bug, it should be considered a -stable candidate. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:22 +08:00
return ZONE_RECLAIM_FULL;
if (zone->all_unreclaimable)
vmscan: do not unconditionally treat zones that fail zone_reclaim() as full On NUMA machines, the administrator can configure zone_reclaim_mode that is a more targetted form of direct reclaim. On machines with large NUMA distances for example, a zone_reclaim_mode defaults to 1 meaning that clean unmapped pages will be reclaimed if the zone watermarks are not being met. The problem is that zone_reclaim() failing at all means the zone gets marked full. This can cause situations where a zone is usable, but is being skipped because it has been considered full. Take a situation where a large tmpfs mount is occuping a large percentage of memory overall. The pages do not get cleaned or reclaimed by zone_reclaim(), but the zone gets marked full and the zonelist cache considers them not worth trying in the future. This patch makes zone_reclaim() return more fine-grained information about what occured when zone_reclaim() failued. The zone only gets marked full if it really is unreclaimable. If it's a case that the scan did not occur or if enough pages were not reclaimed with the limited reclaim_mode, then the zone is simply skipped. There is a side-effect to this patch. Currently, if zone_reclaim() successfully reclaimed SWAP_CLUSTER_MAX, an allocation attempt would go ahead. With this patch applied, zone watermarks are rechecked after zone_reclaim() does some work. This bug was introduced by commit 9276b1bc96a132f4068fdee00983c532f43d3a26 ("memory page_alloc zonelist caching speedup") way back in 2.6.19 when the zonelist_cache was introduced. It was not intended that zone_reclaim() aggressively consider the zone to be full when it failed as full direct reclaim can still be an option. Due to the age of the bug, it should be considered a -stable candidate. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:22 +08:00
return ZONE_RECLAIM_FULL;
/*
* Do not scan if the allocation should not be delayed.
*/
if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
vmscan: do not unconditionally treat zones that fail zone_reclaim() as full On NUMA machines, the administrator can configure zone_reclaim_mode that is a more targetted form of direct reclaim. On machines with large NUMA distances for example, a zone_reclaim_mode defaults to 1 meaning that clean unmapped pages will be reclaimed if the zone watermarks are not being met. The problem is that zone_reclaim() failing at all means the zone gets marked full. This can cause situations where a zone is usable, but is being skipped because it has been considered full. Take a situation where a large tmpfs mount is occuping a large percentage of memory overall. The pages do not get cleaned or reclaimed by zone_reclaim(), but the zone gets marked full and the zonelist cache considers them not worth trying in the future. This patch makes zone_reclaim() return more fine-grained information about what occured when zone_reclaim() failued. The zone only gets marked full if it really is unreclaimable. If it's a case that the scan did not occur or if enough pages were not reclaimed with the limited reclaim_mode, then the zone is simply skipped. There is a side-effect to this patch. Currently, if zone_reclaim() successfully reclaimed SWAP_CLUSTER_MAX, an allocation attempt would go ahead. With this patch applied, zone watermarks are rechecked after zone_reclaim() does some work. This bug was introduced by commit 9276b1bc96a132f4068fdee00983c532f43d3a26 ("memory page_alloc zonelist caching speedup") way back in 2.6.19 when the zonelist_cache was introduced. It was not intended that zone_reclaim() aggressively consider the zone to be full when it failed as full direct reclaim can still be an option. Due to the age of the bug, it should be considered a -stable candidate. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:22 +08:00
return ZONE_RECLAIM_NOSCAN;
/*
* Only run zone reclaim on the local zone or on zones that do not
* have associated processors. This will favor the local processor
* over remote processors and spread off node memory allocations
* as wide as possible.
*/
node_id = zone_to_nid(zone);
if (node_state(node_id, N_CPU) && node_id != numa_node_id())
vmscan: do not unconditionally treat zones that fail zone_reclaim() as full On NUMA machines, the administrator can configure zone_reclaim_mode that is a more targetted form of direct reclaim. On machines with large NUMA distances for example, a zone_reclaim_mode defaults to 1 meaning that clean unmapped pages will be reclaimed if the zone watermarks are not being met. The problem is that zone_reclaim() failing at all means the zone gets marked full. This can cause situations where a zone is usable, but is being skipped because it has been considered full. Take a situation where a large tmpfs mount is occuping a large percentage of memory overall. The pages do not get cleaned or reclaimed by zone_reclaim(), but the zone gets marked full and the zonelist cache considers them not worth trying in the future. This patch makes zone_reclaim() return more fine-grained information about what occured when zone_reclaim() failued. The zone only gets marked full if it really is unreclaimable. If it's a case that the scan did not occur or if enough pages were not reclaimed with the limited reclaim_mode, then the zone is simply skipped. There is a side-effect to this patch. Currently, if zone_reclaim() successfully reclaimed SWAP_CLUSTER_MAX, an allocation attempt would go ahead. With this patch applied, zone watermarks are rechecked after zone_reclaim() does some work. This bug was introduced by commit 9276b1bc96a132f4068fdee00983c532f43d3a26 ("memory page_alloc zonelist caching speedup") way back in 2.6.19 when the zonelist_cache was introduced. It was not intended that zone_reclaim() aggressively consider the zone to be full when it failed as full direct reclaim can still be an option. Due to the age of the bug, it should be considered a -stable candidate. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:22 +08:00
return ZONE_RECLAIM_NOSCAN;
if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
vmscan: do not unconditionally treat zones that fail zone_reclaim() as full On NUMA machines, the administrator can configure zone_reclaim_mode that is a more targetted form of direct reclaim. On machines with large NUMA distances for example, a zone_reclaim_mode defaults to 1 meaning that clean unmapped pages will be reclaimed if the zone watermarks are not being met. The problem is that zone_reclaim() failing at all means the zone gets marked full. This can cause situations where a zone is usable, but is being skipped because it has been considered full. Take a situation where a large tmpfs mount is occuping a large percentage of memory overall. The pages do not get cleaned or reclaimed by zone_reclaim(), but the zone gets marked full and the zonelist cache considers them not worth trying in the future. This patch makes zone_reclaim() return more fine-grained information about what occured when zone_reclaim() failued. The zone only gets marked full if it really is unreclaimable. If it's a case that the scan did not occur or if enough pages were not reclaimed with the limited reclaim_mode, then the zone is simply skipped. There is a side-effect to this patch. Currently, if zone_reclaim() successfully reclaimed SWAP_CLUSTER_MAX, an allocation attempt would go ahead. With this patch applied, zone watermarks are rechecked after zone_reclaim() does some work. This bug was introduced by commit 9276b1bc96a132f4068fdee00983c532f43d3a26 ("memory page_alloc zonelist caching speedup") way back in 2.6.19 when the zonelist_cache was introduced. It was not intended that zone_reclaim() aggressively consider the zone to be full when it failed as full direct reclaim can still be an option. Due to the age of the bug, it should be considered a -stable candidate. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 06:33:22 +08:00
return ZONE_RECLAIM_NOSCAN;
ret = __zone_reclaim(zone, gfp_mask, order);
zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
if (!ret)
count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
return ret;
}
#endif
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
/*
* page_evictable - test whether a page is evictable
* @page: the page to test
* @vma: the VMA in which the page is or will be mapped, may be NULL
*
* Test whether page is evictable--i.e., should be placed on active/inactive
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
* lists vs unevictable list. The vma argument is !NULL when called from the
* fault path to determine how to instantate a new page.
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
*
* Reasons page might not be evictable:
Ramfs and Ram Disk pages are unevictable Christoph Lameter pointed out that ram disk pages also clutter the LRU lists. When vmscan finds them dirty and tries to clean them, the ram disk writeback function just redirties the page so that it goes back onto the active list. Round and round she goes... With the ram disk driver [rd.c] replaced by the newer 'brd.c', this is no longer the case, as ram disk pages are no longer maintained on the lru. [This makes them unmigratable for defrag or memory hot remove, but that can be addressed by a separate patch series.] However, the ramfs pages behave like ram disk pages used to, so: Define new address_space flag [shares address_space flags member with mapping's gfp mask] to indicate that the address space contains all unevictable pages. This will provide for efficient testing of ramfs pages in page_evictable(). Also provide wrapper functions to set/test the unevictable state to minimize #ifdefs in ramfs driver and any other users of this facility. Set the unevictable state on address_space structures for new ramfs inodes. Test the unevictable state in page_evictable() to cull unevictable pages. These changes depend on [CONFIG_]UNEVICTABLE_LRU. [riel@redhat.com: undo the brd.c part] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Debugged-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:42 +08:00
* (1) page's mapping marked unevictable
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
* (2) page is part of an mlocked VMA
Ramfs and Ram Disk pages are unevictable Christoph Lameter pointed out that ram disk pages also clutter the LRU lists. When vmscan finds them dirty and tries to clean them, the ram disk writeback function just redirties the page so that it goes back onto the active list. Round and round she goes... With the ram disk driver [rd.c] replaced by the newer 'brd.c', this is no longer the case, as ram disk pages are no longer maintained on the lru. [This makes them unmigratable for defrag or memory hot remove, but that can be addressed by a separate patch series.] However, the ramfs pages behave like ram disk pages used to, so: Define new address_space flag [shares address_space flags member with mapping's gfp mask] to indicate that the address space contains all unevictable pages. This will provide for efficient testing of ramfs pages in page_evictable(). Also provide wrapper functions to set/test the unevictable state to minimize #ifdefs in ramfs driver and any other users of this facility. Set the unevictable state on address_space structures for new ramfs inodes. Test the unevictable state in page_evictable() to cull unevictable pages. These changes depend on [CONFIG_]UNEVICTABLE_LRU. [riel@redhat.com: undo the brd.c part] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Debugged-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:42 +08:00
*
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
*/
int page_evictable(struct page *page, struct vm_area_struct *vma)
{
Ramfs and Ram Disk pages are unevictable Christoph Lameter pointed out that ram disk pages also clutter the LRU lists. When vmscan finds them dirty and tries to clean them, the ram disk writeback function just redirties the page so that it goes back onto the active list. Round and round she goes... With the ram disk driver [rd.c] replaced by the newer 'brd.c', this is no longer the case, as ram disk pages are no longer maintained on the lru. [This makes them unmigratable for defrag or memory hot remove, but that can be addressed by a separate patch series.] However, the ramfs pages behave like ram disk pages used to, so: Define new address_space flag [shares address_space flags member with mapping's gfp mask] to indicate that the address space contains all unevictable pages. This will provide for efficient testing of ramfs pages in page_evictable(). Also provide wrapper functions to set/test the unevictable state to minimize #ifdefs in ramfs driver and any other users of this facility. Set the unevictable state on address_space structures for new ramfs inodes. Test the unevictable state in page_evictable() to cull unevictable pages. These changes depend on [CONFIG_]UNEVICTABLE_LRU. [riel@redhat.com: undo the brd.c part] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Debugged-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:42 +08:00
if (mapping_unevictable(page_mapping(page)))
return 0;
if (PageMlocked(page) || (vma && mlocked_vma_newpage(vma, page)))
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
return 0;
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
return 1;
}
SHM_UNLOCK: fix long unpreemptible section scan_mapping_unevictable_pages() is used to make SysV SHM_LOCKed pages evictable again once the shared memory is unlocked. It does this with pagevec_lookup()s across the whole object (which might occupy most of memory), and takes 300ms to unlock 7GB here. A cond_resched() every PAGEVEC_SIZE pages would be good. However, KOSAKI-san points out that this is called under shmem.c's info->lock, and it's also under shm.c's shm_lock(), both spinlocks. There is no strong reason for that: we need to take these pages off the unevictable list soonish, but those locks are not required for it. So move the call to scan_mapping_unevictable_pages() from shmem.c's unlock handling up to shm.c's unlock handling. Remove the recently added barrier, not needed now we have spin_unlock() before the scan. Use get_file(), with subsequent fput(), to make sure we have a reference to mapping throughout scan_mapping_unevictable_pages(): that's something that was previously guaranteed by the shm_lock(). Remove shmctl's lru_add_drain_all(): we don't fault in pages at SHM_LOCK time, and we lazily discover them to be Unevictable later, so it serves no purpose for SHM_LOCK; and serves no purpose for SHM_UNLOCK, since pages still on pagevec are not marked Unevictable. The original code avoided redundant rescans by checking VM_LOCKED flag at its level: now avoid them by checking shp's SHM_LOCKED. The original code called scan_mapping_unevictable_pages() on a locked area at shm_destroy() time: perhaps we once had accounting cross-checks which required that, but not now, so skip the overhead and just let inode eviction deal with them. Put check_move_unevictable_page() and scan_mapping_unevictable_pages() under CONFIG_SHMEM (with stub for the TINY case when ramfs is used), more as comment than to save space; comment them used for SHM_UNLOCK. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:19 +08:00
#ifdef CONFIG_SHMEM
/**
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
* check_move_unevictable_pages - check pages for evictability and move to appropriate zone lru list
* @pages: array of pages to check
* @nr_pages: number of pages to check
*
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
* Checks pages for evictability and moves them to the appropriate lru list.
SHM_UNLOCK: fix long unpreemptible section scan_mapping_unevictable_pages() is used to make SysV SHM_LOCKed pages evictable again once the shared memory is unlocked. It does this with pagevec_lookup()s across the whole object (which might occupy most of memory), and takes 300ms to unlock 7GB here. A cond_resched() every PAGEVEC_SIZE pages would be good. However, KOSAKI-san points out that this is called under shmem.c's info->lock, and it's also under shm.c's shm_lock(), both spinlocks. There is no strong reason for that: we need to take these pages off the unevictable list soonish, but those locks are not required for it. So move the call to scan_mapping_unevictable_pages() from shmem.c's unlock handling up to shm.c's unlock handling. Remove the recently added barrier, not needed now we have spin_unlock() before the scan. Use get_file(), with subsequent fput(), to make sure we have a reference to mapping throughout scan_mapping_unevictable_pages(): that's something that was previously guaranteed by the shm_lock(). Remove shmctl's lru_add_drain_all(): we don't fault in pages at SHM_LOCK time, and we lazily discover them to be Unevictable later, so it serves no purpose for SHM_LOCK; and serves no purpose for SHM_UNLOCK, since pages still on pagevec are not marked Unevictable. The original code avoided redundant rescans by checking VM_LOCKED flag at its level: now avoid them by checking shp's SHM_LOCKED. The original code called scan_mapping_unevictable_pages() on a locked area at shm_destroy() time: perhaps we once had accounting cross-checks which required that, but not now, so skip the overhead and just let inode eviction deal with them. Put check_move_unevictable_page() and scan_mapping_unevictable_pages() under CONFIG_SHMEM (with stub for the TINY case when ramfs is used), more as comment than to save space; comment them used for SHM_UNLOCK. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:19 +08:00
*
* This function is only used for SysV IPC SHM_UNLOCK.
*/
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
void check_move_unevictable_pages(struct page **pages, int nr_pages)
{
struct lruvec *lruvec;
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
struct zone *zone = NULL;
int pgscanned = 0;
int pgrescued = 0;
int i;
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
for (i = 0; i < nr_pages; i++) {
struct page *page = pages[i];
struct zone *pagezone;
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
pgscanned++;
pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock_irq(&zone->lru_lock);
zone = pagezone;
spin_lock_irq(&zone->lru_lock);
}
lruvec = mem_cgroup_page_lruvec(page, zone);
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
if (!PageLRU(page) || !PageUnevictable(page))
continue;
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
if (page_evictable(page, NULL)) {
enum lru_list lru = page_lru_base_type(page);
VM_BUG_ON(PageActive(page));
ClearPageUnevictable(page);
del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE);
add_page_to_lru_list(page, lruvec, lru);
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
pgrescued++;
}
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
}
SHM_UNLOCK: fix Unevictable pages stranded after swap Commit cc39c6a9bbde ("mm: account skipped entries to avoid looping in find_get_pages") correctly fixed an infinite loop; but left a problem that find_get_pages() on shmem would return 0 (appearing to callers to mean end of tree) when it meets a run of nr_pages swap entries. The only uses of find_get_pages() on shmem are via pagevec_lookup(), called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's scan_mapping_unevictable_pages(). The first is already commented, and not worth worrying about; but the second can leave pages on the Unevictable list after an unusual sequence of swapping and locking. Fix that by using shmem_find_get_pages_and_swap() (then ignoring the swap) instead of pagevec_lookup(). But I don't want to contaminate vmscan.c with shmem internals, nor shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into shmem.c, renaming it shmem_unlock_mapping(); and rename check_move_unevictable_page() to check_move_unevictable_pages(), looping down an array of pages, oftentimes under the same lock. Leave out the "rotate unevictable list" block: that's a leftover from when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed handling involved looking at pages at tail of LRU. Was there significance to the sequence first ClearPageUnevictable, then test page_evictable, then SetPageUnevictable here? I think not, we're under LRU lock, and have no barriers between those. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:21 +08:00
if (zone) {
__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
spin_unlock_irq(&zone->lru_lock);
}
}
SHM_UNLOCK: fix long unpreemptible section scan_mapping_unevictable_pages() is used to make SysV SHM_LOCKed pages evictable again once the shared memory is unlocked. It does this with pagevec_lookup()s across the whole object (which might occupy most of memory), and takes 300ms to unlock 7GB here. A cond_resched() every PAGEVEC_SIZE pages would be good. However, KOSAKI-san points out that this is called under shmem.c's info->lock, and it's also under shm.c's shm_lock(), both spinlocks. There is no strong reason for that: we need to take these pages off the unevictable list soonish, but those locks are not required for it. So move the call to scan_mapping_unevictable_pages() from shmem.c's unlock handling up to shm.c's unlock handling. Remove the recently added barrier, not needed now we have spin_unlock() before the scan. Use get_file(), with subsequent fput(), to make sure we have a reference to mapping throughout scan_mapping_unevictable_pages(): that's something that was previously guaranteed by the shm_lock(). Remove shmctl's lru_add_drain_all(): we don't fault in pages at SHM_LOCK time, and we lazily discover them to be Unevictable later, so it serves no purpose for SHM_LOCK; and serves no purpose for SHM_UNLOCK, since pages still on pagevec are not marked Unevictable. The original code avoided redundant rescans by checking VM_LOCKED flag at its level: now avoid them by checking shp's SHM_LOCKED. The original code called scan_mapping_unevictable_pages() on a locked area at shm_destroy() time: perhaps we once had accounting cross-checks which required that, but not now, so skip the overhead and just let inode eviction deal with them. Put check_move_unevictable_page() and scan_mapping_unevictable_pages() under CONFIG_SHMEM (with stub for the TINY case when ramfs is used), more as comment than to save space; comment them used for SHM_UNLOCK. Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-21 06:34:19 +08:00
#endif /* CONFIG_SHMEM */
static void warn_scan_unevictable_pages(void)
{
printk_once(KERN_WARNING
"%s: The scan_unevictable_pages sysctl/node-interface has been "
"disabled for lack of a legitimate use case. If you have "
"one, please send an email to linux-mm@kvack.org.\n",
current->comm);
}
/*
* scan_unevictable_pages [vm] sysctl handler. On demand re-scan of
* all nodes' unevictable lists for evictable pages
*/
unsigned long scan_unevictable_pages;
int scan_unevictable_handler(struct ctl_table *table, int write,
void __user *buffer,
size_t *length, loff_t *ppos)
{
warn_scan_unevictable_pages();
proc_doulongvec_minmax(table, write, buffer, length, ppos);
scan_unevictable_pages = 0;
return 0;
}
#ifdef CONFIG_NUMA
/*
* per node 'scan_unevictable_pages' attribute. On demand re-scan of
* a specified node's per zone unevictable lists for evictable pages.
*/
static ssize_t read_scan_unevictable_node(struct device *dev,
struct device_attribute *attr,
char *buf)
{
warn_scan_unevictable_pages();
return sprintf(buf, "0\n"); /* always zero; should fit... */
}
static ssize_t write_scan_unevictable_node(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
warn_scan_unevictable_pages();
return 1;
}
static DEVICE_ATTR(scan_unevictable_pages, S_IRUGO | S_IWUSR,
read_scan_unevictable_node,
write_scan_unevictable_node);
int scan_unevictable_register_node(struct node *node)
{
return device_create_file(&node->dev, &dev_attr_scan_unevictable_pages);
}
void scan_unevictable_unregister_node(struct node *node)
{
device_remove_file(&node->dev, &dev_attr_scan_unevictable_pages);
}
#endif