2008-02-07 16:13:50 +08:00
|
|
|
/* memcontrol.h - Memory Controller
|
|
|
|
*
|
|
|
|
* Copyright IBM Corporation, 2007
|
|
|
|
* Author Balbir Singh <balbir@linux.vnet.ibm.com>
|
|
|
|
*
|
2008-02-07 16:13:51 +08:00
|
|
|
* Copyright 2007 OpenVZ SWsoft Inc
|
|
|
|
* Author: Pavel Emelianov <xemul@openvz.org>
|
|
|
|
*
|
2008-02-07 16:13:50 +08:00
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License as published by
|
|
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
|
|
* (at your option) any later version.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
* GNU General Public License for more details.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _LINUX_MEMCONTROL_H
|
|
|
|
#define _LINUX_MEMCONTROL_H
|
2009-01-08 10:08:02 +08:00
|
|
|
#include <linux/cgroup.h>
|
2011-05-27 07:25:38 +08:00
|
|
|
#include <linux/vm_event_item.h>
|
2012-12-19 06:21:56 +08:00
|
|
|
#include <linux/hardirq.h>
|
2012-12-19 06:22:09 +08:00
|
|
|
#include <linux/jump_label.h>
|
2015-09-09 06:01:02 +08:00
|
|
|
#include <linux/page_counter.h>
|
|
|
|
#include <linux/vmpressure.h>
|
|
|
|
#include <linux/eventfd.h>
|
|
|
|
#include <linux/mmzone.h>
|
|
|
|
#include <linux/writeback.h>
|
2016-03-16 05:57:25 +08:00
|
|
|
#include <linux/page-flags.h>
|
2011-05-27 07:25:38 +08:00
|
|
|
|
2008-02-07 16:13:51 +08:00
|
|
|
struct mem_cgroup;
|
2008-02-07 16:13:59 +08:00
|
|
|
struct page;
|
|
|
|
struct mm_struct;
|
2012-12-19 06:22:34 +08:00
|
|
|
struct kmem_cache;
|
2008-02-07 16:13:51 +08:00
|
|
|
|
2013-09-13 06:13:50 +08:00
|
|
|
/*
|
|
|
|
* The corresponding mem_cgroup_stat_names is defined in mm/memcontrol.c,
|
|
|
|
* These two lists should keep in accord with each other.
|
|
|
|
*/
|
|
|
|
enum mem_cgroup_stat_index {
|
|
|
|
/*
|
|
|
|
* For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
|
|
|
|
*/
|
|
|
|
MEM_CGROUP_STAT_CACHE, /* # of pages charged as cache */
|
|
|
|
MEM_CGROUP_STAT_RSS, /* # of pages charged as anon rss */
|
|
|
|
MEM_CGROUP_STAT_RSS_HUGE, /* # of pages charged as anon huge */
|
|
|
|
MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
|
memcg: add per cgroup dirty page accounting
When modifying PG_Dirty on cached file pages, update the new
MEM_CGROUP_STAT_DIRTY counter. This is done in the same places where
global NR_FILE_DIRTY is managed. The new memcg stat is visible in the
per memcg memory.stat cgroupfs file. The most recent past attempt at
this was http://thread.gmane.org/gmane.linux.kernel.cgroups/8632
The new accounting supports future efforts to add per cgroup dirty
page throttling and writeback. It also helps an administrator break
down a container's memory usage and provides evidence to understand
memcg oom kills (the new dirty count is included in memcg oom kill
messages).
The ability to move page accounting between memcg
(memory.move_charge_at_immigrate) makes this accounting more
complicated than the global counter. The existing
mem_cgroup_{begin,end}_page_stat() lock is used to serialize move
accounting with stat updates.
Typical update operation:
memcg = mem_cgroup_begin_page_stat(page)
if (TestSetPageDirty()) {
[...]
mem_cgroup_update_page_stat(memcg)
}
mem_cgroup_end_page_stat(memcg)
Summary of mem_cgroup_end_page_stat() overhead:
- Without CONFIG_MEMCG it's a no-op
- With CONFIG_MEMCG and no inter memcg task movement, it's just
rcu_read_lock()
- With CONFIG_MEMCG and inter memcg task movement, it's
rcu_read_lock() + spin_lock_irqsave()
A memcg parameter is added to several routines because their callers
now grab mem_cgroup_begin_page_stat() which returns the memcg later
needed by for mem_cgroup_update_page_stat().
Because mem_cgroup_begin_page_stat() may disable interrupts, some
adjustments are needed:
- move __mark_inode_dirty() from __set_page_dirty() to its caller.
__mark_inode_dirty() locking does not want interrupts disabled.
- use spin_lock_irqsave(tree_lock) rather than spin_lock_irq() in
__delete_from_page_cache(), replace_page_cache_page(),
invalidate_complete_page2(), and __remove_mapping().
text data bss dec hex filename
8925147 1774832 1785856 12485835 be84cb vmlinux-!CONFIG_MEMCG-before
8925339 1774832 1785856 12486027 be858b vmlinux-!CONFIG_MEMCG-after
+192 text bytes
8965977 1784992 1785856 12536825 bf4bf9 vmlinux-CONFIG_MEMCG-before
8966750 1784992 1785856 12537598 bf4efe vmlinux-CONFIG_MEMCG-after
+773 text bytes
Performance tests run on v4.0-rc1-36-g4f671fe2f952. Lower is better for
all metrics, they're all wall clock or cycle counts. The read and write
fault benchmarks just measure fault time, they do not include I/O time.
* CONFIG_MEMCG not set:
baseline patched
kbuild 1m25.030000(+-0.088% 3 samples) 1m25.426667(+-0.120% 3 samples)
dd write 100 MiB 0.859211561 +-15.10% 0.874162885 +-15.03%
dd write 200 MiB 1.670653105 +-17.87% 1.669384764 +-11.99%
dd write 1000 MiB 8.434691190 +-14.15% 8.474733215 +-14.77%
read fault cycles 254.0(+-0.000% 10 samples) 253.0(+-0.000% 10 samples)
write fault cycles 2021.2(+-3.070% 10 samples) 1984.5(+-1.036% 10 samples)
* CONFIG_MEMCG=y root_memcg:
baseline patched
kbuild 1m25.716667(+-0.105% 3 samples) 1m25.686667(+-0.153% 3 samples)
dd write 100 MiB 0.855650830 +-14.90% 0.887557919 +-14.90%
dd write 200 MiB 1.688322953 +-12.72% 1.667682724 +-13.33%
dd write 1000 MiB 8.418601605 +-14.30% 8.673532299 +-15.00%
read fault cycles 266.0(+-0.000% 10 samples) 266.0(+-0.000% 10 samples)
write fault cycles 2051.7(+-1.349% 10 samples) 2049.6(+-1.686% 10 samples)
* CONFIG_MEMCG=y non-root_memcg:
baseline patched
kbuild 1m26.120000(+-0.273% 3 samples) 1m25.763333(+-0.127% 3 samples)
dd write 100 MiB 0.861723964 +-15.25% 0.818129350 +-14.82%
dd write 200 MiB 1.669887569 +-13.30% 1.698645885 +-13.27%
dd write 1000 MiB 8.383191730 +-14.65% 8.351742280 +-14.52%
read fault cycles 265.7(+-0.172% 10 samples) 267.0(+-0.000% 10 samples)
write fault cycles 2070.6(+-1.512% 10 samples) 2084.4(+-2.148% 10 samples)
As expected anon page faults are not affected by this patch.
tj: Updated to apply on top of the recent cancel_dirty_page() changes.
Signed-off-by: Sha Zhengju <handai.szj@gmail.com>
Signed-off-by: Greg Thelen <gthelen@google.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-23 05:13:16 +08:00
|
|
|
MEM_CGROUP_STAT_DIRTY, /* # of dirty pages in page cache */
|
2013-09-13 06:13:53 +08:00
|
|
|
MEM_CGROUP_STAT_WRITEBACK, /* # of pages under writeback */
|
2013-09-13 06:13:50 +08:00
|
|
|
MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
|
|
|
|
MEM_CGROUP_STAT_NSTATS,
|
2016-01-21 07:03:22 +08:00
|
|
|
/* default hierarchy stats */
|
2016-07-29 06:48:17 +08:00
|
|
|
MEMCG_KERNEL_STACK_KB = MEM_CGROUP_STAT_NSTATS,
|
2016-03-18 05:17:35 +08:00
|
|
|
MEMCG_SLAB_RECLAIMABLE,
|
|
|
|
MEMCG_SLAB_UNRECLAIMABLE,
|
2016-03-18 05:17:38 +08:00
|
|
|
MEMCG_SOCK,
|
2016-01-21 07:03:22 +08:00
|
|
|
MEMCG_NR_STAT,
|
2011-01-14 07:47:37 +08:00
|
|
|
};
|
|
|
|
|
2012-01-13 09:17:59 +08:00
|
|
|
struct mem_cgroup_reclaim_cookie {
|
2016-07-29 06:46:05 +08:00
|
|
|
pg_data_t *pgdat;
|
2012-01-13 09:17:59 +08:00
|
|
|
int priority;
|
|
|
|
unsigned int generation;
|
|
|
|
};
|
|
|
|
|
mm: memcontrol: default hierarchy interface for memory
Introduce the basic control files to account, partition, and limit
memory using cgroups in default hierarchy mode.
This interface versioning allows us to address fundamental design
issues in the existing memory cgroup interface, further explained
below. The old interface will be maintained indefinitely, but a
clearer model and improved workload performance should encourage
existing users to switch over to the new one eventually.
The control files are thus:
- memory.current shows the current consumption of the cgroup and its
descendants, in bytes.
- memory.low configures the lower end of the cgroup's expected
memory consumption range. The kernel considers memory below that
boundary to be a reserve - the minimum that the workload needs in
order to make forward progress - and generally avoids reclaiming
it, unless there is an imminent risk of entering an OOM situation.
- memory.high configures the upper end of the cgroup's expected
memory consumption range. A cgroup whose consumption grows beyond
this threshold is forced into direct reclaim, to work off the
excess and to throttle new allocations heavily, but is generally
allowed to continue and the OOM killer is not invoked.
- memory.max configures the hard maximum amount of memory that the
cgroup is allowed to consume before the OOM killer is invoked.
- memory.events shows event counters that indicate how often the
cgroup was reclaimed while below memory.low, how often it was
forced to reclaim excess beyond memory.high, how often it hit
memory.max, and how often it entered OOM due to memory.max. This
allows users to identify configuration problems when observing a
degradation in workload performance. An overcommitted system will
have an increased rate of low boundary breaches, whereas increased
rates of high limit breaches, maximum hits, or even OOM situations
will indicate internally overcommitted cgroups.
For existing users of memory cgroups, the following deviations from
the current interface are worth pointing out and explaining:
- The original lower boundary, the soft limit, is defined as a limit
that is per default unset. As a result, the set of cgroups that
global reclaim prefers is opt-in, rather than opt-out. The costs
for optimizing these mostly negative lookups are so high that the
implementation, despite its enormous size, does not even provide
the basic desirable behavior. First off, the soft limit has no
hierarchical meaning. All configured groups are organized in a
global rbtree and treated like equal peers, regardless where they
are located in the hierarchy. This makes subtree delegation
impossible. Second, the soft limit reclaim pass is so aggressive
that it not just introduces high allocation latencies into the
system, but also impacts system performance due to overreclaim, to
the point where the feature becomes self-defeating.
The memory.low boundary on the other hand is a top-down allocated
reserve. A cgroup enjoys reclaim protection when it and all its
ancestors are below their low boundaries, which makes delegation
of subtrees possible. Secondly, new cgroups have no reserve per
default and in the common case most cgroups are eligible for the
preferred reclaim pass. This allows the new low boundary to be
efficiently implemented with just a minor addition to the generic
reclaim code, without the need for out-of-band data structures and
reclaim passes. Because the generic reclaim code considers all
cgroups except for the ones running low in the preferred first
reclaim pass, overreclaim of individual groups is eliminated as
well, resulting in much better overall workload performance.
- The original high boundary, the hard limit, is defined as a strict
limit that can not budge, even if the OOM killer has to be called.
But this generally goes against the goal of making the most out of
the available memory. The memory consumption of workloads varies
during runtime, and that requires users to overcommit. But doing
that with a strict upper limit requires either a fairly accurate
prediction of the working set size or adding slack to the limit.
Since working set size estimation is hard and error prone, and
getting it wrong results in OOM kills, most users tend to err on
the side of a looser limit and end up wasting precious resources.
The memory.high boundary on the other hand can be set much more
conservatively. When hit, it throttles allocations by forcing
them into direct reclaim to work off the excess, but it never
invokes the OOM killer. As a result, a high boundary that is
chosen too aggressively will not terminate the processes, but
instead it will lead to gradual performance degradation. The user
can monitor this and make corrections until the minimal memory
footprint that still gives acceptable performance is found.
In extreme cases, with many concurrent allocations and a complete
breakdown of reclaim progress within the group, the high boundary
can be exceeded. But even then it's mostly better to satisfy the
allocation from the slack available in other groups or the rest of
the system than killing the group. Otherwise, memory.max is there
to limit this type of spillover and ultimately contain buggy or
even malicious applications.
- The original control file names are unwieldy and inconsistent in
many different ways. For example, the upper boundary hit count is
exported in the memory.failcnt file, but an OOM event count has to
be manually counted by listening to memory.oom_control events, and
lower boundary / soft limit events have to be counted by first
setting a threshold for that value and then counting those events.
Also, usage and limit files encode their units in the filename.
That makes the filenames very long, even though this is not
information that a user needs to be reminded of every time they
type out those names.
To address these naming issues, as well as to signal clearly that
the new interface carries a new configuration model, the naming
conventions in it necessarily differ from the old interface.
- The original limit files indicate the state of an unset limit with
a very high number, and a configured limit can be unset by echoing
-1 into those files. But that very high number is implementation
and architecture dependent and not very descriptive. And while -1
can be understood as an underflow into the highest possible value,
-2 or -10M etc. do not work, so it's not inconsistent.
memory.low, memory.high, and memory.max will use the string
"infinity" to indicate and set the highest possible value.
[akpm@linux-foundation.org: use seq_puts() for basic strings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 07:26:06 +08:00
|
|
|
enum mem_cgroup_events_index {
|
|
|
|
MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */
|
|
|
|
MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */
|
|
|
|
MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */
|
|
|
|
MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */
|
|
|
|
MEM_CGROUP_EVENTS_NSTATS,
|
|
|
|
/* default hierarchy events */
|
|
|
|
MEMCG_LOW = MEM_CGROUP_EVENTS_NSTATS,
|
|
|
|
MEMCG_HIGH,
|
|
|
|
MEMCG_MAX,
|
|
|
|
MEMCG_OOM,
|
|
|
|
MEMCG_NR_EVENTS,
|
|
|
|
};
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
/*
|
|
|
|
* Per memcg event counter is incremented at every pagein/pageout. With THP,
|
|
|
|
* it will be incremated by the number of pages. This counter is used for
|
|
|
|
* for trigger some periodic events. This is straightforward and better
|
|
|
|
* than using jiffies etc. to handle periodic memcg event.
|
|
|
|
*/
|
|
|
|
enum mem_cgroup_events_target {
|
|
|
|
MEM_CGROUP_TARGET_THRESH,
|
|
|
|
MEM_CGROUP_TARGET_SOFTLIMIT,
|
|
|
|
MEM_CGROUP_TARGET_NUMAINFO,
|
|
|
|
MEM_CGROUP_NTARGETS,
|
|
|
|
};
|
|
|
|
|
2012-08-01 07:43:02 +08:00
|
|
|
#ifdef CONFIG_MEMCG
|
2016-03-16 05:57:16 +08:00
|
|
|
|
|
|
|
#define MEM_CGROUP_ID_SHIFT 16
|
|
|
|
#define MEM_CGROUP_ID_MAX USHRT_MAX
|
|
|
|
|
2016-07-21 06:44:57 +08:00
|
|
|
struct mem_cgroup_id {
|
|
|
|
int id;
|
|
|
|
atomic_t ref;
|
|
|
|
};
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
struct mem_cgroup_stat_cpu {
|
2016-01-21 07:03:22 +08:00
|
|
|
long count[MEMCG_NR_STAT];
|
2015-09-09 06:01:02 +08:00
|
|
|
unsigned long events[MEMCG_NR_EVENTS];
|
|
|
|
unsigned long nr_page_events;
|
|
|
|
unsigned long targets[MEM_CGROUP_NTARGETS];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct mem_cgroup_reclaim_iter {
|
|
|
|
struct mem_cgroup *position;
|
|
|
|
/* scan generation, increased every round-trip */
|
|
|
|
unsigned int generation;
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* per-zone information in memory controller.
|
|
|
|
*/
|
2016-07-29 06:46:05 +08:00
|
|
|
struct mem_cgroup_per_node {
|
2015-09-09 06:01:02 +08:00
|
|
|
struct lruvec lruvec;
|
2017-01-11 08:58:04 +08:00
|
|
|
unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
|
2015-09-09 06:01:02 +08:00
|
|
|
|
|
|
|
struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1];
|
|
|
|
|
|
|
|
struct rb_node tree_node; /* RB tree node */
|
|
|
|
unsigned long usage_in_excess;/* Set to the value by which */
|
|
|
|
/* the soft limit is exceeded*/
|
|
|
|
bool on_tree;
|
|
|
|
struct mem_cgroup *memcg; /* Back pointer, we cannot */
|
|
|
|
/* use container_of */
|
|
|
|
};
|
|
|
|
|
|
|
|
struct mem_cgroup_threshold {
|
|
|
|
struct eventfd_ctx *eventfd;
|
|
|
|
unsigned long threshold;
|
|
|
|
};
|
|
|
|
|
|
|
|
/* For threshold */
|
|
|
|
struct mem_cgroup_threshold_ary {
|
|
|
|
/* An array index points to threshold just below or equal to usage. */
|
|
|
|
int current_threshold;
|
|
|
|
/* Size of entries[] */
|
|
|
|
unsigned int size;
|
|
|
|
/* Array of thresholds */
|
|
|
|
struct mem_cgroup_threshold entries[0];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct mem_cgroup_thresholds {
|
|
|
|
/* Primary thresholds array */
|
|
|
|
struct mem_cgroup_threshold_ary *primary;
|
|
|
|
/*
|
|
|
|
* Spare threshold array.
|
|
|
|
* This is needed to make mem_cgroup_unregister_event() "never fail".
|
|
|
|
* It must be able to store at least primary->size - 1 entries.
|
|
|
|
*/
|
|
|
|
struct mem_cgroup_threshold_ary *spare;
|
|
|
|
};
|
|
|
|
|
2016-01-21 07:02:24 +08:00
|
|
|
enum memcg_kmem_state {
|
|
|
|
KMEM_NONE,
|
|
|
|
KMEM_ALLOCATED,
|
|
|
|
KMEM_ONLINE,
|
|
|
|
};
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
/*
|
|
|
|
* The memory controller data structure. The memory controller controls both
|
|
|
|
* page cache and RSS per cgroup. We would eventually like to provide
|
|
|
|
* statistics based on the statistics developed by Rik Van Riel for clock-pro,
|
|
|
|
* to help the administrator determine what knobs to tune.
|
|
|
|
*/
|
|
|
|
struct mem_cgroup {
|
|
|
|
struct cgroup_subsys_state css;
|
|
|
|
|
2016-07-21 06:44:57 +08:00
|
|
|
/* Private memcg ID. Used to ID objects that outlive the cgroup */
|
|
|
|
struct mem_cgroup_id id;
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
/* Accounted resources */
|
|
|
|
struct page_counter memory;
|
mm: memcontrol: charge swap to cgroup2
This patchset introduces swap accounting to cgroup2.
This patch (of 7):
In the legacy hierarchy we charge memsw, which is dubious, because:
- memsw.limit must be >= memory.limit, so it is impossible to limit
swap usage less than memory usage. Taking into account the fact that
the primary limiting mechanism in the unified hierarchy is
memory.high while memory.limit is either left unset or set to a very
large value, moving memsw.limit knob to the unified hierarchy would
effectively make it impossible to limit swap usage according to the
user preference.
- memsw.usage != memory.usage + swap.usage, because a page occupying
both swap entry and a swap cache page is charged only once to memsw
counter. As a result, it is possible to effectively eat up to
memory.limit of memory pages *and* memsw.limit of swap entries, which
looks unexpected.
That said, we should provide a different swap limiting mechanism for
cgroup2.
This patch adds mem_cgroup->swap counter, which charges the actual number
of swap entries used by a cgroup. It is only charged in the unified
hierarchy, while the legacy hierarchy memsw logic is left intact.
The swap usage can be monitored using new memory.swap.current file and
limited using memory.swap.max.
Note, to charge swap resource properly in the unified hierarchy, we have
to make swap_entry_free uncharge swap only when ->usage reaches zero, not
just ->count, i.e. when all references to a swap entry, including the one
taken by swap cache, are gone. This is necessary, because otherwise
swap-in could result in uncharging swap even if the page is still in swap
cache and hence still occupies a swap entry. At the same time, this
shouldn't break memsw counter logic, where a page is never charged twice
for using both memory and swap, because in case of legacy hierarchy we
uncharge swap on commit (see mem_cgroup_commit_charge).
Signed-off-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-21 07:02:56 +08:00
|
|
|
struct page_counter swap;
|
2016-01-21 07:02:50 +08:00
|
|
|
|
|
|
|
/* Legacy consumer-oriented counters */
|
2015-09-09 06:01:02 +08:00
|
|
|
struct page_counter memsw;
|
|
|
|
struct page_counter kmem;
|
2016-01-21 07:02:50 +08:00
|
|
|
struct page_counter tcpmem;
|
2015-09-09 06:01:02 +08:00
|
|
|
|
|
|
|
/* Normal memory consumption range */
|
|
|
|
unsigned long low;
|
|
|
|
unsigned long high;
|
|
|
|
|
2016-01-15 07:21:29 +08:00
|
|
|
/* Range enforcement for interrupt charges */
|
|
|
|
struct work_struct high_work;
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
unsigned long soft_limit;
|
|
|
|
|
|
|
|
/* vmpressure notifications */
|
|
|
|
struct vmpressure vmpressure;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Should the accounting and control be hierarchical, per subtree?
|
|
|
|
*/
|
|
|
|
bool use_hierarchy;
|
|
|
|
|
|
|
|
/* protected by memcg_oom_lock */
|
|
|
|
bool oom_lock;
|
|
|
|
int under_oom;
|
|
|
|
|
|
|
|
int swappiness;
|
|
|
|
/* OOM-Killer disable */
|
|
|
|
int oom_kill_disable;
|
|
|
|
|
2015-09-19 06:01:59 +08:00
|
|
|
/* handle for "memory.events" */
|
|
|
|
struct cgroup_file events_file;
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
/* protect arrays of thresholds */
|
|
|
|
struct mutex thresholds_lock;
|
|
|
|
|
|
|
|
/* thresholds for memory usage. RCU-protected */
|
|
|
|
struct mem_cgroup_thresholds thresholds;
|
|
|
|
|
|
|
|
/* thresholds for mem+swap usage. RCU-protected */
|
|
|
|
struct mem_cgroup_thresholds memsw_thresholds;
|
|
|
|
|
|
|
|
/* For oom notifier event fd */
|
|
|
|
struct list_head oom_notify;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Should we move charges of a task when a task is moved into this
|
|
|
|
* mem_cgroup ? And what type of charges should we move ?
|
|
|
|
*/
|
|
|
|
unsigned long move_charge_at_immigrate;
|
|
|
|
/*
|
|
|
|
* set > 0 if pages under this cgroup are moving to other cgroup.
|
|
|
|
*/
|
|
|
|
atomic_t moving_account;
|
|
|
|
/* taken only while moving_account > 0 */
|
|
|
|
spinlock_t move_lock;
|
|
|
|
struct task_struct *move_lock_task;
|
|
|
|
unsigned long move_lock_flags;
|
|
|
|
/*
|
|
|
|
* percpu counter.
|
|
|
|
*/
|
|
|
|
struct mem_cgroup_stat_cpu __percpu *stat;
|
|
|
|
|
2016-01-21 07:02:47 +08:00
|
|
|
unsigned long socket_pressure;
|
|
|
|
|
|
|
|
/* Legacy tcp memory accounting */
|
2016-01-21 07:02:50 +08:00
|
|
|
bool tcpmem_active;
|
|
|
|
int tcpmem_pressure;
|
2016-01-21 07:02:47 +08:00
|
|
|
|
2016-01-21 07:02:32 +08:00
|
|
|
#ifndef CONFIG_SLOB
|
2015-09-09 06:01:02 +08:00
|
|
|
/* Index in the kmem_cache->memcg_params.memcg_caches array */
|
|
|
|
int kmemcg_id;
|
2016-01-21 07:02:24 +08:00
|
|
|
enum memcg_kmem_state kmem_state;
|
2017-02-23 07:41:21 +08:00
|
|
|
struct list_head kmem_caches;
|
2015-09-09 06:01:02 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
int last_scanned_node;
|
|
|
|
#if MAX_NUMNODES > 1
|
|
|
|
nodemask_t scan_nodes;
|
|
|
|
atomic_t numainfo_events;
|
|
|
|
atomic_t numainfo_updating;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
|
|
|
struct list_head cgwb_list;
|
|
|
|
struct wb_domain cgwb_domain;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* List of events which userspace want to receive */
|
|
|
|
struct list_head event_list;
|
|
|
|
spinlock_t event_list_lock;
|
|
|
|
|
|
|
|
struct mem_cgroup_per_node *nodeinfo[0];
|
|
|
|
/* WARNING: nodeinfo must be the last member here */
|
|
|
|
};
|
2016-01-15 07:20:56 +08:00
|
|
|
|
|
|
|
extern struct mem_cgroup *root_mem_cgroup;
|
2015-05-23 05:13:20 +08:00
|
|
|
|
2016-03-16 05:57:16 +08:00
|
|
|
static inline bool mem_cgroup_disabled(void)
|
|
|
|
{
|
|
|
|
return !cgroup_subsys_enabled(memory_cgrp_subsys);
|
|
|
|
}
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
/**
|
|
|
|
* mem_cgroup_events - count memory events against a cgroup
|
|
|
|
* @memcg: the memory cgroup
|
|
|
|
* @idx: the event index
|
|
|
|
* @nr: the number of events to account for
|
|
|
|
*/
|
|
|
|
static inline void mem_cgroup_events(struct mem_cgroup *memcg,
|
mm: memcontrol: default hierarchy interface for memory
Introduce the basic control files to account, partition, and limit
memory using cgroups in default hierarchy mode.
This interface versioning allows us to address fundamental design
issues in the existing memory cgroup interface, further explained
below. The old interface will be maintained indefinitely, but a
clearer model and improved workload performance should encourage
existing users to switch over to the new one eventually.
The control files are thus:
- memory.current shows the current consumption of the cgroup and its
descendants, in bytes.
- memory.low configures the lower end of the cgroup's expected
memory consumption range. The kernel considers memory below that
boundary to be a reserve - the minimum that the workload needs in
order to make forward progress - and generally avoids reclaiming
it, unless there is an imminent risk of entering an OOM situation.
- memory.high configures the upper end of the cgroup's expected
memory consumption range. A cgroup whose consumption grows beyond
this threshold is forced into direct reclaim, to work off the
excess and to throttle new allocations heavily, but is generally
allowed to continue and the OOM killer is not invoked.
- memory.max configures the hard maximum amount of memory that the
cgroup is allowed to consume before the OOM killer is invoked.
- memory.events shows event counters that indicate how often the
cgroup was reclaimed while below memory.low, how often it was
forced to reclaim excess beyond memory.high, how often it hit
memory.max, and how often it entered OOM due to memory.max. This
allows users to identify configuration problems when observing a
degradation in workload performance. An overcommitted system will
have an increased rate of low boundary breaches, whereas increased
rates of high limit breaches, maximum hits, or even OOM situations
will indicate internally overcommitted cgroups.
For existing users of memory cgroups, the following deviations from
the current interface are worth pointing out and explaining:
- The original lower boundary, the soft limit, is defined as a limit
that is per default unset. As a result, the set of cgroups that
global reclaim prefers is opt-in, rather than opt-out. The costs
for optimizing these mostly negative lookups are so high that the
implementation, despite its enormous size, does not even provide
the basic desirable behavior. First off, the soft limit has no
hierarchical meaning. All configured groups are organized in a
global rbtree and treated like equal peers, regardless where they
are located in the hierarchy. This makes subtree delegation
impossible. Second, the soft limit reclaim pass is so aggressive
that it not just introduces high allocation latencies into the
system, but also impacts system performance due to overreclaim, to
the point where the feature becomes self-defeating.
The memory.low boundary on the other hand is a top-down allocated
reserve. A cgroup enjoys reclaim protection when it and all its
ancestors are below their low boundaries, which makes delegation
of subtrees possible. Secondly, new cgroups have no reserve per
default and in the common case most cgroups are eligible for the
preferred reclaim pass. This allows the new low boundary to be
efficiently implemented with just a minor addition to the generic
reclaim code, without the need for out-of-band data structures and
reclaim passes. Because the generic reclaim code considers all
cgroups except for the ones running low in the preferred first
reclaim pass, overreclaim of individual groups is eliminated as
well, resulting in much better overall workload performance.
- The original high boundary, the hard limit, is defined as a strict
limit that can not budge, even if the OOM killer has to be called.
But this generally goes against the goal of making the most out of
the available memory. The memory consumption of workloads varies
during runtime, and that requires users to overcommit. But doing
that with a strict upper limit requires either a fairly accurate
prediction of the working set size or adding slack to the limit.
Since working set size estimation is hard and error prone, and
getting it wrong results in OOM kills, most users tend to err on
the side of a looser limit and end up wasting precious resources.
The memory.high boundary on the other hand can be set much more
conservatively. When hit, it throttles allocations by forcing
them into direct reclaim to work off the excess, but it never
invokes the OOM killer. As a result, a high boundary that is
chosen too aggressively will not terminate the processes, but
instead it will lead to gradual performance degradation. The user
can monitor this and make corrections until the minimal memory
footprint that still gives acceptable performance is found.
In extreme cases, with many concurrent allocations and a complete
breakdown of reclaim progress within the group, the high boundary
can be exceeded. But even then it's mostly better to satisfy the
allocation from the slack available in other groups or the rest of
the system than killing the group. Otherwise, memory.max is there
to limit this type of spillover and ultimately contain buggy or
even malicious applications.
- The original control file names are unwieldy and inconsistent in
many different ways. For example, the upper boundary hit count is
exported in the memory.failcnt file, but an OOM event count has to
be manually counted by listening to memory.oom_control events, and
lower boundary / soft limit events have to be counted by first
setting a threshold for that value and then counting those events.
Also, usage and limit files encode their units in the filename.
That makes the filenames very long, even though this is not
information that a user needs to be reminded of every time they
type out those names.
To address these naming issues, as well as to signal clearly that
the new interface carries a new configuration model, the naming
conventions in it necessarily differ from the old interface.
- The original limit files indicate the state of an unset limit with
a very high number, and a configured limit can be unset by echoing
-1 into those files. But that very high number is implementation
and architecture dependent and not very descriptive. And while -1
can be understood as an underflow into the highest possible value,
-2 or -10M etc. do not work, so it's not inconsistent.
memory.low, memory.high, and memory.max will use the string
"infinity" to indicate and set the highest possible value.
[akpm@linux-foundation.org: use seq_puts() for basic strings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 07:26:06 +08:00
|
|
|
enum mem_cgroup_events_index idx,
|
2015-09-09 06:01:02 +08:00
|
|
|
unsigned int nr)
|
|
|
|
{
|
|
|
|
this_cpu_add(memcg->stat->events[idx], nr);
|
2015-09-19 06:01:59 +08:00
|
|
|
cgroup_file_notify(&memcg->events_file);
|
2015-09-09 06:01:02 +08:00
|
|
|
}
|
mm: memcontrol: default hierarchy interface for memory
Introduce the basic control files to account, partition, and limit
memory using cgroups in default hierarchy mode.
This interface versioning allows us to address fundamental design
issues in the existing memory cgroup interface, further explained
below. The old interface will be maintained indefinitely, but a
clearer model and improved workload performance should encourage
existing users to switch over to the new one eventually.
The control files are thus:
- memory.current shows the current consumption of the cgroup and its
descendants, in bytes.
- memory.low configures the lower end of the cgroup's expected
memory consumption range. The kernel considers memory below that
boundary to be a reserve - the minimum that the workload needs in
order to make forward progress - and generally avoids reclaiming
it, unless there is an imminent risk of entering an OOM situation.
- memory.high configures the upper end of the cgroup's expected
memory consumption range. A cgroup whose consumption grows beyond
this threshold is forced into direct reclaim, to work off the
excess and to throttle new allocations heavily, but is generally
allowed to continue and the OOM killer is not invoked.
- memory.max configures the hard maximum amount of memory that the
cgroup is allowed to consume before the OOM killer is invoked.
- memory.events shows event counters that indicate how often the
cgroup was reclaimed while below memory.low, how often it was
forced to reclaim excess beyond memory.high, how often it hit
memory.max, and how often it entered OOM due to memory.max. This
allows users to identify configuration problems when observing a
degradation in workload performance. An overcommitted system will
have an increased rate of low boundary breaches, whereas increased
rates of high limit breaches, maximum hits, or even OOM situations
will indicate internally overcommitted cgroups.
For existing users of memory cgroups, the following deviations from
the current interface are worth pointing out and explaining:
- The original lower boundary, the soft limit, is defined as a limit
that is per default unset. As a result, the set of cgroups that
global reclaim prefers is opt-in, rather than opt-out. The costs
for optimizing these mostly negative lookups are so high that the
implementation, despite its enormous size, does not even provide
the basic desirable behavior. First off, the soft limit has no
hierarchical meaning. All configured groups are organized in a
global rbtree and treated like equal peers, regardless where they
are located in the hierarchy. This makes subtree delegation
impossible. Second, the soft limit reclaim pass is so aggressive
that it not just introduces high allocation latencies into the
system, but also impacts system performance due to overreclaim, to
the point where the feature becomes self-defeating.
The memory.low boundary on the other hand is a top-down allocated
reserve. A cgroup enjoys reclaim protection when it and all its
ancestors are below their low boundaries, which makes delegation
of subtrees possible. Secondly, new cgroups have no reserve per
default and in the common case most cgroups are eligible for the
preferred reclaim pass. This allows the new low boundary to be
efficiently implemented with just a minor addition to the generic
reclaim code, without the need for out-of-band data structures and
reclaim passes. Because the generic reclaim code considers all
cgroups except for the ones running low in the preferred first
reclaim pass, overreclaim of individual groups is eliminated as
well, resulting in much better overall workload performance.
- The original high boundary, the hard limit, is defined as a strict
limit that can not budge, even if the OOM killer has to be called.
But this generally goes against the goal of making the most out of
the available memory. The memory consumption of workloads varies
during runtime, and that requires users to overcommit. But doing
that with a strict upper limit requires either a fairly accurate
prediction of the working set size or adding slack to the limit.
Since working set size estimation is hard and error prone, and
getting it wrong results in OOM kills, most users tend to err on
the side of a looser limit and end up wasting precious resources.
The memory.high boundary on the other hand can be set much more
conservatively. When hit, it throttles allocations by forcing
them into direct reclaim to work off the excess, but it never
invokes the OOM killer. As a result, a high boundary that is
chosen too aggressively will not terminate the processes, but
instead it will lead to gradual performance degradation. The user
can monitor this and make corrections until the minimal memory
footprint that still gives acceptable performance is found.
In extreme cases, with many concurrent allocations and a complete
breakdown of reclaim progress within the group, the high boundary
can be exceeded. But even then it's mostly better to satisfy the
allocation from the slack available in other groups or the rest of
the system than killing the group. Otherwise, memory.max is there
to limit this type of spillover and ultimately contain buggy or
even malicious applications.
- The original control file names are unwieldy and inconsistent in
many different ways. For example, the upper boundary hit count is
exported in the memory.failcnt file, but an OOM event count has to
be manually counted by listening to memory.oom_control events, and
lower boundary / soft limit events have to be counted by first
setting a threshold for that value and then counting those events.
Also, usage and limit files encode their units in the filename.
That makes the filenames very long, even though this is not
information that a user needs to be reminded of every time they
type out those names.
To address these naming issues, as well as to signal clearly that
the new interface carries a new configuration model, the naming
conventions in it necessarily differ from the old interface.
- The original limit files indicate the state of an unset limit with
a very high number, and a configured limit can be unset by echoing
-1 into those files. But that very high number is implementation
and architecture dependent and not very descriptive. And while -1
can be understood as an underflow into the highest possible value,
-2 or -10M etc. do not work, so it's not inconsistent.
memory.low, memory.high, and memory.max will use the string
"infinity" to indicate and set the highest possible value.
[akpm@linux-foundation.org: use seq_puts() for basic strings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 07:26:06 +08:00
|
|
|
|
|
|
|
bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
|
|
|
|
|
mm: memcontrol: rewrite charge API
These patches rework memcg charge lifetime to integrate more naturally
with the lifetime of user pages. This drastically simplifies the code and
reduces charging and uncharging overhead. The most expensive part of
charging and uncharging is the page_cgroup bit spinlock, which is removed
entirely after this series.
Here are the top-10 profile entries of a stress test that reads a 128G
sparse file on a freshly booted box, without even a dedicated cgroup (i.e.
executing in the root memcg). Before:
15.36% cat [kernel.kallsyms] [k] copy_user_generic_string
13.31% cat [kernel.kallsyms] [k] memset
11.48% cat [kernel.kallsyms] [k] do_mpage_readpage
4.23% cat [kernel.kallsyms] [k] get_page_from_freelist
2.38% cat [kernel.kallsyms] [k] put_page
2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge
2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common
1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
After:
15.67% cat [kernel.kallsyms] [k] copy_user_generic_string
13.48% cat [kernel.kallsyms] [k] memset
11.42% cat [kernel.kallsyms] [k] do_mpage_readpage
3.98% cat [kernel.kallsyms] [k] get_page_from_freelist
2.46% cat [kernel.kallsyms] [k] put_page
2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk
1.30% cat [kernel.kallsyms] [k] kfree
As you can see, the memcg footprint has shrunk quite a bit.
text data bss dec hex filename
37970 9892 400 48262 bc86 mm/memcontrol.o.old
35239 9892 400 45531 b1db mm/memcontrol.o
This patch (of 4):
The memcg charge API charges pages before they are rmapped - i.e. have an
actual "type" - and so every callsite needs its own set of charge and
uncharge functions to know what type is being operated on. Worse,
uncharge has to happen from a context that is still type-specific, rather
than at the end of the page's lifetime with exclusive access, and so
requires a lot of synchronization.
Rewrite the charge API to provide a generic set of try_charge(),
commit_charge() and cancel_charge() transaction operations, much like
what's currently done for swap-in:
mem_cgroup_try_charge() attempts to reserve a charge, reclaiming
pages from the memcg if necessary.
mem_cgroup_commit_charge() commits the page to the charge once it
has a valid page->mapping and PageAnon() reliably tells the type.
mem_cgroup_cancel_charge() aborts the transaction.
This reduces the charge API and enables subsequent patches to
drastically simplify uncharging.
As pages need to be committed after rmap is established but before they
are added to the LRU, page_add_new_anon_rmap() must stop doing LRU
additions again. Revive lru_cache_add_active_or_unevictable().
[hughd@google.com: fix shmem_unuse]
[hughd@google.com: Add comments on the private use of -EAGAIN]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:19:20 +08:00
|
|
|
int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
|
2016-01-16 08:52:20 +08:00
|
|
|
gfp_t gfp_mask, struct mem_cgroup **memcgp,
|
|
|
|
bool compound);
|
mm: memcontrol: rewrite charge API
These patches rework memcg charge lifetime to integrate more naturally
with the lifetime of user pages. This drastically simplifies the code and
reduces charging and uncharging overhead. The most expensive part of
charging and uncharging is the page_cgroup bit spinlock, which is removed
entirely after this series.
Here are the top-10 profile entries of a stress test that reads a 128G
sparse file on a freshly booted box, without even a dedicated cgroup (i.e.
executing in the root memcg). Before:
15.36% cat [kernel.kallsyms] [k] copy_user_generic_string
13.31% cat [kernel.kallsyms] [k] memset
11.48% cat [kernel.kallsyms] [k] do_mpage_readpage
4.23% cat [kernel.kallsyms] [k] get_page_from_freelist
2.38% cat [kernel.kallsyms] [k] put_page
2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge
2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common
1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
After:
15.67% cat [kernel.kallsyms] [k] copy_user_generic_string
13.48% cat [kernel.kallsyms] [k] memset
11.42% cat [kernel.kallsyms] [k] do_mpage_readpage
3.98% cat [kernel.kallsyms] [k] get_page_from_freelist
2.46% cat [kernel.kallsyms] [k] put_page
2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk
1.30% cat [kernel.kallsyms] [k] kfree
As you can see, the memcg footprint has shrunk quite a bit.
text data bss dec hex filename
37970 9892 400 48262 bc86 mm/memcontrol.o.old
35239 9892 400 45531 b1db mm/memcontrol.o
This patch (of 4):
The memcg charge API charges pages before they are rmapped - i.e. have an
actual "type" - and so every callsite needs its own set of charge and
uncharge functions to know what type is being operated on. Worse,
uncharge has to happen from a context that is still type-specific, rather
than at the end of the page's lifetime with exclusive access, and so
requires a lot of synchronization.
Rewrite the charge API to provide a generic set of try_charge(),
commit_charge() and cancel_charge() transaction operations, much like
what's currently done for swap-in:
mem_cgroup_try_charge() attempts to reserve a charge, reclaiming
pages from the memcg if necessary.
mem_cgroup_commit_charge() commits the page to the charge once it
has a valid page->mapping and PageAnon() reliably tells the type.
mem_cgroup_cancel_charge() aborts the transaction.
This reduces the charge API and enables subsequent patches to
drastically simplify uncharging.
As pages need to be committed after rmap is established but before they
are added to the LRU, page_add_new_anon_rmap() must stop doing LRU
additions again. Revive lru_cache_add_active_or_unevictable().
[hughd@google.com: fix shmem_unuse]
[hughd@google.com: Add comments on the private use of -EAGAIN]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:19:20 +08:00
|
|
|
void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
|
2016-01-16 08:52:20 +08:00
|
|
|
bool lrucare, bool compound);
|
|
|
|
void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
|
|
|
|
bool compound);
|
mm: memcontrol: rewrite uncharge API
The memcg uncharging code that is involved towards the end of a page's
lifetime - truncation, reclaim, swapout, migration - is impressively
complicated and fragile.
Because anonymous and file pages were always charged before they had their
page->mapping established, uncharges had to happen when the page type
could still be known from the context; as in unmap for anonymous, page
cache removal for file and shmem pages, and swap cache truncation for swap
pages. However, these operations happen well before the page is actually
freed, and so a lot of synchronization is necessary:
- Charging, uncharging, page migration, and charge migration all need
to take a per-page bit spinlock as they could race with uncharging.
- Swap cache truncation happens during both swap-in and swap-out, and
possibly repeatedly before the page is actually freed. This means
that the memcg swapout code is called from many contexts that make
no sense and it has to figure out the direction from page state to
make sure memory and memory+swap are always correctly charged.
- On page migration, the old page might be unmapped but then reused,
so memcg code has to prevent untimely uncharging in that case.
Because this code - which should be a simple charge transfer - is so
special-cased, it is not reusable for replace_page_cache().
But now that charged pages always have a page->mapping, introduce
mem_cgroup_uncharge(), which is called after the final put_page(), when we
know for sure that nobody is looking at the page anymore.
For page migration, introduce mem_cgroup_migrate(), which is called after
the migration is successful and the new page is fully rmapped. Because
the old page is no longer uncharged after migration, prevent double
charges by decoupling the page's memcg association (PCG_USED and
pc->mem_cgroup) from the page holding an actual charge. The new bits
PCG_MEM and PCG_MEMSW represent the respective charges and are transferred
to the new page during migration.
mem_cgroup_migrate() is suitable for replace_page_cache() as well,
which gets rid of mem_cgroup_replace_page_cache(). However, care
needs to be taken because both the source and the target page can
already be charged and on the LRU when fuse is splicing: grab the page
lock on the charge moving side to prevent changing pc->mem_cgroup of a
page under migration. Also, the lruvecs of both pages change as we
uncharge the old and charge the new during migration, and putback may
race with us, so grab the lru lock and isolate the pages iff on LRU to
prevent races and ensure the pages are on the right lruvec afterward.
Swap accounting is massively simplified: because the page is no longer
uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can
transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry
before the final put_page() in page reclaim.
Finally, page_cgroup changes are now protected by whatever protection the
page itself offers: anonymous pages are charged under the page table lock,
whereas page cache insertions, swapin, and migration hold the page lock.
Uncharging happens under full exclusion with no outstanding references.
Charging and uncharging also ensure that the page is off-LRU, which
serializes against charge migration. Remove the very costly page_cgroup
lock and set pc->flags non-atomically.
[mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable]
[vdavydov@parallels.com: fix flags definition]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Tested-by: Jet Chen <jet.chen@intel.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:19:22 +08:00
|
|
|
void mem_cgroup_uncharge(struct page *page);
|
2014-08-09 05:19:24 +08:00
|
|
|
void mem_cgroup_uncharge_list(struct list_head *page_list);
|
2009-12-16 08:47:03 +08:00
|
|
|
|
2016-03-16 05:57:19 +08:00
|
|
|
void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
|
2009-12-16 08:47:03 +08:00
|
|
|
|
2016-07-29 06:46:05 +08:00
|
|
|
static struct mem_cgroup_per_node *
|
|
|
|
mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
|
2016-07-29 06:45:10 +08:00
|
|
|
{
|
2016-07-29 06:46:05 +08:00
|
|
|
return memcg->nodeinfo[nid];
|
2016-07-29 06:45:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2016-07-29 06:46:02 +08:00
|
|
|
* mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
|
|
|
|
* @node: node of the wanted lruvec
|
2016-07-29 06:45:10 +08:00
|
|
|
* @memcg: memcg of the wanted lruvec
|
|
|
|
*
|
2016-07-29 06:46:02 +08:00
|
|
|
* Returns the lru list vector holding pages for a given @node or a given
|
|
|
|
* @memcg and @zone. This can be the node lruvec, if the memory controller
|
2016-07-29 06:45:10 +08:00
|
|
|
* is disabled.
|
|
|
|
*/
|
2016-07-29 06:46:02 +08:00
|
|
|
static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
|
2016-07-29 06:46:05 +08:00
|
|
|
struct mem_cgroup *memcg)
|
2016-07-29 06:45:10 +08:00
|
|
|
{
|
2016-07-29 06:46:05 +08:00
|
|
|
struct mem_cgroup_per_node *mz;
|
2016-07-29 06:45:10 +08:00
|
|
|
struct lruvec *lruvec;
|
|
|
|
|
|
|
|
if (mem_cgroup_disabled()) {
|
2016-07-29 06:46:02 +08:00
|
|
|
lruvec = node_lruvec(pgdat);
|
2016-07-29 06:45:10 +08:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2016-07-29 06:46:05 +08:00
|
|
|
mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
|
2016-07-29 06:45:10 +08:00
|
|
|
lruvec = &mz->lruvec;
|
|
|
|
out:
|
|
|
|
/*
|
|
|
|
* Since a node can be onlined after the mem_cgroup was created,
|
2016-07-29 06:45:31 +08:00
|
|
|
* we have to be prepared to initialize lruvec->pgdat here;
|
2016-07-29 06:45:10 +08:00
|
|
|
* and if offlined then reonlined, we need to reinitialize it.
|
|
|
|
*/
|
2016-07-29 06:46:05 +08:00
|
|
|
if (unlikely(lruvec->pgdat != pgdat))
|
|
|
|
lruvec->pgdat = pgdat;
|
2016-07-29 06:45:10 +08:00
|
|
|
return lruvec;
|
|
|
|
}
|
|
|
|
|
2016-07-29 06:45:31 +08:00
|
|
|
struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
|
2008-07-25 16:47:15 +08:00
|
|
|
|
2014-12-11 07:44:33 +08:00
|
|
|
bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
|
2015-09-09 06:01:07 +08:00
|
|
|
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
|
2015-09-10 06:35:35 +08:00
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
static inline
|
|
|
|
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
|
|
|
|
return css ? container_of(css, struct mem_cgroup, css) : NULL;
|
|
|
|
}
|
|
|
|
|
2016-01-15 07:21:32 +08:00
|
|
|
#define mem_cgroup_from_counter(counter, member) \
|
|
|
|
container_of(counter, struct mem_cgroup, member)
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
|
|
|
|
struct mem_cgroup *,
|
|
|
|
struct mem_cgroup_reclaim_cookie *);
|
|
|
|
void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
|
2016-10-08 07:57:23 +08:00
|
|
|
int mem_cgroup_scan_tasks(struct mem_cgroup *,
|
|
|
|
int (*)(struct task_struct *, void *), void *);
|
2015-09-09 06:01:02 +08:00
|
|
|
|
2016-03-16 05:57:16 +08:00
|
|
|
static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return 0;
|
|
|
|
|
2016-07-21 06:44:57 +08:00
|
|
|
return memcg->id.id;
|
2016-03-16 05:57:16 +08:00
|
|
|
}
|
2016-07-21 06:44:57 +08:00
|
|
|
struct mem_cgroup *mem_cgroup_from_id(unsigned short id);
|
2016-03-16 05:57:16 +08:00
|
|
|
|
2016-01-15 07:21:32 +08:00
|
|
|
/**
|
|
|
|
* parent_mem_cgroup - find the accounting parent of a memcg
|
|
|
|
* @memcg: memcg whose parent to find
|
|
|
|
*
|
|
|
|
* Returns the parent memcg, or NULL if this is the root or the memory
|
|
|
|
* controller is in legacy no-hierarchy mode.
|
|
|
|
*/
|
|
|
|
static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
if (!memcg->memory.parent)
|
|
|
|
return NULL;
|
|
|
|
return mem_cgroup_from_counter(memcg->memory.parent, memory);
|
|
|
|
}
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
|
|
|
|
struct mem_cgroup *root)
|
|
|
|
{
|
|
|
|
if (root == memcg)
|
|
|
|
return true;
|
|
|
|
if (!root->use_hierarchy)
|
|
|
|
return false;
|
|
|
|
return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
|
|
|
|
}
|
2011-12-12 05:47:03 +08:00
|
|
|
|
2014-12-11 07:44:33 +08:00
|
|
|
static inline bool mm_match_cgroup(struct mm_struct *mm,
|
|
|
|
struct mem_cgroup *memcg)
|
2009-01-08 10:08:07 +08:00
|
|
|
{
|
2012-10-09 07:34:12 +08:00
|
|
|
struct mem_cgroup *task_memcg;
|
2014-12-11 07:44:30 +08:00
|
|
|
bool match = false;
|
2012-05-30 06:06:25 +08:00
|
|
|
|
2009-01-08 10:08:07 +08:00
|
|
|
rcu_read_lock();
|
2012-10-09 07:34:12 +08:00
|
|
|
task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
|
2014-12-11 07:44:30 +08:00
|
|
|
if (task_memcg)
|
2014-12-11 07:44:33 +08:00
|
|
|
match = mem_cgroup_is_descendant(task_memcg, memcg);
|
2009-01-08 10:08:07 +08:00
|
|
|
rcu_read_unlock();
|
2012-05-30 06:06:25 +08:00
|
|
|
return match;
|
2009-01-08 10:08:07 +08:00
|
|
|
}
|
2008-02-07 16:13:53 +08:00
|
|
|
|
2015-09-09 06:01:07 +08:00
|
|
|
struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
|
memcg: add page_cgroup_ino helper
This patchset introduces a new user API for tracking user memory pages
that have not been used for a given period of time. The purpose of this
is to provide the userspace with the means of tracking a workload's
working set, i.e. the set of pages that are actively used by the
workload. Knowing the working set size can be useful for partitioning the
system more efficiently, e.g. by tuning memory cgroup limits
appropriately, or for job placement within a compute cluster.
==== USE CASES ====
The unified cgroup hierarchy has memory.low and memory.high knobs, which
are defined as the low and high boundaries for the workload working set
size. However, the working set size of a workload may be unknown or
change in time. With this patch set, one can periodically estimate the
amount of memory unused by each cgroup and tune their memory.low and
memory.high parameters accordingly, therefore optimizing the overall
memory utilization.
Another use case is balancing workloads within a compute cluster. Knowing
how much memory is not really used by a workload unit may help take a more
optimal decision when considering migrating the unit to another node
within the cluster.
Also, as noted by Minchan, this would be useful for per-process reclaim
(https://lwn.net/Articles/545668/). With idle tracking, we could reclaim idle
pages only by smart user memory manager.
==== USER API ====
The user API consists of two new files:
* /sys/kernel/mm/page_idle/bitmap. This file implements a bitmap where each
bit corresponds to a page, indexed by PFN. When the bit is set, the
corresponding page is idle. A page is considered idle if it has not been
accessed since it was marked idle. To mark a page idle one should set the
bit corresponding to the page by writing to the file. A value written to the
file is OR-ed with the current bitmap value. Only user memory pages can be
marked idle, for other page types input is silently ignored. Writing to this
file beyond max PFN results in the ENXIO error. Only available when
CONFIG_IDLE_PAGE_TRACKING is set.
This file can be used to estimate the amount of pages that are not
used by a particular workload as follows:
1. mark all pages of interest idle by setting corresponding bits in the
/sys/kernel/mm/page_idle/bitmap
2. wait until the workload accesses its working set
3. read /sys/kernel/mm/page_idle/bitmap and count the number of bits set
* /proc/kpagecgroup. This file contains a 64-bit inode number of the
memory cgroup each page is charged to, indexed by PFN. Only available when
CONFIG_MEMCG is set.
This file can be used to find all pages (including unmapped file pages)
accounted to a particular cgroup. Using /sys/kernel/mm/page_idle/bitmap, one
can then estimate the cgroup working set size.
For an example of using these files for estimating the amount of unused
memory pages per each memory cgroup, please see the script attached
below.
==== REASONING ====
The reason to introduce the new user API instead of using
/proc/PID/{clear_refs,smaps} is that the latter has two serious
drawbacks:
- it does not count unmapped file pages
- it affects the reclaimer logic
The new API attempts to overcome them both. For more details on how it
is achieved, please see the comment to patch 6.
==== PATCHSET STRUCTURE ====
The patch set is organized as follows:
- patch 1 adds page_cgroup_ino() helper for the sake of
/proc/kpagecgroup and patches 2-3 do related cleanup
- patch 4 adds /proc/kpagecgroup, which reports cgroup ino each page is
charged to
- patch 5 introduces a new mmu notifier callback, clear_young, which is
a lightweight version of clear_flush_young; it is used in patch 6
- patch 6 implements the idle page tracking feature, including the
userspace API, /sys/kernel/mm/page_idle/bitmap
- patch 7 exports idle flag via /proc/kpageflags
==== SIMILAR WORKS ====
Originally, the patch for tracking idle memory was proposed back in 2011
by Michel Lespinasse (see http://lwn.net/Articles/459269/). The main
difference between Michel's patch and this one is that Michel implemented
a kernel space daemon for estimating idle memory size per cgroup while
this patch only provides the userspace with the minimal API for doing the
job, leaving the rest up to the userspace. However, they both share the
same idea of Idle/Young page flags to avoid affecting the reclaimer logic.
==== PERFORMANCE EVALUATION ====
SPECjvm2008 (https://www.spec.org/jvm2008/) was used to evaluate the
performance impact introduced by this patch set. Three runs were carried
out:
- base: kernel without the patch
- patched: patched kernel, the feature is not used
- patched-active: patched kernel, 1 minute-period daemon is used for
tracking idle memory
For tracking idle memory, idlememstat utility was used:
https://github.com/locker/idlememstat
testcase base patched patched-active
compiler 537.40 ( 0.00)% 532.26 (-0.96)% 538.31 ( 0.17)%
compress 305.47 ( 0.00)% 301.08 (-1.44)% 300.71 (-1.56)%
crypto 284.32 ( 0.00)% 282.21 (-0.74)% 284.87 ( 0.19)%
derby 411.05 ( 0.00)% 413.44 ( 0.58)% 412.07 ( 0.25)%
mpegaudio 189.96 ( 0.00)% 190.87 ( 0.48)% 189.42 (-0.28)%
scimark.large 46.85 ( 0.00)% 46.41 (-0.94)% 47.83 ( 2.09)%
scimark.small 412.91 ( 0.00)% 415.41 ( 0.61)% 421.17 ( 2.00)%
serial 204.23 ( 0.00)% 213.46 ( 4.52)% 203.17 (-0.52)%
startup 36.76 ( 0.00)% 35.49 (-3.45)% 35.64 (-3.05)%
sunflow 115.34 ( 0.00)% 115.08 (-0.23)% 117.37 ( 1.76)%
xml 620.55 ( 0.00)% 619.95 (-0.10)% 620.39 (-0.03)%
composite 211.50 ( 0.00)% 211.15 (-0.17)% 211.67 ( 0.08)%
time idlememstat:
17.20user 65.16system 2:15:23elapsed 1%CPU (0avgtext+0avgdata 8476maxresident)k
448inputs+40outputs (1major+36052minor)pagefaults 0swaps
==== SCRIPT FOR COUNTING IDLE PAGES PER CGROUP ====
#! /usr/bin/python
#
import os
import stat
import errno
import struct
CGROUP_MOUNT = "/sys/fs/cgroup/memory"
BUFSIZE = 8 * 1024 # must be multiple of 8
def get_hugepage_size():
with open("/proc/meminfo", "r") as f:
for s in f:
k, v = s.split(":")
if k == "Hugepagesize":
return int(v.split()[0]) * 1024
PAGE_SIZE = os.sysconf("SC_PAGE_SIZE")
HUGEPAGE_SIZE = get_hugepage_size()
def set_idle():
f = open("/sys/kernel/mm/page_idle/bitmap", "wb", BUFSIZE)
while True:
try:
f.write(struct.pack("Q", pow(2, 64) - 1))
except IOError as err:
if err.errno == errno.ENXIO:
break
raise
f.close()
def count_idle():
f_flags = open("/proc/kpageflags", "rb", BUFSIZE)
f_cgroup = open("/proc/kpagecgroup", "rb", BUFSIZE)
with open("/sys/kernel/mm/page_idle/bitmap", "rb", BUFSIZE) as f:
while f.read(BUFSIZE): pass # update idle flag
idlememsz = {}
while True:
s1, s2 = f_flags.read(8), f_cgroup.read(8)
if not s1 or not s2:
break
flags, = struct.unpack('Q', s1)
cgino, = struct.unpack('Q', s2)
unevictable = (flags >> 18) & 1
huge = (flags >> 22) & 1
idle = (flags >> 25) & 1
if idle and not unevictable:
idlememsz[cgino] = idlememsz.get(cgino, 0) + \
(HUGEPAGE_SIZE if huge else PAGE_SIZE)
f_flags.close()
f_cgroup.close()
return idlememsz
if __name__ == "__main__":
print "Setting the idle flag for each page..."
set_idle()
raw_input("Wait until the workload accesses its working set, "
"then press Enter")
print "Counting idle pages..."
idlememsz = count_idle()
for dir, subdirs, files in os.walk(CGROUP_MOUNT):
ino = os.stat(dir)[stat.ST_INO]
print dir + ": " + str(idlememsz.get(ino, 0) / 1024) + " kB"
==== END SCRIPT ====
This patch (of 8):
Add page_cgroup_ino() helper to memcg.
This function returns the inode number of the closest online ancestor of
the memory cgroup a page is charged to. It is required for exporting
information about which page is charged to which cgroup to userspace,
which will be introduced by a following patch.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-10 06:35:28 +08:00
|
|
|
ino_t page_cgroup_ino(struct page *page);
|
2009-12-16 19:19:59 +08:00
|
|
|
|
2016-01-21 07:03:02 +08:00
|
|
|
static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return true;
|
|
|
|
return !!(memcg->css.flags & CSS_ONLINE);
|
|
|
|
}
|
|
|
|
|
2008-02-07 16:14:32 +08:00
|
|
|
/*
|
|
|
|
* For memory reclaim.
|
|
|
|
*/
|
2011-05-27 07:25:33 +08:00
|
|
|
int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
|
2015-09-09 06:01:02 +08:00
|
|
|
|
|
|
|
void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
|
2017-01-11 08:58:04 +08:00
|
|
|
int zid, int nr_pages);
|
2015-09-09 06:01:02 +08:00
|
|
|
|
2016-03-18 05:18:42 +08:00
|
|
|
unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
|
|
|
|
int nid, unsigned int lru_mask);
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
static inline
|
|
|
|
unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
|
|
|
|
{
|
2016-07-29 06:46:05 +08:00
|
|
|
struct mem_cgroup_per_node *mz;
|
2017-01-11 08:58:04 +08:00
|
|
|
unsigned long nr_pages = 0;
|
|
|
|
int zid;
|
2015-09-09 06:01:02 +08:00
|
|
|
|
2016-07-29 06:46:05 +08:00
|
|
|
mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
|
2017-01-11 08:58:04 +08:00
|
|
|
for (zid = 0; zid < MAX_NR_ZONES; zid++)
|
|
|
|
nr_pages += mz->lru_zone_size[zid][lru];
|
|
|
|
return nr_pages;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
|
|
|
|
enum lru_list lru, int zone_idx)
|
|
|
|
{
|
|
|
|
struct mem_cgroup_per_node *mz;
|
|
|
|
|
|
|
|
mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
|
|
|
|
return mz->lru_zone_size[zone_idx][lru];
|
2015-09-09 06:01:02 +08:00
|
|
|
}
|
|
|
|
|
memcg: punt high overage reclaim to return-to-userland path
Currently, try_charge() tries to reclaim memory synchronously when the
high limit is breached; however, if the allocation doesn't have
__GFP_WAIT, synchronous reclaim is skipped. If a process performs only
speculative allocations, it can blow way past the high limit. This is
actually easily reproducible by simply doing "find /". slab/slub
allocator tries speculative allocations first, so as long as there's
memory which can be consumed without blocking, it can keep allocating
memory regardless of the high limit.
This patch makes try_charge() always punt the over-high reclaim to the
return-to-userland path. If try_charge() detects that high limit is
breached, it adds the overage to current->memcg_nr_pages_over_high and
schedules execution of mem_cgroup_handle_over_high() which performs
synchronous reclaim from the return-to-userland path.
As long as kernel doesn't have a run-away allocation spree, this should
provide enough protection while making kmemcg behave more consistently.
It also has the following benefits.
- All over-high reclaims can use GFP_KERNEL regardless of the specific
gfp mask in use, e.g. GFP_NOFS, when the limit was breached.
- It copes with prio inversion. Previously, a low-prio task with
small memory.high might perform over-high reclaim with a bunch of
locks held. If a higher prio task needed any of these locks, it
would have to wait until the low prio task finished reclaim and
released the locks. By handing over-high reclaim to the task exit
path this issue can be avoided.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-06 10:46:11 +08:00
|
|
|
void mem_cgroup_handle_over_high(void);
|
|
|
|
|
2016-10-08 07:57:23 +08:00
|
|
|
unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg);
|
|
|
|
|
2015-09-09 06:01:07 +08:00
|
|
|
void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
|
|
|
|
struct task_struct *p);
|
2008-02-07 16:14:32 +08:00
|
|
|
|
2013-10-17 04:46:59 +08:00
|
|
|
static inline void mem_cgroup_oom_enable(void)
|
2013-09-13 06:13:42 +08:00
|
|
|
{
|
2015-11-06 10:46:09 +08:00
|
|
|
WARN_ON(current->memcg_may_oom);
|
|
|
|
current->memcg_may_oom = 1;
|
2013-09-13 06:13:42 +08:00
|
|
|
}
|
|
|
|
|
2013-10-17 04:46:59 +08:00
|
|
|
static inline void mem_cgroup_oom_disable(void)
|
2013-09-13 06:13:42 +08:00
|
|
|
{
|
2015-11-06 10:46:09 +08:00
|
|
|
WARN_ON(!current->memcg_may_oom);
|
|
|
|
current->memcg_may_oom = 0;
|
2013-09-13 06:13:42 +08:00
|
|
|
}
|
|
|
|
|
mm: memcg: do not trap chargers with full callstack on OOM
The memcg OOM handling is incredibly fragile and can deadlock. When a
task fails to charge memory, it invokes the OOM killer and loops right
there in the charge code until it succeeds. Comparably, any other task
that enters the charge path at this point will go to a waitqueue right
then and there and sleep until the OOM situation is resolved. The problem
is that these tasks may hold filesystem locks and the mmap_sem; locks that
the selected OOM victim may need to exit.
For example, in one reported case, the task invoking the OOM killer was
about to charge a page cache page during a write(), which holds the
i_mutex. The OOM killer selected a task that was just entering truncate()
and trying to acquire the i_mutex:
OOM invoking task:
mem_cgroup_handle_oom+0x241/0x3b0
mem_cgroup_cache_charge+0xbe/0xe0
add_to_page_cache_locked+0x4c/0x140
add_to_page_cache_lru+0x22/0x50
grab_cache_page_write_begin+0x8b/0xe0
ext3_write_begin+0x88/0x270
generic_file_buffered_write+0x116/0x290
__generic_file_aio_write+0x27c/0x480
generic_file_aio_write+0x76/0xf0 # takes ->i_mutex
do_sync_write+0xea/0x130
vfs_write+0xf3/0x1f0
sys_write+0x51/0x90
system_call_fastpath+0x18/0x1d
OOM kill victim:
do_truncate+0x58/0xa0 # takes i_mutex
do_last+0x250/0xa30
path_openat+0xd7/0x440
do_filp_open+0x49/0xa0
do_sys_open+0x106/0x240
sys_open+0x20/0x30
system_call_fastpath+0x18/0x1d
The OOM handling task will retry the charge indefinitely while the OOM
killed task is not releasing any resources.
A similar scenario can happen when the kernel OOM killer for a memcg is
disabled and a userspace task is in charge of resolving OOM situations.
In this case, ALL tasks that enter the OOM path will be made to sleep on
the OOM waitqueue and wait for userspace to free resources or increase
the group's limit. But a userspace OOM handler is prone to deadlock
itself on the locks held by the waiting tasks. For example one of the
sleeping tasks may be stuck in a brk() call with the mmap_sem held for
writing but the userspace handler, in order to pick an optimal victim,
may need to read files from /proc/<pid>, which tries to acquire the same
mmap_sem for reading and deadlocks.
This patch changes the way tasks behave after detecting a memcg OOM and
makes sure nobody loops or sleeps with locks held:
1. When OOMing in a user fault, invoke the OOM killer and restart the
fault instead of looping on the charge attempt. This way, the OOM
victim can not get stuck on locks the looping task may hold.
2. When OOMing in a user fault but somebody else is handling it
(either the kernel OOM killer or a userspace handler), don't go to
sleep in the charge context. Instead, remember the OOMing memcg in
the task struct and then fully unwind the page fault stack with
-ENOMEM. pagefault_out_of_memory() will then call back into the
memcg code to check if the -ENOMEM came from the memcg, and then
either put the task to sleep on the memcg's OOM waitqueue or just
restart the fault. The OOM victim can no longer get stuck on any
lock a sleeping task may hold.
Debugged by Michal Hocko.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: azurIt <azurit@pobox.sk>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.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>
2013-09-13 06:13:44 +08:00
|
|
|
static inline bool task_in_memcg_oom(struct task_struct *p)
|
|
|
|
{
|
2015-11-06 10:46:09 +08:00
|
|
|
return p->memcg_in_oom;
|
mm: memcg: do not trap chargers with full callstack on OOM
The memcg OOM handling is incredibly fragile and can deadlock. When a
task fails to charge memory, it invokes the OOM killer and loops right
there in the charge code until it succeeds. Comparably, any other task
that enters the charge path at this point will go to a waitqueue right
then and there and sleep until the OOM situation is resolved. The problem
is that these tasks may hold filesystem locks and the mmap_sem; locks that
the selected OOM victim may need to exit.
For example, in one reported case, the task invoking the OOM killer was
about to charge a page cache page during a write(), which holds the
i_mutex. The OOM killer selected a task that was just entering truncate()
and trying to acquire the i_mutex:
OOM invoking task:
mem_cgroup_handle_oom+0x241/0x3b0
mem_cgroup_cache_charge+0xbe/0xe0
add_to_page_cache_locked+0x4c/0x140
add_to_page_cache_lru+0x22/0x50
grab_cache_page_write_begin+0x8b/0xe0
ext3_write_begin+0x88/0x270
generic_file_buffered_write+0x116/0x290
__generic_file_aio_write+0x27c/0x480
generic_file_aio_write+0x76/0xf0 # takes ->i_mutex
do_sync_write+0xea/0x130
vfs_write+0xf3/0x1f0
sys_write+0x51/0x90
system_call_fastpath+0x18/0x1d
OOM kill victim:
do_truncate+0x58/0xa0 # takes i_mutex
do_last+0x250/0xa30
path_openat+0xd7/0x440
do_filp_open+0x49/0xa0
do_sys_open+0x106/0x240
sys_open+0x20/0x30
system_call_fastpath+0x18/0x1d
The OOM handling task will retry the charge indefinitely while the OOM
killed task is not releasing any resources.
A similar scenario can happen when the kernel OOM killer for a memcg is
disabled and a userspace task is in charge of resolving OOM situations.
In this case, ALL tasks that enter the OOM path will be made to sleep on
the OOM waitqueue and wait for userspace to free resources or increase
the group's limit. But a userspace OOM handler is prone to deadlock
itself on the locks held by the waiting tasks. For example one of the
sleeping tasks may be stuck in a brk() call with the mmap_sem held for
writing but the userspace handler, in order to pick an optimal victim,
may need to read files from /proc/<pid>, which tries to acquire the same
mmap_sem for reading and deadlocks.
This patch changes the way tasks behave after detecting a memcg OOM and
makes sure nobody loops or sleeps with locks held:
1. When OOMing in a user fault, invoke the OOM killer and restart the
fault instead of looping on the charge attempt. This way, the OOM
victim can not get stuck on locks the looping task may hold.
2. When OOMing in a user fault but somebody else is handling it
(either the kernel OOM killer or a userspace handler), don't go to
sleep in the charge context. Instead, remember the OOMing memcg in
the task struct and then fully unwind the page fault stack with
-ENOMEM. pagefault_out_of_memory() will then call back into the
memcg code to check if the -ENOMEM came from the memcg, and then
either put the task to sleep on the memcg's OOM waitqueue or just
restart the fault. The OOM victim can no longer get stuck on any
lock a sleeping task may hold.
Debugged by Michal Hocko.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: azurIt <azurit@pobox.sk>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.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>
2013-09-13 06:13:44 +08:00
|
|
|
}
|
|
|
|
|
2013-10-17 04:46:59 +08:00
|
|
|
bool mem_cgroup_oom_synchronize(bool wait);
|
mm: memcg: do not trap chargers with full callstack on OOM
The memcg OOM handling is incredibly fragile and can deadlock. When a
task fails to charge memory, it invokes the OOM killer and loops right
there in the charge code until it succeeds. Comparably, any other task
that enters the charge path at this point will go to a waitqueue right
then and there and sleep until the OOM situation is resolved. The problem
is that these tasks may hold filesystem locks and the mmap_sem; locks that
the selected OOM victim may need to exit.
For example, in one reported case, the task invoking the OOM killer was
about to charge a page cache page during a write(), which holds the
i_mutex. The OOM killer selected a task that was just entering truncate()
and trying to acquire the i_mutex:
OOM invoking task:
mem_cgroup_handle_oom+0x241/0x3b0
mem_cgroup_cache_charge+0xbe/0xe0
add_to_page_cache_locked+0x4c/0x140
add_to_page_cache_lru+0x22/0x50
grab_cache_page_write_begin+0x8b/0xe0
ext3_write_begin+0x88/0x270
generic_file_buffered_write+0x116/0x290
__generic_file_aio_write+0x27c/0x480
generic_file_aio_write+0x76/0xf0 # takes ->i_mutex
do_sync_write+0xea/0x130
vfs_write+0xf3/0x1f0
sys_write+0x51/0x90
system_call_fastpath+0x18/0x1d
OOM kill victim:
do_truncate+0x58/0xa0 # takes i_mutex
do_last+0x250/0xa30
path_openat+0xd7/0x440
do_filp_open+0x49/0xa0
do_sys_open+0x106/0x240
sys_open+0x20/0x30
system_call_fastpath+0x18/0x1d
The OOM handling task will retry the charge indefinitely while the OOM
killed task is not releasing any resources.
A similar scenario can happen when the kernel OOM killer for a memcg is
disabled and a userspace task is in charge of resolving OOM situations.
In this case, ALL tasks that enter the OOM path will be made to sleep on
the OOM waitqueue and wait for userspace to free resources or increase
the group's limit. But a userspace OOM handler is prone to deadlock
itself on the locks held by the waiting tasks. For example one of the
sleeping tasks may be stuck in a brk() call with the mmap_sem held for
writing but the userspace handler, in order to pick an optimal victim,
may need to read files from /proc/<pid>, which tries to acquire the same
mmap_sem for reading and deadlocks.
This patch changes the way tasks behave after detecting a memcg OOM and
makes sure nobody loops or sleeps with locks held:
1. When OOMing in a user fault, invoke the OOM killer and restart the
fault instead of looping on the charge attempt. This way, the OOM
victim can not get stuck on locks the looping task may hold.
2. When OOMing in a user fault but somebody else is handling it
(either the kernel OOM killer or a userspace handler), don't go to
sleep in the charge context. Instead, remember the OOMing memcg in
the task struct and then fully unwind the page fault stack with
-ENOMEM. pagefault_out_of_memory() will then call back into the
memcg code to check if the -ENOMEM came from the memcg, and then
either put the task to sleep on the memcg's OOM waitqueue or just
restart the fault. The OOM victim can no longer get stuck on any
lock a sleeping task may hold.
Debugged by Michal Hocko.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: azurIt <azurit@pobox.sk>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.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>
2013-09-13 06:13:44 +08:00
|
|
|
|
2012-08-01 07:43:02 +08:00
|
|
|
#ifdef CONFIG_MEMCG_SWAP
|
2009-01-08 10:07:57 +08:00
|
|
|
extern int do_swap_account;
|
|
|
|
#endif
|
2009-01-08 10:08:02 +08:00
|
|
|
|
2016-03-16 05:57:22 +08:00
|
|
|
void lock_page_memcg(struct page *page);
|
|
|
|
void unlock_page_memcg(struct page *page);
|
mm: memcontrol: fix missed end-writeback page accounting
Commit 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API") changed
page migration to uncharge the old page right away. The page is locked,
unmapped, truncated, and off the LRU, but it could race with writeback
ending, which then doesn't unaccount the page properly:
test_clear_page_writeback() migration
wait_on_page_writeback()
TestClearPageWriteback()
mem_cgroup_migrate()
clear PCG_USED
mem_cgroup_update_page_stat()
if (PageCgroupUsed(pc))
decrease memcg pages under writeback
release pc->mem_cgroup->move_lock
The per-page statistics interface is heavily optimized to avoid a
function call and a lookup_page_cgroup() in the file unmap fast path,
which means it doesn't verify whether a page is still charged before
clearing PageWriteback() and it has to do it in the stat update later.
Rework it so that it looks up the page's memcg once at the beginning of
the transaction and then uses it throughout. The charge will be
verified before clearing PageWriteback() and migration can't uncharge
the page as long as that is still set. The RCU lock will protect the
memcg past uncharge.
As far as losing the optimization goes, the following test results are
from a microbenchmark that maps, faults, and unmaps a 4GB sparse file
three times in a nested fashion, so that there are two negative passes
that don't account but still go through the new transaction overhead.
There is no actual difference:
old: 33.195102545 seconds time elapsed ( +- 0.01% )
new: 33.199231369 seconds time elapsed ( +- 0.03% )
The time spent in page_remove_rmap()'s callees still adds up to the
same, but the time spent in the function itself seems reduced:
# Children Self Command Shared Object Symbol
old: 0.12% 0.11% filemapstress [kernel.kallsyms] [k] page_remove_rmap
new: 0.12% 0.08% filemapstress [kernel.kallsyms] [k] page_remove_rmap
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: <stable@vger.kernel.org> [3.17.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-30 05:50:48 +08:00
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
/**
|
|
|
|
* mem_cgroup_update_page_stat - update page state statistics
|
2016-03-16 05:57:22 +08:00
|
|
|
* @page: the page
|
2015-09-09 06:01:02 +08:00
|
|
|
* @idx: page state item to account
|
|
|
|
* @val: number of pages (positive or negative)
|
|
|
|
*
|
2016-03-16 05:57:25 +08:00
|
|
|
* The @page must be locked or the caller must use lock_page_memcg()
|
|
|
|
* to prevent double accounting when the page is concurrently being
|
|
|
|
* moved to another memcg:
|
2016-03-16 05:57:04 +08:00
|
|
|
*
|
2016-03-16 05:57:25 +08:00
|
|
|
* lock_page(page) or lock_page_memcg(page)
|
2016-03-16 05:57:04 +08:00
|
|
|
* if (TestClearPageState(page))
|
2016-03-16 05:57:22 +08:00
|
|
|
* mem_cgroup_update_page_stat(page, state, -1);
|
2016-03-16 05:57:25 +08:00
|
|
|
* unlock_page(page) or unlock_page_memcg(page)
|
2015-09-09 06:01:02 +08:00
|
|
|
*/
|
2016-03-16 05:57:22 +08:00
|
|
|
static inline void mem_cgroup_update_page_stat(struct page *page,
|
2015-09-09 06:01:02 +08:00
|
|
|
enum mem_cgroup_stat_index idx, int val)
|
|
|
|
{
|
2016-03-16 05:57:25 +08:00
|
|
|
VM_BUG_ON(!(rcu_read_lock_held() || PageLocked(page)));
|
2015-09-09 06:01:02 +08:00
|
|
|
|
2016-03-16 05:57:22 +08:00
|
|
|
if (page->mem_cgroup)
|
|
|
|
this_cpu_add(page->mem_cgroup->stat->count[idx], val);
|
2015-09-09 06:01:02 +08:00
|
|
|
}
|
|
|
|
|
2016-03-16 05:57:22 +08:00
|
|
|
static inline void mem_cgroup_inc_page_stat(struct page *page,
|
2013-09-13 06:13:50 +08:00
|
|
|
enum mem_cgroup_stat_index idx)
|
2011-01-14 07:47:37 +08:00
|
|
|
{
|
2016-03-16 05:57:22 +08:00
|
|
|
mem_cgroup_update_page_stat(page, idx, 1);
|
2011-01-14 07:47:37 +08:00
|
|
|
}
|
|
|
|
|
2016-03-16 05:57:22 +08:00
|
|
|
static inline void mem_cgroup_dec_page_stat(struct page *page,
|
2013-09-13 06:13:50 +08:00
|
|
|
enum mem_cgroup_stat_index idx)
|
2011-01-14 07:47:37 +08:00
|
|
|
{
|
2016-03-16 05:57:22 +08:00
|
|
|
mem_cgroup_update_page_stat(page, idx, -1);
|
2011-01-14 07:47:37 +08:00
|
|
|
}
|
|
|
|
|
2016-07-29 06:46:05 +08:00
|
|
|
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
|
2013-09-25 06:27:41 +08:00
|
|
|
gfp_t gfp_mask,
|
|
|
|
unsigned long *total_scanned);
|
oom: badness heuristic rewrite
This a complete rewrite of the oom killer's badness() heuristic which is
used to determine which task to kill in oom conditions. The goal is to
make it as simple and predictable as possible so the results are better
understood and we end up killing the task which will lead to the most
memory freeing while still respecting the fine-tuning from userspace.
Instead of basing the heuristic on mm->total_vm for each task, the task's
rss and swap space is used instead. This is a better indication of the
amount of memory that will be freeable if the oom killed task is chosen
and subsequently exits. This helps specifically in cases where KDE or
GNOME is chosen for oom kill on desktop systems instead of a memory
hogging task.
The baseline for the heuristic is a proportion of memory that each task is
currently using in memory plus swap compared to the amount of "allowable"
memory. "Allowable," in this sense, means the system-wide resources for
unconstrained oom conditions, the set of mempolicy nodes, the mems
attached to current's cpuset, or a memory controller's limit. The
proportion is given on a scale of 0 (never kill) to 1000 (always kill),
roughly meaning that if a task has a badness() score of 500 that the task
consumes approximately 50% of allowable memory resident in RAM or in swap
space.
The proportion is always relative to the amount of "allowable" memory and
not the total amount of RAM systemwide so that mempolicies and cpusets may
operate in isolation; they shall not need to know the true size of the
machine on which they are running if they are bound to a specific set of
nodes or mems, respectively.
Root tasks are given 3% extra memory just like __vm_enough_memory()
provides in LSMs. In the event of two tasks consuming similar amounts of
memory, it is generally better to save root's task.
Because of the change in the badness() heuristic's baseline, it is also
necessary to introduce a new user interface to tune it. It's not possible
to redefine the meaning of /proc/pid/oom_adj with a new scale since the
ABI cannot be changed for backward compatability. Instead, a new tunable,
/proc/pid/oom_score_adj, is added that ranges from -1000 to +1000. It may
be used to polarize the heuristic such that certain tasks are never
considered for oom kill while others may always be considered. The value
is added directly into the badness() score so a value of -500, for
example, means to discount 50% of its memory consumption in comparison to
other tasks either on the system, bound to the mempolicy, in the cpuset,
or sharing the same memory controller.
/proc/pid/oom_adj is changed so that its meaning is rescaled into the
units used by /proc/pid/oom_score_adj, and vice versa. Changing one of
these per-task tunables will rescale the value of the other to an
equivalent meaning. Although /proc/pid/oom_adj was originally defined as
a bitshift on the badness score, it now shares the same linear growth as
/proc/pid/oom_score_adj but with different granularity. This is required
so the ABI is not broken with userspace applications and allows oom_adj to
be deprecated for future removal.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-08-10 08:19:46 +08:00
|
|
|
|
2012-12-13 05:51:57 +08:00
|
|
|
static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
|
|
|
|
enum vm_event_item idx)
|
|
|
|
{
|
2015-09-09 06:01:02 +08:00
|
|
|
struct mem_cgroup *memcg;
|
|
|
|
|
2012-12-13 05:51:57 +08:00
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
return;
|
2015-09-09 06:01:02 +08:00
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
|
|
|
|
if (unlikely(!memcg))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
switch (idx) {
|
|
|
|
case PGFAULT:
|
|
|
|
this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]);
|
|
|
|
break;
|
|
|
|
case PGMAJFAULT:
|
|
|
|
this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]);
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
rcu_read_unlock();
|
2012-12-13 05:51:57 +08:00
|
|
|
}
|
2011-01-21 06:44:24 +08:00
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
2012-01-13 09:18:20 +08:00
|
|
|
void mem_cgroup_split_huge_fixup(struct page *head);
|
2011-01-21 06:44:24 +08:00
|
|
|
#endif
|
|
|
|
|
2012-08-01 07:43:02 +08:00
|
|
|
#else /* CONFIG_MEMCG */
|
2016-03-16 05:57:16 +08:00
|
|
|
|
|
|
|
#define MEM_CGROUP_ID_SHIFT 0
|
|
|
|
#define MEM_CGROUP_ID_MAX 0
|
|
|
|
|
2009-01-08 10:07:48 +08:00
|
|
|
struct mem_cgroup;
|
|
|
|
|
2016-03-16 05:57:16 +08:00
|
|
|
static inline bool mem_cgroup_disabled(void)
|
|
|
|
{
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: default hierarchy interface for memory
Introduce the basic control files to account, partition, and limit
memory using cgroups in default hierarchy mode.
This interface versioning allows us to address fundamental design
issues in the existing memory cgroup interface, further explained
below. The old interface will be maintained indefinitely, but a
clearer model and improved workload performance should encourage
existing users to switch over to the new one eventually.
The control files are thus:
- memory.current shows the current consumption of the cgroup and its
descendants, in bytes.
- memory.low configures the lower end of the cgroup's expected
memory consumption range. The kernel considers memory below that
boundary to be a reserve - the minimum that the workload needs in
order to make forward progress - and generally avoids reclaiming
it, unless there is an imminent risk of entering an OOM situation.
- memory.high configures the upper end of the cgroup's expected
memory consumption range. A cgroup whose consumption grows beyond
this threshold is forced into direct reclaim, to work off the
excess and to throttle new allocations heavily, but is generally
allowed to continue and the OOM killer is not invoked.
- memory.max configures the hard maximum amount of memory that the
cgroup is allowed to consume before the OOM killer is invoked.
- memory.events shows event counters that indicate how often the
cgroup was reclaimed while below memory.low, how often it was
forced to reclaim excess beyond memory.high, how often it hit
memory.max, and how often it entered OOM due to memory.max. This
allows users to identify configuration problems when observing a
degradation in workload performance. An overcommitted system will
have an increased rate of low boundary breaches, whereas increased
rates of high limit breaches, maximum hits, or even OOM situations
will indicate internally overcommitted cgroups.
For existing users of memory cgroups, the following deviations from
the current interface are worth pointing out and explaining:
- The original lower boundary, the soft limit, is defined as a limit
that is per default unset. As a result, the set of cgroups that
global reclaim prefers is opt-in, rather than opt-out. The costs
for optimizing these mostly negative lookups are so high that the
implementation, despite its enormous size, does not even provide
the basic desirable behavior. First off, the soft limit has no
hierarchical meaning. All configured groups are organized in a
global rbtree and treated like equal peers, regardless where they
are located in the hierarchy. This makes subtree delegation
impossible. Second, the soft limit reclaim pass is so aggressive
that it not just introduces high allocation latencies into the
system, but also impacts system performance due to overreclaim, to
the point where the feature becomes self-defeating.
The memory.low boundary on the other hand is a top-down allocated
reserve. A cgroup enjoys reclaim protection when it and all its
ancestors are below their low boundaries, which makes delegation
of subtrees possible. Secondly, new cgroups have no reserve per
default and in the common case most cgroups are eligible for the
preferred reclaim pass. This allows the new low boundary to be
efficiently implemented with just a minor addition to the generic
reclaim code, without the need for out-of-band data structures and
reclaim passes. Because the generic reclaim code considers all
cgroups except for the ones running low in the preferred first
reclaim pass, overreclaim of individual groups is eliminated as
well, resulting in much better overall workload performance.
- The original high boundary, the hard limit, is defined as a strict
limit that can not budge, even if the OOM killer has to be called.
But this generally goes against the goal of making the most out of
the available memory. The memory consumption of workloads varies
during runtime, and that requires users to overcommit. But doing
that with a strict upper limit requires either a fairly accurate
prediction of the working set size or adding slack to the limit.
Since working set size estimation is hard and error prone, and
getting it wrong results in OOM kills, most users tend to err on
the side of a looser limit and end up wasting precious resources.
The memory.high boundary on the other hand can be set much more
conservatively. When hit, it throttles allocations by forcing
them into direct reclaim to work off the excess, but it never
invokes the OOM killer. As a result, a high boundary that is
chosen too aggressively will not terminate the processes, but
instead it will lead to gradual performance degradation. The user
can monitor this and make corrections until the minimal memory
footprint that still gives acceptable performance is found.
In extreme cases, with many concurrent allocations and a complete
breakdown of reclaim progress within the group, the high boundary
can be exceeded. But even then it's mostly better to satisfy the
allocation from the slack available in other groups or the rest of
the system than killing the group. Otherwise, memory.max is there
to limit this type of spillover and ultimately contain buggy or
even malicious applications.
- The original control file names are unwieldy and inconsistent in
many different ways. For example, the upper boundary hit count is
exported in the memory.failcnt file, but an OOM event count has to
be manually counted by listening to memory.oom_control events, and
lower boundary / soft limit events have to be counted by first
setting a threshold for that value and then counting those events.
Also, usage and limit files encode their units in the filename.
That makes the filenames very long, even though this is not
information that a user needs to be reminded of every time they
type out those names.
To address these naming issues, as well as to signal clearly that
the new interface carries a new configuration model, the naming
conventions in it necessarily differ from the old interface.
- The original limit files indicate the state of an unset limit with
a very high number, and a configured limit can be unset by echoing
-1 into those files. But that very high number is implementation
and architecture dependent and not very descriptive. And while -1
can be understood as an underflow into the highest possible value,
-2 or -10M etc. do not work, so it's not inconsistent.
memory.low, memory.high, and memory.max will use the string
"infinity" to indicate and set the highest possible value.
[akpm@linux-foundation.org: use seq_puts() for basic strings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 07:26:06 +08:00
|
|
|
static inline void mem_cgroup_events(struct mem_cgroup *memcg,
|
|
|
|
enum mem_cgroup_events_index idx,
|
|
|
|
unsigned int nr)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool mem_cgroup_low(struct mem_cgroup *root,
|
|
|
|
struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: rewrite charge API
These patches rework memcg charge lifetime to integrate more naturally
with the lifetime of user pages. This drastically simplifies the code and
reduces charging and uncharging overhead. The most expensive part of
charging and uncharging is the page_cgroup bit spinlock, which is removed
entirely after this series.
Here are the top-10 profile entries of a stress test that reads a 128G
sparse file on a freshly booted box, without even a dedicated cgroup (i.e.
executing in the root memcg). Before:
15.36% cat [kernel.kallsyms] [k] copy_user_generic_string
13.31% cat [kernel.kallsyms] [k] memset
11.48% cat [kernel.kallsyms] [k] do_mpage_readpage
4.23% cat [kernel.kallsyms] [k] get_page_from_freelist
2.38% cat [kernel.kallsyms] [k] put_page
2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge
2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common
1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
After:
15.67% cat [kernel.kallsyms] [k] copy_user_generic_string
13.48% cat [kernel.kallsyms] [k] memset
11.42% cat [kernel.kallsyms] [k] do_mpage_readpage
3.98% cat [kernel.kallsyms] [k] get_page_from_freelist
2.46% cat [kernel.kallsyms] [k] put_page
2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk
1.30% cat [kernel.kallsyms] [k] kfree
As you can see, the memcg footprint has shrunk quite a bit.
text data bss dec hex filename
37970 9892 400 48262 bc86 mm/memcontrol.o.old
35239 9892 400 45531 b1db mm/memcontrol.o
This patch (of 4):
The memcg charge API charges pages before they are rmapped - i.e. have an
actual "type" - and so every callsite needs its own set of charge and
uncharge functions to know what type is being operated on. Worse,
uncharge has to happen from a context that is still type-specific, rather
than at the end of the page's lifetime with exclusive access, and so
requires a lot of synchronization.
Rewrite the charge API to provide a generic set of try_charge(),
commit_charge() and cancel_charge() transaction operations, much like
what's currently done for swap-in:
mem_cgroup_try_charge() attempts to reserve a charge, reclaiming
pages from the memcg if necessary.
mem_cgroup_commit_charge() commits the page to the charge once it
has a valid page->mapping and PageAnon() reliably tells the type.
mem_cgroup_cancel_charge() aborts the transaction.
This reduces the charge API and enables subsequent patches to
drastically simplify uncharging.
As pages need to be committed after rmap is established but before they
are added to the LRU, page_add_new_anon_rmap() must stop doing LRU
additions again. Revive lru_cache_add_active_or_unevictable().
[hughd@google.com: fix shmem_unuse]
[hughd@google.com: Add comments on the private use of -EAGAIN]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:19:20 +08:00
|
|
|
static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
|
|
|
|
gfp_t gfp_mask,
|
2016-01-16 08:52:20 +08:00
|
|
|
struct mem_cgroup **memcgp,
|
|
|
|
bool compound)
|
2009-01-08 10:07:48 +08:00
|
|
|
{
|
mm: memcontrol: rewrite charge API
These patches rework memcg charge lifetime to integrate more naturally
with the lifetime of user pages. This drastically simplifies the code and
reduces charging and uncharging overhead. The most expensive part of
charging and uncharging is the page_cgroup bit spinlock, which is removed
entirely after this series.
Here are the top-10 profile entries of a stress test that reads a 128G
sparse file on a freshly booted box, without even a dedicated cgroup (i.e.
executing in the root memcg). Before:
15.36% cat [kernel.kallsyms] [k] copy_user_generic_string
13.31% cat [kernel.kallsyms] [k] memset
11.48% cat [kernel.kallsyms] [k] do_mpage_readpage
4.23% cat [kernel.kallsyms] [k] get_page_from_freelist
2.38% cat [kernel.kallsyms] [k] put_page
2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge
2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common
1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
After:
15.67% cat [kernel.kallsyms] [k] copy_user_generic_string
13.48% cat [kernel.kallsyms] [k] memset
11.42% cat [kernel.kallsyms] [k] do_mpage_readpage
3.98% cat [kernel.kallsyms] [k] get_page_from_freelist
2.46% cat [kernel.kallsyms] [k] put_page
2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk
1.30% cat [kernel.kallsyms] [k] kfree
As you can see, the memcg footprint has shrunk quite a bit.
text data bss dec hex filename
37970 9892 400 48262 bc86 mm/memcontrol.o.old
35239 9892 400 45531 b1db mm/memcontrol.o
This patch (of 4):
The memcg charge API charges pages before they are rmapped - i.e. have an
actual "type" - and so every callsite needs its own set of charge and
uncharge functions to know what type is being operated on. Worse,
uncharge has to happen from a context that is still type-specific, rather
than at the end of the page's lifetime with exclusive access, and so
requires a lot of synchronization.
Rewrite the charge API to provide a generic set of try_charge(),
commit_charge() and cancel_charge() transaction operations, much like
what's currently done for swap-in:
mem_cgroup_try_charge() attempts to reserve a charge, reclaiming
pages from the memcg if necessary.
mem_cgroup_commit_charge() commits the page to the charge once it
has a valid page->mapping and PageAnon() reliably tells the type.
mem_cgroup_cancel_charge() aborts the transaction.
This reduces the charge API and enables subsequent patches to
drastically simplify uncharging.
As pages need to be committed after rmap is established but before they
are added to the LRU, page_add_new_anon_rmap() must stop doing LRU
additions again. Revive lru_cache_add_active_or_unevictable().
[hughd@google.com: fix shmem_unuse]
[hughd@google.com: Add comments on the private use of -EAGAIN]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:19:20 +08:00
|
|
|
*memcgp = NULL;
|
2009-01-08 10:07:48 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: rewrite charge API
These patches rework memcg charge lifetime to integrate more naturally
with the lifetime of user pages. This drastically simplifies the code and
reduces charging and uncharging overhead. The most expensive part of
charging and uncharging is the page_cgroup bit spinlock, which is removed
entirely after this series.
Here are the top-10 profile entries of a stress test that reads a 128G
sparse file on a freshly booted box, without even a dedicated cgroup (i.e.
executing in the root memcg). Before:
15.36% cat [kernel.kallsyms] [k] copy_user_generic_string
13.31% cat [kernel.kallsyms] [k] memset
11.48% cat [kernel.kallsyms] [k] do_mpage_readpage
4.23% cat [kernel.kallsyms] [k] get_page_from_freelist
2.38% cat [kernel.kallsyms] [k] put_page
2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge
2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common
1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
After:
15.67% cat [kernel.kallsyms] [k] copy_user_generic_string
13.48% cat [kernel.kallsyms] [k] memset
11.42% cat [kernel.kallsyms] [k] do_mpage_readpage
3.98% cat [kernel.kallsyms] [k] get_page_from_freelist
2.46% cat [kernel.kallsyms] [k] put_page
2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk
1.30% cat [kernel.kallsyms] [k] kfree
As you can see, the memcg footprint has shrunk quite a bit.
text data bss dec hex filename
37970 9892 400 48262 bc86 mm/memcontrol.o.old
35239 9892 400 45531 b1db mm/memcontrol.o
This patch (of 4):
The memcg charge API charges pages before they are rmapped - i.e. have an
actual "type" - and so every callsite needs its own set of charge and
uncharge functions to know what type is being operated on. Worse,
uncharge has to happen from a context that is still type-specific, rather
than at the end of the page's lifetime with exclusive access, and so
requires a lot of synchronization.
Rewrite the charge API to provide a generic set of try_charge(),
commit_charge() and cancel_charge() transaction operations, much like
what's currently done for swap-in:
mem_cgroup_try_charge() attempts to reserve a charge, reclaiming
pages from the memcg if necessary.
mem_cgroup_commit_charge() commits the page to the charge once it
has a valid page->mapping and PageAnon() reliably tells the type.
mem_cgroup_cancel_charge() aborts the transaction.
This reduces the charge API and enables subsequent patches to
drastically simplify uncharging.
As pages need to be committed after rmap is established but before they
are added to the LRU, page_add_new_anon_rmap() must stop doing LRU
additions again. Revive lru_cache_add_active_or_unevictable().
[hughd@google.com: fix shmem_unuse]
[hughd@google.com: Add comments on the private use of -EAGAIN]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:19:20 +08:00
|
|
|
static inline void mem_cgroup_commit_charge(struct page *page,
|
|
|
|
struct mem_cgroup *memcg,
|
2016-01-16 08:52:20 +08:00
|
|
|
bool lrucare, bool compound)
|
2009-01-08 10:07:48 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: rewrite charge API
These patches rework memcg charge lifetime to integrate more naturally
with the lifetime of user pages. This drastically simplifies the code and
reduces charging and uncharging overhead. The most expensive part of
charging and uncharging is the page_cgroup bit spinlock, which is removed
entirely after this series.
Here are the top-10 profile entries of a stress test that reads a 128G
sparse file on a freshly booted box, without even a dedicated cgroup (i.e.
executing in the root memcg). Before:
15.36% cat [kernel.kallsyms] [k] copy_user_generic_string
13.31% cat [kernel.kallsyms] [k] memset
11.48% cat [kernel.kallsyms] [k] do_mpage_readpage
4.23% cat [kernel.kallsyms] [k] get_page_from_freelist
2.38% cat [kernel.kallsyms] [k] put_page
2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge
2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common
1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
After:
15.67% cat [kernel.kallsyms] [k] copy_user_generic_string
13.48% cat [kernel.kallsyms] [k] memset
11.42% cat [kernel.kallsyms] [k] do_mpage_readpage
3.98% cat [kernel.kallsyms] [k] get_page_from_freelist
2.46% cat [kernel.kallsyms] [k] put_page
2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list
1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup
1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn
1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk
1.30% cat [kernel.kallsyms] [k] kfree
As you can see, the memcg footprint has shrunk quite a bit.
text data bss dec hex filename
37970 9892 400 48262 bc86 mm/memcontrol.o.old
35239 9892 400 45531 b1db mm/memcontrol.o
This patch (of 4):
The memcg charge API charges pages before they are rmapped - i.e. have an
actual "type" - and so every callsite needs its own set of charge and
uncharge functions to know what type is being operated on. Worse,
uncharge has to happen from a context that is still type-specific, rather
than at the end of the page's lifetime with exclusive access, and so
requires a lot of synchronization.
Rewrite the charge API to provide a generic set of try_charge(),
commit_charge() and cancel_charge() transaction operations, much like
what's currently done for swap-in:
mem_cgroup_try_charge() attempts to reserve a charge, reclaiming
pages from the memcg if necessary.
mem_cgroup_commit_charge() commits the page to the charge once it
has a valid page->mapping and PageAnon() reliably tells the type.
mem_cgroup_cancel_charge() aborts the transaction.
This reduces the charge API and enables subsequent patches to
drastically simplify uncharging.
As pages need to be committed after rmap is established but before they
are added to the LRU, page_add_new_anon_rmap() must stop doing LRU
additions again. Revive lru_cache_add_active_or_unevictable().
[hughd@google.com: fix shmem_unuse]
[hughd@google.com: Add comments on the private use of -EAGAIN]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:19:20 +08:00
|
|
|
static inline void mem_cgroup_cancel_charge(struct page *page,
|
2016-01-16 08:52:20 +08:00
|
|
|
struct mem_cgroup *memcg,
|
|
|
|
bool compound)
|
2009-01-08 10:07:48 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
mm: memcontrol: rewrite uncharge API
The memcg uncharging code that is involved towards the end of a page's
lifetime - truncation, reclaim, swapout, migration - is impressively
complicated and fragile.
Because anonymous and file pages were always charged before they had their
page->mapping established, uncharges had to happen when the page type
could still be known from the context; as in unmap for anonymous, page
cache removal for file and shmem pages, and swap cache truncation for swap
pages. However, these operations happen well before the page is actually
freed, and so a lot of synchronization is necessary:
- Charging, uncharging, page migration, and charge migration all need
to take a per-page bit spinlock as they could race with uncharging.
- Swap cache truncation happens during both swap-in and swap-out, and
possibly repeatedly before the page is actually freed. This means
that the memcg swapout code is called from many contexts that make
no sense and it has to figure out the direction from page state to
make sure memory and memory+swap are always correctly charged.
- On page migration, the old page might be unmapped but then reused,
so memcg code has to prevent untimely uncharging in that case.
Because this code - which should be a simple charge transfer - is so
special-cased, it is not reusable for replace_page_cache().
But now that charged pages always have a page->mapping, introduce
mem_cgroup_uncharge(), which is called after the final put_page(), when we
know for sure that nobody is looking at the page anymore.
For page migration, introduce mem_cgroup_migrate(), which is called after
the migration is successful and the new page is fully rmapped. Because
the old page is no longer uncharged after migration, prevent double
charges by decoupling the page's memcg association (PCG_USED and
pc->mem_cgroup) from the page holding an actual charge. The new bits
PCG_MEM and PCG_MEMSW represent the respective charges and are transferred
to the new page during migration.
mem_cgroup_migrate() is suitable for replace_page_cache() as well,
which gets rid of mem_cgroup_replace_page_cache(). However, care
needs to be taken because both the source and the target page can
already be charged and on the LRU when fuse is splicing: grab the page
lock on the charge moving side to prevent changing pc->mem_cgroup of a
page under migration. Also, the lruvecs of both pages change as we
uncharge the old and charge the new during migration, and putback may
race with us, so grab the lru lock and isolate the pages iff on LRU to
prevent races and ensure the pages are on the right lruvec afterward.
Swap accounting is massively simplified: because the page is no longer
uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can
transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry
before the final put_page() in page reclaim.
Finally, page_cgroup changes are now protected by whatever protection the
page itself offers: anonymous pages are charged under the page table lock,
whereas page cache insertions, swapin, and migration hold the page lock.
Uncharging happens under full exclusion with no outstanding references.
Charging and uncharging also ensure that the page is off-LRU, which
serializes against charge migration. Remove the very costly page_cgroup
lock and set pc->flags non-atomically.
[mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable]
[vdavydov@parallels.com: fix flags definition]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Tested-by: Jet Chen <jet.chen@intel.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:19:22 +08:00
|
|
|
static inline void mem_cgroup_uncharge(struct page *page)
|
2009-12-16 08:47:03 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2014-08-09 05:19:24 +08:00
|
|
|
static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
|
2008-02-07 16:13:53 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2016-03-16 05:57:19 +08:00
|
|
|
static inline void mem_cgroup_migrate(struct page *old, struct page *new)
|
memcg: remove refcnt from page_cgroup
memcg: performance improvements
Patch Description
1/5 ... remove refcnt fron page_cgroup patch (shmem handling is fixed)
2/5 ... swapcache handling patch
3/5 ... add helper function for shmem's memory reclaim patch
4/5 ... optimize by likely/unlikely ppatch
5/5 ... remove redundunt check patch (shmem handling is fixed.)
Unix bench result.
== 2.6.26-rc2-mm1 + memory resource controller
Execl Throughput 2915.4 lps (29.6 secs, 3 samples)
C Compiler Throughput 1019.3 lpm (60.0 secs, 3 samples)
Shell Scripts (1 concurrent) 5796.0 lpm (60.0 secs, 3 samples)
Shell Scripts (8 concurrent) 1097.7 lpm (60.0 secs, 3 samples)
Shell Scripts (16 concurrent) 565.3 lpm (60.0 secs, 3 samples)
File Read 1024 bufsize 2000 maxblocks 1022128.0 KBps (30.0 secs, 3 samples)
File Write 1024 bufsize 2000 maxblocks 544057.0 KBps (30.0 secs, 3 samples)
File Copy 1024 bufsize 2000 maxblocks 346481.0 KBps (30.0 secs, 3 samples)
File Read 256 bufsize 500 maxblocks 319325.0 KBps (30.0 secs, 3 samples)
File Write 256 bufsize 500 maxblocks 148788.0 KBps (30.0 secs, 3 samples)
File Copy 256 bufsize 500 maxblocks 99051.0 KBps (30.0 secs, 3 samples)
File Read 4096 bufsize 8000 maxblocks 2058917.0 KBps (30.0 secs, 3 samples)
File Write 4096 bufsize 8000 maxblocks 1606109.0 KBps (30.0 secs, 3 samples)
File Copy 4096 bufsize 8000 maxblocks 854789.0 KBps (30.0 secs, 3 samples)
Dc: sqrt(2) to 99 decimal places 126145.2 lpm (30.0 secs, 3 samples)
INDEX VALUES
TEST BASELINE RESULT INDEX
Execl Throughput 43.0 2915.4 678.0
File Copy 1024 bufsize 2000 maxblocks 3960.0 346481.0 875.0
File Copy 256 bufsize 500 maxblocks 1655.0 99051.0 598.5
File Copy 4096 bufsize 8000 maxblocks 5800.0 854789.0 1473.8
Shell Scripts (8 concurrent) 6.0 1097.7 1829.5
=========
FINAL SCORE 991.3
== 2.6.26-rc2-mm1 + this set ==
Execl Throughput 3012.9 lps (29.9 secs, 3 samples)
C Compiler Throughput 981.0 lpm (60.0 secs, 3 samples)
Shell Scripts (1 concurrent) 5872.0 lpm (60.0 secs, 3 samples)
Shell Scripts (8 concurrent) 1120.3 lpm (60.0 secs, 3 samples)
Shell Scripts (16 concurrent) 578.0 lpm (60.0 secs, 3 samples)
File Read 1024 bufsize 2000 maxblocks 1003993.0 KBps (30.0 secs, 3 samples)
File Write 1024 bufsize 2000 maxblocks 550452.0 KBps (30.0 secs, 3 samples)
File Copy 1024 bufsize 2000 maxblocks 347159.0 KBps (30.0 secs, 3 samples)
File Read 256 bufsize 500 maxblocks 314644.0 KBps (30.0 secs, 3 samples)
File Write 256 bufsize 500 maxblocks 151852.0 KBps (30.0 secs, 3 samples)
File Copy 256 bufsize 500 maxblocks 101000.0 KBps (30.0 secs, 3 samples)
File Read 4096 bufsize 8000 maxblocks 2033256.0 KBps (30.0 secs, 3 samples)
File Write 4096 bufsize 8000 maxblocks 1611814.0 KBps (30.0 secs, 3 samples)
File Copy 4096 bufsize 8000 maxblocks 847979.0 KBps (30.0 secs, 3 samples)
Dc: sqrt(2) to 99 decimal places 128148.7 lpm (30.0 secs, 3 samples)
INDEX VALUES
TEST BASELINE RESULT INDEX
Execl Throughput 43.0 3012.9 700.7
File Copy 1024 bufsize 2000 maxblocks 3960.0 347159.0 876.7
File Copy 256 bufsize 500 maxblocks 1655.0 101000.0 610.3
File Copy 4096 bufsize 8000 maxblocks 5800.0 847979.0 1462.0
Shell Scripts (8 concurrent) 6.0 1120.3 1867.2
=========
FINAL SCORE 1004.6
This patch:
Remove refcnt from page_cgroup().
After this,
* A page is charged only when !page_mapped() && no page_cgroup is assigned.
* Anon page is newly mapped.
* File page is added to mapping->tree.
* A page is uncharged only when
* Anon page is fully unmapped.
* File page is removed from LRU.
There is no change in behavior from user's view.
This patch also removes unnecessary calls in rmap.c which was used only for
refcnt mangement.
[akpm@linux-foundation.org: fix warning]
[hugh@veritas.com: fix shmem_unuse_inode charging]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Paul Menage <menage@google.com>
Cc: David Rientjes <rientjes@google.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>
2008-07-25 16:47:14 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2016-07-29 06:46:02 +08:00
|
|
|
static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
|
2016-07-29 06:46:05 +08:00
|
|
|
struct mem_cgroup *memcg)
|
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
|
|
|
{
|
2016-07-29 06:46:02 +08:00
|
|
|
return node_lruvec(pgdat);
|
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
|
|
|
}
|
|
|
|
|
2012-05-30 06:07:09 +08:00
|
|
|
static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
|
2016-07-29 06:45:31 +08:00
|
|
|
struct pglist_data *pgdat)
|
2008-02-07 16:13:56 +08:00
|
|
|
{
|
2016-07-29 06:45:31 +08:00
|
|
|
return &pgdat->lruvec;
|
2008-02-07 16:13:56 +08:00
|
|
|
}
|
|
|
|
|
2012-10-09 07:34:12 +08:00
|
|
|
static inline bool mm_match_cgroup(struct mm_struct *mm,
|
2011-11-03 04:38:15 +08:00
|
|
|
struct mem_cgroup *memcg)
|
2008-02-07 16:14:01 +08:00
|
|
|
{
|
2012-10-09 07:34:12 +08:00
|
|
|
return true;
|
2008-02-07 16:14:01 +08:00
|
|
|
}
|
|
|
|
|
2013-07-04 06:01:23 +08:00
|
|
|
static inline bool task_in_mem_cgroup(struct task_struct *task,
|
|
|
|
const struct mem_cgroup *memcg)
|
2008-02-07 16:14:06 +08:00
|
|
|
{
|
2013-07-04 06:01:23 +08:00
|
|
|
return true;
|
2008-02-07 16:14:06 +08:00
|
|
|
}
|
|
|
|
|
2012-01-13 09:17:59 +08:00
|
|
|
static inline struct mem_cgroup *
|
|
|
|
mem_cgroup_iter(struct mem_cgroup *root,
|
|
|
|
struct mem_cgroup *prev,
|
|
|
|
struct mem_cgroup_reclaim_cookie *reclaim)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void mem_cgroup_iter_break(struct mem_cgroup *root,
|
|
|
|
struct mem_cgroup *prev)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2016-10-08 07:57:23 +08:00
|
|
|
static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
|
|
|
|
int (*fn)(struct task_struct *, void *), void *arg)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2016-03-16 05:57:16 +08:00
|
|
|
static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
|
2009-01-08 10:08:02 +08:00
|
|
|
{
|
2016-03-16 05:57:16 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
|
|
|
|
{
|
|
|
|
WARN_ON_ONCE(id);
|
|
|
|
/* XXX: This should always return root_mem_cgroup */
|
|
|
|
return NULL;
|
2009-01-08 10:08:02 +08:00
|
|
|
}
|
2009-01-08 10:08:08 +08:00
|
|
|
|
2016-01-21 07:03:02 +08:00
|
|
|
static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
|
2009-01-08 10:08:18 +08:00
|
|
|
{
|
2015-11-06 10:47:40 +08:00
|
|
|
return true;
|
2009-01-08 10:08:18 +08:00
|
|
|
}
|
|
|
|
|
2009-01-08 10:08:19 +08:00
|
|
|
static inline unsigned long
|
2012-05-30 06:07:08 +08:00
|
|
|
mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
|
2009-01-08 10:08:19 +08:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2017-01-11 08:58:04 +08:00
|
|
|
static inline
|
|
|
|
unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
|
|
|
|
enum lru_list lru, int zone_idx)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2009-01-08 10:08:19 +08:00
|
|
|
|
2016-03-18 05:18:42 +08:00
|
|
|
static inline unsigned long
|
|
|
|
mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
|
|
|
|
int nid, unsigned int lru_mask)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2016-10-08 07:57:23 +08:00
|
|
|
static inline unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-04-03 07:57:39 +08:00
|
|
|
static inline void
|
|
|
|
mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2016-03-16 05:57:22 +08:00
|
|
|
static inline void lock_page_memcg(struct page *page)
|
memcg: use new logic for page stat accounting
Now, page-stat-per-memcg is recorded into per page_cgroup flag by
duplicating page's status into the flag. The reason is that memcg has a
feature to move a page from a group to another group and we have race
between "move" and "page stat accounting",
Under current logic, assume CPU-A and CPU-B. CPU-A does "move" and CPU-B
does "page stat accounting".
When CPU-A goes 1st,
CPU-A CPU-B
update "struct page" info.
move_lock_mem_cgroup(memcg)
see pc->flags
copy page stat to new group
overwrite pc->mem_cgroup.
move_unlock_mem_cgroup(memcg)
move_lock_mem_cgroup(mem)
set pc->flags
update page stat accounting
move_unlock_mem_cgroup(mem)
stat accounting is guarded by move_lock_mem_cgroup() and "move" logic
(CPU-A) doesn't see changes in "struct page" information.
But it's costly to have the same information both in 'struct page' and
'struct page_cgroup'. And, there is a potential problem.
For example, assume we have PG_dirty accounting in memcg.
PG_..is a flag for struct page.
PCG_ is a flag for struct page_cgroup.
(This is just an example. The same problem can be found in any
kind of page stat accounting.)
CPU-A CPU-B
TestSet PG_dirty
(delay) TestClear PG_dirty
if (TestClear(PCG_dirty))
memcg->nr_dirty--
if (TestSet(PCG_dirty))
memcg->nr_dirty++
Here, memcg->nr_dirty = +1, this is wrong. This race was reported by Greg
Thelen <gthelen@google.com>. Now, only FILE_MAPPED is supported but
fortunately, it's serialized by page table lock and this is not real bug,
_now_,
If this potential problem is caused by having duplicated information in
struct page and struct page_cgroup, we may be able to fix this by using
original 'struct page' information. But we'll have a problem in "move
account"
Assume we use only PG_dirty.
CPU-A CPU-B
TestSet PG_dirty
(delay) move_lock_mem_cgroup()
if (PageDirty(page))
new_memcg->nr_dirty++
pc->mem_cgroup = new_memcg;
move_unlock_mem_cgroup()
move_lock_mem_cgroup()
memcg = pc->mem_cgroup
new_memcg->nr_dirty++
accounting information may be double-counted. This was original reason to
have PCG_xxx flags but it seems PCG_xxx has another problem.
I think we need a bigger lock as
move_lock_mem_cgroup(page)
TestSetPageDirty(page)
update page stats (without any checks)
move_unlock_mem_cgroup(page)
This fixes both of problems and we don't have to duplicate page flag into
page_cgroup. Please note: move_lock_mem_cgroup() is held only when there
are possibility of "account move" under the system. So, in most path,
status update will go without atomic locks.
This patch introduces mem_cgroup_begin_update_page_stat() and
mem_cgroup_end_update_page_stat() both should be called at modifying
'struct page' information if memcg takes care of it. as
mem_cgroup_begin_update_page_stat()
modify page information
mem_cgroup_update_page_stat()
=> never check any 'struct page' info, just update counters.
mem_cgroup_end_update_page_stat().
This patch is slow because we need to call begin_update_page_stat()/
end_update_page_stat() regardless of accounted will be changed or not. A
following patch adds an easy optimization and reduces the cost.
[akpm@linux-foundation.org: s/lock/locked/]
[hughd@google.com: fix deadlock by avoiding stat lock when anon]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Greg Thelen <gthelen@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 07:34:25 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2016-03-16 05:57:22 +08:00
|
|
|
static inline void unlock_page_memcg(struct page *page)
|
memcg: use new logic for page stat accounting
Now, page-stat-per-memcg is recorded into per page_cgroup flag by
duplicating page's status into the flag. The reason is that memcg has a
feature to move a page from a group to another group and we have race
between "move" and "page stat accounting",
Under current logic, assume CPU-A and CPU-B. CPU-A does "move" and CPU-B
does "page stat accounting".
When CPU-A goes 1st,
CPU-A CPU-B
update "struct page" info.
move_lock_mem_cgroup(memcg)
see pc->flags
copy page stat to new group
overwrite pc->mem_cgroup.
move_unlock_mem_cgroup(memcg)
move_lock_mem_cgroup(mem)
set pc->flags
update page stat accounting
move_unlock_mem_cgroup(mem)
stat accounting is guarded by move_lock_mem_cgroup() and "move" logic
(CPU-A) doesn't see changes in "struct page" information.
But it's costly to have the same information both in 'struct page' and
'struct page_cgroup'. And, there is a potential problem.
For example, assume we have PG_dirty accounting in memcg.
PG_..is a flag for struct page.
PCG_ is a flag for struct page_cgroup.
(This is just an example. The same problem can be found in any
kind of page stat accounting.)
CPU-A CPU-B
TestSet PG_dirty
(delay) TestClear PG_dirty
if (TestClear(PCG_dirty))
memcg->nr_dirty--
if (TestSet(PCG_dirty))
memcg->nr_dirty++
Here, memcg->nr_dirty = +1, this is wrong. This race was reported by Greg
Thelen <gthelen@google.com>. Now, only FILE_MAPPED is supported but
fortunately, it's serialized by page table lock and this is not real bug,
_now_,
If this potential problem is caused by having duplicated information in
struct page and struct page_cgroup, we may be able to fix this by using
original 'struct page' information. But we'll have a problem in "move
account"
Assume we use only PG_dirty.
CPU-A CPU-B
TestSet PG_dirty
(delay) move_lock_mem_cgroup()
if (PageDirty(page))
new_memcg->nr_dirty++
pc->mem_cgroup = new_memcg;
move_unlock_mem_cgroup()
move_lock_mem_cgroup()
memcg = pc->mem_cgroup
new_memcg->nr_dirty++
accounting information may be double-counted. This was original reason to
have PCG_xxx flags but it seems PCG_xxx has another problem.
I think we need a bigger lock as
move_lock_mem_cgroup(page)
TestSetPageDirty(page)
update page stats (without any checks)
move_unlock_mem_cgroup(page)
This fixes both of problems and we don't have to duplicate page flag into
page_cgroup. Please note: move_lock_mem_cgroup() is held only when there
are possibility of "account move" under the system. So, in most path,
status update will go without atomic locks.
This patch introduces mem_cgroup_begin_update_page_stat() and
mem_cgroup_end_update_page_stat() both should be called at modifying
'struct page' information if memcg takes care of it. as
mem_cgroup_begin_update_page_stat()
modify page information
mem_cgroup_update_page_stat()
=> never check any 'struct page' info, just update counters.
mem_cgroup_end_update_page_stat().
This patch is slow because we need to call begin_update_page_stat()/
end_update_page_stat() regardless of accounted will be changed or not. A
following patch adds an easy optimization and reduces the cost.
[akpm@linux-foundation.org: s/lock/locked/]
[hughd@google.com: fix deadlock by avoiding stat lock when anon]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Greg Thelen <gthelen@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22 07:34:25 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
memcg: punt high overage reclaim to return-to-userland path
Currently, try_charge() tries to reclaim memory synchronously when the
high limit is breached; however, if the allocation doesn't have
__GFP_WAIT, synchronous reclaim is skipped. If a process performs only
speculative allocations, it can blow way past the high limit. This is
actually easily reproducible by simply doing "find /". slab/slub
allocator tries speculative allocations first, so as long as there's
memory which can be consumed without blocking, it can keep allocating
memory regardless of the high limit.
This patch makes try_charge() always punt the over-high reclaim to the
return-to-userland path. If try_charge() detects that high limit is
breached, it adds the overage to current->memcg_nr_pages_over_high and
schedules execution of mem_cgroup_handle_over_high() which performs
synchronous reclaim from the return-to-userland path.
As long as kernel doesn't have a run-away allocation spree, this should
provide enough protection while making kmemcg behave more consistently.
It also has the following benefits.
- All over-high reclaims can use GFP_KERNEL regardless of the specific
gfp mask in use, e.g. GFP_NOFS, when the limit was breached.
- It copes with prio inversion. Previously, a low-prio task with
small memory.high might perform over-high reclaim with a bunch of
locks held. If a higher prio task needed any of these locks, it
would have to wait until the low prio task finished reclaim and
released the locks. By handing over-high reclaim to the task exit
path this issue can be avoided.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-06 10:46:11 +08:00
|
|
|
static inline void mem_cgroup_handle_over_high(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2013-10-17 04:46:59 +08:00
|
|
|
static inline void mem_cgroup_oom_enable(void)
|
2013-09-13 06:13:42 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2013-10-17 04:46:59 +08:00
|
|
|
static inline void mem_cgroup_oom_disable(void)
|
2013-09-13 06:13:42 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
mm: memcg: do not trap chargers with full callstack on OOM
The memcg OOM handling is incredibly fragile and can deadlock. When a
task fails to charge memory, it invokes the OOM killer and loops right
there in the charge code until it succeeds. Comparably, any other task
that enters the charge path at this point will go to a waitqueue right
then and there and sleep until the OOM situation is resolved. The problem
is that these tasks may hold filesystem locks and the mmap_sem; locks that
the selected OOM victim may need to exit.
For example, in one reported case, the task invoking the OOM killer was
about to charge a page cache page during a write(), which holds the
i_mutex. The OOM killer selected a task that was just entering truncate()
and trying to acquire the i_mutex:
OOM invoking task:
mem_cgroup_handle_oom+0x241/0x3b0
mem_cgroup_cache_charge+0xbe/0xe0
add_to_page_cache_locked+0x4c/0x140
add_to_page_cache_lru+0x22/0x50
grab_cache_page_write_begin+0x8b/0xe0
ext3_write_begin+0x88/0x270
generic_file_buffered_write+0x116/0x290
__generic_file_aio_write+0x27c/0x480
generic_file_aio_write+0x76/0xf0 # takes ->i_mutex
do_sync_write+0xea/0x130
vfs_write+0xf3/0x1f0
sys_write+0x51/0x90
system_call_fastpath+0x18/0x1d
OOM kill victim:
do_truncate+0x58/0xa0 # takes i_mutex
do_last+0x250/0xa30
path_openat+0xd7/0x440
do_filp_open+0x49/0xa0
do_sys_open+0x106/0x240
sys_open+0x20/0x30
system_call_fastpath+0x18/0x1d
The OOM handling task will retry the charge indefinitely while the OOM
killed task is not releasing any resources.
A similar scenario can happen when the kernel OOM killer for a memcg is
disabled and a userspace task is in charge of resolving OOM situations.
In this case, ALL tasks that enter the OOM path will be made to sleep on
the OOM waitqueue and wait for userspace to free resources or increase
the group's limit. But a userspace OOM handler is prone to deadlock
itself on the locks held by the waiting tasks. For example one of the
sleeping tasks may be stuck in a brk() call with the mmap_sem held for
writing but the userspace handler, in order to pick an optimal victim,
may need to read files from /proc/<pid>, which tries to acquire the same
mmap_sem for reading and deadlocks.
This patch changes the way tasks behave after detecting a memcg OOM and
makes sure nobody loops or sleeps with locks held:
1. When OOMing in a user fault, invoke the OOM killer and restart the
fault instead of looping on the charge attempt. This way, the OOM
victim can not get stuck on locks the looping task may hold.
2. When OOMing in a user fault but somebody else is handling it
(either the kernel OOM killer or a userspace handler), don't go to
sleep in the charge context. Instead, remember the OOMing memcg in
the task struct and then fully unwind the page fault stack with
-ENOMEM. pagefault_out_of_memory() will then call back into the
memcg code to check if the -ENOMEM came from the memcg, and then
either put the task to sleep on the memcg's OOM waitqueue or just
restart the fault. The OOM victim can no longer get stuck on any
lock a sleeping task may hold.
Debugged by Michal Hocko.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: azurIt <azurit@pobox.sk>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.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>
2013-09-13 06:13:44 +08:00
|
|
|
static inline bool task_in_memcg_oom(struct task_struct *p)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2013-10-17 04:46:59 +08:00
|
|
|
static inline bool mem_cgroup_oom_synchronize(bool wait)
|
mm: memcg: do not trap chargers with full callstack on OOM
The memcg OOM handling is incredibly fragile and can deadlock. When a
task fails to charge memory, it invokes the OOM killer and loops right
there in the charge code until it succeeds. Comparably, any other task
that enters the charge path at this point will go to a waitqueue right
then and there and sleep until the OOM situation is resolved. The problem
is that these tasks may hold filesystem locks and the mmap_sem; locks that
the selected OOM victim may need to exit.
For example, in one reported case, the task invoking the OOM killer was
about to charge a page cache page during a write(), which holds the
i_mutex. The OOM killer selected a task that was just entering truncate()
and trying to acquire the i_mutex:
OOM invoking task:
mem_cgroup_handle_oom+0x241/0x3b0
mem_cgroup_cache_charge+0xbe/0xe0
add_to_page_cache_locked+0x4c/0x140
add_to_page_cache_lru+0x22/0x50
grab_cache_page_write_begin+0x8b/0xe0
ext3_write_begin+0x88/0x270
generic_file_buffered_write+0x116/0x290
__generic_file_aio_write+0x27c/0x480
generic_file_aio_write+0x76/0xf0 # takes ->i_mutex
do_sync_write+0xea/0x130
vfs_write+0xf3/0x1f0
sys_write+0x51/0x90
system_call_fastpath+0x18/0x1d
OOM kill victim:
do_truncate+0x58/0xa0 # takes i_mutex
do_last+0x250/0xa30
path_openat+0xd7/0x440
do_filp_open+0x49/0xa0
do_sys_open+0x106/0x240
sys_open+0x20/0x30
system_call_fastpath+0x18/0x1d
The OOM handling task will retry the charge indefinitely while the OOM
killed task is not releasing any resources.
A similar scenario can happen when the kernel OOM killer for a memcg is
disabled and a userspace task is in charge of resolving OOM situations.
In this case, ALL tasks that enter the OOM path will be made to sleep on
the OOM waitqueue and wait for userspace to free resources or increase
the group's limit. But a userspace OOM handler is prone to deadlock
itself on the locks held by the waiting tasks. For example one of the
sleeping tasks may be stuck in a brk() call with the mmap_sem held for
writing but the userspace handler, in order to pick an optimal victim,
may need to read files from /proc/<pid>, which tries to acquire the same
mmap_sem for reading and deadlocks.
This patch changes the way tasks behave after detecting a memcg OOM and
makes sure nobody loops or sleeps with locks held:
1. When OOMing in a user fault, invoke the OOM killer and restart the
fault instead of looping on the charge attempt. This way, the OOM
victim can not get stuck on locks the looping task may hold.
2. When OOMing in a user fault but somebody else is handling it
(either the kernel OOM killer or a userspace handler), don't go to
sleep in the charge context. Instead, remember the OOMing memcg in
the task struct and then fully unwind the page fault stack with
-ENOMEM. pagefault_out_of_memory() will then call back into the
memcg code to check if the -ENOMEM came from the memcg, and then
either put the task to sleep on the memcg's OOM waitqueue or just
restart the fault. The OOM victim can no longer get stuck on any
lock a sleeping task may hold.
Debugged by Michal Hocko.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: azurIt <azurit@pobox.sk>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.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>
2013-09-13 06:13:44 +08:00
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2016-03-16 05:57:22 +08:00
|
|
|
static inline void mem_cgroup_inc_page_stat(struct page *page,
|
2013-09-13 06:13:50 +08:00
|
|
|
enum mem_cgroup_stat_index idx)
|
2011-01-14 07:47:37 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2016-03-16 05:57:22 +08:00
|
|
|
static inline void mem_cgroup_dec_page_stat(struct page *page,
|
2013-09-13 06:13:50 +08:00
|
|
|
enum mem_cgroup_stat_index idx)
|
2009-06-18 07:26:34 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2009-09-24 06:56:39 +08:00
|
|
|
static inline
|
2016-07-29 06:46:05 +08:00
|
|
|
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
|
2013-09-25 06:27:41 +08:00
|
|
|
gfp_t gfp_mask,
|
|
|
|
unsigned long *total_scanned)
|
2009-09-24 06:56:39 +08:00
|
|
|
{
|
2013-09-25 06:27:41 +08:00
|
|
|
return 0;
|
2009-09-24 06:56:39 +08:00
|
|
|
}
|
|
|
|
|
2012-01-13 09:18:20 +08:00
|
|
|
static inline void mem_cgroup_split_huge_fixup(struct page *head)
|
2011-01-21 06:44:24 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2011-05-27 07:25:38 +08:00
|
|
|
static inline
|
|
|
|
void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
|
|
|
|
{
|
|
|
|
}
|
2012-08-01 07:43:02 +08:00
|
|
|
#endif /* CONFIG_MEMCG */
|
2008-02-07 16:13:51 +08:00
|
|
|
|
2015-05-23 05:13:37 +08:00
|
|
|
#ifdef CONFIG_CGROUP_WRITEBACK
|
2015-05-23 06:23:33 +08:00
|
|
|
|
2015-05-23 05:13:37 +08:00
|
|
|
struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg);
|
2015-05-23 06:23:33 +08:00
|
|
|
struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
|
writeback: fix incorrect calculation of available memory for memcg domains
For memcg domains, the amount of available memory was calculated as
min(the amount currently in use + headroom according to memcg,
total clean memory)
This isn't quite correct as what should be capped by the amount of
clean memory is the headroom, not the sum of memory in use and
headroom. For example, if a memcg domain has a significant amount of
dirty memory, the above can lead to a value which is lower than the
current amount in use which doesn't make much sense. In most
circumstances, the above leads to a number which is somewhat but not
drastically lower.
As the amount of memory which can be readily allocated to the memcg
domain is capped by the amount of system-wide clean memory which is
not already assigned to the memcg itself, the number we want is
the amount currently in use +
min(headroom according to memcg, clean memory elsewhere in the system)
This patch updates mem_cgroup_wb_stats() to return the number of
filepages and headroom instead of the calculated available pages.
mdtc_cap_avail() is renamed to mdtc_calc_avail() and performs the
above calculation from file, headroom, dirty and globally clean pages.
v2: Dummy mem_cgroup_wb_stats() implementation wasn't updated leading
to build failure when !CGROUP_WRITEBACK. Fixed.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: c2aa723a6093 ("writeback: implement memcg writeback domain based throttling")
Signed-off-by: Jens Axboe <axboe@fb.com>
2015-09-30 01:04:26 +08:00
|
|
|
void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
|
|
|
|
unsigned long *pheadroom, unsigned long *pdirty,
|
|
|
|
unsigned long *pwriteback);
|
2015-05-23 06:23:33 +08:00
|
|
|
|
|
|
|
#else /* CONFIG_CGROUP_WRITEBACK */
|
|
|
|
|
|
|
|
static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2015-05-23 06:23:35 +08:00
|
|
|
static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
|
writeback: fix incorrect calculation of available memory for memcg domains
For memcg domains, the amount of available memory was calculated as
min(the amount currently in use + headroom according to memcg,
total clean memory)
This isn't quite correct as what should be capped by the amount of
clean memory is the headroom, not the sum of memory in use and
headroom. For example, if a memcg domain has a significant amount of
dirty memory, the above can lead to a value which is lower than the
current amount in use which doesn't make much sense. In most
circumstances, the above leads to a number which is somewhat but not
drastically lower.
As the amount of memory which can be readily allocated to the memcg
domain is capped by the amount of system-wide clean memory which is
not already assigned to the memcg itself, the number we want is
the amount currently in use +
min(headroom according to memcg, clean memory elsewhere in the system)
This patch updates mem_cgroup_wb_stats() to return the number of
filepages and headroom instead of the calculated available pages.
mdtc_cap_avail() is renamed to mdtc_calc_avail() and performs the
above calculation from file, headroom, dirty and globally clean pages.
v2: Dummy mem_cgroup_wb_stats() implementation wasn't updated leading
to build failure when !CGROUP_WRITEBACK. Fixed.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: c2aa723a6093 ("writeback: implement memcg writeback domain based throttling")
Signed-off-by: Jens Axboe <axboe@fb.com>
2015-09-30 01:04:26 +08:00
|
|
|
unsigned long *pfilepages,
|
|
|
|
unsigned long *pheadroom,
|
2015-05-23 06:23:35 +08:00
|
|
|
unsigned long *pdirty,
|
|
|
|
unsigned long *pwriteback)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2015-05-23 06:23:33 +08:00
|
|
|
#endif /* CONFIG_CGROUP_WRITEBACK */
|
2015-05-23 05:13:37 +08:00
|
|
|
|
2011-12-12 05:47:03 +08:00
|
|
|
struct sock;
|
2016-01-15 07:21:17 +08:00
|
|
|
bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
|
|
|
|
void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
|
2016-01-21 07:02:47 +08:00
|
|
|
#ifdef CONFIG_MEMCG
|
2016-01-15 07:21:34 +08:00
|
|
|
extern struct static_key_false memcg_sockets_enabled_key;
|
|
|
|
#define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
|
2016-10-08 08:00:58 +08:00
|
|
|
void mem_cgroup_sk_alloc(struct sock *sk);
|
|
|
|
void mem_cgroup_sk_free(struct sock *sk);
|
2016-01-15 07:21:17 +08:00
|
|
|
static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-15 07:21:14 +08:00
|
|
|
{
|
2016-01-21 07:02:50 +08:00
|
|
|
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure)
|
2016-01-15 07:21:32 +08:00
|
|
|
return true;
|
|
|
|
do {
|
|
|
|
if (time_before(jiffies, memcg->socket_pressure))
|
|
|
|
return true;
|
|
|
|
} while ((memcg = parent_mem_cgroup(memcg)));
|
|
|
|
return false;
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-15 07:21:14 +08:00
|
|
|
}
|
|
|
|
#else
|
2016-01-15 07:21:20 +08:00
|
|
|
#define mem_cgroup_sockets_enabled 0
|
2016-10-08 08:00:58 +08:00
|
|
|
static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
|
|
|
|
static inline void mem_cgroup_sk_free(struct sock *sk) { };
|
2016-01-15 07:21:17 +08:00
|
|
|
static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
|
net: tcp_memcontrol: sanitize tcp memory accounting callbacks
There won't be a tcp control soft limit, so integrating the memcg code
into the global skmem limiting scheme complicates things unnecessarily.
Replace this with simple and clear charge and uncharge calls--hidden
behind a jump label--to account skb memory.
Note that this is not purely aesthetic: as a result of shoehorning the
per-memcg code into the same memory accounting functions that handle the
global level, the old code would compare the per-memcg consumption
against the smaller of the per-memcg limit and the global limit. This
allowed the total consumption of multiple sockets to exceed the global
limit, as long as the individual sockets stayed within bounds. After
this change, the code will always compare the per-memcg consumption to
the per-memcg limit, and the global consumption to the global limit, and
thus close this loophole.
Without a soft limit, the per-memcg memory pressure state in sockets is
generally questionable. However, we did it until now, so we continue to
enter it when the hard limit is hit, and packets are dropped, to let
other sockets in the cgroup know that they shouldn't grow their transmit
windows, either. However, keep it simple in the new callback model and
leave memory pressure lazily when the next packet is accepted (as
opposed to doing it synchroneously when packets are processed). When
packets are dropped, network performance will already be in the toilet,
so that should be a reasonable trade-off.
As described above, consumption is now checked on the per-memcg level
and the global level separately. Likewise, memory pressure states are
maintained on both the per-memcg level and the global level, and a
socket is considered under pressure when either level asserts as much.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-15 07:21:14 +08:00
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
#endif
|
2012-12-19 06:21:56 +08:00
|
|
|
|
2016-07-27 06:24:21 +08:00
|
|
|
struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
|
|
|
|
void memcg_kmem_put_cache(struct kmem_cache *cachep);
|
|
|
|
int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
|
|
|
|
struct mem_cgroup *memcg);
|
|
|
|
int memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
|
|
|
|
void memcg_kmem_uncharge(struct page *page, int order);
|
|
|
|
|
2016-01-21 07:02:32 +08:00
|
|
|
#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
|
2016-01-15 07:21:34 +08:00
|
|
|
extern struct static_key_false memcg_kmem_enabled_key;
|
2017-02-23 07:41:36 +08:00
|
|
|
extern struct workqueue_struct *memcg_kmem_cache_wq;
|
2012-12-19 06:23:01 +08:00
|
|
|
|
2015-02-13 06:58:57 +08:00
|
|
|
extern int memcg_nr_cache_ids;
|
2015-09-09 06:01:07 +08:00
|
|
|
void memcg_get_cache_ids(void);
|
|
|
|
void memcg_put_cache_ids(void);
|
2012-12-19 06:23:10 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Helper macro to loop through all memcg-specific caches. Callers must still
|
|
|
|
* check if the cache is valid (it is either valid or NULL).
|
|
|
|
* the slab_mutex must be held when looping through those caches
|
|
|
|
*/
|
2012-12-19 06:23:01 +08:00
|
|
|
#define for_each_memcg_cache_index(_idx) \
|
2015-02-13 06:58:57 +08:00
|
|
|
for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++)
|
2012-12-19 06:23:01 +08:00
|
|
|
|
2012-12-19 06:21:56 +08:00
|
|
|
static inline bool memcg_kmem_enabled(void)
|
|
|
|
{
|
2016-01-15 07:21:34 +08:00
|
|
|
return static_branch_unlikely(&memcg_kmem_enabled_key);
|
2012-12-19 06:21:56 +08:00
|
|
|
}
|
|
|
|
|
2015-09-09 06:01:02 +08:00
|
|
|
/*
|
2016-03-16 05:54:03 +08:00
|
|
|
* helper for accessing a memcg's index. It will be used as an index in the
|
2015-09-09 06:01:02 +08:00
|
|
|
* child cache array in kmem_cache, and also to derive its name. This function
|
|
|
|
* will return -1 when this is not a kmem-limited memcg.
|
|
|
|
*/
|
|
|
|
static inline int memcg_cache_id(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return memcg ? memcg->kmemcg_id : -1;
|
|
|
|
}
|
2014-04-08 06:39:24 +08:00
|
|
|
|
2016-03-18 05:17:35 +08:00
|
|
|
/**
|
|
|
|
* memcg_kmem_update_page_stat - update kmem page state statistics
|
|
|
|
* @page: the page
|
|
|
|
* @idx: page state item to account
|
|
|
|
* @val: number of pages (positive or negative)
|
|
|
|
*/
|
|
|
|
static inline void memcg_kmem_update_page_stat(struct page *page,
|
|
|
|
enum mem_cgroup_stat_index idx, int val)
|
|
|
|
{
|
|
|
|
if (memcg_kmem_enabled() && page->mem_cgroup)
|
|
|
|
this_cpu_add(page->mem_cgroup->stat->count[idx], val);
|
|
|
|
}
|
|
|
|
|
2012-12-19 06:21:56 +08:00
|
|
|
#else
|
2012-12-19 06:23:01 +08:00
|
|
|
#define for_each_memcg_cache_index(_idx) \
|
|
|
|
for (; NULL; )
|
|
|
|
|
2012-12-19 06:22:46 +08:00
|
|
|
static inline bool memcg_kmem_enabled(void)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2012-12-19 06:22:34 +08:00
|
|
|
static inline int memcg_cache_id(struct mem_cgroup *memcg)
|
|
|
|
{
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2015-02-13 06:59:01 +08:00
|
|
|
static inline void memcg_get_cache_ids(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void memcg_put_cache_ids(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2016-03-18 05:17:35 +08:00
|
|
|
static inline void memcg_kmem_update_page_stat(struct page *page,
|
|
|
|
enum mem_cgroup_stat_index idx, int val)
|
|
|
|
{
|
|
|
|
}
|
2016-01-21 07:02:32 +08:00
|
|
|
#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
|
|
|
|
|
2008-02-07 16:13:50 +08:00
|
|
|
#endif /* _LINUX_MEMCONTROL_H */
|