linux-sg2042/block/blk-cgroup.c

1696 lines
43 KiB
C
Raw Normal View History

/*
* Common Block IO controller cgroup interface
*
* Based on ideas and code from CFQ, CFS and BFQ:
* Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
*
* Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
* Paolo Valente <paolo.valente@unimore.it>
*
* Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
* Nauman Rafique <nauman@google.com>
*/
#include <linux/ioprio.h>
#include <linux/seq_file.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
#include <linux/err.h>
#include <linux/blkdev.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include "blk-cgroup.h"
#include <linux/genhd.h>
2010-04-09 14:31:19 +08:00
#define MAX_KEY_LEN 100
static DEFINE_SPINLOCK(blkio_list_lock);
static LIST_HEAD(blkio_list);
struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
EXPORT_SYMBOL_GPL(blkio_root_cgroup);
static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,
struct cgroup *);
static int blkiocg_can_attach(struct cgroup_subsys *, struct cgroup *,
struct cgroup_taskset *);
static void blkiocg_attach(struct cgroup_subsys *, struct cgroup *,
struct cgroup_taskset *);
static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *);
static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
/* for encoding cft->private value on file */
#define BLKIOFILE_PRIVATE(x, val) (((x) << 16) | (val))
/* What policy owns the file, proportional or throttle */
#define BLKIOFILE_POLICY(val) (((val) >> 16) & 0xffff)
#define BLKIOFILE_ATTR(val) ((val) & 0xffff)
struct cgroup_subsys blkio_subsys = {
.name = "blkio",
.create = blkiocg_create,
.can_attach = blkiocg_can_attach,
.attach = blkiocg_attach,
.destroy = blkiocg_destroy,
.populate = blkiocg_populate,
#ifdef CONFIG_BLK_CGROUP
/* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */
.subsys_id = blkio_subsys_id,
#endif
.use_id = 1,
.module = THIS_MODULE,
};
EXPORT_SYMBOL_GPL(blkio_subsys);
static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg,
struct blkio_policy_node *pn)
{
list_add(&pn->node, &blkcg->policy_list);
}
static inline bool cftype_blkg_same_policy(struct cftype *cft,
struct blkio_group *blkg)
{
enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
if (blkg->plid == plid)
return 1;
return 0;
}
/* Determines if policy node matches cgroup file being accessed */
static inline bool pn_matches_cftype(struct cftype *cft,
struct blkio_policy_node *pn)
{
enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
int fileid = BLKIOFILE_ATTR(cft->private);
return (plid == pn->plid && fileid == pn->fileid);
}
/* Must be called with blkcg->lock held */
static inline void blkio_policy_delete_node(struct blkio_policy_node *pn)
{
list_del(&pn->node);
}
/* Must be called with blkcg->lock held */
static struct blkio_policy_node *
blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev,
enum blkio_policy_id plid, int fileid)
{
struct blkio_policy_node *pn;
list_for_each_entry(pn, &blkcg->policy_list, node) {
if (pn->dev == dev && pn->plid == plid && pn->fileid == fileid)
return pn;
}
return NULL;
}
struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
{
return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
struct blkio_cgroup, css);
}
EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
struct blkio_cgroup *task_blkio_cgroup(struct task_struct *tsk)
{
return container_of(task_subsys_state(tsk, blkio_subsys_id),
struct blkio_cgroup, css);
}
EXPORT_SYMBOL_GPL(task_blkio_cgroup);
static inline void
blkio_update_group_weight(struct blkio_group *blkg, unsigned int weight)
{
struct blkio_policy_type *blkiop;
list_for_each_entry(blkiop, &blkio_list, list) {
/* If this policy does not own the blkg, do not send updates */
if (blkiop->plid != blkg->plid)
continue;
if (blkiop->ops.blkio_update_group_weight_fn)
blkiop->ops.blkio_update_group_weight_fn(blkg->key,
blkg, weight);
}
}
static inline void blkio_update_group_bps(struct blkio_group *blkg, u64 bps,
int fileid)
{
struct blkio_policy_type *blkiop;
list_for_each_entry(blkiop, &blkio_list, list) {
/* If this policy does not own the blkg, do not send updates */
if (blkiop->plid != blkg->plid)
continue;
if (fileid == BLKIO_THROTL_read_bps_device
&& blkiop->ops.blkio_update_group_read_bps_fn)
blkiop->ops.blkio_update_group_read_bps_fn(blkg->key,
blkg, bps);
if (fileid == BLKIO_THROTL_write_bps_device
&& blkiop->ops.blkio_update_group_write_bps_fn)
blkiop->ops.blkio_update_group_write_bps_fn(blkg->key,
blkg, bps);
}
}
static inline void blkio_update_group_iops(struct blkio_group *blkg,
unsigned int iops, int fileid)
{
struct blkio_policy_type *blkiop;
list_for_each_entry(blkiop, &blkio_list, list) {
/* If this policy does not own the blkg, do not send updates */
if (blkiop->plid != blkg->plid)
continue;
if (fileid == BLKIO_THROTL_read_iops_device
&& blkiop->ops.blkio_update_group_read_iops_fn)
blkiop->ops.blkio_update_group_read_iops_fn(blkg->key,
blkg, iops);
if (fileid == BLKIO_THROTL_write_iops_device
&& blkiop->ops.blkio_update_group_write_iops_fn)
blkiop->ops.blkio_update_group_write_iops_fn(blkg->key,
blkg,iops);
}
}
/*
* Add to the appropriate stat variable depending on the request type.
* This should be called with the blkg->stats_lock held.
*/
2010-04-09 14:31:19 +08:00
static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction,
bool sync)
{
2010-04-09 14:31:19 +08:00
if (direction)
stat[BLKIO_STAT_WRITE] += add;
else
2010-04-09 14:31:19 +08:00
stat[BLKIO_STAT_READ] += add;
if (sync)
stat[BLKIO_STAT_SYNC] += add;
else
2010-04-09 14:31:19 +08:00
stat[BLKIO_STAT_ASYNC] += add;
}
/*
* Decrements the appropriate stat variable if non-zero depending on the
* request type. Panics on value being zero.
* This should be called with the blkg->stats_lock held.
*/
static void blkio_check_and_dec_stat(uint64_t *stat, bool direction, bool sync)
{
if (direction) {
BUG_ON(stat[BLKIO_STAT_WRITE] == 0);
stat[BLKIO_STAT_WRITE]--;
} else {
BUG_ON(stat[BLKIO_STAT_READ] == 0);
stat[BLKIO_STAT_READ]--;
}
if (sync) {
BUG_ON(stat[BLKIO_STAT_SYNC] == 0);
stat[BLKIO_STAT_SYNC]--;
} else {
BUG_ON(stat[BLKIO_STAT_ASYNC] == 0);
stat[BLKIO_STAT_ASYNC]--;
}
}
#ifdef CONFIG_DEBUG_BLK_CGROUP
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
/* This should be called with the blkg->stats_lock held. */
static void blkio_set_start_group_wait_time(struct blkio_group *blkg,
struct blkio_group *curr_blkg)
{
if (blkio_blkg_waiting(&blkg->stats))
return;
if (blkg == curr_blkg)
return;
blkg->stats.start_group_wait_time = sched_clock();
blkio_mark_blkg_waiting(&blkg->stats);
}
/* This should be called with the blkg->stats_lock held. */
static void blkio_update_group_wait_time(struct blkio_group_stats *stats)
{
unsigned long long now;
if (!blkio_blkg_waiting(stats))
return;
now = sched_clock();
if (time_after64(now, stats->start_group_wait_time))
stats->group_wait_time += now - stats->start_group_wait_time;
blkio_clear_blkg_waiting(stats);
}
/* This should be called with the blkg->stats_lock held. */
static void blkio_end_empty_time(struct blkio_group_stats *stats)
{
unsigned long long now;
if (!blkio_blkg_empty(stats))
return;
now = sched_clock();
if (time_after64(now, stats->start_empty_time))
stats->empty_time += now - stats->start_empty_time;
blkio_clear_blkg_empty(stats);
}
void blkiocg_update_set_idle_time_stats(struct blkio_group *blkg)
{
unsigned long flags;
spin_lock_irqsave(&blkg->stats_lock, flags);
BUG_ON(blkio_blkg_idling(&blkg->stats));
blkg->stats.start_idle_time = sched_clock();
blkio_mark_blkg_idling(&blkg->stats);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_set_idle_time_stats);
void blkiocg_update_idle_time_stats(struct blkio_group *blkg)
{
unsigned long flags;
unsigned long long now;
struct blkio_group_stats *stats;
spin_lock_irqsave(&blkg->stats_lock, flags);
stats = &blkg->stats;
if (blkio_blkg_idling(stats)) {
now = sched_clock();
if (time_after64(now, stats->start_idle_time))
stats->idle_time += now - stats->start_idle_time;
blkio_clear_blkg_idling(stats);
}
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_idle_time_stats);
void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg)
{
unsigned long flags;
struct blkio_group_stats *stats;
spin_lock_irqsave(&blkg->stats_lock, flags);
stats = &blkg->stats;
stats->avg_queue_size_sum +=
stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] +
stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE];
stats->avg_queue_size_samples++;
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
blkio_update_group_wait_time(stats);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_avg_queue_size_stats);
blkio: Fix another BUG_ON() crash due to cfqq movement across groups o Once in a while, I was hitting a BUG_ON() in blkio code. empty_time was assuming that upon slice expiry, group can't be marked empty already (except forced dispatch). But this assumption is broken if cfqq can move (group_isolation=0) across groups after receiving a request. I think most likely in this case we got a request in a cfqq and accounted the rq in one group, later while adding the cfqq to tree, we moved the queue to a different group which was already marked empty and after dispatch from slice we found group already marked empty and raised alarm. This patch does not error out if group is already marked empty. This can introduce some empty_time stat error only in case of group_isolation=0. This is better than crashing. In case of group_isolation=1 we should still get same stats as before this patch. [ 222.308546] ------------[ cut here ]------------ [ 222.309311] kernel BUG at block/blk-cgroup.c:236! [ 222.309311] invalid opcode: 0000 [#1] SMP [ 222.309311] last sysfs file: /sys/devices/virtual/block/dm-3/queue/scheduler [ 222.309311] CPU 1 [ 222.309311] Modules linked in: dm_round_robin dm_multipath qla2xxx scsi_transport_fc dm_zero dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] [ 222.309311] [ 222.309311] Pid: 4780, comm: fio Not tainted 2.6.34-rc4-blkio-config #68 0A98h/HP xw8600 Workstation [ 222.309311] RIP: 0010:[<ffffffff8121ad88>] [<ffffffff8121ad88>] blkiocg_set_start_empty_time+0x50/0x83 [ 222.309311] RSP: 0018:ffff8800ba6e79f8 EFLAGS: 00010002 [ 222.309311] RAX: 0000000000000082 RBX: ffff8800a13b7990 RCX: ffff8800a13b7808 [ 222.309311] RDX: 0000000000002121 RSI: 0000000000000082 RDI: ffff8800a13b7a30 [ 222.309311] RBP: ffff8800ba6e7a18 R08: 0000000000000000 R09: 0000000000000001 [ 222.309311] R10: 000000000002f8c8 R11: ffff8800ba6e7ad8 R12: ffff8800a13b78ff [ 222.309311] R13: ffff8800a13b7990 R14: 0000000000000001 R15: ffff8800a13b7808 [ 222.309311] FS: 00007f3beec476f0(0000) GS:ffff880001e40000(0000) knlGS:0000000000000000 [ 222.309311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.309311] CR2: 000000000040e7f0 CR3: 00000000a12d5000 CR4: 00000000000006e0 [ 222.309311] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.309311] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 222.309311] Process fio (pid: 4780, threadinfo ffff8800ba6e6000, task ffff8800b3d6bf00) [ 222.309311] Stack: [ 222.309311] 0000000000000001 ffff8800bab17a48 ffff8800bab17a48 ffff8800a13b7800 [ 222.309311] <0> ffff8800ba6e7a68 ffffffff8121da35 ffff880000000001 00ff8800ba5c5698 [ 222.309311] <0> ffff8800ba6e7a68 ffff8800a13b7800 0000000000000000 ffff8800bab17a48 [ 222.309311] Call Trace: [ 222.309311] [<ffffffff8121da35>] __cfq_slice_expired+0x2af/0x3ec [ 222.309311] [<ffffffff8121fd7b>] cfq_dispatch_requests+0x2c8/0x8e8 [ 222.309311] [<ffffffff8120f1cd>] ? spin_unlock_irqrestore+0xe/0x10 [ 222.309311] [<ffffffff8120fb1a>] ? blk_insert_cloned_request+0x70/0x7b [ 222.309311] [<ffffffff81210461>] blk_peek_request+0x191/0x1a7 [ 222.309311] [<ffffffffa0002799>] dm_request_fn+0x38/0x14c [dm_mod] [ 222.309311] [<ffffffff810ae61f>] ? sync_page_killable+0x0/0x35 [ 222.309311] [<ffffffff81210fd4>] __generic_unplug_device+0x32/0x37 [ 222.309311] [<ffffffff81211274>] generic_unplug_device+0x2e/0x3c [ 222.309311] [<ffffffffa00011a6>] dm_unplug_all+0x42/0x5b [dm_mod] [ 222.309311] [<ffffffff8120ca37>] blk_unplug+0x29/0x2d [ 222.309311] [<ffffffff8120ca4d>] blk_backing_dev_unplug+0x12/0x14 [ 222.309311] [<ffffffff81109a7a>] block_sync_page+0x35/0x39 [ 222.309311] [<ffffffff810ae616>] sync_page+0x41/0x4a [ 222.309311] [<ffffffff810ae62d>] sync_page_killable+0xe/0x35 [ 222.309311] [<ffffffff8158aa59>] __wait_on_bit_lock+0x46/0x8f [ 222.309311] [<ffffffff810ae4f5>] __lock_page_killable+0x66/0x6d [ 222.309311] [<ffffffff81056f9c>] ? wake_bit_function+0x0/0x33 [ 222.309311] [<ffffffff810ae528>] lock_page_killable+0x2c/0x2e [ 222.309311] [<ffffffff810afbc5>] generic_file_aio_read+0x361/0x4f0 [ 222.309311] [<ffffffff810ea044>] do_sync_read+0xcb/0x108 [ 222.309311] [<ffffffff811e42f7>] ? security_file_permission+0x16/0x18 [ 222.309311] [<ffffffff810ea6ab>] vfs_read+0xab/0x108 [ 222.309311] [<ffffffff810ea7c8>] sys_read+0x4a/0x6e [ 222.309311] [<ffffffff81002b5b>] system_call_fastpath+0x16/0x1b [ 222.309311] Code: 58 01 00 00 00 48 89 c6 75 0a 48 83 bb 60 01 00 00 00 74 09 48 8d bb a0 00 00 00 eb 35 41 fe cc 74 0d f6 83 c0 01 00 00 04 74 04 <0f> 0b eb fe 48 89 75 e8 e8 be e0 de ff 66 83 8b c0 01 00 00 04 [ 222.309311] RIP [<ffffffff8121ad88>] blkiocg_set_start_empty_time+0x50/0x83 [ 222.309311] RSP <ffff8800ba6e79f8> [ 222.309311] ---[ end trace 32b4f71dffc15712 ]--- Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Divyesh Shah <dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-27 01:25:11 +08:00
void blkiocg_set_start_empty_time(struct blkio_group *blkg)
{
unsigned long flags;
struct blkio_group_stats *stats;
spin_lock_irqsave(&blkg->stats_lock, flags);
stats = &blkg->stats;
if (stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] ||
stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]) {
spin_unlock_irqrestore(&blkg->stats_lock, flags);
return;
}
/*
blkio: Fix another BUG_ON() crash due to cfqq movement across groups o Once in a while, I was hitting a BUG_ON() in blkio code. empty_time was assuming that upon slice expiry, group can't be marked empty already (except forced dispatch). But this assumption is broken if cfqq can move (group_isolation=0) across groups after receiving a request. I think most likely in this case we got a request in a cfqq and accounted the rq in one group, later while adding the cfqq to tree, we moved the queue to a different group which was already marked empty and after dispatch from slice we found group already marked empty and raised alarm. This patch does not error out if group is already marked empty. This can introduce some empty_time stat error only in case of group_isolation=0. This is better than crashing. In case of group_isolation=1 we should still get same stats as before this patch. [ 222.308546] ------------[ cut here ]------------ [ 222.309311] kernel BUG at block/blk-cgroup.c:236! [ 222.309311] invalid opcode: 0000 [#1] SMP [ 222.309311] last sysfs file: /sys/devices/virtual/block/dm-3/queue/scheduler [ 222.309311] CPU 1 [ 222.309311] Modules linked in: dm_round_robin dm_multipath qla2xxx scsi_transport_fc dm_zero dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] [ 222.309311] [ 222.309311] Pid: 4780, comm: fio Not tainted 2.6.34-rc4-blkio-config #68 0A98h/HP xw8600 Workstation [ 222.309311] RIP: 0010:[<ffffffff8121ad88>] [<ffffffff8121ad88>] blkiocg_set_start_empty_time+0x50/0x83 [ 222.309311] RSP: 0018:ffff8800ba6e79f8 EFLAGS: 00010002 [ 222.309311] RAX: 0000000000000082 RBX: ffff8800a13b7990 RCX: ffff8800a13b7808 [ 222.309311] RDX: 0000000000002121 RSI: 0000000000000082 RDI: ffff8800a13b7a30 [ 222.309311] RBP: ffff8800ba6e7a18 R08: 0000000000000000 R09: 0000000000000001 [ 222.309311] R10: 000000000002f8c8 R11: ffff8800ba6e7ad8 R12: ffff8800a13b78ff [ 222.309311] R13: ffff8800a13b7990 R14: 0000000000000001 R15: ffff8800a13b7808 [ 222.309311] FS: 00007f3beec476f0(0000) GS:ffff880001e40000(0000) knlGS:0000000000000000 [ 222.309311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.309311] CR2: 000000000040e7f0 CR3: 00000000a12d5000 CR4: 00000000000006e0 [ 222.309311] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.309311] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 222.309311] Process fio (pid: 4780, threadinfo ffff8800ba6e6000, task ffff8800b3d6bf00) [ 222.309311] Stack: [ 222.309311] 0000000000000001 ffff8800bab17a48 ffff8800bab17a48 ffff8800a13b7800 [ 222.309311] <0> ffff8800ba6e7a68 ffffffff8121da35 ffff880000000001 00ff8800ba5c5698 [ 222.309311] <0> ffff8800ba6e7a68 ffff8800a13b7800 0000000000000000 ffff8800bab17a48 [ 222.309311] Call Trace: [ 222.309311] [<ffffffff8121da35>] __cfq_slice_expired+0x2af/0x3ec [ 222.309311] [<ffffffff8121fd7b>] cfq_dispatch_requests+0x2c8/0x8e8 [ 222.309311] [<ffffffff8120f1cd>] ? spin_unlock_irqrestore+0xe/0x10 [ 222.309311] [<ffffffff8120fb1a>] ? blk_insert_cloned_request+0x70/0x7b [ 222.309311] [<ffffffff81210461>] blk_peek_request+0x191/0x1a7 [ 222.309311] [<ffffffffa0002799>] dm_request_fn+0x38/0x14c [dm_mod] [ 222.309311] [<ffffffff810ae61f>] ? sync_page_killable+0x0/0x35 [ 222.309311] [<ffffffff81210fd4>] __generic_unplug_device+0x32/0x37 [ 222.309311] [<ffffffff81211274>] generic_unplug_device+0x2e/0x3c [ 222.309311] [<ffffffffa00011a6>] dm_unplug_all+0x42/0x5b [dm_mod] [ 222.309311] [<ffffffff8120ca37>] blk_unplug+0x29/0x2d [ 222.309311] [<ffffffff8120ca4d>] blk_backing_dev_unplug+0x12/0x14 [ 222.309311] [<ffffffff81109a7a>] block_sync_page+0x35/0x39 [ 222.309311] [<ffffffff810ae616>] sync_page+0x41/0x4a [ 222.309311] [<ffffffff810ae62d>] sync_page_killable+0xe/0x35 [ 222.309311] [<ffffffff8158aa59>] __wait_on_bit_lock+0x46/0x8f [ 222.309311] [<ffffffff810ae4f5>] __lock_page_killable+0x66/0x6d [ 222.309311] [<ffffffff81056f9c>] ? wake_bit_function+0x0/0x33 [ 222.309311] [<ffffffff810ae528>] lock_page_killable+0x2c/0x2e [ 222.309311] [<ffffffff810afbc5>] generic_file_aio_read+0x361/0x4f0 [ 222.309311] [<ffffffff810ea044>] do_sync_read+0xcb/0x108 [ 222.309311] [<ffffffff811e42f7>] ? security_file_permission+0x16/0x18 [ 222.309311] [<ffffffff810ea6ab>] vfs_read+0xab/0x108 [ 222.309311] [<ffffffff810ea7c8>] sys_read+0x4a/0x6e [ 222.309311] [<ffffffff81002b5b>] system_call_fastpath+0x16/0x1b [ 222.309311] Code: 58 01 00 00 00 48 89 c6 75 0a 48 83 bb 60 01 00 00 00 74 09 48 8d bb a0 00 00 00 eb 35 41 fe cc 74 0d f6 83 c0 01 00 00 04 74 04 <0f> 0b eb fe 48 89 75 e8 e8 be e0 de ff 66 83 8b c0 01 00 00 04 [ 222.309311] RIP [<ffffffff8121ad88>] blkiocg_set_start_empty_time+0x50/0x83 [ 222.309311] RSP <ffff8800ba6e79f8> [ 222.309311] ---[ end trace 32b4f71dffc15712 ]--- Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Divyesh Shah <dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-27 01:25:11 +08:00
* group is already marked empty. This can happen if cfqq got new
* request in parent group and moved to this group while being added
* to service tree. Just ignore the event and move on.
*/
blkio: Fix another BUG_ON() crash due to cfqq movement across groups o Once in a while, I was hitting a BUG_ON() in blkio code. empty_time was assuming that upon slice expiry, group can't be marked empty already (except forced dispatch). But this assumption is broken if cfqq can move (group_isolation=0) across groups after receiving a request. I think most likely in this case we got a request in a cfqq and accounted the rq in one group, later while adding the cfqq to tree, we moved the queue to a different group which was already marked empty and after dispatch from slice we found group already marked empty and raised alarm. This patch does not error out if group is already marked empty. This can introduce some empty_time stat error only in case of group_isolation=0. This is better than crashing. In case of group_isolation=1 we should still get same stats as before this patch. [ 222.308546] ------------[ cut here ]------------ [ 222.309311] kernel BUG at block/blk-cgroup.c:236! [ 222.309311] invalid opcode: 0000 [#1] SMP [ 222.309311] last sysfs file: /sys/devices/virtual/block/dm-3/queue/scheduler [ 222.309311] CPU 1 [ 222.309311] Modules linked in: dm_round_robin dm_multipath qla2xxx scsi_transport_fc dm_zero dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] [ 222.309311] [ 222.309311] Pid: 4780, comm: fio Not tainted 2.6.34-rc4-blkio-config #68 0A98h/HP xw8600 Workstation [ 222.309311] RIP: 0010:[<ffffffff8121ad88>] [<ffffffff8121ad88>] blkiocg_set_start_empty_time+0x50/0x83 [ 222.309311] RSP: 0018:ffff8800ba6e79f8 EFLAGS: 00010002 [ 222.309311] RAX: 0000000000000082 RBX: ffff8800a13b7990 RCX: ffff8800a13b7808 [ 222.309311] RDX: 0000000000002121 RSI: 0000000000000082 RDI: ffff8800a13b7a30 [ 222.309311] RBP: ffff8800ba6e7a18 R08: 0000000000000000 R09: 0000000000000001 [ 222.309311] R10: 000000000002f8c8 R11: ffff8800ba6e7ad8 R12: ffff8800a13b78ff [ 222.309311] R13: ffff8800a13b7990 R14: 0000000000000001 R15: ffff8800a13b7808 [ 222.309311] FS: 00007f3beec476f0(0000) GS:ffff880001e40000(0000) knlGS:0000000000000000 [ 222.309311] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 222.309311] CR2: 000000000040e7f0 CR3: 00000000a12d5000 CR4: 00000000000006e0 [ 222.309311] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 222.309311] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 222.309311] Process fio (pid: 4780, threadinfo ffff8800ba6e6000, task ffff8800b3d6bf00) [ 222.309311] Stack: [ 222.309311] 0000000000000001 ffff8800bab17a48 ffff8800bab17a48 ffff8800a13b7800 [ 222.309311] <0> ffff8800ba6e7a68 ffffffff8121da35 ffff880000000001 00ff8800ba5c5698 [ 222.309311] <0> ffff8800ba6e7a68 ffff8800a13b7800 0000000000000000 ffff8800bab17a48 [ 222.309311] Call Trace: [ 222.309311] [<ffffffff8121da35>] __cfq_slice_expired+0x2af/0x3ec [ 222.309311] [<ffffffff8121fd7b>] cfq_dispatch_requests+0x2c8/0x8e8 [ 222.309311] [<ffffffff8120f1cd>] ? spin_unlock_irqrestore+0xe/0x10 [ 222.309311] [<ffffffff8120fb1a>] ? blk_insert_cloned_request+0x70/0x7b [ 222.309311] [<ffffffff81210461>] blk_peek_request+0x191/0x1a7 [ 222.309311] [<ffffffffa0002799>] dm_request_fn+0x38/0x14c [dm_mod] [ 222.309311] [<ffffffff810ae61f>] ? sync_page_killable+0x0/0x35 [ 222.309311] [<ffffffff81210fd4>] __generic_unplug_device+0x32/0x37 [ 222.309311] [<ffffffff81211274>] generic_unplug_device+0x2e/0x3c [ 222.309311] [<ffffffffa00011a6>] dm_unplug_all+0x42/0x5b [dm_mod] [ 222.309311] [<ffffffff8120ca37>] blk_unplug+0x29/0x2d [ 222.309311] [<ffffffff8120ca4d>] blk_backing_dev_unplug+0x12/0x14 [ 222.309311] [<ffffffff81109a7a>] block_sync_page+0x35/0x39 [ 222.309311] [<ffffffff810ae616>] sync_page+0x41/0x4a [ 222.309311] [<ffffffff810ae62d>] sync_page_killable+0xe/0x35 [ 222.309311] [<ffffffff8158aa59>] __wait_on_bit_lock+0x46/0x8f [ 222.309311] [<ffffffff810ae4f5>] __lock_page_killable+0x66/0x6d [ 222.309311] [<ffffffff81056f9c>] ? wake_bit_function+0x0/0x33 [ 222.309311] [<ffffffff810ae528>] lock_page_killable+0x2c/0x2e [ 222.309311] [<ffffffff810afbc5>] generic_file_aio_read+0x361/0x4f0 [ 222.309311] [<ffffffff810ea044>] do_sync_read+0xcb/0x108 [ 222.309311] [<ffffffff811e42f7>] ? security_file_permission+0x16/0x18 [ 222.309311] [<ffffffff810ea6ab>] vfs_read+0xab/0x108 [ 222.309311] [<ffffffff810ea7c8>] sys_read+0x4a/0x6e [ 222.309311] [<ffffffff81002b5b>] system_call_fastpath+0x16/0x1b [ 222.309311] Code: 58 01 00 00 00 48 89 c6 75 0a 48 83 bb 60 01 00 00 00 74 09 48 8d bb a0 00 00 00 eb 35 41 fe cc 74 0d f6 83 c0 01 00 00 04 74 04 <0f> 0b eb fe 48 89 75 e8 e8 be e0 de ff 66 83 8b c0 01 00 00 04 [ 222.309311] RIP [<ffffffff8121ad88>] blkiocg_set_start_empty_time+0x50/0x83 [ 222.309311] RSP <ffff8800ba6e79f8> [ 222.309311] ---[ end trace 32b4f71dffc15712 ]--- Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Divyesh Shah <dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-27 01:25:11 +08:00
if(blkio_blkg_empty(stats)) {
spin_unlock_irqrestore(&blkg->stats_lock, flags);
return;
}
stats->start_empty_time = sched_clock();
blkio_mark_blkg_empty(stats);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_set_start_empty_time);
void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
unsigned long dequeue)
{
blkg->stats.dequeue += dequeue;
}
EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats);
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
#else
static inline void blkio_set_start_group_wait_time(struct blkio_group *blkg,
struct blkio_group *curr_blkg) {}
static inline void blkio_end_empty_time(struct blkio_group_stats *stats) {}
#endif
void blkiocg_update_io_add_stats(struct blkio_group *blkg,
struct blkio_group *curr_blkg, bool direction,
bool sync)
{
unsigned long flags;
spin_lock_irqsave(&blkg->stats_lock, flags);
blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED], 1, direction,
sync);
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
blkio_end_empty_time(&blkg->stats);
blkio_set_start_group_wait_time(blkg, curr_blkg);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_add_stats);
void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
bool direction, bool sync)
{
unsigned long flags;
spin_lock_irqsave(&blkg->stats_lock, flags);
blkio_check_and_dec_stat(blkg->stats.stat_arr[BLKIO_STAT_QUEUED],
direction, sync);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_remove_stats);
void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time,
unsigned long unaccounted_time)
{
unsigned long flags;
spin_lock_irqsave(&blkg->stats_lock, flags);
blkg->stats.time += time;
#ifdef CONFIG_DEBUG_BLK_CGROUP
blkg->stats.unaccounted_time += unaccounted_time;
#endif
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);
/*
* should be called under rcu read lock or queue lock to make sure blkg pointer
* is valid.
*/
2010-04-09 14:31:19 +08:00
void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
uint64_t bytes, bool direction, bool sync)
{
struct blkio_group_stats_cpu *stats_cpu;
unsigned long flags;
/*
* Disabling interrupts to provide mutual exclusion between two
* writes on same cpu. It probably is not needed for 64bit. Not
* optimizing that case yet.
*/
local_irq_save(flags);
stats_cpu = this_cpu_ptr(blkg->stats_cpu);
u64_stats_update_begin(&stats_cpu->syncp);
stats_cpu->sectors += bytes >> 9;
blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_SERVICED],
1, direction, sync);
blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_SERVICE_BYTES],
bytes, direction, sync);
u64_stats_update_end(&stats_cpu->syncp);
local_irq_restore(flags);
}
2010-04-09 14:31:19 +08:00
EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats);
2010-04-09 14:31:19 +08:00
void blkiocg_update_completion_stats(struct blkio_group *blkg,
uint64_t start_time, uint64_t io_start_time, bool direction, bool sync)
{
struct blkio_group_stats *stats;
unsigned long flags;
unsigned long long now = sched_clock();
spin_lock_irqsave(&blkg->stats_lock, flags);
stats = &blkg->stats;
2010-04-09 14:31:19 +08:00
if (time_after64(now, io_start_time))
blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_TIME],
now - io_start_time, direction, sync);
if (time_after64(io_start_time, start_time))
blkio_add_stat(stats->stat_arr[BLKIO_STAT_WAIT_TIME],
io_start_time - start_time, direction, sync);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
2010-04-09 14:31:19 +08:00
EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats);
/* Merged stats are per cpu. */
void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
bool sync)
{
struct blkio_group_stats_cpu *stats_cpu;
unsigned long flags;
/*
* Disabling interrupts to provide mutual exclusion between two
* writes on same cpu. It probably is not needed for 64bit. Not
* optimizing that case yet.
*/
local_irq_save(flags);
stats_cpu = this_cpu_ptr(blkg->stats_cpu);
u64_stats_update_begin(&stats_cpu->syncp);
blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_MERGED], 1,
direction, sync);
u64_stats_update_end(&stats_cpu->syncp);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
/*
* This function allocates the per cpu stats for blkio_group. Should be called
* from sleepable context as alloc_per_cpu() requires that.
*/
int blkio_alloc_blkg_stats(struct blkio_group *blkg)
{
/* Allocate memory for per cpu stats */
blkg->stats_cpu = alloc_percpu(struct blkio_group_stats_cpu);
if (!blkg->stats_cpu)
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL_GPL(blkio_alloc_blkg_stats);
void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
struct blkio_group *blkg, void *key, dev_t dev,
enum blkio_policy_id plid)
{
unsigned long flags;
spin_lock_irqsave(&blkcg->lock, flags);
spin_lock_init(&blkg->stats_lock);
rcu_assign_pointer(blkg->key, key);
blkg->blkcg_id = css_id(&blkcg->css);
hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
blkg->plid = plid;
spin_unlock_irqrestore(&blkcg->lock, flags);
/* Need to take css reference ? */
cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
blkg->dev = dev;
}
EXPORT_SYMBOL_GPL(blkiocg_add_blkio_group);
static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
{
hlist_del_init_rcu(&blkg->blkcg_node);
blkg->blkcg_id = 0;
}
/*
* returns 0 if blkio_group was still on cgroup list. Otherwise returns 1
* indicating that blk_group was unhashed by the time we got to it.
*/
int blkiocg_del_blkio_group(struct blkio_group *blkg)
{
struct blkio_cgroup *blkcg;
unsigned long flags;
struct cgroup_subsys_state *css;
int ret = 1;
rcu_read_lock();
css = css_lookup(&blkio_subsys, blkg->blkcg_id);
if (css) {
blkcg = container_of(css, struct blkio_cgroup, css);
spin_lock_irqsave(&blkcg->lock, flags);
if (!hlist_unhashed(&blkg->blkcg_node)) {
__blkiocg_del_blkio_group(blkg);
ret = 0;
}
spin_unlock_irqrestore(&blkcg->lock, flags);
}
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(blkiocg_del_blkio_group);
/* called under rcu_read_lock(). */
struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
{
struct blkio_group *blkg;
struct hlist_node *n;
void *__key;
hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
__key = blkg->key;
if (__key == key)
return blkg;
}
return NULL;
}
EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
static void blkio_reset_stats_cpu(struct blkio_group *blkg)
{
struct blkio_group_stats_cpu *stats_cpu;
int i, j, k;
/*
* Note: On 64 bit arch this should not be an issue. This has the
* possibility of returning some inconsistent value on 32bit arch
* as 64bit update on 32bit is non atomic. Taking care of this
* corner case makes code very complicated, like sending IPIs to
* cpus, taking care of stats of offline cpus etc.
*
* reset stats is anyway more of a debug feature and this sounds a
* corner case. So I am not complicating the code yet until and
* unless this becomes a real issue.
*/
for_each_possible_cpu(i) {
stats_cpu = per_cpu_ptr(blkg->stats_cpu, i);
stats_cpu->sectors = 0;
for(j = 0; j < BLKIO_STAT_CPU_NR; j++)
for (k = 0; k < BLKIO_STAT_TOTAL; k++)
stats_cpu->stat_arr_cpu[j][k] = 0;
}
}
static int
2010-04-09 14:31:19 +08:00
blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val)
{
struct blkio_cgroup *blkcg;
struct blkio_group *blkg;
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
struct blkio_group_stats *stats;
struct hlist_node *n;
uint64_t queued[BLKIO_STAT_TOTAL];
int i;
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
#ifdef CONFIG_DEBUG_BLK_CGROUP
bool idling, waiting, empty;
unsigned long long now = sched_clock();
#endif
blkcg = cgroup_to_blkio_cgroup(cgroup);
spin_lock_irq(&blkcg->lock);
hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
spin_lock(&blkg->stats_lock);
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
stats = &blkg->stats;
#ifdef CONFIG_DEBUG_BLK_CGROUP
idling = blkio_blkg_idling(stats);
waiting = blkio_blkg_waiting(stats);
empty = blkio_blkg_empty(stats);
#endif
for (i = 0; i < BLKIO_STAT_TOTAL; i++)
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
queued[i] = stats->stat_arr[BLKIO_STAT_QUEUED][i];
memset(stats, 0, sizeof(struct blkio_group_stats));
for (i = 0; i < BLKIO_STAT_TOTAL; i++)
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
stats->stat_arr[BLKIO_STAT_QUEUED][i] = queued[i];
#ifdef CONFIG_DEBUG_BLK_CGROUP
if (idling) {
blkio_mark_blkg_idling(stats);
stats->start_idle_time = now;
}
if (waiting) {
blkio_mark_blkg_waiting(stats);
stats->start_group_wait_time = now;
}
if (empty) {
blkio_mark_blkg_empty(stats);
stats->start_empty_time = now;
}
#endif
spin_unlock(&blkg->stats_lock);
/* Reset Per cpu stats which don't take blkg->stats_lock */
blkio_reset_stats_cpu(blkg);
}
spin_unlock_irq(&blkcg->lock);
return 0;
}
2010-04-09 14:31:19 +08:00
static void blkio_get_key_name(enum stat_sub_type type, dev_t dev, char *str,
int chars_left, bool diskname_only)
{
2010-04-09 14:31:19 +08:00
snprintf(str, chars_left, "%d:%d", MAJOR(dev), MINOR(dev));
chars_left -= strlen(str);
if (chars_left <= 0) {
printk(KERN_WARNING
"Possibly incorrect cgroup stat display format");
return;
}
2010-04-09 14:31:19 +08:00
if (diskname_only)
return;
switch (type) {
2010-04-09 14:31:19 +08:00
case BLKIO_STAT_READ:
strlcat(str, " Read", chars_left);
break;
2010-04-09 14:31:19 +08:00
case BLKIO_STAT_WRITE:
strlcat(str, " Write", chars_left);
break;
2010-04-09 14:31:19 +08:00
case BLKIO_STAT_SYNC:
strlcat(str, " Sync", chars_left);
break;
2010-04-09 14:31:19 +08:00
case BLKIO_STAT_ASYNC:
strlcat(str, " Async", chars_left);
break;
2010-04-09 14:31:19 +08:00
case BLKIO_STAT_TOTAL:
strlcat(str, " Total", chars_left);
break;
default:
strlcat(str, " Invalid", chars_left);
}
}
2010-04-09 14:31:19 +08:00
static uint64_t blkio_fill_stat(char *str, int chars_left, uint64_t val,
struct cgroup_map_cb *cb, dev_t dev)
{
blkio_get_key_name(0, dev, str, chars_left, true);
cb->fill(cb, str, val);
return val;
}
static uint64_t blkio_read_stat_cpu(struct blkio_group *blkg,
enum stat_type_cpu type, enum stat_sub_type sub_type)
{
int cpu;
struct blkio_group_stats_cpu *stats_cpu;
u64 val = 0, tval;
for_each_possible_cpu(cpu) {
unsigned int start;
stats_cpu = per_cpu_ptr(blkg->stats_cpu, cpu);
do {
start = u64_stats_fetch_begin(&stats_cpu->syncp);
if (type == BLKIO_STAT_CPU_SECTORS)
tval = stats_cpu->sectors;
else
tval = stats_cpu->stat_arr_cpu[type][sub_type];
} while(u64_stats_fetch_retry(&stats_cpu->syncp, start));
val += tval;
}
return val;
}
static uint64_t blkio_get_stat_cpu(struct blkio_group *blkg,
struct cgroup_map_cb *cb, dev_t dev, enum stat_type_cpu type)
{
uint64_t disk_total, val;
char key_str[MAX_KEY_LEN];
enum stat_sub_type sub_type;
if (type == BLKIO_STAT_CPU_SECTORS) {
val = blkio_read_stat_cpu(blkg, type, 0);
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, val, cb, dev);
}
for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL;
sub_type++) {
blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false);
val = blkio_read_stat_cpu(blkg, type, sub_type);
cb->fill(cb, key_str, val);
}
disk_total = blkio_read_stat_cpu(blkg, type, BLKIO_STAT_READ) +
blkio_read_stat_cpu(blkg, type, BLKIO_STAT_WRITE);
blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false);
cb->fill(cb, key_str, disk_total);
return disk_total;
}
2010-04-09 14:31:19 +08:00
/* This should be called with blkg->stats_lock held */
static uint64_t blkio_get_stat(struct blkio_group *blkg,
struct cgroup_map_cb *cb, dev_t dev, enum stat_type type)
{
uint64_t disk_total;
char key_str[MAX_KEY_LEN];
2010-04-09 14:31:19 +08:00
enum stat_sub_type sub_type;
if (type == BLKIO_STAT_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.time, cb, dev);
#ifdef CONFIG_DEBUG_BLK_CGROUP
if (type == BLKIO_STAT_UNACCOUNTED_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.unaccounted_time, cb, dev);
if (type == BLKIO_STAT_AVG_QUEUE_SIZE) {
uint64_t sum = blkg->stats.avg_queue_size_sum;
uint64_t samples = blkg->stats.avg_queue_size_samples;
if (samples)
do_div(sum, samples);
else
sum = 0;
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, sum, cb, dev);
}
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
if (type == BLKIO_STAT_GROUP_WAIT_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.group_wait_time, cb, dev);
if (type == BLKIO_STAT_IDLE_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.idle_time, cb, dev);
if (type == BLKIO_STAT_EMPTY_TIME)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.empty_time, cb, dev);
2010-04-09 14:31:19 +08:00
if (type == BLKIO_STAT_DEQUEUE)
return blkio_fill_stat(key_str, MAX_KEY_LEN - 1,
blkg->stats.dequeue, cb, dev);
#endif
2010-04-09 14:31:19 +08:00
for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL;
sub_type++) {
blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false);
cb->fill(cb, key_str, blkg->stats.stat_arr[type][sub_type]);
}
2010-04-09 14:31:19 +08:00
disk_total = blkg->stats.stat_arr[type][BLKIO_STAT_READ] +
blkg->stats.stat_arr[type][BLKIO_STAT_WRITE];
blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false);
cb->fill(cb, key_str, disk_total);
return disk_total;
}
static int blkio_policy_parse_and_set(char *buf,
struct blkio_policy_node *newpn, enum blkio_policy_id plid, int fileid)
{
struct gendisk *disk = NULL;
char *s[4], *p, *major_s = NULL, *minor_s = NULL;
unsigned long major, minor;
int i = 0, ret = -EINVAL;
int part;
dev_t dev;
u64 temp;
memset(s, 0, sizeof(s));
while ((p = strsep(&buf, " ")) != NULL) {
if (!*p)
continue;
s[i++] = p;
/* Prevent from inputing too many things */
if (i == 3)
break;
}
if (i != 2)
goto out;
p = strsep(&s[0], ":");
if (p != NULL)
major_s = p;
else
goto out;
minor_s = s[0];
if (!minor_s)
goto out;
if (strict_strtoul(major_s, 10, &major))
goto out;
if (strict_strtoul(minor_s, 10, &minor))
goto out;
dev = MKDEV(major, minor);
if (strict_strtoull(s[1], 10, &temp))
goto out;
/* For rule removal, do not check for device presence. */
if (temp) {
disk = get_gendisk(dev, &part);
if (!disk || part) {
ret = -ENODEV;
goto out;
}
}
newpn->dev = dev;
switch (plid) {
case BLKIO_POLICY_PROP:
if ((temp < BLKIO_WEIGHT_MIN && temp > 0) ||
temp > BLKIO_WEIGHT_MAX)
goto out;
newpn->plid = plid;
newpn->fileid = fileid;
newpn->val.weight = temp;
break;
case BLKIO_POLICY_THROTL:
switch(fileid) {
case BLKIO_THROTL_read_bps_device:
case BLKIO_THROTL_write_bps_device:
newpn->plid = plid;
newpn->fileid = fileid;
newpn->val.bps = temp;
break;
case BLKIO_THROTL_read_iops_device:
case BLKIO_THROTL_write_iops_device:
if (temp > THROTL_IOPS_MAX)
goto out;
newpn->plid = plid;
newpn->fileid = fileid;
newpn->val.iops = (unsigned int)temp;
break;
}
break;
default:
BUG();
}
ret = 0;
out:
put_disk(disk);
return ret;
}
unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
dev_t dev)
{
struct blkio_policy_node *pn;
unsigned long flags;
unsigned int weight;
spin_lock_irqsave(&blkcg->lock, flags);
pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_PROP,
BLKIO_PROP_weight_device);
if (pn)
weight = pn->val.weight;
else
weight = blkcg->weight;
spin_unlock_irqrestore(&blkcg->lock, flags);
return weight;
}
EXPORT_SYMBOL_GPL(blkcg_get_weight);
uint64_t blkcg_get_read_bps(struct blkio_cgroup *blkcg, dev_t dev)
{
struct blkio_policy_node *pn;
unsigned long flags;
uint64_t bps = -1;
spin_lock_irqsave(&blkcg->lock, flags);
pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
BLKIO_THROTL_read_bps_device);
if (pn)
bps = pn->val.bps;
spin_unlock_irqrestore(&blkcg->lock, flags);
return bps;
}
uint64_t blkcg_get_write_bps(struct blkio_cgroup *blkcg, dev_t dev)
{
struct blkio_policy_node *pn;
unsigned long flags;
uint64_t bps = -1;
spin_lock_irqsave(&blkcg->lock, flags);
pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
BLKIO_THROTL_write_bps_device);
if (pn)
bps = pn->val.bps;
spin_unlock_irqrestore(&blkcg->lock, flags);
return bps;
}
unsigned int blkcg_get_read_iops(struct blkio_cgroup *blkcg, dev_t dev)
{
struct blkio_policy_node *pn;
unsigned long flags;
unsigned int iops = -1;
spin_lock_irqsave(&blkcg->lock, flags);
pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
BLKIO_THROTL_read_iops_device);
if (pn)
iops = pn->val.iops;
spin_unlock_irqrestore(&blkcg->lock, flags);
return iops;
}
unsigned int blkcg_get_write_iops(struct blkio_cgroup *blkcg, dev_t dev)
{
struct blkio_policy_node *pn;
unsigned long flags;
unsigned int iops = -1;
spin_lock_irqsave(&blkcg->lock, flags);
pn = blkio_policy_search_node(blkcg, dev, BLKIO_POLICY_THROTL,
BLKIO_THROTL_write_iops_device);
if (pn)
iops = pn->val.iops;
spin_unlock_irqrestore(&blkcg->lock, flags);
return iops;
}
/* Checks whether user asked for deleting a policy rule */
static bool blkio_delete_rule_command(struct blkio_policy_node *pn)
{
switch(pn->plid) {
case BLKIO_POLICY_PROP:
if (pn->val.weight == 0)
return 1;
break;
case BLKIO_POLICY_THROTL:
switch(pn->fileid) {
case BLKIO_THROTL_read_bps_device:
case BLKIO_THROTL_write_bps_device:
if (pn->val.bps == 0)
return 1;
break;
case BLKIO_THROTL_read_iops_device:
case BLKIO_THROTL_write_iops_device:
if (pn->val.iops == 0)
return 1;
}
break;
default:
BUG();
}
return 0;
}
static void blkio_update_policy_rule(struct blkio_policy_node *oldpn,
struct blkio_policy_node *newpn)
{
switch(oldpn->plid) {
case BLKIO_POLICY_PROP:
oldpn->val.weight = newpn->val.weight;
break;
case BLKIO_POLICY_THROTL:
switch(newpn->fileid) {
case BLKIO_THROTL_read_bps_device:
case BLKIO_THROTL_write_bps_device:
oldpn->val.bps = newpn->val.bps;
break;
case BLKIO_THROTL_read_iops_device:
case BLKIO_THROTL_write_iops_device:
oldpn->val.iops = newpn->val.iops;
}
break;
default:
BUG();
}
}
/*
* Some rules/values in blkg have changed. Propagate those to respective
* policies.
*/
static void blkio_update_blkg_policy(struct blkio_cgroup *blkcg,
struct blkio_group *blkg, struct blkio_policy_node *pn)
{
unsigned int weight, iops;
u64 bps;
switch(pn->plid) {
case BLKIO_POLICY_PROP:
weight = pn->val.weight ? pn->val.weight :
blkcg->weight;
blkio_update_group_weight(blkg, weight);
break;
case BLKIO_POLICY_THROTL:
switch(pn->fileid) {
case BLKIO_THROTL_read_bps_device:
case BLKIO_THROTL_write_bps_device:
bps = pn->val.bps ? pn->val.bps : (-1);
blkio_update_group_bps(blkg, bps, pn->fileid);
break;
case BLKIO_THROTL_read_iops_device:
case BLKIO_THROTL_write_iops_device:
iops = pn->val.iops ? pn->val.iops : (-1);
blkio_update_group_iops(blkg, iops, pn->fileid);
break;
}
break;
default:
BUG();
}
}
/*
* A policy node rule has been updated. Propagate this update to all the
* block groups which might be affected by this update.
*/
static void blkio_update_policy_node_blkg(struct blkio_cgroup *blkcg,
struct blkio_policy_node *pn)
{
struct blkio_group *blkg;
struct hlist_node *n;
spin_lock(&blkio_list_lock);
spin_lock_irq(&blkcg->lock);
hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
if (pn->dev != blkg->dev || pn->plid != blkg->plid)
continue;
blkio_update_blkg_policy(blkcg, blkg, pn);
}
spin_unlock_irq(&blkcg->lock);
spin_unlock(&blkio_list_lock);
}
static int blkiocg_file_write(struct cgroup *cgrp, struct cftype *cft,
const char *buffer)
{
int ret = 0;
char *buf;
struct blkio_policy_node *newpn, *pn;
struct blkio_cgroup *blkcg;
int keep_newpn = 0;
enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
int fileid = BLKIOFILE_ATTR(cft->private);
buf = kstrdup(buffer, GFP_KERNEL);
if (!buf)
return -ENOMEM;
newpn = kzalloc(sizeof(*newpn), GFP_KERNEL);
if (!newpn) {
ret = -ENOMEM;
goto free_buf;
}
ret = blkio_policy_parse_and_set(buf, newpn, plid, fileid);
if (ret)
goto free_newpn;
blkcg = cgroup_to_blkio_cgroup(cgrp);
spin_lock_irq(&blkcg->lock);
pn = blkio_policy_search_node(blkcg, newpn->dev, plid, fileid);
if (!pn) {
if (!blkio_delete_rule_command(newpn)) {
blkio_policy_insert_node(blkcg, newpn);
keep_newpn = 1;
}
spin_unlock_irq(&blkcg->lock);
goto update_io_group;
}
if (blkio_delete_rule_command(newpn)) {
blkio_policy_delete_node(pn);
kfree(pn);
spin_unlock_irq(&blkcg->lock);
goto update_io_group;
}
spin_unlock_irq(&blkcg->lock);
blkio_update_policy_rule(pn, newpn);
update_io_group:
blkio_update_policy_node_blkg(blkcg, newpn);
free_newpn:
if (!keep_newpn)
kfree(newpn);
free_buf:
kfree(buf);
return ret;
}
static void
blkio_print_policy_node(struct seq_file *m, struct blkio_policy_node *pn)
{
switch(pn->plid) {
case BLKIO_POLICY_PROP:
if (pn->fileid == BLKIO_PROP_weight_device)
seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
MINOR(pn->dev), pn->val.weight);
break;
case BLKIO_POLICY_THROTL:
switch(pn->fileid) {
case BLKIO_THROTL_read_bps_device:
case BLKIO_THROTL_write_bps_device:
seq_printf(m, "%u:%u\t%llu\n", MAJOR(pn->dev),
MINOR(pn->dev), pn->val.bps);
break;
case BLKIO_THROTL_read_iops_device:
case BLKIO_THROTL_write_iops_device:
seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
MINOR(pn->dev), pn->val.iops);
break;
}
break;
default:
BUG();
}
}
/* cgroup files which read their data from policy nodes end up here */
static void blkio_read_policy_node_files(struct cftype *cft,
struct blkio_cgroup *blkcg, struct seq_file *m)
{
struct blkio_policy_node *pn;
if (!list_empty(&blkcg->policy_list)) {
spin_lock_irq(&blkcg->lock);
list_for_each_entry(pn, &blkcg->policy_list, node) {
if (!pn_matches_cftype(cft, pn))
continue;
blkio_print_policy_node(m, pn);
}
spin_unlock_irq(&blkcg->lock);
}
}
static int blkiocg_file_read(struct cgroup *cgrp, struct cftype *cft,
struct seq_file *m)
{
struct blkio_cgroup *blkcg;
enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
int name = BLKIOFILE_ATTR(cft->private);
blkcg = cgroup_to_blkio_cgroup(cgrp);
switch(plid) {
case BLKIO_POLICY_PROP:
switch(name) {
case BLKIO_PROP_weight_device:
blkio_read_policy_node_files(cft, blkcg, m);
return 0;
default:
BUG();
}
break;
case BLKIO_POLICY_THROTL:
switch(name){
case BLKIO_THROTL_read_bps_device:
case BLKIO_THROTL_write_bps_device:
case BLKIO_THROTL_read_iops_device:
case BLKIO_THROTL_write_iops_device:
blkio_read_policy_node_files(cft, blkcg, m);
return 0;
default:
BUG();
}
break;
default:
BUG();
}
return 0;
}
static int blkio_read_blkg_stats(struct blkio_cgroup *blkcg,
struct cftype *cft, struct cgroup_map_cb *cb,
enum stat_type type, bool show_total, bool pcpu)
{
struct blkio_group *blkg;
struct hlist_node *n;
uint64_t cgroup_total = 0;
rcu_read_lock();
hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
if (blkg->dev) {
if (!cftype_blkg_same_policy(cft, blkg))
continue;
if (pcpu)
cgroup_total += blkio_get_stat_cpu(blkg, cb,
blkg->dev, type);
else {
spin_lock_irq(&blkg->stats_lock);
cgroup_total += blkio_get_stat(blkg, cb,
blkg->dev, type);
spin_unlock_irq(&blkg->stats_lock);
}
}
}
if (show_total)
cb->fill(cb, "Total", cgroup_total);
rcu_read_unlock();
return 0;
}
/* All map kind of cgroup file get serviced by this function */
static int blkiocg_file_read_map(struct cgroup *cgrp, struct cftype *cft,
struct cgroup_map_cb *cb)
{
struct blkio_cgroup *blkcg;
enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
int name = BLKIOFILE_ATTR(cft->private);
blkcg = cgroup_to_blkio_cgroup(cgrp);
switch(plid) {
case BLKIO_POLICY_PROP:
switch(name) {
case BLKIO_PROP_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_TIME, 0, 0);
case BLKIO_PROP_sectors:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_CPU_SECTORS, 0, 1);
case BLKIO_PROP_io_service_bytes:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_CPU_SERVICE_BYTES, 1, 1);
case BLKIO_PROP_io_serviced:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_CPU_SERVICED, 1, 1);
case BLKIO_PROP_io_service_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_SERVICE_TIME, 1, 0);
case BLKIO_PROP_io_wait_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_WAIT_TIME, 1, 0);
case BLKIO_PROP_io_merged:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_CPU_MERGED, 1, 1);
case BLKIO_PROP_io_queued:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_QUEUED, 1, 0);
#ifdef CONFIG_DEBUG_BLK_CGROUP
case BLKIO_PROP_unaccounted_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_UNACCOUNTED_TIME, 0, 0);
case BLKIO_PROP_dequeue:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_DEQUEUE, 0, 0);
case BLKIO_PROP_avg_queue_size:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_AVG_QUEUE_SIZE, 0, 0);
case BLKIO_PROP_group_wait_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_GROUP_WAIT_TIME, 0, 0);
case BLKIO_PROP_idle_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_IDLE_TIME, 0, 0);
case BLKIO_PROP_empty_time:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_EMPTY_TIME, 0, 0);
#endif
default:
BUG();
}
break;
case BLKIO_POLICY_THROTL:
switch(name){
case BLKIO_THROTL_io_service_bytes:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_CPU_SERVICE_BYTES, 1, 1);
case BLKIO_THROTL_io_serviced:
return blkio_read_blkg_stats(blkcg, cft, cb,
BLKIO_STAT_CPU_SERVICED, 1, 1);
default:
BUG();
}
break;
default:
BUG();
}
return 0;
}
static int blkio_weight_write(struct blkio_cgroup *blkcg, u64 val)
{
struct blkio_group *blkg;
struct hlist_node *n;
struct blkio_policy_node *pn;
if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
return -EINVAL;
spin_lock(&blkio_list_lock);
spin_lock_irq(&blkcg->lock);
blkcg->weight = (unsigned int)val;
hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
pn = blkio_policy_search_node(blkcg, blkg->dev,
BLKIO_POLICY_PROP, BLKIO_PROP_weight_device);
if (pn)
continue;
blkio_update_group_weight(blkg, blkcg->weight);
}
spin_unlock_irq(&blkcg->lock);
spin_unlock(&blkio_list_lock);
return 0;
}
static u64 blkiocg_file_read_u64 (struct cgroup *cgrp, struct cftype *cft) {
struct blkio_cgroup *blkcg;
enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
int name = BLKIOFILE_ATTR(cft->private);
blkcg = cgroup_to_blkio_cgroup(cgrp);
switch(plid) {
case BLKIO_POLICY_PROP:
switch(name) {
case BLKIO_PROP_weight:
return (u64)blkcg->weight;
}
break;
default:
BUG();
}
return 0;
}
static int
blkiocg_file_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
{
struct blkio_cgroup *blkcg;
enum blkio_policy_id plid = BLKIOFILE_POLICY(cft->private);
int name = BLKIOFILE_ATTR(cft->private);
blkcg = cgroup_to_blkio_cgroup(cgrp);
switch(plid) {
case BLKIO_POLICY_PROP:
switch(name) {
case BLKIO_PROP_weight:
return blkio_weight_write(blkcg, val);
}
break;
default:
BUG();
}
return 0;
}
struct cftype blkio_files[] = {
{
.name = "weight_device",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_weight_device),
.read_seq_string = blkiocg_file_read,
.write_string = blkiocg_file_write,
.max_write_len = 256,
},
{
.name = "weight",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_weight),
.read_u64 = blkiocg_file_read_u64,
.write_u64 = blkiocg_file_write_u64,
},
{
.name = "time",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_time),
.read_map = blkiocg_file_read_map,
},
{
.name = "sectors",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_sectors),
.read_map = blkiocg_file_read_map,
},
{
.name = "io_service_bytes",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_io_service_bytes),
.read_map = blkiocg_file_read_map,
},
{
.name = "io_serviced",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_io_serviced),
.read_map = blkiocg_file_read_map,
},
{
.name = "io_service_time",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_io_service_time),
.read_map = blkiocg_file_read_map,
},
{
.name = "io_wait_time",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_io_wait_time),
.read_map = blkiocg_file_read_map,
2010-04-09 14:31:19 +08:00
},
{
.name = "io_merged",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_io_merged),
.read_map = blkiocg_file_read_map,
},
{
.name = "io_queued",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_io_queued),
.read_map = blkiocg_file_read_map,
},
2010-04-09 14:31:19 +08:00
{
.name = "reset_stats",
.write_u64 = blkiocg_reset_stats,
},
#ifdef CONFIG_BLK_DEV_THROTTLING
{
.name = "throttle.read_bps_device",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
BLKIO_THROTL_read_bps_device),
.read_seq_string = blkiocg_file_read,
.write_string = blkiocg_file_write,
.max_write_len = 256,
},
{
.name = "throttle.write_bps_device",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
BLKIO_THROTL_write_bps_device),
.read_seq_string = blkiocg_file_read,
.write_string = blkiocg_file_write,
.max_write_len = 256,
},
{
.name = "throttle.read_iops_device",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
BLKIO_THROTL_read_iops_device),
.read_seq_string = blkiocg_file_read,
.write_string = blkiocg_file_write,
.max_write_len = 256,
},
{
.name = "throttle.write_iops_device",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
BLKIO_THROTL_write_iops_device),
.read_seq_string = blkiocg_file_read,
.write_string = blkiocg_file_write,
.max_write_len = 256,
},
{
.name = "throttle.io_service_bytes",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
BLKIO_THROTL_io_service_bytes),
.read_map = blkiocg_file_read_map,
},
{
.name = "throttle.io_serviced",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_THROTL,
BLKIO_THROTL_io_serviced),
.read_map = blkiocg_file_read_map,
},
#endif /* CONFIG_BLK_DEV_THROTTLING */
#ifdef CONFIG_DEBUG_BLK_CGROUP
{
.name = "avg_queue_size",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_avg_queue_size),
.read_map = blkiocg_file_read_map,
},
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
{
.name = "group_wait_time",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_group_wait_time),
.read_map = blkiocg_file_read_map,
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
},
{
.name = "idle_time",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_idle_time),
.read_map = blkiocg_file_read_map,
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
},
{
.name = "empty_time",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_empty_time),
.read_map = blkiocg_file_read_map,
blkio: Add more debug-only per-cgroup stats 1) group_wait_time - This is the amount of time the cgroup had to wait to get a timeslice for one of its queues from when it became busy, i.e., went from 0 to 1 request queued. This is different from the io_wait_time which is the cumulative total of the amount of time spent by each IO in that cgroup waiting in the scheduler queue. This stat is a great way to find out any jobs in the fleet that are being starved or waiting for longer than what is expected (due to an IO controller bug or any other issue). 2) empty_time - This is the amount of time a cgroup spends w/o any pending requests. This stat is useful when a job does not seem to be able to use its assigned disk share by helping check if that is happening due to an IO controller bug or because the job is not submitting enough IOs. 3) idle_time - This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the exising ones from other queues/cgroups. All these stats are recorded using start and stop events. When reading these stats, we do not add the delta between the current time and the last start time if we're between the start and stop events. We avoid doing this to make sure that these numbers are always monotonically increasing when read. Since we're using sched_clock() which may use the tsc as its source, it may induce some inconsistency (due to tsc resync across cpus) if we included the current delta. Signed-off-by: Divyesh Shah<dpshah@google.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-09 12:15:35 +08:00
},
{
.name = "dequeue",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_dequeue),
.read_map = blkiocg_file_read_map,
},
{
.name = "unaccounted_time",
.private = BLKIOFILE_PRIVATE(BLKIO_POLICY_PROP,
BLKIO_PROP_unaccounted_time),
.read_map = blkiocg_file_read_map,
},
#endif
};
static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
return cgroup_add_files(cgroup, subsys, blkio_files,
ARRAY_SIZE(blkio_files));
}
static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
unsigned long flags;
struct blkio_group *blkg;
void *key;
struct blkio_policy_type *blkiop;
struct blkio_policy_node *pn, *pntmp;
rcu_read_lock();
do {
spin_lock_irqsave(&blkcg->lock, flags);
if (hlist_empty(&blkcg->blkg_list)) {
spin_unlock_irqrestore(&blkcg->lock, flags);
break;
}
blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group,
blkcg_node);
key = rcu_dereference(blkg->key);
__blkiocg_del_blkio_group(blkg);
spin_unlock_irqrestore(&blkcg->lock, flags);
/*
* This blkio_group is being unlinked as associated cgroup is
* going away. Let all the IO controlling policies know about
* this event.
*/
spin_lock(&blkio_list_lock);
list_for_each_entry(blkiop, &blkio_list, list) {
if (blkiop->plid != blkg->plid)
continue;
blkiop->ops.blkio_unlink_group_fn(key, blkg);
}
spin_unlock(&blkio_list_lock);
} while (1);
list_for_each_entry_safe(pn, pntmp, &blkcg->policy_list, node) {
blkio_policy_delete_node(pn);
kfree(pn);
}
free_css_id(&blkio_subsys, &blkcg->css);
rcu_read_unlock();
if (blkcg != &blkio_root_cgroup)
kfree(blkcg);
}
static struct cgroup_subsys_state *
blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
struct blkio_cgroup *blkcg;
struct cgroup *parent = cgroup->parent;
if (!parent) {
blkcg = &blkio_root_cgroup;
goto done;
}
blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
if (!blkcg)
return ERR_PTR(-ENOMEM);
blkcg->weight = BLKIO_WEIGHT_DEFAULT;
done:
spin_lock_init(&blkcg->lock);
INIT_HLIST_HEAD(&blkcg->blkg_list);
INIT_LIST_HEAD(&blkcg->policy_list);
return &blkcg->css;
}
/*
* We cannot support shared io contexts, as we have no mean to support
* two tasks with the same ioc in two different groups without major rework
* of the main cic data structures. For now we allow a task to change
* its cgroup only if it's the only owner of its ioc.
*/
static int blkiocg_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
struct cgroup_taskset *tset)
{
struct task_struct *task;
struct io_context *ioc;
int ret = 0;
/* task_lock() is needed to avoid races with exit_io_context() */
cgroup_taskset_for_each(task, cgrp, tset) {
task_lock(task);
ioc = task->io_context;
if (ioc && atomic_read(&ioc->nr_tasks) > 1)
ret = -EINVAL;
task_unlock(task);
if (ret)
break;
}
return ret;
}
static void blkiocg_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
struct cgroup_taskset *tset)
{
struct task_struct *task;
struct io_context *ioc;
cgroup_taskset_for_each(task, cgrp, tset) {
/* we don't lose anything even if ioc allocation fails */
ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
if (ioc) {
ioc_cgroup_changed(ioc);
put_io_context(ioc, NULL);
}
}
}
void blkio_policy_register(struct blkio_policy_type *blkiop)
{
spin_lock(&blkio_list_lock);
list_add_tail(&blkiop->list, &blkio_list);
spin_unlock(&blkio_list_lock);
}
EXPORT_SYMBOL_GPL(blkio_policy_register);
void blkio_policy_unregister(struct blkio_policy_type *blkiop)
{
spin_lock(&blkio_list_lock);
list_del_init(&blkiop->list);
spin_unlock(&blkio_list_lock);
}
EXPORT_SYMBOL_GPL(blkio_policy_unregister);
static int __init init_cgroup_blkio(void)
{
return cgroup_load_subsys(&blkio_subsys);
}
static void __exit exit_cgroup_blkio(void)
{
cgroup_unload_subsys(&blkio_subsys);
}
module_init(init_cgroup_blkio);
module_exit(exit_cgroup_blkio);
MODULE_LICENSE("GPL");