linux_dsm_epyc7002/kernel/delayacct.c

171 lines
4.6 KiB
C
Raw Normal View History

/* delayacct.c - per-task delay accounting
*
* Copyright (C) Shailabh Nagar, IBM Corp. 2006
*
* 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 would 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.
*/
#include <linux/sched.h>
#include <linux/sched/task.h>
#include <linux/sched/cputime.h>
#include <linux/slab.h>
#include <linux/taskstats.h>
#include <linux/time.h>
#include <linux/sysctl.h>
#include <linux/delayacct.h>
#include <linux/module.h>
int delayacct_on __read_mostly = 1; /* Delay accounting turned on/off */
EXPORT_SYMBOL_GPL(delayacct_on);
struct kmem_cache *delayacct_cache;
static int __init delayacct_setup_disable(char *str)
{
delayacct_on = 0;
return 1;
}
__setup("nodelayacct", delayacct_setup_disable);
void delayacct_init(void)
{
2016-01-15 06:18:21 +07:00
delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC|SLAB_ACCOUNT);
delayacct_tsk_init(&init_task);
}
void __delayacct_tsk_init(struct task_struct *tsk)
{
tsk->delays = kmem_cache_zalloc(delayacct_cache, GFP_KERNEL);
if (tsk->delays)
spin_lock_init(&tsk->delays->lock);
}
/*
* Finish delay accounting for a statistic using its timestamps (@start),
* accumalator (@total) and @count
*/
delayacct: Account blkio completion on the correct task Before commit: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") delayacct_blkio_end() was called after context-switching into the task which completed I/O. This resulted in double counting: the task would account a delay both waiting for I/O and for time spent in the runqueue. With e33a9bba85a8, delayacct_blkio_end() is called by try_to_wake_up(). In ttwu, we have not yet context-switched. This is more correct, in that the delay accounting ends when the I/O is complete. But delayacct_blkio_end() relies on 'get_current()', and we have not yet context-switched into the task whose I/O completed. This results in the wrong task having its delay accounting statistics updated. Instead of doing that, pass the task_struct being woken to delayacct_blkio_end(), so that it can update the statistics of the correct task. Signed-off-by: Josh Snyder <joshs@netflix.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Balbir Singh <bsingharora@gmail.com> Cc: <stable@vger.kernel.org> Cc: Brendan Gregg <bgregg@netflix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-block@vger.kernel.org Fixes: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") Link: http://lkml.kernel.org/r/1513613712-571-1-git-send-email-joshs@netflix.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-18 23:15:10 +07:00
static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count)
{
s64 ns = ktime_get_ns() - *start;
unsigned long flags;
if (ns > 0) {
delayacct: Account blkio completion on the correct task Before commit: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") delayacct_blkio_end() was called after context-switching into the task which completed I/O. This resulted in double counting: the task would account a delay both waiting for I/O and for time spent in the runqueue. With e33a9bba85a8, delayacct_blkio_end() is called by try_to_wake_up(). In ttwu, we have not yet context-switched. This is more correct, in that the delay accounting ends when the I/O is complete. But delayacct_blkio_end() relies on 'get_current()', and we have not yet context-switched into the task whose I/O completed. This results in the wrong task having its delay accounting statistics updated. Instead of doing that, pass the task_struct being woken to delayacct_blkio_end(), so that it can update the statistics of the correct task. Signed-off-by: Josh Snyder <joshs@netflix.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Balbir Singh <bsingharora@gmail.com> Cc: <stable@vger.kernel.org> Cc: Brendan Gregg <bgregg@netflix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-block@vger.kernel.org Fixes: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") Link: http://lkml.kernel.org/r/1513613712-571-1-git-send-email-joshs@netflix.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-18 23:15:10 +07:00
spin_lock_irqsave(lock, flags);
*total += ns;
(*count)++;
delayacct: Account blkio completion on the correct task Before commit: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") delayacct_blkio_end() was called after context-switching into the task which completed I/O. This resulted in double counting: the task would account a delay both waiting for I/O and for time spent in the runqueue. With e33a9bba85a8, delayacct_blkio_end() is called by try_to_wake_up(). In ttwu, we have not yet context-switched. This is more correct, in that the delay accounting ends when the I/O is complete. But delayacct_blkio_end() relies on 'get_current()', and we have not yet context-switched into the task whose I/O completed. This results in the wrong task having its delay accounting statistics updated. Instead of doing that, pass the task_struct being woken to delayacct_blkio_end(), so that it can update the statistics of the correct task. Signed-off-by: Josh Snyder <joshs@netflix.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Balbir Singh <bsingharora@gmail.com> Cc: <stable@vger.kernel.org> Cc: Brendan Gregg <bgregg@netflix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-block@vger.kernel.org Fixes: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") Link: http://lkml.kernel.org/r/1513613712-571-1-git-send-email-joshs@netflix.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-18 23:15:10 +07:00
spin_unlock_irqrestore(lock, flags);
}
}
void __delayacct_blkio_start(void)
{
current->delays->blkio_start = ktime_get_ns();
}
delayacct: Account blkio completion on the correct task Before commit: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") delayacct_blkio_end() was called after context-switching into the task which completed I/O. This resulted in double counting: the task would account a delay both waiting for I/O and for time spent in the runqueue. With e33a9bba85a8, delayacct_blkio_end() is called by try_to_wake_up(). In ttwu, we have not yet context-switched. This is more correct, in that the delay accounting ends when the I/O is complete. But delayacct_blkio_end() relies on 'get_current()', and we have not yet context-switched into the task whose I/O completed. This results in the wrong task having its delay accounting statistics updated. Instead of doing that, pass the task_struct being woken to delayacct_blkio_end(), so that it can update the statistics of the correct task. Signed-off-by: Josh Snyder <joshs@netflix.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Balbir Singh <bsingharora@gmail.com> Cc: <stable@vger.kernel.org> Cc: Brendan Gregg <bgregg@netflix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-block@vger.kernel.org Fixes: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") Link: http://lkml.kernel.org/r/1513613712-571-1-git-send-email-joshs@netflix.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-18 23:15:10 +07:00
/*
* We cannot rely on the `current` macro, as we haven't yet switched back to
* the process being woken.
*/
void __delayacct_blkio_end(struct task_struct *p)
{
delayacct: Account blkio completion on the correct task Before commit: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") delayacct_blkio_end() was called after context-switching into the task which completed I/O. This resulted in double counting: the task would account a delay both waiting for I/O and for time spent in the runqueue. With e33a9bba85a8, delayacct_blkio_end() is called by try_to_wake_up(). In ttwu, we have not yet context-switched. This is more correct, in that the delay accounting ends when the I/O is complete. But delayacct_blkio_end() relies on 'get_current()', and we have not yet context-switched into the task whose I/O completed. This results in the wrong task having its delay accounting statistics updated. Instead of doing that, pass the task_struct being woken to delayacct_blkio_end(), so that it can update the statistics of the correct task. Signed-off-by: Josh Snyder <joshs@netflix.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Balbir Singh <bsingharora@gmail.com> Cc: <stable@vger.kernel.org> Cc: Brendan Gregg <bgregg@netflix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-block@vger.kernel.org Fixes: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") Link: http://lkml.kernel.org/r/1513613712-571-1-git-send-email-joshs@netflix.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-18 23:15:10 +07:00
struct task_delay_info *delays = p->delays;
u64 *total;
u32 *count;
if (p->delays->flags & DELAYACCT_PF_SWAPIN) {
total = &delays->swapin_delay;
count = &delays->swapin_count;
} else {
total = &delays->blkio_delay;
count = &delays->blkio_count;
}
delayacct_end(&delays->lock, &delays->blkio_start, total, count);
}
int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
{
u64 utime, stime, stimescaled, utimescaled;
unsigned long long t2, t3;
unsigned long flags, t1;
s64 tmp;
task_cputime(tsk, &utime, &stime);
tmp = (s64)d->cpu_run_real_total;
tmp += utime + stime;
d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp;
task_cputime_scaled(tsk, &utimescaled, &stimescaled);
tmp = (s64)d->cpu_scaled_run_real_total;
tmp += utimescaled + stimescaled;
d->cpu_scaled_run_real_total =
(tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp;
/*
* No locking available for sched_info (and too expensive to add one)
* Mitigate by taking snapshot of values
*/
t1 = tsk->sched_info.pcount;
t2 = tsk->sched_info.run_delay;
t3 = tsk->se.sum_exec_runtime;
d->cpu_count += t1;
tmp = (s64)d->cpu_delay_total + t2;
d->cpu_delay_total = (tmp < (s64)d->cpu_delay_total) ? 0 : tmp;
tmp = (s64)d->cpu_run_virtual_total + t3;
d->cpu_run_virtual_total =
(tmp < (s64)d->cpu_run_virtual_total) ? 0 : tmp;
/* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */
spin_lock_irqsave(&tsk->delays->lock, flags);
tmp = d->blkio_delay_total + tsk->delays->blkio_delay;
d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
d->blkio_count += tsk->delays->blkio_count;
d->swapin_count += tsk->delays->swapin_count;
d->freepages_count += tsk->delays->freepages_count;
spin_unlock_irqrestore(&tsk->delays->lock, flags);
return 0;
}
__u64 __delayacct_blkio_ticks(struct task_struct *tsk)
{
__u64 ret;
unsigned long flags;
spin_lock_irqsave(&tsk->delays->lock, flags);
ret = nsec_to_clock_t(tsk->delays->blkio_delay +
tsk->delays->swapin_delay);
spin_unlock_irqrestore(&tsk->delays->lock, flags);
return ret;
}
per-task-delay-accounting: add memory reclaim delay Sometimes, application responses become bad under heavy memory load. Applications take a bit time to reclaim memory. The statistics, how long memory reclaim takes, will be useful to measure memory usage. This patch adds accounting memory reclaim to per-task-delay-accounting for accounting the time of do_try_to_free_pages(). <i.e> - When System is under low memory load, memory reclaim may not occur. $ free total used free shared buffers cached Mem: 8197800 1577300 6620500 0 4808 1516724 -/+ buffers/cache: 55768 8142032 Swap: 16386292 0 16386292 $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 0 5069748 10612 3014060 0 0 0 0 3 26 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 4 22 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 3 18 0 0 100 0 Measure the time of tar command. $ ls -s test.dat 1501472 test.dat $ time tar cvf test.tar test.dat real 0m13.388s user 0m0.116s sys 0m5.304s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 428 5528345500 5477116080 62749891 IO count delay total 338 8078977189 SWAP count delay total 0 0 RECLAIM count delay total 0 0 - When system is under heavy memory load memory reclaim may occur. $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 7159032 49724 1812 3012 0 0 0 0 3 24 0 0 100 0 0 0 7159032 49724 1812 3012 0 0 0 0 4 24 0 0 100 0 0 0 7159032 49848 1812 3012 0 0 0 0 3 22 0 0 100 0 In this case, one process uses more 8G memory by execution of malloc() and memset(). $ time tar cvf test.tar test.dat real 1m38.563s <- increased by 85 sec user 0m0.140s sys 0m7.060s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 9021 7140446250 7315277975 923201824 IO count delay total 8965 90466349669 SWAP count delay total 3 21036367 RECLAIM count delay total 740 61011951153 In the later case, the value of RECLAIM is increasing. So, taskstats can show how much memory reclaim influences TAT. Signed-off-by: Keika Kobayashi <kobayashi.kk@ncos.nec.co.jp> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujistu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 15:48:52 +07:00
void __delayacct_freepages_start(void)
{
current->delays->freepages_start = ktime_get_ns();
per-task-delay-accounting: add memory reclaim delay Sometimes, application responses become bad under heavy memory load. Applications take a bit time to reclaim memory. The statistics, how long memory reclaim takes, will be useful to measure memory usage. This patch adds accounting memory reclaim to per-task-delay-accounting for accounting the time of do_try_to_free_pages(). <i.e> - When System is under low memory load, memory reclaim may not occur. $ free total used free shared buffers cached Mem: 8197800 1577300 6620500 0 4808 1516724 -/+ buffers/cache: 55768 8142032 Swap: 16386292 0 16386292 $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 0 5069748 10612 3014060 0 0 0 0 3 26 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 4 22 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 3 18 0 0 100 0 Measure the time of tar command. $ ls -s test.dat 1501472 test.dat $ time tar cvf test.tar test.dat real 0m13.388s user 0m0.116s sys 0m5.304s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 428 5528345500 5477116080 62749891 IO count delay total 338 8078977189 SWAP count delay total 0 0 RECLAIM count delay total 0 0 - When system is under heavy memory load memory reclaim may occur. $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 7159032 49724 1812 3012 0 0 0 0 3 24 0 0 100 0 0 0 7159032 49724 1812 3012 0 0 0 0 4 24 0 0 100 0 0 0 7159032 49848 1812 3012 0 0 0 0 3 22 0 0 100 0 In this case, one process uses more 8G memory by execution of malloc() and memset(). $ time tar cvf test.tar test.dat real 1m38.563s <- increased by 85 sec user 0m0.140s sys 0m7.060s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 9021 7140446250 7315277975 923201824 IO count delay total 8965 90466349669 SWAP count delay total 3 21036367 RECLAIM count delay total 740 61011951153 In the later case, the value of RECLAIM is increasing. So, taskstats can show how much memory reclaim influences TAT. Signed-off-by: Keika Kobayashi <kobayashi.kk@ncos.nec.co.jp> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujistu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 15:48:52 +07:00
}
void __delayacct_freepages_end(void)
{
delayacct: Account blkio completion on the correct task Before commit: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") delayacct_blkio_end() was called after context-switching into the task which completed I/O. This resulted in double counting: the task would account a delay both waiting for I/O and for time spent in the runqueue. With e33a9bba85a8, delayacct_blkio_end() is called by try_to_wake_up(). In ttwu, we have not yet context-switched. This is more correct, in that the delay accounting ends when the I/O is complete. But delayacct_blkio_end() relies on 'get_current()', and we have not yet context-switched into the task whose I/O completed. This results in the wrong task having its delay accounting statistics updated. Instead of doing that, pass the task_struct being woken to delayacct_blkio_end(), so that it can update the statistics of the correct task. Signed-off-by: Josh Snyder <joshs@netflix.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Balbir Singh <bsingharora@gmail.com> Cc: <stable@vger.kernel.org> Cc: Brendan Gregg <bgregg@netflix.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-block@vger.kernel.org Fixes: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") Link: http://lkml.kernel.org/r/1513613712-571-1-git-send-email-joshs@netflix.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-12-18 23:15:10 +07:00
delayacct_end(
&current->delays->lock,
&current->delays->freepages_start,
&current->delays->freepages_delay,
&current->delays->freepages_count);
per-task-delay-accounting: add memory reclaim delay Sometimes, application responses become bad under heavy memory load. Applications take a bit time to reclaim memory. The statistics, how long memory reclaim takes, will be useful to measure memory usage. This patch adds accounting memory reclaim to per-task-delay-accounting for accounting the time of do_try_to_free_pages(). <i.e> - When System is under low memory load, memory reclaim may not occur. $ free total used free shared buffers cached Mem: 8197800 1577300 6620500 0 4808 1516724 -/+ buffers/cache: 55768 8142032 Swap: 16386292 0 16386292 $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 0 5069748 10612 3014060 0 0 0 0 3 26 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 4 22 0 0 100 0 0 0 0 5069748 10612 3014060 0 0 0 0 3 18 0 0 100 0 Measure the time of tar command. $ ls -s test.dat 1501472 test.dat $ time tar cvf test.tar test.dat real 0m13.388s user 0m0.116s sys 0m5.304s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 428 5528345500 5477116080 62749891 IO count delay total 338 8078977189 SWAP count delay total 0 0 RECLAIM count delay total 0 0 - When system is under heavy memory load memory reclaim may occur. $ vmstat 1 procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 7159032 49724 1812 3012 0 0 0 0 3 24 0 0 100 0 0 0 7159032 49724 1812 3012 0 0 0 0 4 24 0 0 100 0 0 0 7159032 49848 1812 3012 0 0 0 0 3 22 0 0 100 0 In this case, one process uses more 8G memory by execution of malloc() and memset(). $ time tar cvf test.tar test.dat real 1m38.563s <- increased by 85 sec user 0m0.140s sys 0m7.060s $ ./delayget -d -p <pid> CPU count real total virtual total delay total 9021 7140446250 7315277975 923201824 IO count delay total 8965 90466349669 SWAP count delay total 3 21036367 RECLAIM count delay total 740 61011951153 In the later case, the value of RECLAIM is increasing. So, taskstats can show how much memory reclaim influences TAT. Signed-off-by: Keika Kobayashi <kobayashi.kk@ncos.nec.co.jp> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujistu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 15:48:52 +07:00
}