873b477177
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>
181 lines
4.7 KiB
C
181 lines
4.7 KiB
C
/* 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/slab.h>
|
|
#include <linux/time.h>
|
|
#include <linux/sysctl.h>
|
|
#include <linux/delayacct.h>
|
|
|
|
int delayacct_on __read_mostly = 1; /* Delay accounting turned on/off */
|
|
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)
|
|
{
|
|
delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC);
|
|
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);
|
|
}
|
|
|
|
/*
|
|
* Start accounting for a delay statistic using
|
|
* its starting timestamp (@start)
|
|
*/
|
|
|
|
static inline void delayacct_start(struct timespec *start)
|
|
{
|
|
do_posix_clock_monotonic_gettime(start);
|
|
}
|
|
|
|
/*
|
|
* Finish delay accounting for a statistic using
|
|
* its timestamps (@start, @end), accumalator (@total) and @count
|
|
*/
|
|
|
|
static void delayacct_end(struct timespec *start, struct timespec *end,
|
|
u64 *total, u32 *count)
|
|
{
|
|
struct timespec ts;
|
|
s64 ns;
|
|
unsigned long flags;
|
|
|
|
do_posix_clock_monotonic_gettime(end);
|
|
ts = timespec_sub(*end, *start);
|
|
ns = timespec_to_ns(&ts);
|
|
if (ns < 0)
|
|
return;
|
|
|
|
spin_lock_irqsave(¤t->delays->lock, flags);
|
|
*total += ns;
|
|
(*count)++;
|
|
spin_unlock_irqrestore(¤t->delays->lock, flags);
|
|
}
|
|
|
|
void __delayacct_blkio_start(void)
|
|
{
|
|
delayacct_start(¤t->delays->blkio_start);
|
|
}
|
|
|
|
void __delayacct_blkio_end(void)
|
|
{
|
|
if (current->delays->flags & DELAYACCT_PF_SWAPIN)
|
|
/* Swapin block I/O */
|
|
delayacct_end(¤t->delays->blkio_start,
|
|
¤t->delays->blkio_end,
|
|
¤t->delays->swapin_delay,
|
|
¤t->delays->swapin_count);
|
|
else /* Other block I/O */
|
|
delayacct_end(¤t->delays->blkio_start,
|
|
¤t->delays->blkio_end,
|
|
¤t->delays->blkio_delay,
|
|
¤t->delays->blkio_count);
|
|
}
|
|
|
|
int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
|
|
{
|
|
s64 tmp;
|
|
unsigned long t1;
|
|
unsigned long long t2, t3;
|
|
unsigned long flags;
|
|
struct timespec ts;
|
|
|
|
/* Though tsk->delays accessed later, early exit avoids
|
|
* unnecessary returning of other data
|
|
*/
|
|
if (!tsk->delays)
|
|
goto done;
|
|
|
|
tmp = (s64)d->cpu_run_real_total;
|
|
cputime_to_timespec(tsk->utime + tsk->stime, &ts);
|
|
tmp += timespec_to_ns(&ts);
|
|
d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp;
|
|
|
|
tmp = (s64)d->cpu_scaled_run_real_total;
|
|
cputime_to_timespec(tsk->utimescaled + tsk->stimescaled, &ts);
|
|
tmp += timespec_to_ns(&ts);
|
|
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->sched_info.cpu_time;
|
|
|
|
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;
|
|
d->blkio_count += tsk->delays->blkio_count;
|
|
d->swapin_count += tsk->delays->swapin_count;
|
|
spin_unlock_irqrestore(&tsk->delays->lock, flags);
|
|
|
|
done:
|
|
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;
|
|
}
|
|
|
|
void __delayacct_freepages_start(void)
|
|
{
|
|
delayacct_start(¤t->delays->freepages_start);
|
|
}
|
|
|
|
void __delayacct_freepages_end(void)
|
|
{
|
|
delayacct_end(¤t->delays->freepages_start,
|
|
¤t->delays->freepages_end,
|
|
¤t->delays->freepages_delay,
|
|
¤t->delays->freepages_count);
|
|
}
|
|
|