c96f5471ce
Before commit:e33a9bba85
("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. Withe33a9bba85
, 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:e33a9bba85
("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>
188 lines
5.2 KiB
C
188 lines
5.2 KiB
C
/* delayacct.h - 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 will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
|
|
* the GNU General Public License for more details.
|
|
*
|
|
*/
|
|
|
|
#ifndef _LINUX_DELAYACCT_H
|
|
#define _LINUX_DELAYACCT_H
|
|
|
|
#include <uapi/linux/taskstats.h>
|
|
|
|
/*
|
|
* Per-task flags relevant to delay accounting
|
|
* maintained privately to avoid exhausting similar flags in sched.h:PF_*
|
|
* Used to set current->delays->flags
|
|
*/
|
|
#define DELAYACCT_PF_SWAPIN 0x00000001 /* I am doing a swapin */
|
|
#define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */
|
|
|
|
#ifdef CONFIG_TASK_DELAY_ACCT
|
|
struct task_delay_info {
|
|
spinlock_t lock;
|
|
unsigned int flags; /* Private per-task flags */
|
|
|
|
/* For each stat XXX, add following, aligned appropriately
|
|
*
|
|
* struct timespec XXX_start, XXX_end;
|
|
* u64 XXX_delay;
|
|
* u32 XXX_count;
|
|
*
|
|
* Atomicity of updates to XXX_delay, XXX_count protected by
|
|
* single lock above (split into XXX_lock if contention is an issue).
|
|
*/
|
|
|
|
/*
|
|
* XXX_count is incremented on every XXX operation, the delay
|
|
* associated with the operation is added to XXX_delay.
|
|
* XXX_delay contains the accumulated delay time in nanoseconds.
|
|
*/
|
|
u64 blkio_start; /* Shared by blkio, swapin */
|
|
u64 blkio_delay; /* wait for sync block io completion */
|
|
u64 swapin_delay; /* wait for swapin block io completion */
|
|
u32 blkio_count; /* total count of the number of sync block */
|
|
/* io operations performed */
|
|
u32 swapin_count; /* total count of the number of swapin block */
|
|
/* io operations performed */
|
|
|
|
u64 freepages_start;
|
|
u64 freepages_delay; /* wait for memory reclaim */
|
|
u32 freepages_count; /* total count of memory reclaim */
|
|
};
|
|
#endif
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/slab.h>
|
|
|
|
#ifdef CONFIG_TASK_DELAY_ACCT
|
|
extern int delayacct_on; /* Delay accounting turned on/off */
|
|
extern struct kmem_cache *delayacct_cache;
|
|
extern void delayacct_init(void);
|
|
extern void __delayacct_tsk_init(struct task_struct *);
|
|
extern void __delayacct_tsk_exit(struct task_struct *);
|
|
extern void __delayacct_blkio_start(void);
|
|
extern void __delayacct_blkio_end(struct task_struct *);
|
|
extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *);
|
|
extern __u64 __delayacct_blkio_ticks(struct task_struct *);
|
|
extern void __delayacct_freepages_start(void);
|
|
extern void __delayacct_freepages_end(void);
|
|
|
|
static inline int delayacct_is_task_waiting_on_io(struct task_struct *p)
|
|
{
|
|
if (p->delays)
|
|
return (p->delays->flags & DELAYACCT_PF_BLKIO);
|
|
else
|
|
return 0;
|
|
}
|
|
|
|
static inline void delayacct_set_flag(int flag)
|
|
{
|
|
if (current->delays)
|
|
current->delays->flags |= flag;
|
|
}
|
|
|
|
static inline void delayacct_clear_flag(int flag)
|
|
{
|
|
if (current->delays)
|
|
current->delays->flags &= ~flag;
|
|
}
|
|
|
|
static inline void delayacct_tsk_init(struct task_struct *tsk)
|
|
{
|
|
/* reinitialize in case parent's non-null pointer was dup'ed*/
|
|
tsk->delays = NULL;
|
|
if (delayacct_on)
|
|
__delayacct_tsk_init(tsk);
|
|
}
|
|
|
|
/* Free tsk->delays. Called from bad fork and __put_task_struct
|
|
* where there's no risk of tsk->delays being accessed elsewhere
|
|
*/
|
|
static inline void delayacct_tsk_free(struct task_struct *tsk)
|
|
{
|
|
if (tsk->delays)
|
|
kmem_cache_free(delayacct_cache, tsk->delays);
|
|
tsk->delays = NULL;
|
|
}
|
|
|
|
static inline void delayacct_blkio_start(void)
|
|
{
|
|
delayacct_set_flag(DELAYACCT_PF_BLKIO);
|
|
if (current->delays)
|
|
__delayacct_blkio_start();
|
|
}
|
|
|
|
static inline void delayacct_blkio_end(struct task_struct *p)
|
|
{
|
|
if (current->delays)
|
|
__delayacct_blkio_end(p);
|
|
delayacct_clear_flag(DELAYACCT_PF_BLKIO);
|
|
}
|
|
|
|
static inline int delayacct_add_tsk(struct taskstats *d,
|
|
struct task_struct *tsk)
|
|
{
|
|
if (!delayacct_on || !tsk->delays)
|
|
return 0;
|
|
return __delayacct_add_tsk(d, tsk);
|
|
}
|
|
|
|
static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk)
|
|
{
|
|
if (tsk->delays)
|
|
return __delayacct_blkio_ticks(tsk);
|
|
return 0;
|
|
}
|
|
|
|
static inline void delayacct_freepages_start(void)
|
|
{
|
|
if (current->delays)
|
|
__delayacct_freepages_start();
|
|
}
|
|
|
|
static inline void delayacct_freepages_end(void)
|
|
{
|
|
if (current->delays)
|
|
__delayacct_freepages_end();
|
|
}
|
|
|
|
#else
|
|
static inline void delayacct_set_flag(int flag)
|
|
{}
|
|
static inline void delayacct_clear_flag(int flag)
|
|
{}
|
|
static inline void delayacct_init(void)
|
|
{}
|
|
static inline void delayacct_tsk_init(struct task_struct *tsk)
|
|
{}
|
|
static inline void delayacct_tsk_free(struct task_struct *tsk)
|
|
{}
|
|
static inline void delayacct_blkio_start(void)
|
|
{}
|
|
static inline void delayacct_blkio_end(struct task_struct *p)
|
|
{}
|
|
static inline int delayacct_add_tsk(struct taskstats *d,
|
|
struct task_struct *tsk)
|
|
{ return 0; }
|
|
static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk)
|
|
{ return 0; }
|
|
static inline int delayacct_is_task_waiting_on_io(struct task_struct *p)
|
|
{ return 0; }
|
|
static inline void delayacct_freepages_start(void)
|
|
{}
|
|
static inline void delayacct_freepages_end(void)
|
|
{}
|
|
|
|
#endif /* CONFIG_TASK_DELAY_ACCT */
|
|
|
|
#endif
|