Files
linux-stable-mirror/include/linux/delayacct.h
T
Wang Yaxin 658eb5ab91 delayacct: add delay max to record delay peak
Introduce the use cases of delay max, which can help quickly detect
potential abnormal delays in the system and record the types and specific
details of delay spikes.

Problem
========
Delay accounting can track the average delay of processes to show
system workload. However, when a process experiences a significant
delay, maybe a delay spike, which adversely affects performance,
getdelays can only display the average system delay over a period
of time. Yet, average delay is unhelpful for diagnosing delay peak.
It is not even possible to determine which type of delay has spiked,
as this information might be masked by the average delay.

Solution
=========
the 'delay max' can display delay peak since the system's startup,
which can record potential abnormal delays over time, including
the type of delay and the maximum delay. This is helpful for
quickly identifying crash caused by delay.

Use case
=========
bash# ./getdelays -d -p 244
print delayacct stats ON
PID     244

CPU             count     real total  virtual total    delay total  delay average      delay max
                   68      192000000      213676651         705643          0.010ms     0.306381ms
IO              count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms
SWAP            count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms
RECLAIM         count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms
THRASHING       count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms
COMPACT         count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms
WPCOPY          count    delay total  delay average      delay max
                  235       15648284          0.067ms     0.263842ms
IRQ             count    delay total  delay average      delay max
                    0              0          0.000ms     0.000000ms

[wang.yaxin@zte.com.cn: update docs and fix some spelling errors]
  Link: https://lkml.kernel.org/r/20241213192700771XKZ8H30OtHSeziGqRVMs0@zte.com.cn
Link: https://lkml.kernel.org/r/20241203164848805CS62CQPQWG9GLdQj2_BxS@zte.com.cn
Co-developed-by: Wang Yong <wang.yong12@zte.com.cn>
Signed-off-by: Wang Yong <wang.yong12@zte.com.cn>
Co-developed-by: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: xu xin <xu.xin16@zte.com.cn>
Co-developed-by: Wang Yaxin <wang.yaxin@zte.com.cn>
Signed-off-by: Wang Yaxin <wang.yaxin@zte.com.cn>
Signed-off-by: Kun Jiang <jiang.kun2@zte.com.cn>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Fan Yu <fan.yu9@zte.com.cn>
Cc: Peilin He <he.peilin@zte.com.cn>
Cc: tuqiang <tu.qiang35@zte.com.cn>
Cc: Yang Yang <yang.yang29@zte.com.cn>
Cc: ye xingchen <ye.xingchen@zte.com.cn>
Cc: Yunkai Zhang <zhang.yunkai@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2025-01-12 20:20:59 -08:00

282 lines
6.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
/* delayacct.h - per-task delay accounting
*
* Copyright (C) Shailabh Nagar, IBM Corp. 2006
*/
#ifndef _LINUX_DELAYACCT_H
#define _LINUX_DELAYACCT_H
#include <uapi/linux/taskstats.h>
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info {
raw_spinlock_t lock;
/* 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;
u64 blkio_delay_max;
u64 blkio_delay; /* wait for sync block io completion */
u64 swapin_start;
u64 swapin_delay_max;
u64 swapin_delay; /* wait for swapin */
u32 blkio_count; /* total count of the number of sync block */
/* io operations performed */
u32 swapin_count; /* total count of swapin */
u64 freepages_start;
u64 freepages_delay_max;
u64 freepages_delay; /* wait for memory reclaim */
u64 thrashing_start;
u64 thrashing_delay_max;
u64 thrashing_delay; /* wait for thrashing page */
u64 compact_start;
u64 compact_delay_max;
u64 compact_delay; /* wait for memory compact */
u64 wpcopy_start;
u64 wpcopy_delay_max;
u64 wpcopy_delay; /* wait for write-protect copy */
u64 irq_delay_max;
u64 irq_delay; /* wait for IRQ/SOFTIRQ */
u32 freepages_count; /* total count of memory reclaim */
u32 thrashing_count; /* total count of thrash waits */
u32 compact_count; /* total count of memory compact */
u32 wpcopy_count; /* total count of write-protect copy */
u32 irq_count; /* total count of IRQ/SOFTIRQ */
};
#endif
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/jump_label.h>
#ifdef CONFIG_TASK_DELAY_ACCT
DECLARE_STATIC_KEY_FALSE(delayacct_key);
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);
extern void __delayacct_thrashing_start(bool *in_thrashing);
extern void __delayacct_thrashing_end(bool *in_thrashing);
extern void __delayacct_swapin_start(void);
extern void __delayacct_swapin_end(void);
extern void __delayacct_compact_start(void);
extern void __delayacct_compact_end(void);
extern void __delayacct_wpcopy_start(void);
extern void __delayacct_wpcopy_end(void);
extern void __delayacct_irq(struct task_struct *task, u32 delta);
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)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_blkio_start();
}
static inline void delayacct_blkio_end(struct task_struct *p)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (p->delays)
__delayacct_blkio_end(p);
}
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 (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_freepages_start();
}
static inline void delayacct_freepages_end(void)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_freepages_end();
}
static inline void delayacct_thrashing_start(bool *in_thrashing)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_thrashing_start(in_thrashing);
}
static inline void delayacct_thrashing_end(bool *in_thrashing)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_thrashing_end(in_thrashing);
}
static inline void delayacct_swapin_start(void)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_swapin_start();
}
static inline void delayacct_swapin_end(void)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_swapin_end();
}
static inline void delayacct_compact_start(void)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_compact_start();
}
static inline void delayacct_compact_end(void)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_compact_end();
}
static inline void delayacct_wpcopy_start(void)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_wpcopy_start();
}
static inline void delayacct_wpcopy_end(void)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (current->delays)
__delayacct_wpcopy_end();
}
static inline void delayacct_irq(struct task_struct *task, u32 delta)
{
if (!static_branch_unlikely(&delayacct_key))
return;
if (task->delays)
__delayacct_irq(task, delta);
}
#else
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)
{}
static inline void delayacct_thrashing_start(bool *in_thrashing)
{}
static inline void delayacct_thrashing_end(bool *in_thrashing)
{}
static inline void delayacct_swapin_start(void)
{}
static inline void delayacct_swapin_end(void)
{}
static inline void delayacct_compact_start(void)
{}
static inline void delayacct_compact_end(void)
{}
static inline void delayacct_wpcopy_start(void)
{}
static inline void delayacct_wpcopy_end(void)
{}
static inline void delayacct_irq(struct task_struct *task, u32 delta)
{}
#endif /* CONFIG_TASK_DELAY_ACCT */
#endif