Commit 43d2b113 authored by KAMEZAWA Hiroyuki's avatar KAMEZAWA Hiroyuki Committed by Linus Torvalds
Browse files

tracepoint: add tracepoints for debugging oom_score_adj 



oom_score_adj is used for guarding processes from OOM-Killer.  One of
problem is that it's inherited at fork().  When a daemon set oom_score_adj
and make children, it's hard to know where the value is set.

This patch adds some tracepoints useful for debugging. This patch adds
3 trace points.
  - creating new task
  - renaming a task (exec)
  - set oom_score_adj

To debug, users need to enable some trace pointer. Maybe filtering is useful as

# EVENT=/sys/kernel/debug/tracing/events/task/
# echo "oom_score_adj != 0" > $EVENT/task_newtask/filter
# echo "oom_score_adj != 0" > $EVENT/task_rename/filter
# echo 1 > $EVENT/enable
# EVENT=/sys/kernel/debug/tracing/events/oom/
# echo 1 > $EVENT/enable

output will be like this.
# grep oom /sys/kernel/debug/tracing/trace
bash-7699  [007] d..3  5140.744510: oom_score_adj_update: pid=7699 comm=bash oom_score_adj=-1000
bash-7699  [007] ...1  5151.818022: task_newtask: pid=7729 comm=bash clone_flags=1200011 oom_score_adj=-1000
ls-7729  [003] ...2  5151.818504: task_rename: pid=7729 oldcomm=bash newcomm=ls oom_score_adj=-1000
bash-7699  [002] ...1  5175.701468: task_newtask: pid=7730 comm=bash clone_flags=1200011 oom_score_adj=-1000
grep-7730  [007] ...2  5175.701993: task_rename: pid=7730 oldcomm=bash newcomm=grep oom_score_adj=-1000

Signed-off-by: default avatarKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: default avatarDavid Rientjes <rientjes@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 6bd4837d

fs/exec.c

+4 −0
Original line number Diff line number Diff line
@@ -59,6 +59,8 @@ 
#include <asm/uaccess.h>

#include <asm/mmu_context.h>

#include <asm/tlb.h>



#include <trace/events/task.h>

#include "internal.h"



int core_uses_pid;
@@ -1054,6 +1056,8 @@ void set_task_comm(struct task_struct *tsk, char *buf) 
{

	task_lock(tsk);



	trace_task_rename(tsk, buf);



	/*

	 * Threads may access current->comm without holding

	 * the task lock, so write the string carefully.

fs/proc/base.c

+3 −0
Original line number Diff line number Diff line
@@ -86,6 +86,7 @@ 
#ifdef CONFIG_HARDWALL

#include <asm/hardwall.h>

#endif

#include <trace/events/oom.h>

#include "internal.h"



/* NOTE:
@@ -1010,6 +1011,7 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, 
	else

		task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) /

								-OOM_DISABLE;

	trace_oom_score_adj_update(task);

err_sighand:

	unlock_task_sighand(task, &flags);

err_task_lock:
@@ -1097,6 +1099,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, 
	task->signal->oom_score_adj = oom_score_adj;

	if (has_capability_noaudit(current, CAP_SYS_RESOURCE))

		task->signal->oom_score_adj_min = oom_score_adj;

	trace_oom_score_adj_update(task);

	/*

	 * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is

	 * always attainable.

include/trace/events/oom.h

0 → 100644
+33 −0
Original line number Diff line number Diff line 
#undef TRACE_SYSTEM

#define TRACE_SYSTEM oom



#if !defined(_TRACE_OOM_H) || defined(TRACE_HEADER_MULTI_READ)

#define _TRACE_OOM_H

#include <linux/tracepoint.h>



TRACE_EVENT(oom_score_adj_update,



	TP_PROTO(struct task_struct *task),



	TP_ARGS(task),



	TP_STRUCT__entry(

		__field(	pid_t,	pid)

		__array(	char,	comm,	TASK_COMM_LEN )

		__field(	 int,	oom_score_adj)

	),



	TP_fast_assign(

		__entry->pid = task->pid;

		memcpy(__entry->comm, task->comm, TASK_COMM_LEN);

		__entry->oom_score_adj = task->signal->oom_score_adj;

	),



	TP_printk("pid=%d comm=%s oom_score_adj=%d",

		__entry->pid, __entry->comm, __entry->oom_score_adj)

);



#endif



/* This part must be outside protection */

#include <trace/define_trace.h>

include/trace/events/task.h

0 → 100644
+61 −0
Original line number Diff line number Diff line 
#undef TRACE_SYSTEM

#define TRACE_SYSTEM task



#if !defined(_TRACE_TASK_H) || defined(TRACE_HEADER_MULTI_READ)

#define _TRACE_TASK_H

#include <linux/tracepoint.h>



TRACE_EVENT(task_newtask,



	TP_PROTO(struct task_struct *task, unsigned long clone_flags),



	TP_ARGS(task, clone_flags),



	TP_STRUCT__entry(

		__field(	pid_t,	pid)

		__array(	char,	comm, TASK_COMM_LEN)

		__field( unsigned long, clone_flags)

		__field(	int,    oom_score_adj)

	),



	TP_fast_assign(

		__entry->pid = task->pid;

		memcpy(__entry->comm, task->comm, TASK_COMM_LEN);

		__entry->clone_flags = clone_flags;

		__entry->oom_score_adj = task->signal->oom_score_adj;

	),



	TP_printk("pid=%d comm=%s clone_flags=%lx oom_score_adj=%d",

		__entry->pid, __entry->comm,

		__entry->clone_flags, __entry->oom_score_adj)

);



TRACE_EVENT(task_rename,



	TP_PROTO(struct task_struct *task, char *comm),



	TP_ARGS(task, comm),



	TP_STRUCT__entry(

		__field(	pid_t,	pid)

		__array(	char, oldcomm,  TASK_COMM_LEN)

		__array(	char, newcomm,  TASK_COMM_LEN)

		__field(	int, oom_score_adj)

	),



	TP_fast_assign(

		__entry->pid = task->pid;

		memcpy(entry->oldcomm, task->comm, TASK_COMM_LEN);

		memcpy(entry->newcomm, comm, TASK_COMM_LEN);

		__entry->oom_score_adj = task->signal->oom_score_adj;

	),



	TP_printk("pid=%d oldcomm=%s newcomm=%s oom_score_adj=%d",

		__entry->pid, __entry->oldcomm,

		__entry->newcomm, __entry->oom_score_adj)

);



#endif



/* This part must be outside protection */

#include <trace/define_trace.h>

kernel/fork.c

+6 −0
Original line number Diff line number Diff line
@@ -76,6 +76,9 @@ 


#include <trace/events/sched.h>



#define CREATE_TRACE_POINTS

#include <trace/events/task.h>



/*

 * Protected counters by write_lock_irq(&tasklist_lock)

 */
@@ -1370,6 +1373,9 @@ static struct task_struct *copy_process(unsigned long clone_flags, 
	if (clone_flags & CLONE_THREAD)

		threadgroup_change_end(current);

	perf_event_fork(p);



	trace_task_newtask(p, clone_flags);



	return p;



bad_fork_free_pid:

CRA Git | Maintained and supported by SUSTech CRA and CCSE