Re: [patch 2/3 v3] oom: avoid killing a task if a thread sharing its mm cannot be killed

[KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>]

> 
> The oom killer's goal is to kill a memory-hogging task so that it may
> exit, free its memory, and allow the current context to allocate the
> memory that triggered it in the first place.  Thus, killing a task is
> pointless if other threads sharing its mm cannot be killed because of its
> /proc/pid/oom_adj or /proc/pid/oom_score_adj value.
> 
> This patch checks whether any other thread sharing p->mm has an
> oom_score_adj of OOM_SCORE_ADJ_MIN.  If so, the thread cannot be killed
> and oom_badness(p) returns 0, meaning it's unkillable.
> 
> Signed-off-by: David Rientjes <rientjes@google.com>
> ---
>  mm/oom_kill.c |    9 +++++----
>  1 files changed, 5 insertions(+), 4 deletions(-)
> 
> diff --git a/mm/oom_kill.c b/mm/oom_kill.c
> --- a/mm/oom_kill.c
> +++ b/mm/oom_kill.c
> @@ -162,10 +162,11 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
>  		return 0;
>  
>  	/*
> -	 * Shortcut check for OOM_SCORE_ADJ_MIN so the entire heuristic doesn't
> -	 * need to be executed for something that cannot be killed.
> +	 * Shortcut check for a thread sharing p->mm that is OOM_SCORE_ADJ_MIN
> +	 * so the entire heuristic doesn't need to be executed for something
> +	 * that cannot be killed.
>  	 */
> -	if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
> +	if (atomic_read(&p->mm->oom_disable_count)) {
>  		task_unlock(p);
>  		return 0;
>  	}
> @@ -675,7 +676,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
>  	read_lock(&tasklist_lock);
>  	if (sysctl_oom_kill_allocating_task &&
>  	    !oom_unkillable_task(current, NULL, nodemask) &&
> -	    (current->signal->oom_adj != OOM_DISABLE)) {
> +	    current->mm && !atomic_read(&current->mm->oom_disable_count)) {
>  		/*
>  		 * oom_kill_process() needs tasklist_lock held.  If it returns
>  		 * non-zero, current could not be killed so we must fallback to

This seems significantly cleaner than previous. Of cource, even though I need 
to review [1/3] carefully. Unfortunatelly I'm very busy in this week, then
my responce might late a while. but it's not mean silinetly nak.

Thanks.



--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>