Re: [PATCH] ipc: remove memcg accounting for sops objects in do_semtimedop()

[Michal Hocko <mhocko@suse.com>]

On Sat 11-09-21 10:40:08, Vasily Averin wrote:
> Linus proposes to revert an accounting for sops objects in
> do_semtimedop() because it's really just a temporary buffer
> for a single semtimedop() system call.
> 
> This object can consume up to 2 pages, syscall is sleeping one,
> size and duration can be controlled by user, and this allocation
> can be repeated by many thread at the same time.

Is there any upper bound or is it just bounded by the number of
tasks/threads (that can be controlled by pid controller at least)?

> However Shakeel Butt pointed that there are much more popular objects
> with the same life time and similar memory consumption, the accounting
> of which was decided to be rejected for performance reasons.

Is there any measurable performance impact in this particular case?
 
> In addition, any usual task consumes much more accounted memory,
> so 2 pages of this temporal buffer can be safely ignored.
> 
> Link: https://patchwork.kernel.org/project/linux-fsdevel/patch/20171005222144.123797-1-shakeelb@google.com/
> 
> Fixes: 18319498fdd4 ("memcg: enable accounting of ipc resources")
> Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
> ---
>  ipc/sem.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/ipc/sem.c b/ipc/sem.c
> index f833238df1ce..6693daf4fe11 100644
> --- a/ipc/sem.c
> +++ b/ipc/sem.c
> @@ -2238,7 +2238,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops,
>  		return -EINVAL;
>  
>  	if (nsops > SEMOPM_FAST) {
> -		sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL_ACCOUNT);
> +		sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL);
>  		if (sops == NULL)
>  			return -ENOMEM;
>  	}
> -- 
> 2.25.1

-- 
Michal Hocko
SUSE Labs