Re: [PATCH] mm,oom: use per signal_struct flag rather than clear TIF_MEMDIE

[Oleg Nesterov <oleg@redhat.com>]

On 06/27, Michal Hocko wrote:
>
> Yes this is really unfortunate. I am trying to converge to per mm
> behavior as much as possible. We are getting there slowly but not yet
> there.

Yes, agreed, everything should be per-mm.

Say wake_oom_reaper/oom_reap_task. It is simply ugly we pass task_struct
to oom_reap_task(), it should work with mm_struct. Again, this is because
of TIF_MEMDIE/exit_oom_victim.  Except pr_info(), but this is minor...

> So the flag acts
> both as memory reserve access key and the exclusion.

Yes, and this should be separeted imo.

As for memory reserve access, I feel that we should only set this flag
if task == current... but this needs more discussion.

> I am not sure
> setting the flag to all threads in the same thread group would help all
> that much. Processes sharing the mm outside of the thread group should
> behave in a similar way. The general reluctance to give access to all
> threads was to prevent from thundering herd effect which is more likely
> that way.

Agreed, that is why I said it is not that simple.

Oleg.

--
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>