Re: [PATCH 1/2] mm, oom: introduce oom reaper

[Michal Hocko <mhocko@kernel.org>]

On Thu 17-12-15 13:13:56, Andrew Morton wrote:
[...]
> Also, re-reading your description:
> 
> : It has been shown (e.g.  by Tetsuo Handa) that it is not that hard to
> : construct workloads which break the core assumption mentioned above and
> : the OOM victim might take unbounded amount of time to exit because it
> : might be blocked in the uninterruptible state waiting for on an event
> : (e.g.  lock) which is blocked by another task looping in the page
> : allocator.
> 
> So the allocating task has done an oom-kill and is waiting for memory
> to become available.  The killed task is stuck on some lock, unable to
> free memory.
> 
> But the problematic lock will sometimes be the killed tasks's mmap_sem,
> so the reaper won't reap anything.  This scenario requires that the
> mmap_sem is held for writing, which sounds like it will be uncommon. 

Yes, I have mentioned that in the changelog:
"
oom_reaper has to take mmap_sem on the target task for reading so the
solution is not 100% because the semaphore might be held or blocked for
write but the probability is reduced considerably wrt. basically any
lock blocking forward progress as described above.
"

Another thing is to do is to change down_write(mmap_sem) to
down_write_killable in most cases where we have a clear ENITR semantic.
This is on my todo list.

> hm.  sigh.  I hate the oom-killer.  Just buy some more memory already!

Tell me something about that...
-- 
Michal Hocko
SUSE Labs