Re: [PATCH] mm/oom_kill: count global and memory cgroup oom kills

[Tetsuo Handa]

On 2017/05/23 20:05, Konstantin Khlebnikov wrote:
> On 23.05.2017 10:27, Michal Hocko wrote:
>> On Fri 19-05-17 17:22:30, Konstantin Khlebnikov wrote:
>>> Show count of global oom killer invocations in /proc/vmstat and
>>> count of oom kills inside memory cgroup in knob "memory.events"
>>> (in memory.oom_control for v1 cgroup).
>>>
>>> Also describe difference between "oom" and "oom_kill" in memory
>>> cgroup documentation. Currently oom in memory cgroup kills tasks
>>> iff shortage has happened inside page fault.
>>>
>>> These counters helps in monitoring oom kills - for now
>>> the only way is grepping for magic words in kernel log.
>>
>> Have you considered adding memcg's oom alternative for the global case
>> as well. It would be useful to see how many times we hit the OOM
>> condition without killing anything. That could help debugging issues
>> when the OOM killer cannot be invoked (e.g. GFP_NO{FS,IO} contextx)
>> and the system cannot get out of the oom situation.
> 
> I think present warn_alloc() should be enough for debugging,
> maybe it should taint kernel in some cases to give a hint for future warnings/bugs.
> 

I don't think warn_alloc() is enough. We can fail to warn using warn_alloc(), see
http://lkml.kernel.org/r/1495331504-12480-1-git-send-email-penguin-kernel@xxxxxxxxxxxxxxxxxxx .