Re: [PATCH v2] mm,oom: exclude oom_task_origin processes if they are OOM-unkillable.

From	David Rientjes <rientjes@google.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH v2] mm,oom: exclude oom_task_origin processes if they are OOM-unkillable.
Date	2016-02-24 22:40 +0100
Message-ID	<r5Pk7-27v-23@gated-at.bofh.it> (permalink)
References	(2 earlier) <r3rOV-2FS-1@gated-at.bofh.it> <r59Ee-6jF-9@gated-at.bofh.it> <r5kpY-5q1-15@gated-at.bofh.it> <r5tMC-3DJ-21@gated-at.bofh.it> <r5Eyo-2WS-65@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Wed, 24 Feb 2016, Michal Hocko wrote:

> Hmm, is it really helpful though? What would you deduce from seeing a
> large rss an OOM_SCORE_ADJ_MIN task? Misconfigured system? There must
> have been a reason to mark the task that way in the first place so you
> can hardly do anything about it. Moreover you can deduce the same from
> the available information.
> 

Users run processes that are vital to the machine with OOM_SCORE_ADJ_MIN.  
This does not make them immune to having memory leaks that caused the oom 
condition, and identifying that has triaged many bugs in the past.

Thanks.

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

Re: [PATCH v2] mm,oom: exclude oom_task_origin processes if they  are OOM-unkillable. David Rientjes <rientjes@google.com> - 2016-02-23 02:10 +0100
  Re: [PATCH v2] mm,oom: exclude oom_task_origin processes if they are  OOM-unkillable. Michal Hocko <mhocko@kernel.org> - 2016-02-23 13:40 +0100
    Re: [PATCH v2] mm,oom: exclude oom_task_origin processes if they  are OOM-unkillable. David Rientjes <rientjes@google.com> - 2016-02-23 23:40 +0100
      Re: [PATCH v2] mm,oom: exclude oom_task_origin processes if they are  OOM-unkillable. Michal Hocko <mhocko@kernel.org> - 2016-02-24 11:10 +0100
        Re: [PATCH v2] mm,oom: exclude oom_task_origin processes if they  are OOM-unkillable. David Rientjes <rientjes@google.com> - 2016-02-24 22:40 +0100

csiph-web