Re: [BUGFIX][PATCH] oom-kill: fix NUMA consraint check withnodemask v4.2

[KAMEZAWA Hiroyuki]

On Mon, 14 Dec 2009 17:16:32 -0800
Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:

> 
> So I have a note-to-self here that these patches:
> 
> oom_kill-use-rss-value-instead-of-vm-size-for-badness.patch
> oom-kill-show-virtual-size-and-rss-information-of-the-killed-process.patch
> oom-kill-fix-numa-consraint-check-with-nodemask-v42.patch
> 
> are tentative and it was unclear whether I should merge them.
> 
> What do we think?
> 

In my view,
  oom-kill-show-virtual-size-and-rss-information-of-the-killed-process.patch
  - should be merged. Because we tend to get several OOM reports in a month,
    More precise information is always welcomed.

  oom-kill-fix-numa-consraint-check-with-nodemask-v42.patch
  - should be merged. This is a bug fix.

  oom_kill-use-rss-value-instead-of-vm-size-for-badness.patch
  - should not be merged.
    I'm now preparing more counters for mm's statistics. It's better to
    wait  and to see what we can do more. And other patches for total
    oom-killer improvement is under development.

    And, there is a compatibility problem.
    As David says, this may break some crazy software which uses
    fake_numa+cpuset+oom_killer+oom_adj for resource controlling.
   (even if I recommend them to use memcg rather than crazy tricks...)
    
    2 ideas which I can think of now are..
    1) add sysctl_oom_calc_on_committed_memory 
       If this is set, use vm-size instead of rss.

    2) add /proc/<pid>/oom_guard_size
       This allows users to specify "valid/expected size" of a task.
       When
       #echo 10M > /proc/<pid>/oom_guard_size
       At OOM calculation, 10Mbytes is subtracted from rss size.
       (The best way is to estimate this automatically from vm_size..but...)



Thanks,
-Kame

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/