[lkml]   [2009]   [Dec]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: [BUGFIX][PATCH] oom-kill: fix NUMA consraint check with nodemask v4.2
    On Mon, 14 Dec 2009 17:16:32 -0800
    Andrew Morton <> 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,
    - should be merged. Because we tend to get several OOM reports in a month,
    More precise information is always welcomed.

    - should be merged. This is a bug fix.

    - 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.
    #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...)


     \ /
      Last update: 2009-12-15 02:37    [W:0.024 / U:0.056 seconds]
    ©2003-2017 Jasper Spaans. hosted at Digital OceanAdvertise on this site