[lkml]   [2021]   [Oct]   [20]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
Subject[PATCH memcg RFC 0/3] memcg: prohibit unconditional exceeding the limit of dying tasks
Dear Michal,
as you requested, I splited v4 patch version into 3 separate parts.
Let's discuss each of them.

Open questions/ToDo:

- Update patch descriptions (and add some comments)

- in part 2 aka "memcg: remove charge forcinig for dying tasks":
should we keep task_is_dying() in mem_cgroup_out_of_memory() ?

- in part 3 aka "memcg: handle memcg oom failures"
what is the best way to notify pagefault_out_of_memory() about
mem_cgroup_out_of_memory failure ?

- what is the best way to handle memcg failure doe to kmem limit,
it can trigger false global OOM

Vasily Averin (3):
mm: do not firce global OOM from inside dying tasks
memcg: remove charge forcinig for dying tasks
memcg: handle memcg oom failures

mm/memcontrol.c | 52 ++++++++++++++++++++++++++++---------------------
mm/oom_kill.c | 3 +++
2 files changed, 33 insertions(+), 22 deletions(-)


 \ /
  Last update: 2021-10-20 14:12    [W:0.151 / U:0.876 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site