All of lore.kernel.org
 help / color / mirror / Atom feed
From: Michal Hocko <mhocko@kernel.org>
To: David Rientjes <rientjes@google.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>,
	linux-mm@kvack.org, Roman Gushchin <guro@fb.com>
Subject: Re: [PATCH 4/4] mm, oom: Fix unnecessary killing of additional processes.
Date: Wed, 22 Aug 2018 10:03:42 +0200	[thread overview]
Message-ID: <20180822080342.GE29735@dhcp22.suse.cz> (raw)
In-Reply-To: <alpine.DEB.2.21.1808211016400.258924@chino.kir.corp.google.com>

On Tue 21-08-18 10:20:00, David Rientjes wrote:
> On Tue, 21 Aug 2018, Michal Hocko wrote:
> 
> > > Ok, so it appears you're suggesting a per-mm counter of oom reaper retries 
> > > and once it reaches a certain threshold, either give up and set 
> > > MMF_OOM_SKIP or declare that exit_mmap() is responsible for it.  That's 
> > > fine, but obviously I'll be suggesting that the threshold is rather large.  
> > > So if I adjust my patch to be a retry counter rather than timestamp, do 
> > > you have any other reservations?
> > 
> > It absolutely has to be an internal thing without any user API to be
> > set. Also I still haven't heard any specific argument why would oom
> > reaper need to do per-task attempt and loop over all victims on the
> > list. Maybe you have some examples though.
> > 
> 
> It would be per-mm in this case, the task itself is no longer important 
> other than printing to the kernel log.  I think we could simply print that 
> the oom reaper has reaped mm->owner.
> 
> The oom reaper would need to loop over the per-mm list because the retry 
> counter is going to have a high threshold so that processes have the 
> ability to free their memory before the oom reaper declares it can no 
> longer make forward progress.

What do you actually mean by a high threshold?

> We cannot stall trying to reap a single mm 
> with a high retry threshold from a memcg hierarchy when another memcg 
> hierarchy is also oom.  The ability for one victim to make forward 
> progress can depend on a lock held by another oom memcg hierarchy where 
> reaping would allow it to be dropped.

Could you be more specific please?

-- 
Michal Hocko
SUSE Labs

  reply	other threads:[~2018-08-22  8:03 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-04 13:29 [PATCH 1/4] mm, oom: Remove wake_oom_reaper() Tetsuo Handa
2018-08-04 13:29 ` [PATCH 2/4] mm, oom: Check pending victims earlier in out_of_memory() Tetsuo Handa
2018-08-04 13:29 ` [PATCH 3/4] mm, oom: Remove unused "abort" path Tetsuo Handa
2018-08-04 13:29 ` [PATCH 4/4] mm, oom: Fix unnecessary killing of additional processes Tetsuo Handa
2018-08-06 13:45   ` Michal Hocko
2018-08-06 20:19     ` David Rientjes
2018-08-06 20:51       ` Michal Hocko
2018-08-09 20:16         ` David Rientjes
2018-08-10  9:07           ` Michal Hocko
2018-08-10 10:54             ` Tetsuo Handa
2018-08-10 11:16               ` Michal Hocko
2018-08-11  3:12                 ` Tetsuo Handa
2018-08-14 11:33                   ` Michal Hocko
2018-08-19 14:23                     ` Tetsuo Handa
2018-08-20  5:54                       ` Michal Hocko
2018-08-20 22:03                         ` Tetsuo Handa
2018-08-21  6:16                           ` Michal Hocko
2018-08-21 13:39                             ` Tetsuo Handa
2018-08-19 23:45             ` David Rientjes
2018-08-20  6:07               ` Michal Hocko
2018-08-20 21:31                 ` David Rientjes
2018-08-21  6:09                   ` Michal Hocko
2018-08-21 17:20                     ` David Rientjes
2018-08-22  8:03                       ` Michal Hocko [this message]
2018-08-22 20:54                         ` David Rientjes
2018-09-01 11:48         ` Tetsuo Handa
2018-09-06 11:35           ` Michal Hocko
2018-09-06 11:50             ` Tetsuo Handa
2018-09-06 12:05               ` Michal Hocko
2018-09-06 13:40                 ` Tetsuo Handa
2018-09-06 13:56                   ` Michal Hocko
2018-09-06 14:06                     ` Tetsuo Handa
2018-09-06 14:16                       ` Michal Hocko
2018-09-06 21:13                         ` Tetsuo Handa
2018-09-07 11:10                           ` Michal Hocko
2018-09-07 11:36                             ` Tetsuo Handa
2018-09-07 11:51                               ` Michal Hocko
2018-09-07 13:30                                 ` Tetsuo Handa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180822080342.GE29735@dhcp22.suse.cz \
    --to=mhocko@kernel.org \
    --cc=guro@fb.com \
    --cc=linux-mm@kvack.org \
    --cc=penguin-kernel@i-love.sakura.ne.jp \
    --cc=rientjes@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.