linux-kernel - Re: [v5 2/4] mm, oom: cgroup-aware OOM killer

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 15 Aug 2017 13:57:50 +0100
From:   Roman Gushchin <guro@...com>
To:     Aleksa Sarai <asarai@...e.de>
CC:     David Rientjes <rientjes@...gle.com>, <linux-mm@...ck.org>,
        Michal Hocko <mhocko@...nel.org>,
        Vladimir Davydov <vdavydov.dev@...il.com>,
        Johannes Weiner <hannes@...xchg.org>,
        Tetsuo Handa <penguin-kernel@...ove.sakura.ne.jp>,
        Tejun Heo <tj@...nel.org>, <kernel-team@...com>,
        <cgroups@...r.kernel.org>, <linux-doc@...r.kernel.org>,
        <linux-kernel@...r.kernel.org>
Subject: Re: [v5 2/4] mm, oom: cgroup-aware OOM killer

On Tue, Aug 15, 2017 at 10:20:18PM +1000, Aleksa Sarai wrote:
> On 08/15/2017 10:15 PM, Roman Gushchin wrote:
> > Generally, oom_score_adj should have a meaning only on a cgroup level,
> > so extending it to the system level doesn't sound as a good idea.
> 
> But wasn't the original purpose of oom_score (and oom_score_adj) to work on
> a system level, aka "normal" OOM? Is there some peculiarity about memcg OOM
> that I'm missing?

I'm sorry, if it wasn't clear from my message, it's not about
the system-wide OOM vs the memcg-wide OOM, it's about the isolation.

In general, decision is made on memcg level first (based on oom_priority
and size), and only then on a task level (based on size and oom_score_adj).

Oom_score_adj affects which task inside the cgroup will be killed,
but we never compare tasks from different cgroups. This is what I mean,
when I'm saying, that oom_score_adj should not have a system-wide meaning.

Thanks!