linux-kernel - Re: [PATCH v2] memcg: allow exiting tasks to write back data to swap

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]

Message-ID: <Z1uEp5lCGFQK4vFb@google.com>
Date: Fri, 13 Dec 2024 00:49:43 +0000
From: Roman Gushchin <roman.gushchin@...ux.dev>
To: Rik van Riel <riel@...riel.com>
Cc: Yosry Ahmed <yosryahmed@...gle.com>, Balbir Singh <balbirs@...dia.com>,
	Johannes Weiner <hannes@...xchg.org>,
	Michal Hocko <mhocko@...nel.org>,
	hakeel Butt <shakeel.butt@...ux.dev>,
	Muchun Song <muchun.song@...ux.dev>,
	Andrew Morton <akpm@...ux-foundation.org>, cgroups@...r.kernel.org,
	linux-mm@...ck.org, linux-kernel@...r.kernel.org,
	kernel-team@...a.com, Nhat Pham <nphamcs@...il.com>
Subject: Re: [PATCH v2] memcg: allow exiting tasks to write back data to swap

On Thu, Dec 12, 2024 at 03:00:03PM -0500, Rik van Riel wrote:
> On Thu, 12 Dec 2024 18:31:57 +0000
> Roman Gushchin <roman.gushchin@...ux.dev> wrote:
> 
> > Is it about a single task or groups of tasks or the entire cgroup?
> > If former, why it's a problem? A tight memcg limit can slow things down
> > in general and I don't see why we should treat the exit() path differently.
> > 
> I think the exit path does need to be treated a little differently,
> since this exit may be the only way such a cgroup can free up memory.

It's true if all tasks in a cgroup are exiting. Otherwise there are
other options (at least in theory).

> 
> > If it's about the entire cgroup and we have essentially a deadlock,
> > I feel like we need to look into the oom reaper side.
> 
> You mean something like the below?
> 
> I have not tested it yet, because we don't have any stuck
> cgroups right now among the workloads that I'm monitoring.

Yeah, something like this...

Thanks!