From: Shakeel Butt <shakeel.butt@linux.dev>
To: "Christian König" <christian.koenig@amd.com>
Cc: Dave Airlie <airlied@gmail.com>,
dri-devel@lists.freedesktop.org, tj@kernel.org,
Johannes Weiner <hannes@cmpxchg.org>,
Michal Hocko <mhocko@kernel.org>,
Roman Gushchin <roman.gushchin@linux.dev>,
Muchun Song <muchun.song@linux.dev>,
cgroups@vger.kernel.org, Dave Chinner <david@fromorbit.com>,
Waiman Long <longman@redhat.com>,
simona@ffwll.ch
Subject: Re: [PATCH 07/16] memcg: add support for GPU page counters. (v4)
Date: Mon, 2 Mar 2026 06:15:45 -0800 [thread overview]
Message-ID: <aaWZrTZGsxxjbBYv@linux.dev> (raw)
In-Reply-To: <4fddf319-50c4-40ab-9e36-04d629a8855e@amd.com>
On Wed, Feb 25, 2026 at 10:09:55AM +0100, Christian König wrote:
> On 2/24/26 20:28, Dave Airlie wrote:
[...]
>
> > This has been a pain in the ass for desktop for years, and I'd like to
> > fix it, the HPC use case if purely a driver for me doing the work.
>
> Wait a second. How does accounting to cgroups help with that in any way?
>
> The last time I looked into this problem the OOM killer worked based on the per task_struct stats which couldn't be influenced this way.
>
It depends on the context of the oom-killer. If the oom-killer is triggered due
to memcg limits then only the processes in the scope of the memcg will be
targetted by the oom-killer. With the specific setting, the oom-killer can kill
all the processes in the target memcg.
However nowadays the userspace oom-killer is preferred over the kernel
oom-killer due to flexibility and configurability. Userspace oom-killers like
systmd-oomd, Android's LMKD or fb-oomd are being used in containerized
environments. Such oom-killers looks at memcg stats and hiding something
something from memcg i.e. not charging to memcg will hide such usage from these
oom-killers.
next prev parent reply other threads:[~2026-03-02 14:15 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-24 2:06 drm/ttm/memcg/lru: enable memcg tracking for ttm and amdgpu driver (complete series v5) Dave Airlie
2026-02-24 2:06 ` [PATCH 01/16] mm: add gpu active/reclaim per-node stat counters (v2) Dave Airlie
2026-02-24 2:06 ` [PATCH 02/16] drm/ttm: use gpu mm stats to track gpu memory allocations. (v4) Dave Airlie
2026-02-24 2:06 ` [PATCH 03/16] ttm/pool: port to list_lru. (v2) Dave Airlie
2026-02-24 2:06 ` [PATCH 04/16] ttm/pool: drop numa specific pools Dave Airlie
2026-02-24 2:06 ` [PATCH 05/16] ttm/pool: make pool shrinker NUMA aware (v2) Dave Airlie
2026-02-24 2:06 ` [PATCH 06/16] ttm/pool: track allocated_pages per numa node Dave Airlie
2026-02-24 2:06 ` [PATCH 07/16] memcg: add support for GPU page counters. (v4) Dave Airlie
2026-02-24 7:20 ` kernel test robot
2026-02-24 7:50 ` Christian König
2026-02-24 19:28 ` Dave Airlie
2026-02-25 9:09 ` Christian König
2026-03-02 14:15 ` Shakeel Butt [this message]
2026-03-02 14:37 ` Christian König
2026-03-02 15:40 ` Shakeel Butt
2026-03-02 15:51 ` Christian König
2026-03-02 17:16 ` Shakeel Butt
2026-03-02 19:36 ` Christian König
2026-03-05 3:23 ` Dave Airlie
2026-03-02 19:35 ` T.J. Mercier
2026-03-03 9:29 ` Christian König
2026-03-03 17:25 ` T.J. Mercier
2026-03-05 3:19 ` Dave Airlie
2026-03-05 9:25 ` Christian König
2026-03-10 1:27 ` T.J. Mercier
2026-02-24 2:06 ` [PATCH 08/16] ttm: add a memcg accounting flag to the alloc/populate APIs Dave Airlie
2026-02-24 8:42 ` kernel test robot
2026-02-24 2:06 ` [PATCH 09/16] ttm/pool: initialise the shrinker earlier Dave Airlie
2026-02-24 2:06 ` [PATCH 10/16] ttm: add objcg pointer to bo and tt (v2) Dave Airlie
2026-02-24 2:06 ` [PATCH 11/16] ttm/pool: enable memcg tracking and shrinker. (v3) Dave Airlie
2026-02-24 2:06 ` [PATCH 12/16] ttm: hook up memcg placement flags Dave Airlie
2026-02-24 2:06 ` [PATCH 13/16] memcontrol: allow objcg api when memcg is config off Dave Airlie
2026-02-24 2:06 ` [PATCH 14/16] amdgpu: add support for memory cgroups Dave Airlie
2026-02-24 2:06 ` [PATCH 15/16] ttm: add support for a module option to disable memcg integration Dave Airlie
2026-02-24 2:06 ` [PATCH 16/16] xe: create a flag to enable memcg accounting for XE as well Dave Airlie
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=aaWZrTZGsxxjbBYv@linux.dev \
--to=shakeel.butt@linux.dev \
--cc=airlied@gmail.com \
--cc=cgroups@vger.kernel.org \
--cc=christian.koenig@amd.com \
--cc=david@fromorbit.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=hannes@cmpxchg.org \
--cc=longman@redhat.com \
--cc=mhocko@kernel.org \
--cc=muchun.song@linux.dev \
--cc=roman.gushchin@linux.dev \
--cc=simona@ffwll.ch \
--cc=tj@kernel.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox