From: "Christian König" <ckoenig.leichtzumerken@gmail.com>
To: "Michal Hocko" <mhocko@kernel.org>, "Michel Dänzer" <michel@daenzer.net>
Cc: linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org,
Christian.Koenig@amd.com, linux-mm@kvack.org,
amd-gfx@lists.freedesktop.org, Roman Gushchin <guro@fb.com>
Subject: Re: [RFC] Per file OOM badness
Date: Wed, 24 Jan 2018 13:11:09 +0100 [thread overview]
Message-ID: <381a868c-78fd-d0d1-029e-a2cf4ab06d37@gmail.com> (raw)
In-Reply-To: <20180124115059.GC28465@dhcp22.suse.cz>
Am 24.01.2018 um 12:50 schrieb Michal Hocko:
> On Wed 24-01-18 12:23:10, Michel DA?nzer wrote:
>> On 2018-01-24 12:01 PM, Michal Hocko wrote:
>>> On Wed 24-01-18 11:27:15, Michel DA?nzer wrote:
> [...]
>>>> 2. If the OOM killer kills a process which is sharing BOs with another
>>>> process, this should result in the other process dropping its references
>>>> to the BOs as well, at which point the memory is released.
>>> OK. How exactly are those BOs mapped to the userspace?
>> I'm not sure what you're asking. Userspace mostly uses a GEM handle to
>> refer to a BO. There can also be userspace CPU mappings of the BO's
>> memory, but userspace doesn't need CPU mappings for all BOs and only
>> creates them as needed.
> OK, I guess you have to bear with me some more. This whole stack is a
> complete uknonwn. I am mostly after finding a boundary where you can
> charge the allocated memory to the process so that the oom killer can
> consider it. Is there anything like that? Except for the proposed file
> handle hack?
Not that I knew of.
As I said before we need some kind of callback that a process now starts
to use a file descriptor, but without anything from that file descriptor
mapped into the address space.
Regards,
Christian.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2018-01-24 12:11 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-18 16:47 [RFC] Per file OOM badness Andrey Grodzovsky
2018-01-18 16:47 ` [PATCH 1/4] fs: add OOM badness callback in file_operatrations struct Andrey Grodzovsky
2018-01-18 16:47 ` [PATCH 2/4] oom: take per file badness into account Andrey Grodzovsky
2018-01-18 16:47 ` [PATCH 3/4] drm/gem: adjust per file OOM badness on handling buffers Andrey Grodzovsky
2018-01-19 6:01 ` Chunming Zhou
2018-01-18 16:47 ` [PATCH 4/4] drm/amdgpu: Use drm_oom_badness for amdgpu Andrey Grodzovsky
2018-01-30 9:24 ` Daniel Vetter
2018-01-30 12:42 ` Andrey Grodzovsky
2018-01-18 17:00 ` [RFC] Per file OOM badness Michal Hocko
2018-01-18 17:13 ` Michal Hocko
2018-01-18 20:01 ` Eric Anholt
2018-01-19 8:20 ` Michal Hocko
2018-01-19 8:39 ` Christian König
2018-01-19 9:32 ` Michel Dänzer
2018-01-19 9:58 ` Christian König
2018-01-19 10:02 ` Michel Dänzer
2018-01-19 15:07 ` Michel Dänzer
2018-01-21 6:50 ` Eric Anholt
2018-01-19 10:40 ` Michal Hocko
2018-01-19 11:37 ` Christian König
2018-01-19 12:13 ` Michal Hocko
2018-01-19 12:20 ` Michal Hocko
2018-01-19 16:54 ` Christian König
2018-01-23 11:39 ` Michal Hocko
2018-01-19 16:48 ` Michel Dänzer
2018-01-19 8:35 ` Christian König
2018-01-19 6:01 ` He, Roger
2018-01-19 8:25 ` Michal Hocko
2018-01-19 10:02 ` roger
2018-01-23 15:27 ` Roman Gushchin
2018-01-23 15:36 ` Michal Hocko
2018-01-23 16:39 ` Michel Dänzer
2018-01-24 9:28 ` Michal Hocko
2018-01-24 10:27 ` Michel Dänzer
2018-01-24 11:01 ` Michal Hocko
2018-01-24 11:23 ` Michel Dänzer
2018-01-24 11:50 ` Michal Hocko
2018-01-24 12:11 ` Christian König [this message]
2018-01-30 9:31 ` Daniel Vetter
2018-01-30 9:43 ` Michel Dänzer
2018-01-30 10:40 ` Christian König
2018-01-30 11:02 ` Michel Dänzer
2018-01-30 11:28 ` Christian König
2018-01-30 11:34 ` Michel Dänzer
2018-01-30 11:36 ` Nicolai Hähnle
2018-01-30 11:42 ` Michel Dänzer
2018-01-30 11:56 ` Christian König
2018-01-30 15:52 ` Michel Dänzer
2018-01-30 10:42 ` Daniel Vetter
2018-01-30 10:48 ` Michel Dänzer
2018-01-30 11:35 ` Nicolai Hähnle
2018-01-24 14:31 ` Michel Dänzer
2018-01-30 9:29 ` Michel Dänzer
2018-01-30 10:28 ` Michal Hocko
2018-03-26 14:36 ` Lucas Stach
2018-04-04 9:09 ` Michel Dänzer
2018-04-04 9:36 ` Lucas Stach
2018-04-04 9:46 ` Michel Dänzer
2018-01-19 5:39 ` He, Roger
2018-01-19 8:17 ` Christian König
2018-01-22 23:23 ` Andrew Morton
2018-01-23 1:59 ` Andrey Grodzovsky
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=381a868c-78fd-d0d1-029e-a2cf4ab06d37@gmail.com \
--to=ckoenig.leichtzumerken@gmail.com \
--cc=Christian.Koenig@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=guro@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=michel@daenzer.net \
/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;
as well as URLs for NNTP newsgroup(s).