linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@linux-foundation.org>
To: David Rientjes <rientjes@google.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>,
	Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Divyesh Shah <dpshah@google.com>,
	linux-mm@kvack.org
Subject: Re: [patch] memcg: add oom killer delay
Date: Tue, 21 Dec 2010 23:59:24 -0800	[thread overview]
Message-ID: <20101221235924.b5c1aecc.akpm@linux-foundation.org> (raw)
In-Reply-To: <alpine.DEB.2.00.1012212318140.22773@chino.kir.corp.google.com>

On Tue, 21 Dec 2010 23:27:25 -0800 (PST) David Rientjes <rientjes@google.com> wrote:

> Completely disabling the oom killer for a memcg is problematic if
> userspace is unable to address the condition itself, usually because
> userspace is unresponsive.  This scenario creates a memcg livelock:
> tasks are continuously trying to allocate memory and nothing is getting
> killed, so memory freeing is impossible since reclaim has failed, and
> all work stalls with no remedy in sight.

Userspace was buggy, surely.  If userspace has elected to disable the
oom-killer then it should ensure that it can cope with the ensuing result.

One approach might be to run a mlockall()ed watchdog which monitors the
worker tasks via shared memory.  Another approach would be to run that
watchdog in a different memcg, without mlockall().  There are surely
plenty of other ways of doing it.

> This patch adds an oom killer delay so that a memcg may be configured to
> wait at least a pre-defined number of milliseconds before calling the
> oom killer.  If the oom condition persists for this number of
> milliseconds, the oom killer will be called the next time the memory
> controller attempts to charge a page (and memory.oom_control is set to
> 0).  This allows userspace to have a short period of time to respond to
> the condition before timing out and deferring to the kernel to kill a
> task.
> 
> Admins may set the oom killer timeout using the new interface:
> 
> 	# echo 60000 > memory.oom_delay
> 
> This will defer oom killing to the kernel only after 60 seconds has
> elapsed.  When setting memory.oom_delay, all pending timeouts are
> restarted.
> 

eww, ick ick ick.


Minutea:

- changelog and docs forgot to mention that oom_delay=0 disables.

- it's called oom_kill_delay in the kernel and oom_delay in userspace.

- oom_delay_millisecs would be a better name for the pseudo file.

- Also, ick.

--
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/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2010-12-22  8:03 UTC|newest]

Thread overview: 58+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-12-22  7:27 [patch] memcg: add oom killer delay David Rientjes
2010-12-22  7:59 ` Andrew Morton [this message]
2010-12-22  8:17   ` KAMEZAWA Hiroyuki
2010-12-22  8:31     ` KOSAKI Motohiro
2010-12-22  8:48     ` David Rientjes
2010-12-22  8:48       ` KAMEZAWA Hiroyuki
2010-12-22  8:55         ` KAMEZAWA Hiroyuki
2010-12-22  9:21           ` David Rientjes
2010-12-27  1:47             ` KAMEZAWA Hiroyuki
2010-12-22  9:04         ` David Rientjes
2010-12-22  8:42   ` David Rientjes
2010-12-22 22:45     ` [patch v2] " David Rientjes
2010-12-27  0:52       ` KAMEZAWA Hiroyuki
2010-12-28  5:22         ` David Rientjes
2010-12-28  6:29           ` [patch v3] " David Rientjes
2011-01-04  1:41             ` KAMEZAWA Hiroyuki
2011-01-04  3:59               ` Balbir Singh
2011-01-06  1:53                 ` KAMEZAWA Hiroyuki
2011-01-06  5:46                   ` Balbir Singh
2011-01-06  5:52                     ` KAMEZAWA Hiroyuki
2010-12-25 10:47 ` [patch] " Balbir Singh
2010-12-26 20:35   ` David Rientjes
  -- strict thread matches above, loose matches on Subject: below --
2011-02-08  0:24 David Rientjes
2011-02-08  1:55 ` KAMEZAWA Hiroyuki
2011-02-08  2:13   ` David Rientjes
2011-02-08  2:13     ` KAMEZAWA Hiroyuki
2011-02-08  2:20       ` KAMEZAWA Hiroyuki
2011-02-08  2:37         ` David Rientjes
2011-02-08 10:25           ` Balbir Singh
2011-02-09 22:19 ` David Rientjes
2011-02-10  0:04   ` KAMEZAWA Hiroyuki
2011-02-16  3:15     ` David Rientjes
2011-02-20 22:19       ` David Rientjes
2011-02-23 23:08   ` Andrew Morton
2011-02-24  0:13     ` KAMEZAWA Hiroyuki
2011-02-24  0:51     ` David Rientjes
2011-03-03 20:11       ` David Rientjes
2011-03-03 21:52       ` Andrew Morton
2011-03-08  0:12         ` David Rientjes
2011-03-08  0:29           ` Andrew Morton
2011-03-08  0:36             ` David Rientjes
2011-03-08  0:51               ` Andrew Morton
2011-03-08  1:02                 ` David Rientjes
2011-03-08  1:18                   ` Andrew Morton
2011-03-08  1:33                     ` David Rientjes
2011-03-08  2:51                       ` KAMEZAWA Hiroyuki
2011-03-08  3:07                         ` David Rientjes
2011-03-08  3:13                           ` KAMEZAWA Hiroyuki
2011-03-08  3:56                             ` David Rientjes
2011-03-08  4:17                               ` KAMEZAWA Hiroyuki
2011-03-08  5:30                                 ` David Rientjes
2011-03-08  5:49                                   ` KAMEZAWA Hiroyuki
2011-03-08 23:49                                     ` David Rientjes
2011-03-09  6:04                                       ` KAMEZAWA Hiroyuki
2011-03-09  6:44                                         ` David Rientjes
2011-03-09  7:16                                           ` KAMEZAWA Hiroyuki
2011-03-09 21:12                                             ` David Rientjes
2011-03-08  3:06                     ` KAMEZAWA Hiroyuki

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=20101221235924.b5c1aecc.akpm@linux-foundation.org \
    --to=akpm@linux-foundation.org \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=dpshah@google.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-mm@kvack.org \
    --cc=nishimura@mxp.nes.nec.co.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 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).