linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: David Rientjes <rientjes@google.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Rik van Riel <riel@redhat.com>, Nick Piggin <npiggin@suse.de>,
	Balbir Singh <balbir@linux.vnet.ibm.com>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	linux-mm@kvack.org
Subject: [patch -mm v2 00/10] oom killer rewrite
Date: Fri, 26 Feb 2010 15:52:56 -0800 (PST)	[thread overview]
Message-ID: <alpine.DEB.2.00.1002261549290.30830@chino.kir.corp.google.com> (raw)

This patchset is a rewrite of the out of memory killer to address several
issues that have been raised recently.  The most notable change is a
complete rewrite of the badness heuristic that determines which task is
killed; the goal was to make it as simple and predictable as possible
while still addressing issues that plague the VM.

Changes from version 2:

 - updated to 2.6.33, no longer based on mmotm

 - removed "oom: remove compulsory panic_on_oom mode"

 - mempolicy detachment is now protected by task_lock(); otherwise, it is
   possible for a mempolicy to be freed out from under code that is using
   it.  This isn't necessary for current->mempolicy, but all other tasks
   require it.

 - tasks that have mempolicies of MPOL_PREFERED (or MPOL_F_LOCAL) are now
   always considered for oom kill when it is mempolicy constrained since
   they may allocate elsewhere as fallback when their preferred (or local)
   node is oom.

 - lowmem allocations that are __GFP_NOFAIL are now retried in the page
   allocator instead of returning NULL.

 - added: [patch 4/10] oom: remove special handling for pagefault ooms

 - added: [patch 10/10] oom: default to killing current for pagefault ooms

This patchset has two dependencies from the -mm tree:

	[patch 5/10] oom: badness heuristic rewrite:
		mm-count-swap-usage.patch

	[patch 7/10] oom: replace sysctls with quick mode:
		sysctl-clean-up-vm-related-variable-delcarations.patch

To apply to mainline, download 2.6.33 and apply

	mm-clean-up-mm_counter.patch
	mm-avoid-false-sharing-of-mm_counter.patch
	mm-avoid-false-sharing-of-mm_counter-checkpatch-fixes.patch
	mm-count-swap-usage.patch
	mm-count-swap-usage-checkpatch-fixes.patch
	mm-introduce-dump_page-and-print-symbolic-flag-names.patch
	sysctl-clean-up-vm-related-variable-declarations.patch
	sysctl-clean-up-vm-related-variable-declarations-fix.patch

from http://userweb.kernel.org/~akpm/mmotm/broken-out.tar.gz first.

This patchset is also available for each kernel release from:

	http://www.kernel.org/pub/linux/kernel/people/rientjes/oom-killer-rewrite/

including broken out patches and the prerequisite patches listed above.
---
 Documentation/feature-removal-schedule.txt |   30 +
 Documentation/filesystems/proc.txt         |  100 +++--
 Documentation/sysctl/vm.txt                |   51 +-
 fs/proc/base.c                             |  106 +++++
 include/linux/memcontrol.h                 |   14 
 include/linux/mempolicy.h                  |   13 
 include/linux/oom.h                        |   24 +
 include/linux/sched.h                      |    3 
 kernel/exit.c                              |    8 
 kernel/fork.c                              |    1 
 kernel/sysctl.c                            |   15 
 mm/memcontrol.c                            |   43 --
 mm/mempolicy.c                             |   44 ++
 mm/oom_kill.c                              |  572 +++++++++++++++--------------
 mm/page_alloc.c                            |   29 +
 15 files changed, 653 insertions(+), 400 deletions(-)

--
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>

             reply	other threads:[~2010-02-26 23:53 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-02-26 23:52 David Rientjes [this message]
2010-02-26 23:53 ` [patch -mm v2 01/10] oom: filter tasks not sharing the same cpuset David Rientjes
2010-03-02  4:54   ` Balbir Singh
2010-02-26 23:53 ` [patch -mm v2 02/10] oom: sacrifice child with highest badness score for parent David Rientjes
2010-03-02  4:54   ` Balbir Singh
2010-02-26 23:53 ` [patch -mm v2 03/10] oom: select task from tasklist for mempolicy ooms David Rientjes
2010-02-26 23:53 ` [patch -mm v2 04/10] oom: remove special handling for pagefault ooms David Rientjes
2010-03-01  1:12   ` KAMEZAWA Hiroyuki
2010-03-01 10:13     ` David Rientjes
2010-03-01 23:59       ` KAMEZAWA Hiroyuki
2010-03-02 23:55         ` David Rientjes
2010-03-03  0:24           ` KAMEZAWA Hiroyuki
2010-03-03  0:44             ` David Rientjes
2010-03-01  5:23   ` Balbir Singh
2010-03-01 10:04     ` David Rientjes
2010-03-01 23:55       ` KAMEZAWA Hiroyuki
2010-03-03  0:01         ` David Rientjes
2010-03-03  0:22           ` KAMEZAWA Hiroyuki
2010-03-03  0:38             ` David Rientjes
2010-03-03  0:44               ` KAMEZAWA Hiroyuki
2010-03-03  0:53                 ` David Rientjes
2010-03-03  0:58                   ` KAMEZAWA Hiroyuki
2010-03-03 23:27                     ` David Rientjes
2010-03-04  3:59                       ` KAMEZAWA Hiroyuki
2010-03-04  6:50                         ` David Rientjes
2010-03-04  7:00                           ` KAMEZAWA Hiroyuki
2010-03-04  9:50                             ` David Rientjes
2010-03-05  0:58                               ` KAMEZAWA Hiroyuki
2010-03-02  2:21   ` KAMEZAWA Hiroyuki
2010-03-02 23:59     ` David Rientjes
2010-02-26 23:53 ` [patch -mm v2 05/10] oom: badness heuristic rewrite David Rientjes
2010-02-26 23:53 ` [patch -mm v2 06/10] oom: deprecate oom_adj tunable David Rientjes
2010-02-26 23:53 ` [patch -mm v2 07/10] oom: replace sysctls with quick mode David Rientjes
2010-02-26 23:53 ` [patch -mm v2 08/10] oom: avoid oom killer for lowmem allocations David Rientjes
2010-02-26 23:53 ` [patch -mm v2 09/10] oom: remove unnecessary code and cleanup David Rientjes
2010-02-26 23:53 ` [patch -mm v2 10/10] oom: default to killing current for pagefault ooms David Rientjes

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=alpine.DEB.2.00.1002261549290.30830@chino.kir.corp.google.com \
    --to=rientjes@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=kosaki.motohiro@jp.fujitsu.com \
    --cc=linux-mm@kvack.org \
    --cc=npiggin@suse.de \
    --cc=riel@redhat.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