All of lore.kernel.org
 help / color / mirror / Atom feed
From: Evgeniy Polyakov <zbr@ioremap.net>
To: linux-kernel@vger.kernel.org
Cc: David Rientjes <rientjes@google.com>,
	Balbir Singh <balbir@linux.vnet.ibm.com>,
	Alan Cox <alan@lxorguk.ukuu.org.uk>,
	Dave Jones <davej@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Theodore Tso <tytso@mit.edu>,
	Matthias Andree <matthias.andree@gmx.de>
Subject: [take2] OOM documentation update [was: Linux killed Kenny, bastard!]
Date: Wed, 14 Jan 2009 20:06:06 +0300	[thread overview]
Message-ID: <20090114170606.GB12102@ioremap.net> (raw)
In-Reply-To: <20090114161225.GA9584@ioremap.net>

Updated version fixes some errors and extends description by adding
swapping and children relation explaintaion.

Signed.

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index d105eb4..4aa1918 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -2311,6 +2311,33 @@ increase the likelihood of this process being killed by the oom-killer.  Valid
 values are in the range -16 to +15, plus the special value -17, which disables
 oom-killing altogether for this process.
 
+The process to be killed in an out-of-memory situation is selected among all others
+based on its badness score. This value equals the original memory size of the process
+originally and is then updated according to its CPU time (utime + stime) and the
+run time (uptime - start time). The longer it runs the smaller is the score.
+Badness score is divided by the square root of the cpu time and then by
+the double square root of the run time.
+
+Swapped out tasks are killed first. Half of each child's memory size is added to
+the parent's score if they do not share the same memory. Thus forking servers
+are the prime candidates to be killed. Having only one 'hungry' child will make
+parent less preferable than the child.
+
+/proc/<pid>/oom_score shows process' current badness score.
+
+The following heuristics are then applied:
+ * if the task was reniced, its score doubles
+ * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE
+ 	or CAP_SYS_RAWIO) have their score divided by 4
+ * if oom condition happened in one cpuset and checked task does not belong
+ 	to it, its score is divided by 8
+ * resulted score is multiplied by the two in the power of oom_adj when it is
+ 	positive, and divided otherwise, i.e.
+	points <<= oom_adj when it is positive and
+	points >>= oom_adj otherwise
+
+The task with the highest badness score is then killed.
+
 2.13 /proc/<pid>/oom_score - Display current oom-killer score
 -------------------------------------------------------------
 


-- 
	Evgeniy Polyakov

  reply	other threads:[~2009-01-14 17:06 UTC|newest]

Thread overview: 71+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-01-12 15:33 Linux killed Kenny, bastard! Evgeniy Polyakov
2009-01-12 15:44 ` Dave Jones
2009-01-12 15:48   ` Evgeniy Polyakov
2009-01-12 15:51     ` Alan Cox
2009-01-12 15:52       ` Evgeniy Polyakov
2009-01-12 21:29         ` Chris Snook
2009-01-12 21:42           ` Evgeniy Polyakov
2009-01-13 13:52       ` [why oom_adj does not work] " Evgeniy Polyakov
2009-01-13 14:06         ` Alan Cox
2009-01-13 14:24           ` Evgeniy Polyakov
2009-01-13 15:00             ` Balbir Singh
2009-01-13 15:21               ` Evgeniy Polyakov
2009-01-13 18:04                 ` Valdis.Kletnieks
2009-01-13 19:46                 ` David Rientjes
2009-01-13 21:33                   ` Evgeniy Polyakov
2009-01-13 21:39                     ` David Rientjes
2009-01-13 22:05                       ` Evgeniy Polyakov
2009-01-14 16:12                       ` OOM documentation update [was: Linux killed Kenny, bastard!] Evgeniy Polyakov
2009-01-14 17:06                         ` Evgeniy Polyakov [this message]
2009-01-14 21:34                           ` [take2] " Randy Dunlap
2009-01-14 21:53                           ` Bryan Donlan
2009-01-14 22:10                             ` Evgeniy Polyakov
2009-01-14 22:14                             ` [take3] " Evgeniy Polyakov
2009-01-15  0:58                               ` David Rientjes
2009-01-15  8:51                                 ` Evgeniy Polyakov
2009-01-15  8:57                                 ` [take4] " Evgeniy Polyakov
2009-01-15 11:13                                   ` David Rientjes
2009-01-12 15:49 ` Linux killed Kenny, bastard! Alan Cox
2009-01-12 15:50   ` Evgeniy Polyakov
2009-01-12 15:52     ` Alan Cox
2009-01-12 15:56       ` Evgeniy Polyakov
2009-01-12 16:19         ` Alan Cox
2009-01-12 16:29           ` Evgeniy Polyakov
2009-01-12 23:00             ` Bill Davidsen
2009-01-12 23:17               ` Evgeniy Polyakov
2009-01-13  1:53                 ` David Rientjes
2009-01-13  8:52                   ` Evgeniy Polyakov
2009-01-13  9:54                     ` David Rientjes
2009-01-13 11:54                       ` Evgeniy Polyakov
2009-01-13 12:15                         ` Alan Cox
2009-01-13 12:29                           ` Evgeniy Polyakov
2009-01-13 13:19                             ` Theodore Tso
2009-01-13 13:35                               ` Evgeniy Polyakov
2009-01-14  0:24                                 ` Bill Davidsen
2009-01-14  0:35                                   ` Evgeniy Polyakov
2009-01-13 13:47                               ` Alan Cox
2009-01-13 19:36                             ` David Rientjes
2009-01-13 21:46                               ` Evgeniy Polyakov
2009-01-13 22:49                                 ` Theodore Tso
2009-01-13 23:02                                   ` Evgeniy Polyakov
2009-01-14  1:11                                     ` Theodore Tso
2009-01-14  1:20                                       ` Evgeniy Polyakov
2009-01-14  4:06                                         ` Theodore Tso
2009-01-13 23:10                                 ` David Rientjes
2009-01-13 23:35                                   ` Evgeniy Polyakov
2009-01-13 23:43                                     ` David Rientjes
2009-01-13 23:55                                       ` Evgeniy Polyakov
2009-01-14  0:32                                         ` David Rientjes
2009-01-14  0:53                                           ` Evgeniy Polyakov
2009-01-14  4:23                                     ` Valdis.Kletnieks
2009-01-14  9:07                                       ` Evgeniy Polyakov
2009-01-13 19:15                         ` David Rientjes
2009-01-13 22:00                           ` Evgeniy Polyakov
2009-01-13 23:26                         ` Valdis.Kletnieks
2009-01-13 23:36                           ` Evgeniy Polyakov
2009-01-13 13:41                       ` Jan-Frode Myklebust
2009-01-13 13:59                         ` Alan Cox
2009-01-12 16:22         ` Dave Jones
2009-01-12 16:28           ` Evgeniy Polyakov
2009-01-13 16:35 ` KOSAKI Motohiro
2009-01-13 22:04   ` Evgeniy Polyakov

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=20090114170606.GB12102@ioremap.net \
    --to=zbr@ioremap.net \
    --cc=akpm@linux-foundation.org \
    --cc=alan@lxorguk.ukuu.org.uk \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=davej@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=matthias.andree@gmx.de \
    --cc=rientjes@google.com \
    --cc=torvalds@linux-foundation.org \
    --cc=tytso@mit.edu \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.