All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@osdl.org>
To: Peter Zaitsev <peter@mysql.com>
Cc: andrea@suse.de, linux-kernel@vger.kernel.org
Subject: Re: VM Problems in 2.6.7 (Too active OOM Killer)
Date: Tue, 13 Jul 2004 21:17:21 -0700	[thread overview]
Message-ID: <20040713211721.05781fb7.akpm@osdl.org> (raw)
In-Reply-To: <1089776640.15336.2557.camel@abyss.home>

Peter Zaitsev <peter@mysql.com> wrote:
>
> The reason for me to disable swap both in 2.4 and 2.6 is - it really
>  hurts performance. In some cases performance can be 2-3 times slower
>  with swap file enabled.   Using O_DIRECT and mlock() for buffers helps 
>  but not completely.

It's strange that swap should harm performance in this manner.  Is that
also the case on 2.6?

wrt this OOM problem: it's possible that your ZONE_NORMAL got filled with
anonymous memory which the VM is unable to do anything about.  If you're
going to run a highmem box swapless then you should tune the kernel so that
it doesn't use so much ZONE_NORMAL memory for anonymous pages.

Try

	echo 500 > /proc/sys/vm/lower_zone_protection

then do:

	echo m > /proc/sysrq-trigger; dmesg -c

You'll get output like this:


Normal free:407192kB min:936kB low:1872kB high:2808kB active:1572kB inactive:410348kB present:901120kB
protections[]: 0 468 128724

                     ^^^^^^

This number here means that the VM will make 128724 pages (500MB) of the
normal zone ineligible for anonymous memory and pagecache allocations. 
That is probably an appropriate setting for your application.  If you set
lower_zone_protection too low you'll still get OOMs.  If you set it too
high the file caching efficiency may suffer a little.

  parent reply	other threads:[~2004-07-14  4:18 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-07-14  2:23 VM Problems in 2.6.7 (Too active OOM Killer) Peter Zaitsev
2004-07-14  2:40 ` William Lee Irwin III
2004-07-14  3:20   ` Peter Zaitsev
2004-07-14  3:17 ` Andrea Arcangeli
2004-07-14  3:44   ` Peter Zaitsev
2004-07-14  4:10     ` Andrea Arcangeli
2004-07-14  4:22       ` Andrew Morton
2004-07-14  4:47         ` Andrea Arcangeli
2004-07-14  4:17     ` Andrew Morton [this message]
2004-07-14 23:47       ` Peter Zaitsev
2004-07-14 22:44         ` Andrew Morton
2004-07-15  0:06           ` Andrea Arcangeli
2004-07-15  0:30           ` Peter Zaitsev
2004-07-15  0:46             ` Andrea Arcangeli
2004-07-15  1:54             ` William Lee Irwin III
2004-07-15  2:13               ` Peter Zaitsev
2004-07-15  2:33                 ` William Lee Irwin III
2004-07-15  2:39                   ` William Lee Irwin III
2004-07-15  2:44                     ` William Lee Irwin III
2004-08-13 22:23                       ` William Lee Irwin III
2004-07-19 20:27                   ` Bill Davidsen
2004-07-18 16:13               ` Kurt Garloff
2004-07-20  9:14                 ` R. J. Wysocki
2004-07-20 13:29                 ` Andrea Arcangeli
2004-07-20 13:53                   ` William Lee Irwin III
2004-07-20 13:29                 ` William Lee Irwin III
2004-07-19 20:21               ` Bill Davidsen
2004-07-15  0:04         ` Andrea Arcangeli
2004-07-15  0:43           ` Peter Zaitsev
2004-07-15  0:43           ` William Lee Irwin III
2004-07-15  1:04             ` Peter Zaitsev
2004-07-15  1:29               ` William Lee Irwin III
2004-07-14  3:50   ` William Lee Irwin III

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=20040713211721.05781fb7.akpm@osdl.org \
    --to=akpm@osdl.org \
    --cc=andrea@suse.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peter@mysql.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 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.