From: Con Kolivas <kernel@kolivas.org>
To: Andrew Morton <akpm@osdl.org>
Cc: "Andy Chittenden" <AChittenden@bluearc.com>,
linux-kernel@vger.kernel.org
Subject: Re: Out of Memory: Killed process 16498 (java).
Date: Thu, 19 Jan 2006 20:36:20 +1100 [thread overview]
Message-ID: <200601192036.20355.kernel@kolivas.org> (raw)
In-Reply-To: <20060119005600.4e465e9d.akpm@osdl.org>
On Thursday 19 January 2006 19:56, Andrew Morton wrote:
> "Andy Chittenden" <AChittenden@bluearc.com> wrote:
> > Why does running the following command cause processes to be killed:
> >
> > dd if=/dev/zero of=/u/u1/andyc/tmpfile bs=1M count=8k
> >
> > And I noticed one of my windows disappeared. Further investigation
> > showed that was my terminator window (java based app: see
> > http://software.jessies.org/terminator/). I found this in my syslog:
> >
> > Jan 17 11:12:58 boco kernel: Out of Memory: Killed process 16498 (java).
> >
> > My hardware: amd64 based machine (ASUS A8V Deluxe motherboard) with 4Gb
> > of memory.
> > My kernel: debian package linux-image-2.6.15-1-amd64-k8 package
> > installed. IE its running 2.6.15 compiled for amd64.
> >
> > This is repeatable. The above dd command also causes the machine to
> > become very unresponsive (eg windows don't focus).
>
> What type of filesytem is being written to?
>
> Has someone tuned /proc/sys/vm/swappiness, or something else under
> /proc/sys/vm?
>
> It'd be useful to see the dmesg output from that oom event.
Are you using scsi? Someone just posted what looks to be a scsi slab leak (Re:
scsi cmd slab leak? (Was Re: [ck] Anyone been having OOM killer problems
lately?) that causes oom kills. Check your slabinfo for a large
scsi_cmd_cache.
Cheers,
Con
next prev parent reply other threads:[~2006-01-19 9:36 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-01-19 8:43 Out of Memory: Killed process 16498 (java) Andy Chittenden
2006-01-19 8:56 ` Andrew Morton
2006-01-19 9:36 ` Con Kolivas [this message]
2006-01-19 20:54 ` Martin Bligh
2006-01-19 9:40 Andy Chittenden
2006-01-19 9:41 ` Con Kolivas
[not found] <89E85E0168AD994693B574C80EDB9C2703555F8E@uk-email.terastack.bluearc.com>
2006-01-19 9:44 ` Andrew Morton
2006-01-19 15:11 Andy Chittenden
2006-01-19 19:48 ` Dave Jones
2006-01-19 22:15 ` Andrew Morton
2006-01-20 8:12 ` Jens Axboe
2006-01-20 8:23 ` Andrew Morton
2006-01-20 12:08 ` Jens Axboe
2006-01-20 12:17 ` Andrew Morton
2006-01-20 12:28 ` Jens Axboe
2006-01-20 12:51 ` Andrew Morton
2006-01-20 1:03 ` Andrew Morton
2006-01-20 1:28 ` Dave Jones
2006-01-20 1:49 ` Andrew Morton
2006-01-21 20:00 ` Dan Aloni
[not found] <89E85E0168AD994693B574C80EDB9C27035560E4@uk-email.terastack.bluearc.com>
2006-01-20 12:37 ` Larry Woodman
[not found] <89E85E0168AD994693B574C80EDB9C27035561DE@uk-email.terastack.bluearc.com>
2006-01-20 17:39 ` Jens Axboe
2006-01-21 21:47 Andy Chittenden
2006-01-23 9:27 ` Jens Axboe
2006-01-23 10:03 Andy Chittenden
2006-01-23 10:11 ` Jens Axboe
2006-01-27 11:53 Andy Chittenden
2006-01-27 14:21 ` Jens Axboe
2006-01-27 14:39 ` Anton Altaparmakov
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=200601192036.20355.kernel@kolivas.org \
--to=kernel@kolivas.org \
--cc=AChittenden@bluearc.com \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
/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).