From: Michal Hocko <mhocko@suse.cz>
To: Han Pingtian <hanpt@linux.vnet.ibm.com>
Cc: linux-kernel@vger.kernel.org, rientjes@google.com
Subject: Re: OOM-killer and strange RSS value in 3.9-rc7
Date: Mon, 22 Apr 2013 13:40:52 +0200 [thread overview]
Message-ID: <20130422114052.GB18286@dhcp22.suse.cz> (raw)
In-Reply-To: <20130422031849.GG2672@localhost.localdomain>
On Mon 22-04-13 11:18:49, Han Pingtian wrote:
> On Fri, Apr 19, 2013 at 09:43:10AM -0700, Michal Hocko wrote:
> > [Do not drop people from the CC please]
> >
> > On Fri 19-04-13 10:33:45, Han Pingtian wrote:
> > > On Thu, Apr 18, 2013 at 10:55:14AM -0700, Michal Hocko wrote:
> > [...]
> > > > What is the kernel that you are using and what config?
> > > >
> > > We are testing a alpha version of a enterprise linux which using a 3.7
> > > series kernel. On this 3.7 kernel we encountered the oom killer problem. So
> > > we decide to see if the problem can be reproduced on 3.9-rc7. We
> > > configured 3.9-rc7 by copying the enterprise linux's config file to
> > > .config and then run 'make localmodconfig' and pressed enter to all the
> > > questions. Then the oom problem is reproduced on the 3.9-rc7.
> > >
> > > But we also used the same method to config 3.9-rc7 on another company's
> > > enterprise linux yesterday and found that the problem cannot be
> > > reproduced there. So maybe the leak is caused by some userspace
> > > applications?
> >
> > No application should cause in-kernel mem leak. What is the difference
> > in the two configs?
>
> This is the diff output of those two .config:
>
>
> --- /tmp/config.bad 2013-04-21 22:03:13.000000000 -0500
> +++ /tmp/config.good 2013-04-21 22:03:27.000000000 -0500
> @@ -9,21 +9,21 @@
> #
> CONFIG_PPC_BOOK3S_64=y
> # CONFIG_PPC_BOOK3E_64 is not set
> -CONFIG_GENERIC_CPU=y
> +# CONFIG_GENERIC_CPU is not set
> # CONFIG_CELL_CPU is not set
> # CONFIG_POWER4_CPU is not set
> # CONFIG_POWER5_CPU is not set
> # CONFIG_POWER6_CPU is not set
> -# CONFIG_POWER7_CPU is not set
> +CONFIG_POWER7_CPU=y
Wow, so the two configs are for different architectures? Not very much
helpful. Could you stick with a single machine and do just small updates
to the config to the point where the problem is no longer present,
please?
[...]
> -CONFIG_MEMCG=y
> -CONFIG_MEMCG_SWAP=y
> -CONFIG_MEMCG_SWAP_ENABLED=y
> -CONFIG_MEMCG_KMEM=y
> +# CONFIG_MEMCG is not set
Is it possible that you have used MEMCG resp. KMEM extension in the bad
config configuration?
[...]
> -CONFIG_SLUB_DEBUG=y
> -# CONFIG_COMPAT_BRK is not set
> -# CONFIG_SLAB is not set
> -CONFIG_SLUB=y
> +CONFIG_COMPAT_BRK=y
> +CONFIG_SLAB=y
I would start with the bad config and SLUB changed to SLAB in the first
step, though.
[...]
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2013-04-22 11:40 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-16 11:00 OOM-killer and strange RSS value in 3.9-rc7 Han Pingtian
2013-04-16 20:16 ` David Rientjes
2013-04-17 8:46 ` Han Pingtian
2013-04-21 0:49 ` Jiri Kosina
2013-04-22 3:15 ` Han Pingtian
2013-04-17 9:47 ` Han Pingtian
2013-04-17 14:19 ` Michal Hocko
2013-04-18 10:15 ` Han Pingtian
2013-04-18 14:17 ` Michal Hocko
2013-04-18 16:55 ` Han Pingtian
2013-04-18 17:55 ` Michal Hocko
2013-04-19 2:33 ` Han Pingtian
2013-04-19 16:43 ` Michal Hocko
2013-04-22 3:18 ` Han Pingtian
2013-04-22 11:40 ` Michal Hocko [this message]
2013-04-23 4:22 ` Han Pingtian
2013-04-23 13:15 ` Michal Hocko
2013-04-24 4:48 ` Han Pingtian
2013-04-24 9:47 ` Michal Hocko
2013-04-24 15:36 ` Christoph Lameter
2013-04-25 6:07 ` Han Pingtian
2013-04-25 17:17 ` Christoph Lameter
2013-04-27 8:20 ` Will Huck
2013-04-29 14:49 ` Christoph Lameter
2013-05-01 3:13 ` Will Huck
2013-05-02 15:10 ` Christoph Lameter
2013-04-25 18:24 ` Christoph Lameter
2013-04-26 6:24 ` Han Pingtian
2013-04-26 14:42 ` Christoph Lameter
2013-04-27 11:24 ` Han Pingtian
2013-04-29 14:50 ` Christoph Lameter
2013-04-29 14:57 ` Michal Hocko
2013-05-02 10:56 ` Han Pingtian
2013-05-02 15:10 ` Christoph Lameter
2013-05-03 3:03 ` Han Pingtian
2013-05-03 15:25 ` Christoph Lameter
2013-05-03 15:34 ` Michal Hocko
2013-05-03 16:16 ` Christoph Lameter
[not found] ` <52bd58da.2501440a.6368.16ddSMTPIN_ADDED_BROKEN@mx.google.com>
[not found] ` <52caac5c.27cb440a.533d.ffffbbd2SMTPIN_ADDED_BROKEN@mx.google.com>
2014-01-21 22:12 ` David Rientjes
2013-04-25 5:41 ` Han Pingtian
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=20130422114052.GB18286@dhcp22.suse.cz \
--to=mhocko@suse.cz \
--cc=hanpt@linux.vnet.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--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).