linux-nfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Simon Kirby <sim@hostway.ca>
To: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: linux-nfs@vger.kernel.org
Subject: Re: System CPU increasing on idle 2.6.36
Date: Wed, 8 Dec 2010 14:36:22 -0800	[thread overview]
Message-ID: <20101208223622.GA3796@hostway.ca> (raw)
In-Reply-To: <1291845189.3067.31.camel@heimdal.trondhjem.org>

On Wed, Dec 08, 2010 at 04:53:09PM -0500, Trond Myklebust wrote:

> Possibly a side effect of the fs/fs-writeback.c changes in 2.6.36? You
> do appear to be hitting a lot of spinlock contention, but I suspect that
> a lot of it is coming from writeback_sb_inodes, writeback_single_inode
> and queue_io, all of which seem unnaturally high on your stats above.
> 
> I don't see how you can be seeing no traffic on the wire. You are
> certainly hitting some page writeout (0.2% nfs_pageio_doio).

It really seems to not be doing anything.  I ran nfsstat -Zcv for 5
minutes, and the only non-zero counters are rpc calls and authrefrsh,
even though perf top shows similar profiles the whole time.

Simon-

  reply	other threads:[~2010-12-08 22:36 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-12-08 21:25 System CPU increasing on idle 2.6.36 Simon Kirby
2010-12-08 21:53 ` Trond Myklebust
2010-12-08 22:36   ` Simon Kirby [this message]
2010-12-09  4:37     ` Trond Myklebust
2010-12-14 23:38       ` Simon Kirby
2010-12-15  1:10         ` Simon Kirby
2010-12-15  1:56           ` Simon Kirby
2010-12-15 18:08             ` J. Bruce Fields
2010-12-15 18:22               ` Trond Myklebust
2010-12-15 18:38                 ` J. Bruce Fields
2010-12-15 19:33                   ` Trond Myklebust
2010-12-15 19:49                     ` J. Bruce Fields
2010-12-15 19:57                       ` Trond Myklebust
2010-12-15 20:19                         ` J. Bruce Fields
2010-12-15 20:32                           ` Trond Myklebust
2010-12-15 21:48                             ` J. Bruce Fields
2010-12-15 22:15                               ` Trond Myklebust
2010-12-15 22:29                                 ` J. Bruce Fields
2010-12-15 22:55                                   ` J. Bruce Fields
2010-12-15 23:58                                     ` Trond Myklebust
2010-12-16  0:36                                       ` J. Bruce Fields
2011-09-27  0:39   ` NFS client growing system CPU Simon Kirby
2011-09-27 11:42     ` Trond Myklebust
2011-09-27 16:49       ` Simon Kirby
2011-09-27 17:04         ` Trond Myklebust
2011-09-28 19:58           ` Simon Kirby
2011-09-30  0:58             ` Simon Kirby
2011-09-30  1:11               ` Myklebust, Trond
2011-10-05 23:07                 ` Simon Kirby
2010-12-18  1:08 ` System CPU increasing on idle 2.6.36 Simon Kirby
2010-12-21 20:31   ` Mark Moseley
2010-12-29 22:03   ` Simon Kirby
2011-01-04 17:42     ` Mark Moseley
2011-01-04 21:40       ` Simon Kirby
2011-01-05 19:43         ` Mark Moseley
2011-01-07 18:05           ` Mark Moseley
2011-01-07 18:12             ` Mark Moseley
2011-01-07 19:33               ` Mark Moseley
2011-01-08  0:52             ` Simon Kirby
2011-01-08  1:30               ` Mark Moseley

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=20101208223622.GA3796@hostway.ca \
    --to=sim@hostway.ca \
    --cc=Trond.Myklebust@netapp.com \
    --cc=linux-nfs@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).