public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Dipankar Sarma <dipankar@in.ibm.com>
To: Christopher Friesen <cfriesen@nortel.com>
Cc: Al Viro <viro@ftp.linux.org.uk>,
	Roland Dreier <rolandd@cisco.com>, Sonny Rao <sonny@burdell.org>,
	linux-kernel@vger.kernel.org, "Theodore Ts'o" <tytso@mit.edu>,
	bharata@in.ibm.com, trond.myklebust@fys.uio.no
Subject: Re: dentry_cache using up all my zone normal memory -- also seen on 2.6.14-rc2
Date: Thu, 22 Sep 2005 23:57:19 +0530	[thread overview]
Message-ID: <20050922182719.GA4729@in.ibm.com> (raw)
In-Reply-To: <4332CAEA.1010509@nortel.com>

On Thu, Sep 22, 2005 at 09:16:58AM -0600, Christopher Friesen wrote:
> Al Viro wrote:
> 
> >Umm...   How many RCU callbacks are pending?
> 
> According to this we had 4127306 pending rcu callbacks.  A few seconds 
> later it was down to 0.
> 
> Full output is below.
> 
> /proc/sys/fs/dentry-state:
> 1611    838     45      0       0       0
> 
> pages_with_[29]_dentries: 142355
> dcache_pages total: 142407
> prune_dcache: requested  1 freed 1
> dcache lru list data:
> dentries total: 839
> dentries in_use: 43
> dentries free: 796
> dentries referenced: 839

These two should make it clear that there were only 1611 dentries
in the dcache and 839 in LRU list. Not too many pinned dentries.
So, all the dentries you saw in the slab were dentries out
of dcache but waiting for corresponding RCU grace periods
to happen.

This can happen if a task runs for too long inside the kernel
holding up context switches or usermode code running on that
cpu. The fact that RCU grace period eventually happens
and the dentries are freed means that something intermittently
holds up RCU. Is this 2.6.10 vanilla or does it have other
patches in there ?

Thanks
Dipankar

  parent reply	other threads:[~2005-09-22 18:33 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-09-21 16:26 dentry_cache using up all my zone normal memory Christopher Friesen
2005-09-21 16:53 ` Christopher Friesen
2005-09-21 19:46   ` dentry_cache using up all my zone normal memory -- also seen on 2.6.14-rc2 Christopher Friesen
2005-09-21 20:07     ` Sonny Rao
2005-09-21 20:27       ` Christopher Friesen
2005-09-21 20:49       ` Christopher Friesen
2005-09-21 20:59       ` Christopher Friesen
2005-09-21 20:58         ` Sonny Rao
2005-09-21 21:00         ` Dipankar Sarma
2005-09-21 21:14           ` Al Viro
2005-09-21 21:14           ` Trond Myklebust
2005-09-21 21:25             ` Christopher Friesen
2005-09-21 21:29               ` Christopher Friesen
2005-09-21 21:25           ` Christopher Friesen
2005-09-21 22:03             ` Roland Dreier
2005-09-22  3:11               ` Al Viro
2005-09-22  3:54                 ` Christopher Friesen
2005-09-22  4:17                   ` Al Viro
2005-09-22 14:47                     ` Christopher Friesen
2005-09-22 15:16                     ` Christopher Friesen
2005-09-22 18:12                       ` dentry_cache using up all my zone normal memory -- new data point Christopher Friesen
2005-09-22 18:27                       ` Dipankar Sarma [this message]
2005-09-22 19:03                         ` dentry_cache using up all my zone normal memory -- also seen on 2.6.14-rc2 Christopher Friesen
2005-09-22 19:18                           ` Dipankar Sarma
2005-09-22 21:37                             ` Christopher Friesen
2005-09-22 21:44                               ` Sonny Rao
2005-09-22 21:55                                 ` Christopher Friesen
2005-09-22 22:04                                   ` Randy.Dunlap
2005-09-26  4:43                                     ` [PATCH/RFC] sysrq: updating console_loglevel Randy.Dunlap
2005-09-22 22:05                             ` dentry_cache using up all my zone normal memory -- also seen on 2.6.14-rc2 Christopher Friesen
2005-10-04 19:43                       ` Dipankar Sarma
2005-10-04 20:02                         ` Christopher Friesen
2005-10-05  4:00                           ` Dipankar Sarma
2005-09-30 22:03 ` dentry_cache using up all my zone normal memory Christopher Friesen
2005-10-01 23:22   ` Marcelo
2005-10-02  6:04     ` Christopher Friesen
2005-10-02 19:55       ` Marcelo

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=20050922182719.GA4729@in.ibm.com \
    --to=dipankar@in.ibm.com \
    --cc=bharata@in.ibm.com \
    --cc=cfriesen@nortel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rolandd@cisco.com \
    --cc=sonny@burdell.org \
    --cc=trond.myklebust@fys.uio.no \
    --cc=tytso@mit.edu \
    --cc=viro@ftp.linux.org.uk \
    /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