linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Sonny Rao <sonny@burdell.org>
To: David Chinner <dgc@sgi.com>
Cc: Bharata B Rao <bharata@in.ibm.com>, Theodore Ts'o <tytso@mit.edu>,
	Dipankar Sarma <dipankar@in.ibm.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: VM balancing issues on 2.6.13: dentry cache not getting shrunk enough
Date: Wed, 14 Sep 2005 11:48:52 -0400	[thread overview]
Message-ID: <20050914154852.GB6172@kevlar.burdell.org> (raw)
In-Reply-To: <20050913215932.GA1654338@melbourne.sgi.com>

On Wed, Sep 14, 2005 at 07:59:32AM +1000, David Chinner wrote:
> On Tue, Sep 13, 2005 at 02:17:52PM +0530, Bharata B Rao wrote:
> > 
> > Second is Sonny Rao's rbtree dentry reclaim patch which is an attempt
> > to improve this dcache fragmentation problem.
> 
> FYI, in the past I've tried this patch to reduce dcache fragmentation on
> an Altix (16k pages, 62 dentries to a slab page) under heavy
> fileserver workloads and it had no measurable effect. It appeared
> that there was almost always at least one active dentry on each page
> in the slab.  The story may very well be different on 4k page
> machines, however.
> 
> Typically, fragmentation was bad enough that reclaim removed ~90% of
> the working set of dentries to free about 1% of the memory in the
> dentry slab. We had to get down to freeing > 95% of the dentry cache
> before fragmentation started to reduce and the system stopped trying to
> reclaim the dcache which we then spent the next 10 minutes
> repopulating......
> 
> We also tried separating out directory dentries into a separate slab
> so that (potentially) longer lived dentries were clustered together
> rather than sparsely distributed around the slab cache.  Once again,
> it had no measurable effect on the level of fragmentation (with or
> without the rbtree patch).

I'm not surprised... With 62 dentrys per page, the likelyhood of
success is very small, and in fact performance could degrade since we
are holding the dcache lock more often and doing less useful work.

It has been over a year and my memory is hazy, but I think I did see
about a 10% improvement on my workload (some sort of SFS simulation
with millions of files being randomly accessed)  on an x86 machine but CPU
utilization also went way up which I think was the dcache lock.

Whatever happened to the  vfs_cache_pressue  band-aid/sledgehammer ?  
Is it not considered an option ?

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2005-09-14 15:48 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-09-11 10:57 Theodore Ts'o
2005-09-11 12:00 ` Dipankar Sarma
2005-09-12  3:16   ` Theodore Ts'o
2005-09-12  6:16     ` Martin J. Bligh
2005-09-12 12:53       ` Bharata B Rao
2005-09-13  8:47     ` Bharata B Rao
2005-09-13 21:59       ` David Chinner
2005-09-14  9:01         ` Andi Kleen
2005-09-14  9:16           ` Manfred Spraul
2005-09-14  9:43             ` Andrew Morton
2005-09-14  9:52               ` Dipankar Sarma
2005-09-14 22:44               ` Theodore Ts'o
2005-09-14  9:35           ` Andrew Morton
2005-09-14 13:57           ` Martin J. Bligh
2005-09-14 15:37             ` Sonny Rao
2005-09-15  7:21             ` Helge Hafting
2005-09-14 22:48           ` David Chinner
2005-09-14 15:48         ` Sonny Rao [this message]
2005-09-14 22:02           ` David Chinner
2005-09-14 22:40             ` Sonny Rao
2005-09-15  1:14               ` David Chinner
2005-10-06  6:27         ` [PATCH] dcache: separate slab for directory dentries David Chinner, gnb
2005-10-06 12:28           ` Dave Kleikamp
2005-10-07  3:54             ` Greg Banks
2005-10-07 13:00               ` Dave Kleikamp
2005-09-14 21:34       ` VM balancing issues on 2.6.13: dentry cache not getting shrunk enough Marcelo Tosatti
2005-09-14 21:43         ` Dipankar Sarma
2005-09-15  4:28         ` Bharata B Rao
2005-09-14 23:08       ` Marcelo Tosatti
2005-09-15  9:39         ` Bharata B Rao
2005-09-15 13:29           ` Marcelo Tosatti
2005-10-02 16:32             ` Bharata B Rao
2005-10-02 20:06               ` Marcelo
2005-10-04 13:36                 ` shrinkable cache statistics [was Re: VM balancing issues on 2.6.13: dentry cache not getting shrunk enough] Bharata B Rao
2005-10-05 21:25                   ` Marcelo Tosatti
2005-10-07  8:12                     ` Bharata B Rao

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=20050914154852.GB6172@kevlar.burdell.org \
    --to=sonny@burdell.org \
    --cc=bharata@in.ibm.com \
    --cc=dgc@sgi.com \
    --cc=dipankar@in.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=tytso@mit.edu \
    /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