linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Chinner <dgc@sgi.com>
To: Eric Sandeen <sandeen@sandeen.net>
Cc: David Chinner <dgc@sgi.com>,
	Justin Piszcz <jpiszcz@lucidpixels.com>,
	Jon Collette <jon@etelos.com>,
	Joshua Baker-LePain <jlb17@duke.edu>,
	linux-ide-arrays@lists.math.uh.edu, linux-raid@vger.kernel.org,
	xfs@oss.sgi.com
Subject: Re: 3ware 9650 tips
Date: Tue, 17 Jul 2007 08:21:24 +1000	[thread overview]
Message-ID: <20070716222124.GF31489@sgi.com> (raw)
In-Reply-To: <469B93CA.30801@sandeen.net>

On Mon, Jul 16, 2007 at 10:50:34AM -0500, Eric Sandeen wrote:
> David Chinner wrote:
> > On Mon, Jul 16, 2007 at 12:41:15PM +1000, David Chinner wrote:
> >> On Fri, Jul 13, 2007 at 03:36:46PM -0400, Justin Piszcz wrote:
> ...
> >> If you've got any sort of serious disk array, ext3 is not the filesystem
> >> to use....
> > 
> > To show what the difference is, I used blktrace and Chris Mason's
> > seekwatcher script on a simple, single threaded dd command on
> > a 12 disk dm RAID0 stripe:
> > 
> > # dd if=/dev/zero of=/mnt/scratch/fred bs=1024k count=10k; sync
> > 
> > http://oss.sgi.com/~dgc/writes/ext3_write.png
> > http://oss.sgi.com/~dgc/writes/xfs_write.png
> 
> Were those all with default mkfs & mount options?  ext3 in writeback
> mode might be an interesting comparison too.

Defaults. i.e.

# mkfs.ext3 /dev/mapper/dm0

# mkfs.xfs /dev/mapper/dm0

The mkfs.xfs picked up sunit/swidth correctly from the dm volume.

Last time I checked, writeback made little difference to ext3 throughput;
maybe 5-10% at most. I'll run it again later today...

Cheers,

Dave.
-- 
Dave Chinner
Principal Engineer
SGI Australian Software Group

  reply	other threads:[~2007-07-16 22:21 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <alpine.LRH.0.999.0707131356520.25773@chaos.egr.duke.edu>
2007-07-13 18:35 ` 3ware 9650 tips Justin Piszcz
2007-07-13 18:54   ` Jon Collette
2007-07-13 19:36     ` Justin Piszcz
2007-07-16  2:41       ` David Chinner
2007-07-16 12:22         ` David Chinner
2007-07-16 12:39           ` Bernd Schubert
2007-07-16 15:50           ` Eric Sandeen
2007-07-16 22:21             ` David Chinner [this message]
2007-07-16 15:43         ` Joshua Baker-LePain
2007-07-16 17:15           ` [Advocacy] " Bryan J. Smith
2007-07-16 17:40             ` Al Boldi
2007-07-16 17:48               ` Matthew Wilcox
2007-07-16 18:28                 ` [RFC] VFS: data=ordered (was: [Advocacy] Re: 3ware 9650 tips) Al Boldi
2007-07-16 19:02                   ` Matthew Wilcox
2007-07-16 18:38                 ` [Advocacy] Re: 3ware 9650 tips Bryan J. Smith
2007-07-16 17:34           ` Stuart Levy
2007-07-13 19:04   ` Joshua Baker-LePain
2007-07-13 23:30     ` Michael Tokarev
2007-07-14  1:23   ` Andrew Klaassen
2007-07-14  8:08     ` Justin Piszcz
2007-07-14 16:10       ` Andrew Klaassen
2007-07-14 16:11         ` Justin Piszcz
2007-07-14 16:14           ` Andrew Klaassen
2007-07-14 16:18             ` Justin Piszcz
2007-07-14  9:04   ` Mikael Abrahamsson
2007-07-14 16:11     ` Andrew Klaassen

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=20070716222124.GF31489@sgi.com \
    --to=dgc@sgi.com \
    --cc=jlb17@duke.edu \
    --cc=jon@etelos.com \
    --cc=jpiszcz@lucidpixels.com \
    --cc=linux-ide-arrays@lists.math.uh.edu \
    --cc=linux-raid@vger.kernel.org \
    --cc=sandeen@sandeen.net \
    --cc=xfs@oss.sgi.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).