Re: [Jfs-discussion] benchmark results

From: Larry McVoy <lm@bitmover.com>
To: tytso@mit.edu
Cc: jfs-discussion@lists.sourceforge.net,
	linux-nilfs@vger.kernel.org, linux-ext4@vger.kernel.org,
	Peter Grandi <pg_jf2@jf2.for.sabi.co.UK>,
	reiserfs-devel@vger.kernel.org, ext-users <ext3-users@redhat.com>,
	xfs@oss.sgi.com, linux-btrfs@vger.kernel.org
Subject: Re: [Jfs-discussion] benchmark results
Date: Fri, 25 Dec 2009 08:22:38 -0800	[thread overview]
Message-ID: <20091225162238.GB19303@bitmover.com> (raw)
In-Reply-To: <20091225161453.GD32757@thunk.org>

On Fri, Dec 25, 2009 at 11:14:53AM -0500, tytso@mit.edu wrote:
> On Thu, Dec 24, 2009 at 05:52:34PM -0800, Christian Kujau wrote:
> > 
> > Well, I do "sync" after each operation, so the data should be on disk, but 
> > that doesn't mean it'll clear the filesystem buffers - but this doesn't 
> > happen that often in the real world too. Also, all filesystem were tested 
> > equally (I hope), yet some filesystem perform better than another - even 
> > if all the content copied/tar'ed/removed would perfectly well fit into the 
> > machines RAM.
> 
> Did you include the "sync" in part of what you timed?  Peter was quite
> right --- the fact that the measured bandwidth in your "cp" test is
> five times faster than the disk bandwidth as measured by hdparm, and
> many file systems had exactly the same bandwidth, makes me very
> suspicious that what was being measured was primarily memory bandwidth
> --- and not very useful when trying to measure file system
> performance.

Dudes, sync() doesn't flush the fs cache, you have to unmount for that.
Once upon a time Linux had an ioctl() to flush the fs buffers, I used
it in lmbench.  

	ioctl(fd, BLKFLSBUF, 0);

No idea if that is still supported, but sync() is a joke for benchmarking.
-- 
---
Larry McVoy                lm at bitmover.com           http://www.bitkeeper.com

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs