X-Original-To: pgsql-performance-postgresql.org@postgresql.org
Received: from localhost (wm.hub.org [200.46.204.128])
	by postgresql.org (Postfix) with ESMTP id A157B9FB285
	for <pgsql-performance-postgresql.org@postgresql.org>;
	Wed, 23 Aug 2006 19:23:30 -0300 (ADT)
Received: from postgresql.org ([200.46.204.71])
	by localhost (mx1.hub.org [200.46.204.128]) (amavisd-new, port 10024)
	with ESMTP id 06334-07 for
	<pgsql-performance-postgresql.org@postgresql.org>;
	Wed, 23 Aug 2006 22:23:08 +0000 (UTC)
X-Greylist: from auto-whitelisted by SQLgrey-
Received: from servata.com (ip-216-152-249-241.servata.com [216.152.249.241])
	by postgresql.org (Postfix) with ESMTP id E192E9FA4D1
	for <pgsql-performance@postgresql.org>;
	Wed, 23 Aug 2006 19:23:07 -0300 (ADT)
Received: from [209.162.219.253] (helo=dogma.v10.wvs)
	by servata.com with esmtpa (Exim 4.50) id 1GG17m-00070V-Gu
	for pgsql-performance@postgresql.org; Wed, 23 Aug 2006 15:23:02 -0700
Subject: Which benchmark to use for testing FS?
From: Jeff Davis <pgsql@j-davis.com>
To: pgsql-performance@postgresql.org
Content-Type: text/plain
Date: Wed, 23 Aug 2006 15:23:03 -0700
Message-Id: <1156371783.15743.157.camel@dogma.v10.wvs>
Mime-Version: 1.0
X-Mailer: Evolution 2.0.4 (2.0.4-7) 
Content-Transfer-Encoding: 7bit
X-Virus-Scanned: Maia Mailguard 1.0.1
X-Spam-Status: No, hits=3.816 tagged_above=0 required=5
	tests=SPF_HELO_SOFTFAIL, SPF_SOFTFAIL
X-Spam-Level: ***
X-Archive-Number: 200608/377
X-Sequence-Number: 20562

I am planning to test various filesystems on some new hardware I'm
getting. Is pgbench a good way to try out the filesystem?

I'm currently planning to test some or all of:
Linux: ext2, ext3, XFS, JFS, reiser3, reiser4
FreeBSD: UFS, UFS+SU

So, I'm looking for a good way to test just the filesystem performance
through PostgreSQL (since database access is different than normal FS
activity). Would pgbench give me a good approximation?

Also, do ext2 or UFS without soft updates run the risk of losing or
corrupting my data?

I saw Chris Browne did some benchmarks back in 2003 and determined that
JFS was a good choice. However, I assume things have changed somewhat
since then. Does anyone have a pointer to some newer results?

Regards,
	Jeff Davis