From: "Jeffrey W. Baker" <jwbaker@acm.org>
Subject: ZFS, XFS, and EXT4 compared
Date: Wed, 29 Aug 2007 23:16:51 -0700
Message-ID: <1188454611.23311.13.camel@toonses.gghcwest.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
To: zfs-discuss@opensolaris.org, xfs@oss.sgi.com,
	linux-ext4@vger.kernel.org
Return-path: <zfs-discuss-bounces@opensolaris.org>
List-Unsubscribe: <http://mail.opensolaris.org/mailman/listinfo/zfs-discuss>,
	<mailto:zfs-discuss-request@opensolaris.org?subject=unsubscribe>
List-Archive: <http://mail.opensolaris.org/pipermail/zfs-discuss>
List-Post: <mailto:zfs-discuss@opensolaris.org>
List-Help: <mailto:zfs-discuss-request@opensolaris.org?subject=help>
List-Subscribe: <http://mail.opensolaris.org/mailman/listinfo/zfs-discuss>,
	<mailto:zfs-discuss-request@opensolaris.org?subject=subscribe>
Sender: zfs-discuss-bounces@opensolaris.org
Errors-To: zfs-discuss-bounces@opensolaris.org
List-Id: linux-ext4.vger.kernel.org

I have a lot of people whispering "zfs" in my virtual ear these days,
and at the same time I have an irrational attachment to xfs based
entirely on its lack of the 32000 subdirectory limit.  I'm not afraid of
ext4's newness, since really a lot of that stuff has been in Lustre for
years.  So a-benchmarking I went.  Results at the bottom:

http://tastic.brillig.org/~jwb/zfs-xfs-ext4.html

Short version: ext4 is awesome.  zfs has absurdly fast metadata
operations but falls apart on sequential transfer.  xfs has great
sequential transfer but really bad metadata ops, like 3 minutes to tar
up the kernel.

It would be nice if mke2fs would copy xfs's code for optimal layout on a
software raid.  The mkfs defaults and the mdadm defaults interact badly.

Postmark is somewhat bogus benchmark with some obvious quantization
problems.

Regards,
jwb