From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965525Ab0B0KvX (ORCPT ); Sat, 27 Feb 2010 05:51:23 -0500 Received: from lucidpixels.com ([75.144.35.66]:34705 "EHLO lucidpixels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S965301Ab0B0KvQ (ORCPT ); Sat, 27 Feb 2010 05:51:16 -0500 Date: Sat, 27 Feb 2010 05:51:15 -0500 (EST) From: Justin Piszcz To: Eric Sandeen cc: linux-ext4@vger.kernel.org, linux-kernel@vger.kernel.org, Alan Piszcz Subject: Re: EXT4 is ~2X as slow as XFS (593MB/s vs 304MB/s) for writes? In-Reply-To: Message-ID: References: <4B886CA1.9050906@redhat.com> <4B887160.2090606@redhat.com> <4B887548.50508@redhat.com> User-Agent: Alpine 2.00 (DEB 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sat, 27 Feb 2010, Justin Piszcz wrote: > > > On Fri, 26 Feb 2010, Eric Sandeen wrote: > > > Eric Sandeen wrote: > > > > Oh, you need very recent util-linux-ng as well, and use libblkid from there > > with: > > > > [e2fsprogs] # ./configure --disable-libblkid > > > > Otherwise you can just feed mkfs.ext4 stripe & stride manually. > > > > -Eric > > I also tried with the default chunk size (64KiB) incase ext4 had a problem with chunk sizes > 64KiB, the results were the same for ext4, I also tried ext2 & ext3 as well just to see what their performance would be: p63:~# mkfs.ext2 -b 4096 -E stride=16,stripe-width=176 /dev/md0 p63:~# mount /dev/md0 /r1 p63:/r1# dd if=/dev/zero of=file bs=1M count=10240 10737418240 bytes (11 GB) copied, 19.9434 s, 538 MB/s p63:/r1# p63:~# mkfs.ext3 -b 4096 -E stride=16,stripe-width=176 /dev/md0 p63:~# mount /dev/md0 /r1 p63:/r1# dd if=/dev/zero of=file bs=1M count=10240 10737418240 bytes (11 GB) copied, 31.0195 s, 346 MB/s p63:~# mkfs.ext4 -b 4096 -E stride=16,stripe-width=176 /dev/md0 p63:~# mount /dev/md0 /r1 p63:/r1# dd if=/dev/zero of=file bs=1M count=10240 10737418240 bytes (11 GB) copied, 35.3866 s, 303 MB/s And, for comparison, XFS: p63:~# mkfs.xfs -f /dev/md0 > /dev/null 2>&1 p63:~# mount /dev/md0 /r1 p63:~# cd /r1 p63:/r1# dd if=/dev/zero of=file bs=1M count=10240 10240+0 records in 10240+0 records out 10737418240 bytes (11 GB) copied, 18.1527 s, 592 MB/s p63:/r1#