From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cuda.sgi.com (cuda1.sgi.com [192.48.157.11]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id p41GrIsN184657 for ; Sun, 1 May 2011 11:53:19 -0500 Received: from edge10.ethz.ch (localhost [127.0.0.1]) by cuda.sgi.com (Spam Firewall) with ESMTP id 537D015D1316 for ; Sun, 1 May 2011 09:56:53 -0700 (PDT) Received: from edge10.ethz.ch (edge10.ethz.ch [82.130.75.186]) by cuda.sgi.com with ESMTP id 2SxXuyYkASFDK7Si for ; Sun, 01 May 2011 09:56:53 -0700 (PDT) Message-ID: <4DBD90A3.6000101@inf.ethz.ch> Date: Sun, 1 May 2011 18:56:03 +0200 From: Benjamin Schindler MIME-Version: 1.0 Subject: Re: xfs performance problem References: <201104291828.46420.Martin@lichtvoll.de> In-Reply-To: <201104291828.46420.Martin@lichtvoll.de> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: xfs-bounces@oss.sgi.com Errors-To: xfs-bounces@oss.sgi.com To: Martin Steigerwald Cc: xfs@oss.sgi.com Hi On 29.04.2011 18:28, Martin Steigerwald wrote: > sorry, forgot to cc. > > Am Mittwoch, 27. April 2011 schrieb Dave Chinner: >> On Tue, Apr 26, 2011 at 09:44:04PM +0200, Benjamin Schindler wrote: >>> Hi >>> >>> Since upgrading to newer kernels I have serious problems with xfs >>> performance on my root fs. >>> It runs on a software raid 0 with 2 disks. On the same two disks, >>> there are two more partitions running a software raid-1 with ext3. >>> On the ext3 system, I have no issue, so I assume the drives are >>> fine. >>> But on the xfs filesystem, extracting a linux kernel archive takes 5 >>> minutes or more, running ldconfig similarily long. The harddrives are >>> sata-2. >>> I'm running gentoo linux with kernel 2.6.38-gentoo-r1. I'm attaching >>> the kernel config but I guess more info is needed - just let me know >>> what is needed. >> >> more than likely your problem is that barriers have been enabled for >> MD/DM devices on the new kernel, and they aren't on the old kernel. >> XFS uses barriers by default, ext3 does not. Hence XFS performance >> will change while ext3 will not. Check dmesg output when mounting >> the filesystems on the different kernels. > > But didn't 2.6.38 replace barriers by explicit flushes the filesystem has to > wait for - mitigating most of the performance problems with barriers? > Well, that doesn't seem to work then may be? As always, I'm willing to do testing and provide info if required Cheers Benjamin p.s. please keep the cc _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs