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 p418nEeH165481 for ; Sun, 1 May 2011 03:49:14 -0500 Received: from ipmail06.adl6.internode.on.net (localhost [127.0.0.1]) by cuda.sgi.com (Spam Firewall) with ESMTP id 166DF15D06BF for ; Sun, 1 May 2011 01:52:48 -0700 (PDT) Received: from ipmail06.adl6.internode.on.net (ipmail06.adl6.internode.on.net [150.101.137.145]) by cuda.sgi.com with ESMTP id HGSQeB6hsmDKF0gI for ; Sun, 01 May 2011 01:52:48 -0700 (PDT) Date: Sun, 1 May 2011 18:52:46 +1000 From: Dave Chinner Subject: Re: xfs performance problem Message-ID: <20110501085246.GF13542@dastard> References: <4DB72084.8020205@inf.ethz.ch> <20110427023534.GF12436@dastard> <201104291827.35801.Martin@lichtvoll.de> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <201104291827.35801.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 On Fri, Apr 29, 2011 at 06:27:34PM +0200, Martin Steigerwald wrote: > 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? IIRC, it depends on whether the hardware supports FUA or not. If it doesn't then device cache flushes are used to emulate FUA and so performance can still suck. Christoph will no doubt correct me if I got that wrong ;) Cheers, Dave. -- Dave Chinner david@fromorbit.com _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs