From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cuda.sgi.com (cuda2.sgi.com [192.48.176.25]) by oss.sgi.com (8.14.3/8.14.3/SuSE Linux 0.8) with ESMTP id n84ErPCh216643 for ; Fri, 4 Sep 2009 09:53:42 -0500 Date: Fri, 4 Sep 2009 10:51:09 -0400 From: Christoph Hellwig Subject: Re: [PATCH 00/14] repair memory usage reductions Message-ID: <20090904145109.GA8351@infradead.org> References: <20090902175531.469184575@bombadil.infradead.org> <20090903204940.GB24510@sgi.com> <20090904025753.GB7146@discord.disaster> <20090904133737.GD12052@sgi.com> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <20090904133737.GD12052@sgi.com> 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: Geoffrey Wehrman Cc: Christoph Hellwig , xfs@oss.sgi.com On Fri, Sep 04, 2009 at 08:37:37AM -0500, Geoffrey Wehrman wrote: > On Fri, Sep 04, 2009 at 12:57:53PM +1000, Dave Chinner wrote: > | Christoph asked me to repeat what I said on #xfs w.r.t the regression. > > Thank you for the detailed description. All I had was a statement from > January 2008, "Barry has completed the memory optimization, but initial > testing shows that performance has regressed." That was the last update > recorded on Barry's work. > > | With that in mind, I think the memory usage optimisation is far more > | important to the majority of XFS users than the CPU usage regression > | it causes as the majority of users don't have RAM-rich environments > | to run repair in. > > I agree. In my testing I haven't seen big differences in performance, it sometimes got a bit faster and sometimes a bit slower. I will send out a more detailed performace report in a few days. _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs