From mboxrd@z Thu Jan 1 00:00:00 1970 From: Szakacsits Szabolcs Subject: Re: [benchmark] seek optimization Date: Thu, 15 Jul 2004 12:34:00 +0200 (MEST) Sender: linux-fsdevel-owner@vger.kernel.org Message-ID: References: <20040715055007.GD9383@suse.de> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: Bryan Henderson , Guy , linux-fsdevel@vger.kernel.org, 'Marcel Hilzinger' , 'Per Olofsson' , reiserfs-list@namesys.com Return-path: Received: from mlf.linux.rulez.org ([192.188.244.13]:50702 "EHLO mlf.linux.rulez.org") by vger.kernel.org with ESMTP id S264633AbUGOKeF (ORCPT ); Thu, 15 Jul 2004 06:34:05 -0400 To: Jens Axboe In-Reply-To: <20040715055007.GD9383@suse.de> List-Id: linux-fsdevel.vger.kernel.org On Thu, 15 Jul 2004, Jens Axboe wrote: > > 2) Apparently the 2.6 kernel's IO scheduler has a performance problem. > > Which one did you test? The default in 2.6.7. It seems that one is the AS. I couldn't find any way to query what the IO scheduler is on a running 2.6.7 or how to change it. There were no 'elevator' boot time option given. All IO scheduler were compiled in. The other major suspect for the 2-3% 2.6 performance degradation is the 'block size = GCD(page size, device size)' change. AFAIR the value ended up to be the minimal 512 for the destination device. The 'sys' times are double without using any filesystems: Fs_kernel_method usr sys real CPU raw_24_seek 1.65 17.88 8:19.69 3% raw_26_seek 1.80 33.49 8:27.02 6% It might or might not be related. Szaka