From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1762670AbXGFHyW (ORCPT ); Fri, 6 Jul 2007 03:54:22 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755829AbXGFHyP (ORCPT ); Fri, 6 Jul 2007 03:54:15 -0400 Received: from web32606.mail.mud.yahoo.com ([68.142.207.233]:40434 "HELO web32606.mail.mud.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1754030AbXGFHyO (ORCPT ); Fri, 6 Jul 2007 03:54:14 -0400 X-YMail-OSG: 9HUhH_oVM1kAe0piHQLdBYUK77hwOYti1lAlv4K_S9mB6ViW0I3qt0ZYz4RBmua8Kf5F9iXbeiVpcreI1p.MIOJWrg-- X-RocketYMMF: knobi.rm Date: Fri, 6 Jul 2007 00:54:13 -0700 (PDT) From: Martin Knoblauch Reply-To: spamtrap@knobisoft.de Subject: Re: Understanding I/O behaviour To: Jesper Juhl , Robert Hancock Cc: knobi@knobisoft.de, linux-kernel@vger.kernel.org In-Reply-To: <9a8748490707051653q6e1b6bf3g9a3d6edf213867d9@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7BIT Message-ID: <684951.37870.qm@web32606.mail.mud.yahoo.com> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org --- Jesper Juhl wrote: > On 06/07/07, Robert Hancock wrote: > [snip] > > > > Try playing with reducing /proc/sys/vm/dirty_ratio and see how that > > helps. This workload will fill up memory with dirty data very > quickly, > > and it seems like system responsiveness often goes down the toilet > when > > this happens and the system is going crazy trying to write it all > out. > > > > Perhaps trying out a different elevator would also be worthwhile. > AS seems to be the best one (NOOP and DeadLine seem to be equally OK). CFQ gives less (about 10-15%) throughput except for the kernel with the cfs cpu scheduler, where CFQ is on par with the other IO schedulers. Thanks Martin ------------------------------------------------------ Martin Knoblauch email: k n o b i AT knobisoft DOT de www: http://www.knobisoft.de