Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933109AbXIAWK5 (ORCPT ); Sat, 1 Sep 2007 18:10:57 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756665AbXIAWKs (ORCPT ); Sat, 1 Sep 2007 18:10:48 -0400 Received: from ns.suse.de ([195.135.220.2]:45118 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756577AbXIAWKr (ORCPT ); Sat, 1 Sep 2007 18:10:47 -0400 To: Michal Piotrowski Cc: LKML , "CK Mailinglist" Subject: Re: [ANNOUNCE] DeskOpt - on fly task, i/o scheduler optimization References: <46D8354A.3030208@googlemail.com> From: Andi Kleen Date: 02 Sep 2007 00:10:46 +0200 In-Reply-To: <46D8354A.3030208@googlemail.com> Message-ID: User-Agent: Gnus/5.09 (Gnus v5.9.0) Emacs/21.3 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1197 Lines: 35 Michal Piotrowski writes: > Here is something that might be useful for gamers and audio/video editors > http://www.stardust.webpages.pl/files/tools/deskopt/ To make it double cool combine that with the generic genetic optimizer for parameters that was posted a couple of months ago. > > You can easily tune CFS/CFQ scheduler params > > sched_batch_wakeup_granularity_ns > sched_latency_ns > sched_min_granularity_ns > sched_runtime_limit_ns > sched_stat_granularity_ns > sched_wakeup_granularity_ns > > back_seek_max > back_seek_penalty > fifo_expire_async > fifo_expire_sync > quantum > slice_async > slice_async_rq > slice_idle > slice_sync > You should probably add the device queue length too. That seems to often have a large impact on IO scheduling because on modern long queue controllers the Linux IO scheduler often doesn't have much to do because the device queue just eats it all up quickly. -Andi - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/