Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754912Ab0D0A3G (ORCPT ); Mon, 26 Apr 2010 20:29:06 -0400 Received: from mail-qy0-f179.google.com ([209.85.221.179]:49751 "EHLO mail-qy0-f179.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753559Ab0D0A3E convert rfc822-to-8bit (ORCPT ); Mon, 26 Apr 2010 20:29:04 -0400 MIME-Version: 1.0 In-Reply-To: <201004201124.00326.trenn@suse.de> References: <20100418115949.7b743898@infradead.org> <4BCC147B.10708@tremplin-utc.net> <20100419064325.49cb3108@infradead.org> <201004201124.00326.trenn@suse.de> Date: Mon, 26 Apr 2010 17:29:01 -0700 Message-ID: Subject: Re: [PATCH 7/7] ondemand: Solve the big performance issue with ondemand during disk IO From: Mike Chan To: Thomas Renninger Cc: Arjan van de Ven , =?ISO-8859-1?Q?=C9ric_Piel?= , linux-kernel@vger.kernel.org, akpm@linux-foundation.org, mingo@elte.hu, peterz@infradead.org, tglx@linutronix.de, davej@redhat.com, cpufreq@vger.kernel.org Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2090 Lines: 48 On Tue, Apr 20, 2010 at 2:24 AM, Thomas Renninger wrote: > On Monday 19 April 2010 15:43:25 Arjan van de Ven wrote: >> On Mon, 19 Apr 2010 10:29:47 +0200 >> ?ric Piel wrote: >> > > >> > > The problem and fix are both verified with the "perf timechar" tool. >> > Hi, >> > I don't doubt that keeping the cpu full frequency during IO can >> > improve some specific workloads, however in your log message you >> > don't explain how much we are loosing. >> >> first of all, it's so bad that people will just turn the whole power >> management off... at which point fixing the really bad bug is actually >> quite a win > Not sure you fix a bug, I expect this was done on purpose. > The ondemand governor disadvantages processes with alternating short CPU > load peaks and idle sequences. > IO bound processes typically show up with such a behavior. > > But I follow Eric and agree that if it costs that much, changing > above sounds sane. > Still, I could imagine some people might want to not raise freq on IO bound > process activity, therefore this should get another ondemand param, similar > to ignore_nice_load. > I agree with Thomas here. Some of these assumptions on IO / FSB performance with cpu speed do not hold true on various ARM platforms. Perhaps we could have a min_io_freq value? Which is the min speed for the cpu to run at for IO bound activity. In the original patch, min_io_freq = scaling_max_freq. For various arm devices I can happily set min_io_freq to the lowest cpu speed that satisfies bus speeds. -- Mike > ? ?Thomas > -- > 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/ > -- 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/