From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759596AbYDKIB5 (ORCPT ); Fri, 11 Apr 2008 04:01:57 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1758089AbYDKIBj (ORCPT ); Fri, 11 Apr 2008 04:01:39 -0400 Received: from one.firstfloor.org ([213.235.205.2]:39063 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757997AbYDKIBj (ORCPT ); Fri, 11 Apr 2008 04:01:39 -0400 Date: Fri, 11 Apr 2008 10:06:17 +0200 From: Andi Kleen To: Ingo Molnar Cc: Andi Kleen , Karsten Wiese , linux-kernel@vger.kernel.org Subject: Re: [PATCH] x86: set_cyc2ns_scale() remove tsc_now and ns_now Message-ID: <20080411080617.GP10019@one.firstfloor.org> References: <200804102331.11815.fzu@wemgehoertderstaat.de> <873apsn8g7.fsf@basil.nowhere.org> <20080411075554.GA6834@elte.hu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20080411075554.GA6834@elte.hu> User-Agent: Mutt/1.4.2.1i Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Apr 11, 2008 at 09:55:54AM +0200, Ingo Molnar wrote: > > * Andi Kleen wrote: > > > (actually it is still the wrong time -- really needs a grace period > > during which the TSC is not used > > ftp://firstfloor.org/pub/ak/quilt/patches/sched-clock implemented some > > of these ideas against an older kernel) > > recent CPUs have constant-freq TSCs so it's mostly a legacy issue, but Actually there millions of non constant freq TSC CPUs shipped each quarter ... > we dont really have to worry about complications like grace periods - > higher layers in the scheduler protect against temporary sched_clock() > outliers. But you still get scheduling hickups even with the sanity check. If the scheduler depends on a smooth time that is not good and my (admittedly much less than yours) understanding of CFS is that it relies on that. Especially ondemand can cause quite a lot of cpufreq changes on some workloads. > So i think this can all be done much simpler. Just get rid of > the global cpu_khz notion, sched_clock() should simply follow the ->freq > value - and that's it. At some point you have to generate an offset to something and that offset must be different for different frequencies, otherwise you get large systematic errors () -Andi