From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932862AbXCDOhg (ORCPT ); Sun, 4 Mar 2007 09:37:36 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932873AbXCDOhg (ORCPT ); Sun, 4 Mar 2007 09:37:36 -0500 Received: from cantor.suse.de ([195.135.220.2]:35024 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932862AbXCDOhf (ORCPT ); Sun, 4 Mar 2007 09:37:35 -0500 From: Andi Kleen Organization: SUSE Linux Products GmbH, Nuernberg, GF: Markus Rex, HRB 16746 (AG Nuernberg) To: "Guillaume Chazarain" Subject: Re: [1/3] Bugfix: Don't use the TSC in sched_clock if unstable Date: Sun, 4 Mar 2007 15:37:27 +0100 User-Agent: KMail/1.9.5 Cc: "Ingo Molnar" , linux-kernel@vger.kernel.org References: <3d8471ca0703031341l1768fe7rccf40712e452ea09@mail.gmail.com> In-Reply-To: <3d8471ca0703031341l1768fe7rccf40712e452ea09@mail.gmail.com> MIME-Version: 1.0 Content-Disposition: inline Message-Id: <200703041537.27581.ak@suse.de> Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Saturday 03 March 2007 22:41, Guillaume Chazarain wrote: > http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=f9690982b8c2f9a2c65acdc113e758ec356676a3 > caused a regression by letting sched_clock use the TSC even when cpufreq > disabled it. This caused scheduling weirdnesses. What weirdnesses? Did you actually see any? Hard data please. I don't like this because right now it will effectively disable TSC use on anything with pstate invariant TSC and using cpufreq: that is all modern AMD systems. This is IMHO a serious bug in the timer subsystem which I intend to fix. Also I don't see where your instability should come from. AFAIK there are only minor hickups in the result which shouldn't be a problem IMHO. -Andi