Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1764510AbXKPJT0 (ORCPT ); Fri, 16 Nov 2007 04:19:26 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1763600AbXKPJTI (ORCPT ); Fri, 16 Nov 2007 04:19:08 -0500 Received: from smtp-outbound-1.vmware.com ([65.113.40.141]:50692 "EHLO smtp-outbound-1.vmware.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760035AbXKPJTF (ORCPT ); Fri, 16 Nov 2007 04:19:05 -0500 Date: Fri, 16 Nov 2007 01:19:04 -0800 From: Micah Dowty To: Ingo Molnar Cc: Christoph Lameter , Kyle Moffett , Cyrus Massoumi , LKML Kernel , Andrew Morton , Mike Galbraith , Paul Menage , Dmitry Adamushko , Peter Williams Subject: Re: High priority tasks break SMP balancer? Message-ID: <20071116091904.GB31219@vmware.com> References: <20071110001103.GD16250@vmware.com> <2FAA6826-653E-482F-A037-C539BAEEA1DA@mac.com> <20071115191408.GA4914@vmware.com> <20071115202425.GC4914@vmware.com> <20071115213510.GA16079@vmware.com> <20071116024408.GA20322@vmware.com> <20071116060700.GD16273@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20071116060700.GD16273@elte.hu> User-Agent: Mutt/1.5.16 (2007-06-09) Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1271 Lines: 26 On Fri, Nov 16, 2007 at 07:07:00AM +0100, Ingo Molnar wrote: > > My best guess is that this has something to do with the timing with > > which we sample the CPU's instantaneous load when calculating the load > > averages.. but I still understand only the basics of the scheduler and > > SMP balancer. All I really know for sure at this point regarding your > > patch is that git-bisect found it for me. > > hm, your code uses timeouts for this, right? The CPU load average that > is used for SMP load balancing is sampled from the scheduler tick - and > has been sampled from the scheduler tick for eons. v2.6.23 defaulted to > a different method but v2.6.24 samples it from the tick again. So my > guess is, your testcode behave similarly on 2.6.22 too, correct? My sample program (and the VMware code which I originally observed this behaviour with) wakes up frequently using /dev/rtc. I know the problem occurs on 2.6.20 and 2.6.23.1. I haven't tried 2.6.22 yet, but I'll do so as soon as I can. Thanks, --Micah - 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/