Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756805AbZIDMk7 (ORCPT ); Fri, 4 Sep 2009 08:40:59 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756773AbZIDMk6 (ORCPT ); Fri, 4 Sep 2009 08:40:58 -0400 Received: from mx3.mail.elte.hu ([157.181.1.138]:35284 "EHLO mx3.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756098AbZIDMk5 (ORCPT ); Fri, 4 Sep 2009 08:40:57 -0400 Date: Fri, 4 Sep 2009 14:40:54 +0200 From: Ingo Molnar To: Peter Zijlstra Cc: Marton Balint , Andreas Mohr , linux-kernel@vger.kernel.org Subject: Re: CPU scheduler weirdness? Message-ID: <20090904124054.GA9490@elte.hu> References: <1250683834.7583.360.camel@twins> <1250707331.7154.1.camel@laptop> <20090820105645.GA23635@elte.hu> <1252053631.7564.2.camel@twins> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1252053631.7564.2.camel@twins> User-Agent: Mutt/1.5.18 (2008-05-17) X-ELTE-SpamScore: -1.5 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=-1.5 required=5.9 tests=BAYES_00 autolearn=no SpamAssassin version=3.2.5 -1.5 BAYES_00 BODY: Bayesian spam probability is 0 to 1% [score: 0.0000] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1308 Lines: 39 * Peter Zijlstra wrote: > On Thu, 2009-09-03 at 23:57 +0200, Marton Balint wrote: > > > sched: fine-tune SD_MC_INIT: > > > 14800984706bf6936bbec5187f736e928be5c218 > > > > > > If I add again the removed SD_BALANCE_NEWIDLE to flags, then everything works > > > as expected. So what would be the correct fix for this bug? Revert the patch? > > > Or just add SD_BALANCE_NEWIDLE to flags? > > > > > > Ingo, Peter, could any of you guys have a look at the commit > > that caused this bug? Is it OK to revert it? Or a fix somewhere > > else is necessary? I'm pushing this because I hope that this bug > > will get fixed in the upcoming stable kernel... > > I'm fine with re-adding SD_BALANCE_IDLE and SD_WAKE_IDLE on > SMT/MC/CPU levels. > > Ingo? Ok, agreed. I have re-benchmarked a couple of key workload and it seems like a good change, on top of your load-balancer fixes. Marton, could you please double check the latest -tip tree: http://people.redhat.com/mingo/tip.git/README Does it resolve the problem? Thanks, Ingo -- 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/