Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754306AbZCHSkB (ORCPT ); Sun, 8 Mar 2009 14:40:01 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753384AbZCHSjw (ORCPT ); Sun, 8 Mar 2009 14:39:52 -0400 Received: from mail.gmx.net ([213.165.64.20]:50019 "HELO mail.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1753203AbZCHSjw (ORCPT ); Sun, 8 Mar 2009 14:39:52 -0400 X-Authenticated: #14349625 X-Provags-ID: V01U2FsdGVkX19tvnJcrpdtxukLrsyAgC3BUBXLJSybpF3soe90I1 LIq/hXl8OuDDRk Subject: Re: scheduler oddity [bug?] From: Mike Galbraith To: Ingo Molnar Cc: Balazs Scheidler , linux-kernel@vger.kernel.org, Peter Zijlstra In-Reply-To: <20090308175255.GA22802@elte.hu> References: <1236448069.16726.21.camel@bzorp.balabit> <1236505323.6281.57.camel@marge.simson.net> <1236506309.6972.8.camel@marge.simson.net> <20090308153956.GB19658@elte.hu> <1236529200.7110.16.camel@marge.simson.net> <20090308175255.GA22802@elte.hu> Content-Type: text/plain Date: Sun, 08 Mar 2009 19:39:40 +0100 Message-Id: <1236537580.7094.8.camel@marge.simson.net> Mime-Version: 1.0 X-Mailer: Evolution 2.22.1.1 Content-Transfer-Encoding: 7bit X-Y-GMX-Trusted: 0 X-FuHaFi: 0.53 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2202 Lines: 60 On Sun, 2009-03-08 at 18:52 +0100, Ingo Molnar wrote: > * Mike Galbraith wrote: > > > On Sun, 2009-03-08 at 16:39 +0100, Ingo Molnar wrote: > > > * Mike Galbraith wrote: > > > > > > > The problem with your particular testcase is that while one > > > > half has an avg_overlap (what we use as affinity hint for > > > > synchronous wakeups) which triggers the affinity hint, the > > > > other half has avg_overlap of zero, what it was born with, so > > > > despite significant execution overlap, the scheduler treats > > > > them as if they were truly synchronous tasks. > > > > > > hm, why does it stay on zero? > > > > Wakeup preemption. Presuming here: heavy task wakes light > > task, is preempted, light task stuffs data into pipe, heavy > > task doesn't block, so no avg_overlap is ever computed. The > > heavy task uses 100% CPU. > > > > Running as SCHED_BATCH (virgin source), it becomes sane. > > ah. > > I'd argue then that time spent on the rq preempted _should_ > count in avg_overlap statistics. I.e. couldnt we do something > like ... your patch? :) > > > > if (sleep && p->se.last_wakeup) { > > > update_avg(&p->se.avg_overlap, > > > p->se.sum_exec_runtime - p->se.last_wakeup); > > > p->se.last_wakeup = 0; > > > - } > > > + } else if (p->se.avg_overlap < limit && runtime >= limit) > > > + update_avg(&p->se.avg_overlap, runtime); > > Just done unconditionally, i.e. something like: > > if (sleep) { > runtime = p->se.sum_exec_runtime - p->se.last_wakeup; > p->se.last_wakeup = 0; > } else { > runtime = p->se.sum_exec_runtime - p->se.prev_sum_exec_runtime; > } > > update_avg(&p->se.avg_overlap, runtime); > > ? That'll do it for this load. I'll resume in the a.m., give that some testing, and try to remember all the things I was paranoid about. (getting interrupted a _lot_.. i give up on today;) -Mike -- 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/