From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933869AbaFCRUo (ORCPT ); Tue, 3 Jun 2014 13:20:44 -0400 Received: from fw-tnat.austin.arm.com ([217.140.110.23]:54814 "EHLO collaborate-mta1.arm.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S932560AbaFCRUn (ORCPT ); Tue, 3 Jun 2014 13:20:43 -0400 Date: Tue, 3 Jun 2014 18:20:48 +0100 From: Morten Rasmussen To: Peter Zijlstra Cc: Vincent Guittot , "mingo@kernel.org" , "linux-kernel@vger.kernel.org" , "linux@arm.linux.org.uk" , "linux-arm-kernel@lists.infradead.org" , "preeti@linux.vnet.ibm.com" , "efault@gmx.de" , "nicolas.pitre@linaro.org" , "linaro-kernel@lists.linaro.org" , "daniel.lezcano@linaro.org" , Benjamin Segall , Paul Turner Subject: Re: [PATCH v2 08/11] sched: get CPU's activity statistic Message-ID: <20140603172048.GF29593@e103034-lin> References: <1400860385-14555-1-git-send-email-vincent.guittot@linaro.org> <1400860385-14555-9-git-send-email-vincent.guittot@linaro.org> <20140528121001.GI19967@e103034-lin> <20140528154703.GJ19967@e103034-lin> <20140603155007.GZ30445@twins.programming.kicks-ass.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20140603155007.GZ30445@twins.programming.kicks-ass.net> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jun 03, 2014 at 04:50:07PM +0100, Peter Zijlstra wrote: > On Wed, May 28, 2014 at 04:47:03PM +0100, Morten Rasmussen wrote: > > Since we may do periodic load-balance every 10 ms or so, we will perform > > a number of load-balances where runnable_avg_sum will mostly be > > reflecting the state of the world before a change (new task queued or > > moved a task to a different cpu). If you had have two tasks continuously > > on one cpu and your other cpu is idle, and you move one of the tasks to > > the other cpu, runnable_avg_sum will remain unchanged, 47742, on the > > first cpu while it starts from 0 on the other one. 10 ms later it will > > have increased a bit, 32 ms later it will be 47742/2, and 345 ms later > > it reaches 47742. In the mean time the cpu doesn't appear fully utilized > > and we might decide to put more tasks on it because we don't know if > > runnable_avg_sum represents a partially utilized cpu (for example a 50% > > task) or if it will continue to rise and eventually get to 47742. > > Ah, no, since we track per task, and update the per-cpu ones when we > migrate tasks, the per-cpu values should be instantly updated. No, not for this per-cpu tracking metric :) For cfs.runnable_load_avg you are right, but this patch set is using rq->avg.runnable_avg_sum which is different. See my other reply. > If we were to increase per task storage, we might as well also track > running_avg not only runnable_avg. That could probably make sense. We had that in pjt's first proposal. From mboxrd@z Thu Jan 1 00:00:00 1970 From: morten.rasmussen@arm.com (Morten Rasmussen) Date: Tue, 3 Jun 2014 18:20:48 +0100 Subject: [PATCH v2 08/11] sched: get CPU's activity statistic In-Reply-To: <20140603155007.GZ30445@twins.programming.kicks-ass.net> References: <1400860385-14555-1-git-send-email-vincent.guittot@linaro.org> <1400860385-14555-9-git-send-email-vincent.guittot@linaro.org> <20140528121001.GI19967@e103034-lin> <20140528154703.GJ19967@e103034-lin> <20140603155007.GZ30445@twins.programming.kicks-ass.net> Message-ID: <20140603172048.GF29593@e103034-lin> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Tue, Jun 03, 2014 at 04:50:07PM +0100, Peter Zijlstra wrote: > On Wed, May 28, 2014 at 04:47:03PM +0100, Morten Rasmussen wrote: > > Since we may do periodic load-balance every 10 ms or so, we will perform > > a number of load-balances where runnable_avg_sum will mostly be > > reflecting the state of the world before a change (new task queued or > > moved a task to a different cpu). If you had have two tasks continuously > > on one cpu and your other cpu is idle, and you move one of the tasks to > > the other cpu, runnable_avg_sum will remain unchanged, 47742, on the > > first cpu while it starts from 0 on the other one. 10 ms later it will > > have increased a bit, 32 ms later it will be 47742/2, and 345 ms later > > it reaches 47742. In the mean time the cpu doesn't appear fully utilized > > and we might decide to put more tasks on it because we don't know if > > runnable_avg_sum represents a partially utilized cpu (for example a 50% > > task) or if it will continue to rise and eventually get to 47742. > > Ah, no, since we track per task, and update the per-cpu ones when we > migrate tasks, the per-cpu values should be instantly updated. No, not for this per-cpu tracking metric :) For cfs.runnable_load_avg you are right, but this patch set is using rq->avg.runnable_avg_sum which is different. See my other reply. > If we were to increase per task storage, we might as well also track > running_avg not only runnable_avg. That could probably make sense. We had that in pjt's first proposal.