From mboxrd@z Thu Jan 1 00:00:00 1970 From: Patrick Bellasi Subject: Re: [PATCH v3 2/3] sched/fair: use util_est in LB and WU paths Date: Wed, 24 Jan 2018 19:31:38 +0000 Message-ID: <20180124193138.GB5739@e110439-lin> References: <20180123180847.4477-1-patrick.bellasi@arm.com> <20180123180847.4477-3-patrick.bellasi@arm.com> <20180124113342.GD30677@codeaurora.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from usa-sjc-mx-foss1.foss.arm.com ([217.140.101.70]:56874 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752339AbeAXTbo (ORCPT ); Wed, 24 Jan 2018 14:31:44 -0500 Content-Disposition: inline In-Reply-To: <20180124113342.GD30677@codeaurora.org> Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: Pavan Kondeti Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org, Ingo Molnar , Peter Zijlstra , "Rafael J . Wysocki" , Viresh Kumar , Vincent Guittot , Paul Turner , Dietmar Eggemann , Morten Rasmussen , Juri Lelli , Todd Kjos , Joel Fernandes , Steve Muckle On 24-Jan 17:03, Pavan Kondeti wrote: > Hi Patrick, Hi Pavan, > On Tue, Jan 23, 2018 at 06:08:46PM +0000, Patrick Bellasi wrote: > > static unsigned long cpu_util_wake(int cpu, struct task_struct *p) > > { > > - unsigned long util, capacity; > > + long util, util_est; > > > > /* Task has no contribution or is new */ > > if (cpu != task_cpu(p) || !p->se.avg.last_update_time) > > - return cpu_util(cpu); > > + return cpu_util_est(cpu); > > > > - capacity = capacity_orig_of(cpu); > > - util = max_t(long, cpu_rq(cpu)->cfs.avg.util_avg - task_util(p), 0); > > + /* Discount task's blocked util from CPU's util */ > > + util = cpu_util(cpu) - task_util(p); > > + util = max(util, 0L); > > > > - return (util >= capacity) ? capacity : util; > > + if (!sched_feat(UTIL_EST)) > > + return util; > > At first, It is not clear to me why you are not clamping the capacity to > CPU original capacity. It looks like it is not needed any more with > commit f453ae2200b0 ("sched/fair: Consider RT/IRQ pressure in > capacity_spare_wake()") inclusion. Mainly because the above code now uses only cpu_util() which is already clamped by capacity_orig_of(). However, you made me notice that in the few lines which follows, where I do: > > + /* > > + * These are the main cases covered: > > + * - if *p is the only task sleeping on this CPU, then: > > + * cpu_util (== task_util) > util_est (== 0) > > + * and thus we return: > > + * cpu_util_wake = (cpu_util - task_util) = 0 > > + * > > + * - if other tasks are SLEEPING on the same CPU, which is just waking > > + * up, then: > > + * cpu_util >= task_util > > + * cpu_util > util_est (== 0) > > + * and thus we discount *p's blocked utilization to return: > > + * cpu_util_wake = (cpu_util - task_util) >= 0 > > + * > > + * - if other tasks are RUNNABLE on that CPU and > > + * util_est > cpu_util > > + * then we use util_est since it returns a more restrictive > > + * estimation of the spare capacity on that CPU, by just considering > > + * the expected utilization of tasks already runnable on that CPU. > > + */ > > + util_est = cpu_rq(cpu)->cfs.util_est_runnable; > > + util = max(util, util_est); > > + > > + return util; I should instead clamp util before returning it! ;-) > May be a separate patch to remove the clamping part? No, I think we should keep cpu_util_wake clamped to not affect the existing call sites. I just need to remove it where not needed (done) and add it where needed (will do on the next iteration). > Thanks, > Pavan Cheers Patrick -- #include Patrick Bellasi