Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753313Ab3EIJY6 (ORCPT ); Thu, 9 May 2013 05:24:58 -0400 Received: from mail-we0-f171.google.com ([74.125.82.171]:48053 "EHLO mail-we0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753225Ab3EIJYy (ORCPT ); Thu, 9 May 2013 05:24:54 -0400 MIME-Version: 1.0 In-Reply-To: <518B5CC8.6070601@intel.com> References: <1367804711-30308-1-git-send-email-alex.shi@intel.com> <1367804711-30308-4-git-send-email-alex.shi@intel.com> <5187760D.8060900@intel.com> <51886460.3020009@intel.com> <20130507095715.GE4068@e103034-lin> <5188DFEF.6010403@intel.com> <20130508113442.GB6803@dyad.programming.kicks-ass.net> <518B5CC8.6070601@intel.com> From: Paul Turner Date: Thu, 9 May 2013 02:24:23 -0700 Message-ID: Subject: Re: [PATCH v5 3/7] sched: set initial value of runnable avg for new forked task To: Alex Shi Cc: Peter Zijlstra , Morten Rasmussen , Ingo Molnar , Thomas Gleixner , Andrew Morton , Borislav Petkov , Namhyung Kim , Mike Galbraith , Vincent Guittot , Preeti U Murthy , Viresh Kumar , LKML , Mel Gorman , Rik van Riel , Michael Wang Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3873 Lines: 108 On Thu, May 9, 2013 at 1:22 AM, Alex Shi wrote: > On 05/08/2013 07:34 PM, Peter Zijlstra wrote: >>> > If we wanted to be more exacting about it we could just give them a >>> > sched_slice() worth; this would have a few obvious "nice" properties >>> > (pun intended). >> Oh I see I misunderstood again :/ Its not about the effective load but weight >> of the initial effective load wrt adjustment. >> >> Previous schedulers didn't have this aspect at all, so no experience from me >> here. Paul would be the one, since he's ran longest with this stuff. >> >> That said, I would tend to keep it shorter rather than longer so that it would >> adjust quicker to whatever it really wanted to be. >> >> Morten says the load is unstable specifically on loaded systems. I would think >> this is because we'd experience scheduling latency, we're runnable more pushing >> things up. But if we're really an idle task at heart we'd not run again for a >> long while, pushing things down again. >> >> So on that point Paul's suggestion of maybe starting with __sched_slice() might >> make sense because it increases the weight of the initial avg with nr_running. >> >> Not sure really, we'll have to play and see what works best for a number of >> workloads. > > > The patch of using sched_slice for review, I am testing the benchmarks > > --- > From da40ffa90ec1de520bd7e92f5653734a964e3bb2 Mon Sep 17 00:00:00 2001 > From: Alex Shi > Date: Thu, 9 May 2013 15:28:34 +0800 > Subject: [PATCH 4/8] sched: set initial runnable avg for new task > > --- > kernel/sched/core.c | 2 ++ > kernel/sched/fair.c | 15 +++++++++++++++ > kernel/sched/sched.h | 2 ++ > 3 files changed, 19 insertions(+) > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c > index ecec7f1..c17925b 100644 > --- a/kernel/sched/core.c > +++ b/kernel/sched/core.c > @@ -1716,6 +1716,8 @@ void wake_up_new_task(struct task_struct *p) > set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0)); > #endif > > + /* Give new task a start runnable time */ > + set_task_runnable_avg(p); > rq = __task_rq_lock(p); > activate_task(rq, p, 0); > p->on_rq = 1; > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c > index 2881d42..4ec5f29 100644 > --- a/kernel/sched/fair.c > +++ b/kernel/sched/fair.c > @@ -661,6 +661,21 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) > return calc_delta_fair(sched_slice(cfs_rq, se), se); > } > > +#ifdef CONFIG_SMP > +void set_task_runnable_avg(struct task_struct *p) > +{ > + u64 slice; > + > + slice = sched_slice(task_cfs_rq(p), &p->se); > + p->se.avg.runnable_avg_sum = slice; > + p->se.avg.runnable_avg_period = slice; This needs to be >> 10 right? sched_slice is in ns. We also still want to set load_avg_contrib right? > +} > +#else > +void set_task_runnable_avg(struct task_struct *p) > +{ > +} > +#endif > + > /* > * Update the current task's runtime statistics. Skip current tasks that > * are not in our scheduling class. > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h > index c6634f1..518f3d8a 100644 > --- a/kernel/sched/sched.h > +++ b/kernel/sched/sched.h > @@ -900,6 +900,8 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime > > extern void update_idle_cpu_load(struct rq *this_rq); > > +extern void set_task_runnable_avg(struct task_struct *p); > + > #ifdef CONFIG_CGROUP_CPUACCT > #include > /* track cpu usage of a group of tasks and its child groups */ > -- > 1.7.12 > > -- > Thanks > Alex -- 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/