From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Lezcano Subject: Re: [PATCH v2 2/2] sched/fair: leverage the idle state info when choosing the "idlest" cpu Date: Fri, 05 Sep 2014 09:52:53 +0200 Message-ID: <54096BD5.4030803@linaro.org> References: <1409844730-12273-1-git-send-email-nicolas.pitre@linaro.org> <1409844730-12273-3-git-send-email-nicolas.pitre@linaro.org> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from mail-wi0-f171.google.com ([209.85.212.171]:63936 "EHLO mail-wi0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751641AbaIEHw5 (ORCPT ); Fri, 5 Sep 2014 03:52:57 -0400 Received: by mail-wi0-f171.google.com with SMTP id hi2so332359wib.16 for ; Fri, 05 Sep 2014 00:52:56 -0700 (PDT) In-Reply-To: <1409844730-12273-3-git-send-email-nicolas.pitre@linaro.org> Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: Nicolas Pitre , Peter Zijlstra , Ingo Molnar Cc: "Rafael J. Wysocki" , linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org, linaro-kernel@lists.linaro.org On 09/04/2014 05:32 PM, Nicolas Pitre wrote: > The code in find_idlest_cpu() looks for the CPU with the smallest loa= d. > However, if multiple CPUs are idle, the first idle CPU is selected > irrespective of the depth of its idle state. > > Among the idle CPUs we should pick the one with with the shallowest i= dle > state, or the latest to have gone idle if all idle CPUs are in the sa= me > state. The later applies even when cpuidle is configured out. > > This patch doesn't cover the following issues: > > - The idle exit latency of a CPU might be larger than the time needed > to migrate the waking task to an already running CPU with sufficie= nt > capacity, and therefore performance would benefit from task packin= g > in such case (in most cases task packing is about power saving). > > - Some idle states have a non negligible and non abortable entry late= ncy > which needs to run to completion before the exit latency can start= =2E > A concurrent patch series is making this info available to the cpu= idle > core. Once available, the entry latency with the idle timestamp c= ould > determine when the exit latency may be effective. > > Those issues will be handled in due course. In the mean time, what > is implemented here should improve things already compared to the cur= rent > state of affairs. > > Based on an initial patch from Daniel Lezcano. > > Signed-off-by: Nicolas Pitre Sounds good for me. Acked-by: Daniel Lezcano > --- > kernel/sched/fair.c | 43 ++++++++++++++++++++++++++++++++++++------= - > 1 file changed, 36 insertions(+), 7 deletions(-) > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c > index bfa3c86d0d..416329e1a6 100644 > --- a/kernel/sched/fair.c > +++ b/kernel/sched/fair.c > @@ -23,6 +23,7 @@ > #include > #include > #include > +#include > #include > #include > #include > @@ -4428,20 +4429,48 @@ static int > find_idlest_cpu(struct sched_group *group, struct task_struct *p, i= nt this_cpu) > { > unsigned long load, min_load =3D ULONG_MAX; > - int idlest =3D -1; > + unsigned int min_exit_latency =3D UINT_MAX; > + u64 latest_idle_timestamp =3D 0; > + int least_loaded_cpu =3D this_cpu; > + int shallowest_idle_cpu =3D -1; > int i; > > /* Traverse only the allowed CPUs */ > for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) = { > - load =3D weighted_cpuload(i); > - > - if (load < min_load || (load =3D=3D min_load && i =3D=3D this_cpu)= ) { > - min_load =3D load; > - idlest =3D i; > + if (idle_cpu(i)) { > + struct rq *rq =3D cpu_rq(i); > + struct cpuidle_state *idle =3D idle_get_state(rq); > + if (idle && idle->exit_latency < min_exit_latency) { > + /* > + * We give priority to a CPU whose idle state > + * has the smallest exit latency irrespective > + * of any idle timestamp. > + */ > + min_exit_latency =3D idle->exit_latency; > + latest_idle_timestamp =3D rq->idle_stamp; > + shallowest_idle_cpu =3D i; > + } else if ((!idle || idle->exit_latency =3D=3D min_exit_latency) = && > + rq->idle_stamp > latest_idle_timestamp) { > + /* > + * If equal or no active idle state, then > + * the most recently idled CPU might have > + * a warmer cache. > + */ > + latest_idle_timestamp =3D rq->idle_stamp; > + shallowest_idle_cpu =3D i; > + } > + cpuidle_put_state(rq); > + } else { > + load =3D weighted_cpuload(i); > + if (load < min_load || > + (load =3D=3D min_load && i =3D=3D this_cpu)) { > + min_load =3D load; > + least_loaded_cpu =3D i; > + } > } > } > > - return idlest; > + return shallowest_idle_cpu !=3D -1 ? shallowest_idle_cpu : least_lo= aded_cpu; > } > > /* > --=20 Linaro.org =E2=94=82 Open source software fo= r ARM SoCs =46ollow Linaro: Facebook | Twitter | Blog