Re: [PATCH v2] sched/fair: prefer prev cpu in asymmetric wakeup path

2020-10-29 Thread Valentin Schneider
On 29/10/20 14:19, Vincent Guittot wrote: > On Thu, 29 Oct 2020 at 12:16, Valentin Schneider > wrote: >> On legacy big.LITTLE systems, sd_asym_cpucapacity spans all CPUs, so we >> would iterate over those in select_idle_capacity() anyway - the policy >> we've been going for is that capacity fitn

Re: [PATCH v2] sched/fair: prefer prev cpu in asymmetric wakeup path

2020-10-29 Thread Vincent Guittot
On Thu, 29 Oct 2020 at 15:30, Vincent Guittot wrote: > > On Thu, 29 Oct 2020 at 15:19, Vincent Guittot > wrote: > > > > On Thu, 29 Oct 2020 at 12:16, Valentin Schneider > > wrote: > > > > > > > > > Hi Vincent, > > > > > > On 28/10/20 17:44, Vincent Guittot wrote: > > > > During fast wakeup path,

Re: [PATCH v2] sched/fair: prefer prev cpu in asymmetric wakeup path

2020-10-29 Thread Vincent Guittot
On Thu, 29 Oct 2020 at 15:19, Vincent Guittot wrote: > > On Thu, 29 Oct 2020 at 12:16, Valentin Schneider > wrote: > > > > > > Hi Vincent, > > > > On 28/10/20 17:44, Vincent Guittot wrote: > > > During fast wakeup path, scheduler always check whether local or prev cpus > > > are good candidates f

Re: [PATCH v2] sched/fair: prefer prev cpu in asymmetric wakeup path

2020-10-29 Thread Vincent Guittot
On Thu, 29 Oct 2020 at 12:16, Valentin Schneider wrote: > > > Hi Vincent, > > On 28/10/20 17:44, Vincent Guittot wrote: > > During fast wakeup path, scheduler always check whether local or prev cpus > > are good candidates for the task before looking for other cpus in the > > domain. With > > co

Re: [PATCH v2] sched/fair: prefer prev cpu in asymmetric wakeup path

2020-10-29 Thread Vincent Guittot
On Thu, 29 Oct 2020 at 12:16, Valentin Schneider wrote: > > > Hi Vincent, > > On 28/10/20 17:44, Vincent Guittot wrote: > > During fast wakeup path, scheduler always check whether local or prev cpus > > are good candidates for the task before looking for other cpus in the > > domain. With > > co

Re: [PATCH v2] sched/fair: prefer prev cpu in asymmetric wakeup path

2020-10-29 Thread Vincent Guittot
On Thu, 29 Oct 2020 at 13:17, Tao Zhou wrote: > > Hi Vincent, > > On Wed, Oct 28, 2020 at 06:44:12PM +0100, Vincent Guittot wrote: > > During fast wakeup path, scheduler always check whether local or prev cpus > > are good candidates for the task before looking for other cpus in the > > domain. Wi

Re: [PATCH v2] sched/fair: prefer prev cpu in asymmetric wakeup path

2020-10-29 Thread Valentin Schneider
On 29/10/20 12:17, Tao Zhou wrote: > Hi Vincent, > > On Wed, Oct 28, 2020 at 06:44:12PM +0100, Vincent Guittot wrote: >> @@ -6173,20 +6173,20 @@ static int >> select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int >> target) >> { >> unsigned long best_cap = 0; >> -in

Re: [PATCH v2] sched/fair: prefer prev cpu in asymmetric wakeup path

2020-10-29 Thread Valentin Schneider
Hi Vincent, On 28/10/20 17:44, Vincent Guittot wrote: > During fast wakeup path, scheduler always check whether local or prev cpus > are good candidates for the task before looking for other cpus in the > domain. With > commit b7a331615d25 ("sched/fair: Add asymmetric CPU capacity wakeup scan"