Re: [PATCH 1/2] sched: cpufreq: ignore SMT when determining max cpu capacity

2016-09-12 Thread Rafael J. Wysocki
On Wednesday, August 31, 2016 04:34:37 PM Peter Zijlstra wrote: > On Wed, Aug 31, 2016 at 03:27:30AM +0200, Rafael J. Wysocki wrote: > > On Friday, August 26, 2016 11:40:47 AM Steve Muckle wrote: > > > PELT does not consider SMT when scaling its utilization values via > > > arch_scale_cpu_capacity(

Re: [PATCH 1/2] sched: cpufreq: ignore SMT when determining max cpu capacity

2016-08-31 Thread Peter Zijlstra
On Wed, Aug 31, 2016 at 03:27:30AM +0200, Rafael J. Wysocki wrote: > On Friday, August 26, 2016 11:40:47 AM Steve Muckle wrote: > > PELT does not consider SMT when scaling its utilization values via > > arch_scale_cpu_capacity(). The value in rq->cpu_capacity_orig does > > take SMT into considerati

Re: [PATCH 1/2] sched: cpufreq: ignore SMT when determining max cpu capacity

2016-08-30 Thread Rafael J. Wysocki
On Friday, August 26, 2016 11:40:47 AM Steve Muckle wrote: > PELT does not consider SMT when scaling its utilization values via > arch_scale_cpu_capacity(). The value in rq->cpu_capacity_orig does > take SMT into consideration though and therefore may be smaller than > the utilization reported by P

[PATCH 1/2] sched: cpufreq: ignore SMT when determining max cpu capacity

2016-08-26 Thread Steve Muckle
PELT does not consider SMT when scaling its utilization values via arch_scale_cpu_capacity(). The value in rq->cpu_capacity_orig does take SMT into consideration though and therefore may be smaller than the utilization reported by PELT. On an Intel i7-3630QM for example rq->cpu_capacity_orig is 58