Re: [PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry

2018-07-20 Thread Morten Rasmussen
On Thu, Jul 05, 2018 at 04:03:11PM +0100, Quentin Perret wrote: > On Thursday 05 Jul 2018 at 15:13:49 (+0100), Morten Rasmussen wrote: > > 3. Detecting the flag in generic kernel/sched/* code means that all > > architectures will pay the for the overhead when building/rebuilding the > >

Re: [PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry

2018-07-20 Thread Morten Rasmussen
On Thu, Jul 05, 2018 at 04:03:11PM +0100, Quentin Perret wrote: > On Thursday 05 Jul 2018 at 15:13:49 (+0100), Morten Rasmussen wrote: > > 3. Detecting the flag in generic kernel/sched/* code means that all > > architectures will pay the for the overhead when building/rebuilding the > >

Re: [PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry

2018-07-05 Thread Quentin Perret
On Thursday 05 Jul 2018 at 15:13:49 (+0100), Morten Rasmussen wrote: > On Thu, Jul 05, 2018 at 02:31:43PM +0100, Quentin Perret wrote: > > If SD_ASYM_CPUCAPACITY means that some CPUs have different > > arch_scale_cpu_capacity() values, we could also automatically _set_ > > the flag in sd_init() no

Re: [PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry

2018-07-05 Thread Quentin Perret
On Thursday 05 Jul 2018 at 15:13:49 (+0100), Morten Rasmussen wrote: > On Thu, Jul 05, 2018 at 02:31:43PM +0100, Quentin Perret wrote: > > If SD_ASYM_CPUCAPACITY means that some CPUs have different > > arch_scale_cpu_capacity() values, we could also automatically _set_ > > the flag in sd_init() no

Re: [PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry

2018-07-05 Thread Morten Rasmussen
On Thu, Jul 05, 2018 at 02:31:43PM +0100, Quentin Perret wrote: > Hi Morten, > > On Wednesday 04 Jul 2018 at 11:17:49 (+0100), Morten Rasmussen wrote: > > diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c > > index 71330e0e41db..29c186961345 100644 > > --- a/kernel/sched/topology.c >

Re: [PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry

2018-07-05 Thread Morten Rasmussen
On Thu, Jul 05, 2018 at 02:31:43PM +0100, Quentin Perret wrote: > Hi Morten, > > On Wednesday 04 Jul 2018 at 11:17:49 (+0100), Morten Rasmussen wrote: > > diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c > > index 71330e0e41db..29c186961345 100644 > > --- a/kernel/sched/topology.c >

Re: [PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry

2018-07-05 Thread Quentin Perret
Hi Morten, On Wednesday 04 Jul 2018 at 11:17:49 (+0100), Morten Rasmussen wrote: > diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c > index 71330e0e41db..29c186961345 100644 > --- a/kernel/sched/topology.c > +++ b/kernel/sched/topology.c > @@ -1160,6 +1160,26 @@ sd_init(struct

Re: [PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry

2018-07-05 Thread Quentin Perret
Hi Morten, On Wednesday 04 Jul 2018 at 11:17:49 (+0100), Morten Rasmussen wrote: > diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c > index 71330e0e41db..29c186961345 100644 > --- a/kernel/sched/topology.c > +++ b/kernel/sched/topology.c > @@ -1160,6 +1160,26 @@ sd_init(struct

[PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry

2018-07-04 Thread Morten Rasmussen
When hotplugging cpus out or creating exclusive cpusets (disabling sched_load_balance) systems which were asymmetric at boot might become symmetric. In this case leaving the flag set might lead to suboptimal scheduling decisions. The arch-code proving the flag doesn't have visibility of the

[PATCHv4 11/12] sched/core: Disable SD_ASYM_CPUCAPACITY for root_domains without asymmetry

2018-07-04 Thread Morten Rasmussen
When hotplugging cpus out or creating exclusive cpusets (disabling sched_load_balance) systems which were asymmetric at boot might become symmetric. In this case leaving the flag set might lead to suboptimal scheduling decisions. The arch-code proving the flag doesn't have visibility of the