Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

On 14 December 2017 at 18:08, Joel Fernandes wrote: > Hi Vincent, > Thanks for your reply. > > On Thu, Dec 14, 2017 at 7:46 AM, Vincent Guittot > wrote: >> Hi Joel, >> >> On 13 December 2017 at 21:00, Joel Fernandes wrote: >>> On

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

On 14 December 2017 at 18:08, Joel Fernandes wrote: > Hi Vincent, > Thanks for your reply. > > On Thu, Dec 14, 2017 at 7:46 AM, Vincent Guittot > wrote: >> Hi Joel, >> >> On 13 December 2017 at 21:00, Joel Fernandes wrote: >>> On Mon, Dec 11, 2017 at 4:43 PM, Joel Fernandes wrote: Hi

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

Hi Vincent, Thanks for your reply. On Thu, Dec 14, 2017 at 7:46 AM, Vincent Guittot wrote: > Hi Joel, > > On 13 December 2017 at 21:00, Joel Fernandes wrote: >> On Mon, Dec 11, 2017 at 4:43 PM, Joel Fernandes wrote: >>> Hi

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

Hi Vincent, Thanks for your reply. On Thu, Dec 14, 2017 at 7:46 AM, Vincent Guittot wrote: > Hi Joel, > > On 13 December 2017 at 21:00, Joel Fernandes wrote: >> On Mon, Dec 11, 2017 at 4:43 PM, Joel Fernandes wrote: >>> Hi Vincent, >>> > >> >>>

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

Hi Joel, On 13 December 2017 at 21:00, Joel Fernandes wrote: > On Mon, Dec 11, 2017 at 4:43 PM, Joel Fernandes wrote: >> Hi Vincent, >> > >> >> Here we have RT activity running on

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

Hi Joel, On 13 December 2017 at 21:00, Joel Fernandes wrote: > On Mon, Dec 11, 2017 at 4:43 PM, Joel Fernandes wrote: >> Hi Vincent, >> > >> >> Here we have RT activity running on big CPU cluster induced with rt-app,

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

On Mon, Dec 11, 2017 at 4:43 PM, Joel Fernandes wrote: > Hi Vincent, > >>> > > Here we have RT activity running on big CPU cluster induced with rt-app, > and running hackbench in parallel. The RT

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

On Mon, Dec 11, 2017 at 4:43 PM, Joel Fernandes wrote: > Hi Vincent, > >>> > > Here we have RT activity running on big CPU cluster induced with rt-app, > and running hackbench in parallel. The RT tasks are bound to 4

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

Hi Vincent, >> >>> Here we have RT activity running on big CPU cluster induced with rt-app, and running hackbench in parallel. The RT tasks are bound to 4 CPUs on the big cluster (cpu 4,5,6,7) and have 100ms

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

Hi Vincent, >> >>> Here we have RT activity running on big CPU cluster induced with rt-app, and running hackbench in parallel. The RT tasks are bound to 4 CPUs on the big cluster (cpu 4,5,6,7) and have 100ms

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

On 11/09/2017 06:52 PM, Joel Fernandes wrote: [...] diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 56f343b8e749..ba9609407cb9 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5724,7 +5724,7 @@ static int cpu_util_wake(int cpu, struct task_struct *p); static

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

On 11/09/2017 06:52 PM, Joel Fernandes wrote: [...] diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 56f343b8e749..ba9609407cb9 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5724,7 +5724,7 @@ static int cpu_util_wake(int cpu, struct task_struct *p); static

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

On 16 November 2017 at 22:53, Joel Fernandes wrote: > Hi Vincent, > > Thanks a lot for your reply, and sorry for the late reply. Actually I > just started paternity leave so that's why the delay. My working hours Congratulations ! > and completely random at the moment :-) > >

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

On 16 November 2017 at 22:53, Joel Fernandes wrote: > Hi Vincent, > > Thanks a lot for your reply, and sorry for the late reply. Actually I > just started paternity leave so that's why the delay. My working hours Congratulations ! > and completely random at the moment :-) > > On Fri, Nov 10,

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

Hi Vincent, Thanks a lot for your reply, and sorry for the late reply. Actually I just started paternity leave so that's why the delay. My working hours and completely random at the moment :-) On Fri, Nov 10, 2017 at 12:29 AM, Vincent Guittot wrote: > On 9 November

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

Hi Vincent, Thanks a lot for your reply, and sorry for the late reply. Actually I just started paternity leave so that's why the delay. My working hours and completely random at the moment :-) On Fri, Nov 10, 2017 at 12:29 AM, Vincent Guittot wrote: > On 9 November 2017 at 19:52, Joel Fernandes

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

On 9 November 2017 at 19:52, Joel Fernandes wrote: > capacity_spare_wake in the slow path influences choice of idlest groups, > as we search for groups with maximum spare capacity. In scenarios where > RT pressure is high, a sub optimal group can be chosen and hurt >

Re: [PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

On 9 November 2017 at 19:52, Joel Fernandes wrote: > capacity_spare_wake in the slow path influences choice of idlest groups, > as we search for groups with maximum spare capacity. In scenarios where > RT pressure is high, a sub optimal group can be chosen and hurt > performance of the task being

[PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

capacity_spare_wake in the slow path influences choice of idlest groups, as we search for groups with maximum spare capacity. In scenarios where RT pressure is high, a sub optimal group can be chosen and hurt performance of the task being woken up. Several tests with results are included below to

[PATCH] sched/fair: Consider RT/IRQ pressure in capacity_spare_wake

capacity_spare_wake in the slow path influences choice of idlest groups, as we search for groups with maximum spare capacity. In scenarios where RT pressure is high, a sub optimal group can be chosen and hurt performance of the task being woken up. Several tests with results are included below to