[PATCH v9 10/10] sched: move cfs task on a CPU with higher capacity

[Morten Rasmussen]

On Mon, Nov 24, 2014 at 02:45:45PM +0000, Vincent Guittot wrote:
> On 21 November 2014 at 13:37, Morten Rasmussen <morten.rasmussen at arm.com> wrote:
> > On Mon, Nov 03, 2014 at 04:54:47PM +0000, Vincent Guittot wrote:
> 
> >>
> >> +     /*
> >> +      * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task.
> >> +      * It's worth migrating the task if the src_cpu's capacity is reduced
> >> +      * because of other sched_class or IRQs whereas capacity stays
> >> +      * available on dst_cpu.
> >> +      */
> >> +     if ((env->idle != CPU_NOT_IDLE) &&
> >> +                     (env->src_rq->cfs.h_nr_running == 1)) {
> >> +             unsigned long src_eff_capacity, dst_eff_capacity;
> >> +
> >> +             dst_eff_capacity = 100;
> >> +             dst_eff_capacity *= capacity_of(env->dst_cpu);
> >> +             dst_eff_capacity *= capacity_orig_of(env->src_cpu);
> >> +
> >> +             src_eff_capacity = sd->imbalance_pct;
> >> +             src_eff_capacity *= capacity_of(env->src_cpu);
> >> +             src_eff_capacity *= capacity_orig_of(env->dst_cpu);
> >
> > Do we need to scale by capacity_orig? Shouldn't the absolute capacity be
> > better?
> >
> > if (capacity_of(env->src) * sd->imbalance_pct < capacity_of(env->dst) *
> > 100) ?
> 
> we don't want to compare absolute capacity between CPUs but to compare
> the reduction of their capacity because we want to choose the CPU
> which is less used  by RT tasks or irq

But least relative RT load doesn't necessarily mean most available
compute capacity. 50% RT use of a capacity_orig = 1000 (capacity_of(cpu) =
500, eff_capacity = 50%) gives better CFS throughput than 20% RT use of
a capacity_orig = 500 (capacity_of(cpu) = 400, eff_capacity = 80%). Why pick
the cpu with less throughput?

Morten

> 
> Regards,
> Vincent
> >
> > Isn't it the absolute available capacity that matters? For SMP
> > capacity_orig is the same and cancels out and doesn't change anything.
> > For big.LITTLE we would rather have the task run on a big where rt/irq
> > eats 30% than a little cpu where rq/irq eats 5%, assuming big capacity
> > is much bigger than little capacity so the absolute available capacity
> > (~cycles/time) is larger on the big cpu.
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> > the body of a message to majordomo at vger.kernel.org
> > More majordomo info at  http://vger.kernel.org/majordomo-info.html
> > Please read the FAQ at  http://www.tux.org/lkml/
>