On 14/12/15 16:56, Vincent Guittot wrote:
> On 14 December 2015 at 16:17, Peter Zijlstra <pet...@infradead.org> wrote:
> > On Tue, Dec 08, 2015 at 10:19:30PM -0800, Steve Muckle wrote:
> >> From: Vincent Guittot <vincent.guit...@linaro.org>
> >
> >> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> >> index 8b0a15e..9d9eb50 100644
> >> --- a/kernel/sched/deadline.c
> >> +++ b/kernel/sched/deadline.c
> >> @@ -43,6 +43,24 @@ static inline int on_dl_rq(struct sched_dl_entity
> >> *dl_se)
> >> return !RB_EMPTY_NODE(&dl_se->rb_node);
> >> }
> >>
> >> +static void add_average_bw(struct sched_dl_entity *dl_se, struct dl_rq
> >> *dl_rq)
> >> +{
> >> + u64 se_bw = dl_se->dl_bw;
> >> +
> >> + dl_rq->avg_bw += se_bw;
> >> +}
> >> +
> >> +static void clear_average_bw(struct sched_dl_entity *dl_se, struct dl_rq
> >> *dl_rq)
> >> +{
> >> + u64 se_bw = dl_se->dl_bw;
> >> +
> >> + dl_rq->avg_bw -= se_bw;
> >> + if (dl_rq->avg_bw < 0) {
> >> + WARN_ON(1);
> >> + dl_rq->avg_bw = 0;
> >> + }
> >> +}
> >
> >
> >> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> >> index 4c49f76..ce05f61 100644
> >> --- a/kernel/sched/fair.c
> >> +++ b/kernel/sched/fair.c
> >> @@ -6203,6 +6203,14 @@ static unsigned long scale_rt_capacity(int cpu)
> >>
> >> used = div_u64(avg, total);
> >>
> >> + /*
> >> + * deadline bandwidth is defined at system level so we must
> >> + * weight this bandwidth with the max capacity of the system.
> >> + * As a reminder, avg_bw is 20bits width and
> >> + * scale_cpu_capacity is 10 bits width
> >> + */
> >> + used += div_u64(rq->dl.avg_bw, arch_scale_cpu_capacity(NULL, cpu));
> >> +
> >> if (likely(used < SCHED_CAPACITY_SCALE))
> >> return SCHED_CAPACITY_SCALE - used;
> >>
> >> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> >> index 08858d1..e44c6be 100644
> >> --- a/kernel/sched/sched.h
> >> +++ b/kernel/sched/sched.h
> >> @@ -519,6 +519,8 @@ struct dl_rq {
> >> #else
> >> struct dl_bw dl_bw;
> >> #endif
> >> + /* This is the "average utilization" for this runqueue */
> >> + s64 avg_bw;
> >> };
> >
> > So I don't think this is right. AFAICT this projects the WCET as the
> > amount of time actually used by DL. This will, under many circumstances,
> > vastly overestimate the amount of time actually spend on it. Therefore
> > unduly pessimisme the fair capacity of this CPU.
>
> I agree that if the WCET is far from reality, we will underestimate
> available capacity for CFS. Have you got some use case in mind which
> overestimates the WCET ?
I guess simply the fact that one task can be admitted to the system, but
then in practice sleep, waiting from some event to happen.
> If we can't rely on this parameters to evaluate the amount of capacity
> used by deadline scheduler on a core, this will imply that we can't
> also use it for requesting capacity to cpufreq and we should fallback
> on a monitoring mechanism which reacts to a change instead of
> anticipating it.
>
There is at least one way in the middle: use utilization of active
servers (as I think Luca was already mentioning). This solution should
remove some of the pessimism, but still be safe for our needs. I should
be able to play with this alternative in the (hopefully) near future.
Thanks,
- Juri
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
