Re: [RFC PATCH v3 4/6] sched/cpufreq: Introduce sugov_cpu_ramp_boost

[Douglas Raillard]

Hi Peter,

On 10/14/19 3:33 PM, Peter Zijlstra wrote:
> On Fri, Oct 11, 2019 at 02:44:58PM +0100, Douglas RAILLARD wrote:
> > Use the utilization signals dynamic to detect when the utilization of a
> > set of tasks starts increasing because of a change in tasks' behavior.
> > This allows detecting when spending extra power for faster frequency
> > ramp up response would be beneficial to the reactivity of the system.
> >
> > This ramp boost is computed as the difference
> > util_avg-util_est_enqueued. This number somehow represents a lower bound
>
> That reads funny, maybe 'as the difference between util_avg and
> util_est_enqueued' ?

Indeed, it was not clear that it was a formula. Talking about formulas, I remember laying down
the relations between the various flavors of util signals in the v2 thread. This could be
turned rather easily into a doc page for PELT, along with a signal-processing-friendly
accurate description of how the PELT signals are built. Would such a patch be of any
interest the kernel tree ?

> > of how much extra utilization this tasks is actually using, compared to
> > our best current stable knowledge of it (which is util_est_enqueued).
> >
> > When the set of runnable tasks changes, the boost is disabled as the
> > impact of blocked utilization on util_avg will make the delta with
> > util_est_enqueued not very informative.
>
> > @@ -561,6 +604,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
> >   		}
> >   	}
> >   
> > +
> >   	return get_next_freq(sg_policy, util, max);
> >   }
>
> Surely we can do without this extra whitespace? :-)
woops ...

Cheers,
Douglas