Re: [PATCH V2 1/2] sched/core: Rename and move schedutil_cpu_util() to core.c

[Vincent Guittot]

On Fri, 23 Oct 2020 at 12:54, Viresh Kumar <viresh.kumar@xxxxxxxxxx> wrote:
>
> On 23-10-20, 12:34, Peter Zijlstra wrote:
> > On Fri, Oct 23, 2020 at 03:50:20PM +0530, Viresh Kumar wrote:
> > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > > index d2003a7d5ab5..369ff54d11d4 100644
> > > --- a/kernel/sched/core.c
> > > +++ b/kernel/sched/core.c
> > > @@ -5117,6 +5117,119 @@ struct task_struct *idle_task(int cpu)
> > >     return cpu_rq(cpu)->idle;
> > >  }
> > >
> > > +/*
> > > + * This function computes an effective utilization for the given CPU, to be
> > > + * used for frequency selection given the linear relation: f = u * f_max.
> > > + *
> > > + * The scheduler tracks the following metrics:
> > > + *
> > > + *   cpu_util_{cfs,rt,dl,irq}()
> > > + *   cpu_bw_dl()
> > > + *
> > > + * Where the cfs,rt and dl util numbers are tracked with the same metric and
> > > + * synchronized windows and are thus directly comparable.
> > > + *
> > > + * The cfs,rt,dl utilization are the running times measured with rq->clock_task
> > > + * which excludes things like IRQ and steal-time. These latter are then accrued
> > > + * in the irq utilization.
> > > + *
> > > + * The DL bandwidth number otoh is not a measured metric but a value computed
> > > + * based on the task model parameters and gives the minimal utilization
> > > + * required to meet deadlines.
> > > + */
> > > +unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
> > > +                            unsigned long max, enum cpu_util_type type,
> > > +                            struct task_struct *p)
> > > +{
> >       ...
> > > +}
> > > +
> > > +unsigned long sched_cpu_util(int cpu, enum cpu_util_type type,
> > > +                        unsigned long max)
> > > +{
> > > +   return effective_cpu_util(cpu, cpu_util_cfs(cpu_rq(cpu)), max, type,
> > > +                             NULL);
> > > +}
> >
> > Shouldn't all that be: #ifdef CONFIG_SMP ?
>
> I didn't realize that these matrices are only available in case of SMP
> and that's why schedutil isn't available for !SMP. I wonder what we

Maybe it's time to make sched_util and pelt available for !SMP too.

With util_est and uclamp, I can see some benefits for !SMP compare to ondemand

> should be doing in cpufreq_cooling now ? Make it depend on SMP ? Or
> calculate load the traditional way (the stuff I just removed) for !SMP
> case ?
>
> :)
>
> --
> viresh