On Friday 17 Jul 2020 at 11:33:05 (+0100), Quentin Perret wrote:
> On Friday 17 Jul 2020 at 11:14:38 (+0100), Quentin Perret wrote:
> > On Tuesday 14 Jul 2020 at 12:06:53 (+0530), Viresh Kumar wrote:
> > > /**
> > > - * get_load() - get load for a cpu since last updated
> > > + * get_load() - get current load for a cpu
> > > * @cpufreq_cdev: &struct cpufreq_cooling_device for this cpu
> > > * @cpu: cpu number
> > > - * @cpu_idx: index of the cpu in time_in_idle*
> > > + * @cpu_idx: index of the cpu
> > > *
> > > - * Return: The average load of cpu @cpu in percentage since this
> > > - * function was last called.
> > > + * Return: The current load of cpu @cpu in percentage.
> > > */
> > > static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu,
> > > int cpu_idx)
> > > {
> > > - u32 load;
> > > - u64 now, now_idle, delta_time, delta_idle;
> > > - struct time_in_idle *idle_time = &cpufreq_cdev->idle_time[cpu_idx];
> > > -
> > > - now_idle = get_cpu_idle_time(cpu, &now, 0);
> > > - delta_idle = now_idle - idle_time->time;
> > > - delta_time = now - idle_time->timestamp;
> > > + unsigned long util = cpu_util_cfs(cpu_rq(cpu));
> > > + unsigned long max = arch_scale_cpu_capacity(cpu);
> >
> > Should we subtract the thermal PELT signal from max?
>
> Actually, that or add it the ENERGY_UTIL case in effective_cpu_util() as
> this appears to be missing for EAS too ...
Scratch that. I do think there is something missing in the EAS path, but
not sure that would fix it. I'll have a think and stop spamming
everybody in the meantime ...
The first question is still valid, though :)
Sorry for the noise,
Quentin
