Re: [PATCH v4 2/3] sched/fair: Take thermal pressure into account while estimating energy

[Lukasz Luba]

On 6/16/21 8:25 PM, Vincent Guittot wrote:
> On Wed, 16 Jun 2021 at 19:24, Dietmar Eggemann <dietmar.eggemann@xxxxxxx> wrote:
> > On 15/06/2021 18:09, Lukasz Luba wrote:
> > > On 6/15/21 4:31 PM, Dietmar Eggemann wrote:
> > > > On 14/06/2021 21:11, Lukasz Luba wrote:
> >
> > [...]
> >
> > > > It's important to highlight that this will only fix this issue between
> > > > schedutil and EAS when it's due to `thermal pressure` (today only via
> > > > CPU cooling). There are other places which could restrict policy->max
> > > > via freq_qos_update_request() and EAS will be unaware of it.
> > >
> > > True, but for this I have some other plans.
> >
> > As long as people are aware of the fact that this was developed to be
> > beneficial for `EAS - IPA` integration, I'm fine with this.
>
> I don't think it's only for EAS - IPA. Thermal_pressure can be used by
> HW throttling like here:
> https://lkml.org/lkml/2021/6/8/1791
>
> EAS is involved but not IPA

Thank you Vincent for pointing to Thara's patches. Indeed, this is a
good example. We will have to provide similar for our SCMI perf
notifications - these are the plans that I've mentioned. In both
new examples, the IPA (or other governors) won't be even involved.