On Wed, Apr 12, 2017 at 02:34:48PM +0100, Patrick Bellasi wrote:
> On 12-Apr 14:15, Peter Zijlstra wrote:
> > On Tue, Apr 11, 2017 at 06:58:33PM +0100, Patrick Bellasi wrote:
> > > We should consider also that at the CPUFreq side we already expose
> > > knobs like scaling_{min,max}_freq which are much more platform
> > > dependant than capacity.
> >
> > So I've always objected to these knobs.
> >
> > That said; they are a pre-existing user interface so changing them isn't
> > really feasible much.
> >
> > But at the very least we should integrate them properly. Which for
> > schedutil would mean they have to directly modify the relevant CPU
> > capacity values. Is this currently done? (I think not.)
>
> AFAICS they are clamping the policy decisions, thus the frequency
> domain... which can be more then one CPU on ARM platforms.
Right, knew that. Must've missed the 's' when typing ;-)
> When you say you would like them to "directly modify the relevant CPU
> capacity values" I really see this as exactly what we do with
> capacity_{min,max}.
What I mean is that when we set max as lower than max-freq, it should
reduce the CPU(s)' capacity. That's something entirely different from what
you're attempting (and not something we do currently afaik).
Also; there's as yet unexplored interaction between these knobs and the
RT bandwidth limits.
But the main point is that these knobs are system wide and do not affect
tasks.
