Re: [RFC PATCH 1/7] PM: Introduce em_pd_get_higher_freq()

[Douglas Raillard]

Hi Patrick,

On 5/16/19 1:42 PM, Patrick Bellasi wrote:
> On 08-May 18:42, douglas.raillard@xxxxxxx wrote:
> > From: Douglas RAILLARD <douglas.raillard@xxxxxxx>
> >
> > em_pd_get_higher_freq() returns a frequency greater or equal to the
> > provided one while taking into account a given cost margin. It also
> > skips inefficient OPPs that have a higher cost than another one with a
> > higher frequency.
>
> It's worth to add a small description and definition of what we mean by
> "OPP efficiency". Despite being just an RFC, it could help to better
> understand what we are after.

Right, here efficiency=capacity/power.

> [...]
>
> > +/** + * em_pd_get_higher_freq() - Get the highest frequency that
> > does not exceed the
> > + * given cost margin compared to min_freq
> > + * @pd		: performance domain for which this must be done
> > + * @min_freq	: minimum frequency to return
> > + * @cost_margin	: allowed margin compared to min_freq, as a per-1024 value.
>                                                                      ^^^^^^^^
> here...
>
> > + *
> > + * Return: the chosen frequency, guaranteed to be at least as high as min_freq.
> > + */
> > +static inline unsigned long em_pd_get_higher_freq(struct em_perf_domain *pd,
> > +	unsigned long min_freq, unsigned long cost_margin)
> > +{
> > +	unsigned long max_cost = 0;
> > +	struct em_cap_state *cs;
> > +	int i;
> > +
> > +	if (!pd)
> > +		return min_freq;
> > +
> > +	/* Compute the maximum allowed cost */
> > +	for (i = 0; i < pd->nr_cap_states; i++) {
> > +		cs = &pd->table[i];
> > +		if (cs->frequency >= min_freq) {
> > +			max_cost = cs->cost + (cs->cost * cost_margin) / 1024;
>                                                                           ^^^^
> ... end here we should probably better use SCHED_CAPACITY_SCALE
> instead of hard-coding in values, isn't it?

"cs->cost*cost_margin/1024" is not a capacity, it's a cost as defined here:
https://elixir.bootlin.com/linux/latest/source/include/linux/energy_model.h#L17

Actually, it's in milliwatts, but it's not better the better way to look at
it to understand it IMHO.

The margin is expressed as a "per-1024" value just like we use percents'
in everyday life, so it has no unit. If we want to avoid hard-coded values
here, I can introduce an ENERGY_COST_MARGIN_SCALE macro.

> > +			break;
> > +		}
> > +	}
> > +
>
> [...]
>
> Best,
> Patrick

Thanks,
Douglas