Re: [PATCH 2/4] sched/uclamp: Remove rq max aggregation

[Qais Yousef <qyousef@layalina.io>]

On 12/08/23 01:52, Qais Yousef wrote:

> +/* Request freq update on context switch if necessary */
> +static inline void uclamp_context_switch(struct rq *rq)
>  {
> -	return static_branch_likely(&sched_uclamp_used);
> +	unsigned long uclamp_min;
> +	unsigned long uclamp_max;
> +	unsigned long util;
> +
> +	/* Only RT and FAIR tasks are aware of uclamp */
> +	if (!rt_policy(current->policy) && !fair_policy(current->policy))
> +		return;

We have a dependency on min_granularity_ns (or base_slice_ns) here that
I forgot to add before posting.

If our base_slice_ns is smaller than dvfs_update_delay, then tasks won't run
long enough for the hardware to apply their performance hints before they get
context switched out.

Beside the new proposed sched_runtime being able to request a smaller slice; in
practice default base_slice_ns is okay-ish.

> +
> +	uclamp_min = uclamp_eff_value(current, UCLAMP_MIN);
> +	uclamp_max = uclamp_eff_value(current, UCLAMP_MAX);
> +	util = rq->cfs.avg.util_avg;
> +
> +	if (uclamp_min > util || uclamp_max < util)
> +		cpufreq_update_util(rq, SCHED_CPUFREQ_PERF_HINTS);
>  }