On Tue, Jul 24, 2018 at 01:25:19PM +0100, Quentin Perret wrote:
> @@ -6385,18 +6492,26 @@ static int
> select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int
> wake_flags)
> {
> struct sched_domain *tmp, *sd = NULL;
> + struct freq_domain *fd;
> int cpu = smp_processor_id();
> int new_cpu = prev_cpu;
> - int want_affine = 0;
> + int want_affine = 0, want_energy = 0;
> int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);
>
> + rcu_read_lock();
> if (sd_flag & SD_BALANCE_WAKE) {
> record_wakee(p);
> - want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
> - && cpumask_test_cpu(cpu, &p->cpus_allowed);
> + fd = rd_freq_domain(cpu_rq(cpu)->rd);
> + want_energy = fd && !READ_ONCE(cpu_rq(cpu)->rd->overutilized);
> + want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
> + cpumask_test_cpu(cpu, &p->cpus_allowed);
> + }
> +
> + if (want_energy) {
> + new_cpu = find_energy_efficient_cpu(p, prev_cpu, fd);
> + goto unlock;
> }
>
And I suppose you rely on the compiler to optimize that for the static
key inside rd_freq_domain()... Does it do a good job of that?
That is, would not something like:
rcu_read_lock();
if (sd_flag & SD_BALANCE_WAKE) {
record_wakee(p);
if (static_branch_unlikely(&sched_energy_present)) {
struct root_domain *rd = cpu_rq(cpu)->rd;
struct freq_domain *fd = rd_freq_domain(rd);
if (fd && !READ_ONCE(rd->overutilized)) {
new_cpu = find_energy_efficient_cpu(p,
prev_cpu, fd);
goto unlock;
}
}
/* ... */
}
Be far more clear ?
