On Thu, Jul 12, 2018 at 01:29:40PM -0400, Johannes Weiner wrote:
> +static bool psi_update_stats(struct psi_group *group)
> +{
> + u64 some[NR_PSI_RESOURCES] = { 0, };
> + u64 full[NR_PSI_RESOURCES] = { 0, };
> + unsigned long nonidle_total = 0;
> + unsigned long missed_periods;
> + unsigned long expires;
> + int cpu;
> + int r;
> +
> + mutex_lock(&group->stat_lock);
> +
> + /*
> + * Collect the per-cpu time buckets and average them into a
> + * single time sample that is normalized to wallclock time.
> + *
> + * For averaging, each CPU is weighted by its non-idle time in
> + * the sampling period. This eliminates artifacts from uneven
> + * loading, or even entirely idle CPUs.
> + *
> + * We could pin the online CPUs here, but the noise introduced
> + * by missing up to one sample period from CPUs that are going
> + * away shouldn't matter in practice - just like the noise of
> + * previously offlined CPUs returning with a non-zero sample.
But why!? cpuu_read_lock() is neither expensive nor complicated. So why
try and avoid it?
> + */
> + for_each_online_cpu(cpu) {
> + struct psi_group_cpu *groupc = per_cpu_ptr(group->cpus, cpu);
> + unsigned long nonidle;
> +
> + if (!groupc->nonidle_time)
> + continue;
> +
> + nonidle = nsecs_to_jiffies(groupc->nonidle_time);
> + groupc->nonidle_time = 0;
> + nonidle_total += nonidle;
> +
> + for (r = 0; r < NR_PSI_RESOURCES; r++) {
> + struct psi_resource *res = &groupc->res[r];
> +
> + some[r] += (res->times[0] + res->times[1]) * nonidle;
> + full[r] += res->times[1] * nonidle;
> +
> + /* It's racy, but we can tolerate some error */
> + res->times[0] = 0;
> + res->times[1] = 0;
> + }
> + }
> +
> + /*
> + * Integrate the sample into the running statistics that are
> + * reported to userspace: the cumulative stall times and the
> + * decaying averages.
> + *
> + * Pressure percentages are sampled at PSI_FREQ. We might be
> + * called more often when the user polls more frequently than
> + * that; we might be called less often when there is no task
> + * activity, thus no data, and clock ticks are sporadic. The
> + * below handles both.
> + */
> +
> + /* total= */
> + for (r = 0; r < NR_PSI_RESOURCES; r++) {
> + do_div(some[r], max(nonidle_total, 1UL));
> + do_div(full[r], max(nonidle_total, 1UL));
> +
> + group->some[r] += some[r];
> + group->full[r] += full[r];
group->some[r] = div64_ul(some[r], max(nonidle_total, 1UL));
group->full[r] = div64_ul(full[r], max(nonidle_total, 1UL));
Is easier to read imo.
> + }
> +
> + /* avgX= */
> + expires = group->period_expires;
> + if (time_before(jiffies, expires))
> + goto out;
> +
> + missed_periods = (jiffies - expires) / PSI_FREQ;
> + group->period_expires = expires + ((1 + missed_periods) * PSI_FREQ);
> +
> + for (r = 0; r < NR_PSI_RESOURCES; r++) {
> + u64 some, full;
> +
> + some = group->some[r] - group->last_some[r];
> + full = group->full[r] - group->last_full[r];
> +
> + calc_avgs(group->avg_some[r], some, missed_periods);
> + calc_avgs(group->avg_full[r], full, missed_periods);
> +
> + group->last_some[r] = group->some[r];
> + group->last_full[r] = group->full[r];
> + }
> +out:
> + mutex_unlock(&group->stat_lock);
> + return nonidle_total;
> +}
