| Message ID | 20190627171603.14767-5-douglas.raillard@arm.com (mailing list archive) |
|---|---|
| State | RFC, archived |
| Headers | show |
| Series | sched/cpufreq: Make schedutil energy aware | expand |
Hi Douglas, On 27-Jun 18:16, Douglas RAILLARD wrote: > Use the utilization signals dynamic to detect when the utilization of a > set of tasks starts increasing because of a change in tasks' behavior. > This allows detecting when spending extra power for faster frequency > ramp up response would be beneficial to the reactivity of the system. > > This ramp boost is computed as the difference > util_avg-util_est_enqueued. This number somehow represents a lower bound > of how much extra utilization this tasks is actually using, compared to > our best current stable knowledge of it (which is util_est_enqueued). Maybe it's worth to call out here that at rq-level we don't have an EWMA. However, the enqueued estimated utilization is derived by considering the _task_util_est() which factors in the moving average of tasks and thus makes the signal more stable even in case of tasks switching between big and small activations. > When the set of runnable tasks changes, the boost is disabled as the > impact of blocked utilization on util_avg will make the delta with > util_est_enqueued not very informative. > > Signed-off-by: Douglas RAILLARD <douglas.raillard@arm.com> > --- > kernel/sched/cpufreq_schedutil.c | 42 ++++++++++++++++++++++++++++++++ > 1 file changed, 42 insertions(+) > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c > index 7ffc6fe3b670..3eabfd815195 100644 > --- a/kernel/sched/cpufreq_schedutil.c > +++ b/kernel/sched/cpufreq_schedutil.c > @@ -60,6 +60,9 @@ struct sugov_cpu { > unsigned long bw_dl; > unsigned long max; > > + unsigned long ramp_boost; > + unsigned long util_est_enqueued; > + > /* The field below is for single-CPU policies only: */ > #ifdef CONFIG_NO_HZ_COMMON > unsigned long saved_idle_calls; > @@ -174,6 +177,41 @@ static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time, > } > } > > +static unsigned long sugov_cpu_ramp_boost(struct sugov_cpu *sg_cpu) > +{ > + return READ_ONCE(sg_cpu->ramp_boost); > +} > + > +static unsigned long sugov_cpu_ramp_boost_update(struct sugov_cpu *sg_cpu, > + unsigned long util) > +{ > + struct rq *rq = cpu_rq(sg_cpu->cpu); Since you don't really need the rq below, maybe better: struct sched_avg *sa = &cpu_rq(sg_cpu->cpu)->cfs.avg; ? > + unsigned long util_est_enqueued; > + unsigned long util_avg; > + unsigned long boost = 0; > + > + util_est_enqueued = READ_ONCE(rq->cfs.avg.util_est.enqueued); > + util_avg = READ_ONCE(rq->cfs.avg.util_avg); > + > + /* > + * Boost when util_avg becomes higher than the previous stable > + * knowledge of the enqueued tasks' set util, which is CPU's > + * util_est_enqueued. > + * > + * We try to spot changes in the workload itself, so we want to > + * avoid the noise of tasks being enqueued/dequeued. To do that, > + * we only trigger boosting when the "amount of work' enqueued > + * is stable. > + */ > + if (util_est_enqueued == sg_cpu->util_est_enqueued > + && util_avg > util_est_enqueued) > + boost = util_avg - util_est_enqueued; The above should be: if (util_est_enqueued == sg_cpu->util_est_enqueue && util_avg > util_est_enqueued) { boost = util_avg - util_est_enqueued; } but perhaps you can also go for a fast bailout with something like: if (util_avg <= util_est_enqueued) return 0; if (util_est_enqueued == sg_cpu->util_est_enqueue) boost = util_avg - util_est_enqueued; Moreover: could it make sense to add a threshold on a minimal boost value to return non zero? > + > + sg_cpu->util_est_enqueued = util_est_enqueued; > + WRITE_ONCE(sg_cpu->ramp_boost, boost); > + return boost; You don't seem to use this returned value: should be void? > +} > + > /** > * get_next_freq - Compute a new frequency for a given cpufreq policy. > * @sg_policy: schedutil policy object to compute the new frequency for. > @@ -504,6 +542,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, > busy = sugov_cpu_is_busy(sg_cpu); > > util = sugov_get_util(sg_cpu); > + sugov_cpu_ramp_boost_update(sg_cpu, util); > max = sg_cpu->max; > util = sugov_iowait_apply(sg_cpu, time, util, max); > next_f = get_next_freq(sg_policy, util, max); > @@ -544,6 +583,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) > unsigned long j_util, j_max; > > j_util = sugov_get_util(j_sg_cpu); > + if (j_sg_cpu == sg_cpu) > + sugov_cpu_ramp_boost_update(sg_cpu, j_util); > j_max = j_sg_cpu->max; > j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max); > > @@ -553,6 +594,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) > } > } > > + > return get_next_freq(sg_policy, util, max); > } Best, Patrick
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 7ffc6fe3b670..3eabfd815195 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -60,6 +60,9 @@ struct sugov_cpu { unsigned long bw_dl; unsigned long max; + unsigned long ramp_boost; + unsigned long util_est_enqueued; + /* The field below is for single-CPU policies only: */ #ifdef CONFIG_NO_HZ_COMMON unsigned long saved_idle_calls; @@ -174,6 +177,41 @@ static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time, } } +static unsigned long sugov_cpu_ramp_boost(struct sugov_cpu *sg_cpu) +{ + return READ_ONCE(sg_cpu->ramp_boost); +} + +static unsigned long sugov_cpu_ramp_boost_update(struct sugov_cpu *sg_cpu, + unsigned long util) +{ + struct rq *rq = cpu_rq(sg_cpu->cpu); + unsigned long util_est_enqueued; + unsigned long util_avg; + unsigned long boost = 0; + + util_est_enqueued = READ_ONCE(rq->cfs.avg.util_est.enqueued); + util_avg = READ_ONCE(rq->cfs.avg.util_avg); + + /* + * Boost when util_avg becomes higher than the previous stable + * knowledge of the enqueued tasks' set util, which is CPU's + * util_est_enqueued. + * + * We try to spot changes in the workload itself, so we want to + * avoid the noise of tasks being enqueued/dequeued. To do that, + * we only trigger boosting when the "amount of work' enqueued + * is stable. + */ + if (util_est_enqueued == sg_cpu->util_est_enqueued + && util_avg > util_est_enqueued) + boost = util_avg - util_est_enqueued; + + sg_cpu->util_est_enqueued = util_est_enqueued; + WRITE_ONCE(sg_cpu->ramp_boost, boost); + return boost; +} + /** * get_next_freq - Compute a new frequency for a given cpufreq policy. * @sg_policy: schedutil policy object to compute the new frequency for. @@ -504,6 +542,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, busy = sugov_cpu_is_busy(sg_cpu); util = sugov_get_util(sg_cpu); + sugov_cpu_ramp_boost_update(sg_cpu, util); max = sg_cpu->max; util = sugov_iowait_apply(sg_cpu, time, util, max); next_f = get_next_freq(sg_policy, util, max); @@ -544,6 +583,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) unsigned long j_util, j_max; j_util = sugov_get_util(j_sg_cpu); + if (j_sg_cpu == sg_cpu) + sugov_cpu_ramp_boost_update(sg_cpu, j_util); j_max = j_sg_cpu->max; j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max); @@ -553,6 +594,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) } } + return get_next_freq(sg_policy, util, max); }
Use the utilization signals dynamic to detect when the utilization of a set of tasks starts increasing because of a change in tasks' behavior. This allows detecting when spending extra power for faster frequency ramp up response would be beneficial to the reactivity of the system. This ramp boost is computed as the difference util_avg-util_est_enqueued. This number somehow represents a lower bound of how much extra utilization this tasks is actually using, compared to our best current stable knowledge of it (which is util_est_enqueued). When the set of runnable tasks changes, the boost is disabled as the impact of blocked utilization on util_avg will make the delta with util_est_enqueued not very informative. Signed-off-by: Douglas RAILLARD <douglas.raillard@arm.com> --- kernel/sched/cpufreq_schedutil.c | 42 ++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+)