sched/pelt: Add a new runnable average signal

Now that runnable_load_avg has been removed, we can replace it by a new
signal that will highlight the runnable pressure on a cfs_rq. This signal
track the waiting time of tasks on rq and can help to better define the
state of rqs.

At now, only util_avg is used to define the state of a rq:
  A rq with more that around 80% of utilization and more than 1 tasks is
  considered as overloaded.

But the util_avg signal of a rq can become temporaly low after that a task
migrated onto another rq which can bias the classification of the rq.

When tasks compete for the same rq, their runnable average signal will be
higher than util_avg as it will include the waiting time and we can use
this signal to better classify cfs_rqs.

The new runnable_avg will track the runnable time of a task which simply
adds the waiting time to the running time. The runnable _avg of cfs_rq
will be the /Sum of se's runnable_avg and the runnable_avg of group entity
will follow the one of the rq similarly to util_avg.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: "Dietmar Eggemann <dietmar.eggemann@arm.com>"
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-9-mgorman@techsingularity.net

kernel/sched/fair.c

@@ -794,6 +794,8 @@ void post_init_entity_util_avg(struct task_struct *p)
 		}
 	}
 
+	sa->runnable_avg = cpu_scale;
+
 	if (p->sched_class != &fair_sched_class) {
 		/*
 		 * For !fair tasks do:
@@ -3215,9 +3217,9 @@ void set_task_rq_fair(struct sched_entity *se,
  * _IFF_ we look at the pure running and runnable sums. Because they
  * represent the very same entity, just at different points in the hierarchy.
  *
- * Per the above update_tg_cfs_util() is trivial  * and simply copies the
- * running sum over (but still wrong, because the group entity and group rq do
- * not have their PELT windows aligned).
+ * Per the above update_tg_cfs_util() and update_tg_cfs_runnable() are trivial
+ * and simply copies the running/runnable sum over (but still wrong, because
+ * the group entity and group rq do not have their PELT windows aligned).
  *
  * However, update_tg_cfs_load() is more complex. So we have:
  *
@@ -3299,6 +3301,32 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
 	cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
 }
 
+static inline void
+update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
+{
+	long delta = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg;
+
+	/* Nothing to update */
+	if (!delta)
+		return;
+
+	/*
+	 * The relation between sum and avg is:
+	 *
+	 *   LOAD_AVG_MAX - 1024 + sa->period_contrib
+	 *
+	 * however, the PELT windows are not aligned between grq and gse.
+	 */
+
+	/* Set new sched_entity's runnable */
+	se->avg.runnable_avg = gcfs_rq->avg.runnable_avg;
+	se->avg.runnable_sum = se->avg.runnable_avg * LOAD_AVG_MAX;
+
+	/* Update parent cfs_rq runnable */
+	add_positive(&cfs_rq->avg.runnable_avg, delta);
+	cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * LOAD_AVG_MAX;
+}
+
 static inline void
 update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
@@ -3379,6 +3407,7 @@ static inline int propagate_entity_load_avg(struct sched_entity *se)
 	add_tg_cfs_propagate(cfs_rq, gcfs_rq->prop_runnable_sum);
 
 	update_tg_cfs_util(cfs_rq, se, gcfs_rq);
+	update_tg_cfs_runnable(cfs_rq, se, gcfs_rq);
 	update_tg_cfs_load(cfs_rq, se, gcfs_rq);
 
 	trace_pelt_cfs_tp(cfs_rq);
@@ -3449,7 +3478,7 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum
 static inline int
 update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 {
-	unsigned long removed_load = 0, removed_util = 0, removed_runnable_sum = 0;
+	unsigned long removed_load = 0, removed_util = 0, removed_runnable = 0;
 	struct sched_avg *sa = &cfs_rq->avg;
 	int decayed = 0;
 
@@ -3460,7 +3489,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 		raw_spin_lock(&cfs_rq->removed.lock);
 		swap(cfs_rq->removed.util_avg, removed_util);
 		swap(cfs_rq->removed.load_avg, removed_load);
-		swap(cfs_rq->removed.runnable_sum, removed_runnable_sum);
+		swap(cfs_rq->removed.runnable_avg, removed_runnable);
 		cfs_rq->removed.nr = 0;
 		raw_spin_unlock(&cfs_rq->removed.lock);
 
@@ -3472,7 +3501,16 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 		sub_positive(&sa->util_avg, r);
 		sub_positive(&sa->util_sum, r * divider);
 
-		add_tg_cfs_propagate(cfs_rq, -(long)removed_runnable_sum);
+		r = removed_runnable;
+		sub_positive(&sa->runnable_avg, r);
+		sub_positive(&sa->runnable_sum, r * divider);
+
+		/*
+		 * removed_runnable is the unweighted version of removed_load so we
+		 * can use it to estimate removed_load_sum.
+		 */
+		add_tg_cfs_propagate(cfs_rq,
+			-(long)(removed_runnable * divider) >> SCHED_CAPACITY_SHIFT);
 
 		decayed = 1;
 	}
@@ -3517,6 +3555,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	 */
 	se->avg.util_sum = se->avg.util_avg * divider;
 
+	se->avg.runnable_sum = se->avg.runnable_avg * divider;
+
 	se->avg.load_sum = divider;
 	if (se_weight(se)) {
 		se->avg.load_sum =
@@ -3526,6 +3566,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	enqueue_load_avg(cfs_rq, se);
 	cfs_rq->avg.util_avg += se->avg.util_avg;
 	cfs_rq->avg.util_sum += se->avg.util_sum;
+	cfs_rq->avg.runnable_avg += se->avg.runnable_avg;
+	cfs_rq->avg.runnable_sum += se->avg.runnable_sum;
 
 	add_tg_cfs_propagate(cfs_rq, se->avg.load_sum);
 
@@ -3547,6 +3589,8 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	dequeue_load_avg(cfs_rq, se);
 	sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
 	sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+	sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg);
+	sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum);
 
 	add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum);
 
@@ -3653,10 +3697,15 @@ static void remove_entity_load_avg(struct sched_entity *se)
 	++cfs_rq->removed.nr;
 	cfs_rq->removed.util_avg	+= se->avg.util_avg;
 	cfs_rq->removed.load_avg	+= se->avg.load_avg;
-	cfs_rq->removed.runnable_sum	+= se->avg.load_sum; /* == runnable_sum */
+	cfs_rq->removed.runnable_avg	+= se->avg.runnable_avg;
 	raw_spin_unlock_irqrestore(&cfs_rq->removed.lock, flags);
 }
 
+static inline unsigned long cfs_rq_runnable_avg(struct cfs_rq *cfs_rq)
+{
+	return cfs_rq->avg.runnable_avg;
+}
+
 static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
 {
 	return cfs_rq->avg.load_avg;
@@ -3983,11 +4032,13 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	/*
 	 * When enqueuing a sched_entity, we must:
 	 *   - Update loads to have both entity and cfs_rq synced with now.
+	 *   - Add its load to cfs_rq->runnable_avg
 	 *   - For group_entity, update its weight to reflect the new share of
 	 *     its group cfs_rq
 	 *   - Add its new weight to cfs_rq->load.weight
 	 */
 	update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH);
+	se_update_runnable(se);
 	update_cfs_group(se);
 	account_entity_enqueue(cfs_rq, se);
 
@@ -4065,11 +4116,13 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	/*
 	 * When dequeuing a sched_entity, we must:
 	 *   - Update loads to have both entity and cfs_rq synced with now.
+	 *   - Subtract its load from the cfs_rq->runnable_avg.
 	 *   - Subtract its previous weight from cfs_rq->load.weight.
 	 *   - For group entity, update its weight to reflect the new share
 	 *     of its group cfs_rq.
 	 */
 	update_load_avg(cfs_rq, se, UPDATE_TG);
+	se_update_runnable(se);
 
 	update_stats_dequeue(cfs_rq, se, flags);
 
@@ -5240,6 +5293,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 			goto enqueue_throttle;
 
 		update_load_avg(cfs_rq, se, UPDATE_TG);
+		se_update_runnable(se);
 		update_cfs_group(se);
 
 		cfs_rq->h_nr_running++;
@@ -5337,6 +5391,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 			goto dequeue_throttle;
 
 		update_load_avg(cfs_rq, se, UPDATE_TG);
+		se_update_runnable(se);
 		update_cfs_group(se);
 
 		cfs_rq->h_nr_running--;
@@ -5409,6 +5464,11 @@ static unsigned long cpu_load_without(struct rq *rq, struct task_struct *p)
 	return load;
 }
 
+static unsigned long cpu_runnable(struct rq *rq)
+{
+	return cfs_rq_runnable_avg(&rq->cfs);
+}
+
 static unsigned long capacity_of(int cpu)
 {
 	return cpu_rq(cpu)->cpu_capacity;
@@ -7554,6 +7614,9 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
 	if (cfs_rq->avg.util_sum)
 		return false;
 
+	if (cfs_rq->avg.runnable_sum)
+		return false;
+
 	return true;
 }