Re: [PATCH -v2 12/18] sched/fair: Rewrite PELT migration propagation

[Vincent Guittot]

Subject: [PATCH v2] sched: Update runnable propagation rule

Unlike running, the runnable part can't be directly propagated through
the hierarchy when we migrate a task. The main reason is that runnable
time can be shared with other sched_entities that stay on the rq and this
runnable time will also remain on prev cfs_rq and must not be removed.
Instead, we can estimate what should be the new runnable of the prev cfs_rq
and check that this estimation stay in a possible range.
The prop_runnable_sum is a good estimation when adding runnable_sum but
fails most often when we remove it. Instead, we could use the formula below
instead:

  gcfs_rq's runnable_sum = gcfs_rq->avg.load_sum / gcfs_rq->load.weight (1)

(1) assumes that tasks are equally runnable which is not true but easy to
compute.

Beside these estimates, we have several simple rules that help us to filter
out wrong ones:
-ge->avg.runnable_sum <= than LOAD_AVG_MAX
-ge->avg.runnable_sum >= ge->avg.running_sum (ge->avg.util_sum << LOAD_AVG_MAX)
-ge->avg.runnable_sum can't increase when we detach a task

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---

v2:
- Fixed some type mismatch warnings

 kernel/sched/fair.c | 46 +++++++++++++++++++++++++++++++++++-----------
 1 file changed, 35 insertions(+), 11 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 56f343b..aea89df 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3489,33 +3489,57 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
 static inline void
 update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
 {
-	long runnable_sum = gcfs_rq->prop_runnable_sum;
-	long runnable_load_avg, load_avg;
-	s64 runnable_load_sum, load_sum;
+	long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum;
+	unsigned long runnable_load_avg, load_avg;
+	s64 delta_sum;
+	u64 runnable_load_sum, load_sum = 0;
 
 	if (!runnable_sum)
 		return;
 
 	gcfs_rq->prop_runnable_sum = 0;
 
+	if (runnable_sum >= 0) {
+		/* Get a rough estimate of the new gcfs_rq's runnable */
+		runnable_sum += se->avg.load_sum;
+		/* ge->avg.runnable_sum can't be higher than LOAD_AVG_MAX */
+		runnable_sum = min(runnable_sum, (long)LOAD_AVG_MAX);
+	} else {
+		/* Get a rough estimate of the new gcfs_rq's runnable */
+		if (scale_load_down(gcfs_rq->load.weight))
+			load_sum = div_s64(gcfs_rq->avg.load_sum,
+				scale_load_down(gcfs_rq->load.weight));
+
+		/* ge->avg.runnable_sum can't increase when removing runnable */
+		runnable_sum = min(se->avg.load_sum, load_sum);
+	}
+
+	/* runnable_sum can't be lower than running_sum */
+	running_sum = se->avg.util_sum >> SCHED_CAPACITY_SHIFT;
+	runnable_sum = max(runnable_sum, running_sum);
+
 	load_sum = (s64)se_weight(se) * runnable_sum;
 	load_avg = div_s64(load_sum, LOAD_AVG_MAX);
 
-	add_positive(&se->avg.load_sum, runnable_sum);
-	add_positive(&se->avg.load_avg, load_avg);
+	delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum;
+	delta_avg = load_avg - se->avg.load_avg;
 
-	add_positive(&cfs_rq->avg.load_avg, load_avg);
-	add_positive(&cfs_rq->avg.load_sum, load_sum);
+	se->avg.load_sum = runnable_sum;
+	se->avg.load_avg = load_avg;
+	add_positive(&cfs_rq->avg.load_avg, delta_avg);
+	add_positive(&cfs_rq->avg.load_sum, delta_sum);
 
 	runnable_load_sum = (s64)se_runnable(se) * runnable_sum;
 	runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX);
+	delta_sum = runnable_load_sum - se_weight(se) * se->avg.runnable_load_sum;
+	delta_avg = runnable_load_avg - se->avg.runnable_load_avg;
 
-	add_positive(&se->avg.runnable_load_sum, runnable_sum);
-	add_positive(&se->avg.runnable_load_avg, runnable_load_avg);
+	se->avg.runnable_load_sum = runnable_sum;
+	se->avg.runnable_load_avg = runnable_load_avg;
 
 	if (se->on_rq) {
-		add_positive(&cfs_rq->avg.runnable_load_avg, runnable_load_avg);
-		add_positive(&cfs_rq->avg.runnable_load_sum, runnable_load_sum);
+		add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg);
+		add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum);
 	}
 }
 
-- 
2.7.4