sched/fair: Align PELT windows between cfs_rq and its se

The PELT _sum values are a saw-tooth function, dropping on the decay
edge and then growing back up again during the window.

When these window-edges are not aligned between cfs_rq and se, we can
have the situation where, for example, on dequeue, the se decays
first.

Its _sum values will be small(er), while the cfs_rq _sum values will
still be on their way up. Because of this, the subtraction:
cfs_rq->avg._sum -= se->avg._sum will result in a positive value. This
will then, once the cfs_rq reaches an edge, translate into its _avg
value jumping up.

This is especially visible with the runnable_load bits, since they get
added/subtracted a lot.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 31 insertions, 14 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 92dbcc0fea46..954b332cd899 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -716,13 +716,8 @@ void init_entity_runnable_average(struct sched_entity *se)
 {
 	struct sched_avg *sa = &se->avg;
 
-	sa->last_update_time = 0;
-	/*
-	 * sched_avg's period_contrib should be strictly less then 1024, so
-	 * we give it 1023 to make sure it is almost a period (1024us), and
-	 * will definitely be update (after enqueue).
-	 */
-	sa->period_contrib = 1023;
+	memset(sa, 0, sizeof(*sa));
+
 	/*
 	 * Tasks are intialized with full load to be seen as heavy tasks until
 	 * they get a chance to stabilize to their real load level.
@@ -731,13 +726,9 @@ void init_entity_runnable_average(struct sched_entity *se)
 	 */
 	if (entity_is_task(se))
 		sa->runnable_load_avg = sa->load_avg = scale_load_down(se->load.weight);
-	sa->runnable_load_sum = sa->load_sum = LOAD_AVG_MAX;
 
-	/*
-	 * At this point, util_avg won't be used in select_task_rq_fair anyway
-	 */
-	sa->util_avg = 0;
-	sa->util_sum = 0;
+	se->runnable_weight = se->load.weight;
+
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
 
@@ -785,7 +776,6 @@ void post_init_entity_util_avg(struct sched_entity *se)
 		} else {
 			sa->util_avg = cap;
 		}
-		sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
 	}
 
 	if (entity_is_task(se)) {
@@ -3632,7 +3622,34 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
  */
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	u32 divider = LOAD_AVG_MAX - 1024 + cfs_rq->avg.period_contrib;
+
+	/*
+	 * When we attach the @se to the @cfs_rq, we must align the decay
+	 * window because without that, really weird and wonderful things can
+	 * happen.
+	 *
+	 * XXX illustrate
+	 */
 	se->avg.last_update_time = cfs_rq->avg.last_update_time;
+	se->avg.period_contrib = cfs_rq->avg.period_contrib;
+
+	/*
+	 * Hell(o) Nasty stuff.. we need to recompute _sum based on the new
+	 * period_contrib. This isn't strictly correct, but since we're
+	 * entirely outside of the PELT hierarchy, nobody cares if we truncate
+	 * _sum a little.
+	 */
+	se->avg.util_sum = se->avg.util_avg * divider;
+
+	se->avg.load_sum = divider;
+	if (se_weight(se)) {
+		se->avg.load_sum =
+			div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se));
+	}
+
+	se->avg.runnable_load_sum = se->avg.load_sum;
+
 	enqueue_load_avg(cfs_rq, se);
 	cfs_rq->avg.util_avg += se->avg.util_avg;
 	cfs_rq->avg.util_sum += se->avg.util_sum;