sched/fair: Make load tracking frequency scale-invariant

Apply frequency scaling correction factor to per-entity load tracking to
make it frequency invariant. Currently, load appears bigger when the CPU
is running slower which affects load-balancing decisions.

Each segment of the sched_avg.load_sum geometric series is now scaled by
the current frequency so that the sched_avg.load_avg of each sched entity
will be invariant from frequency scaling.

Moreover, cfs_rq.runnable_load_sum is scaled by the current frequency as
well.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <Dietmar.Eggemann@arm.com>
Cc: Juri Lelli <Juri.Lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: daniel.lezcano@linaro.org
Cc: mturquette@baylibre.com
Cc: pang.xunlei@zte.com.cn
Cc: rjw@rjwysocki.net
Cc: sgurrappadi@nvidia.com
Cc: yuyang.du@intel.com
Link: http://lkml.kernel.org/r/1439569394-11974-2-git-send-email-morten.rasmussen@arm.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/sched.h

@@ -1177,9 +1177,9 @@ struct load_weight {
 
 /*
  * The load_avg/util_avg accumulates an infinite geometric series.
- * 1) load_avg factors the amount of time that a sched_entity is
- * runnable on a rq into its weight. For cfs_rq, it is the aggregated
- * such weights of all runnable and blocked sched_entities.
+ * 1) load_avg factors frequency scaling into the amount of time that a
+ * sched_entity is runnable on a rq into its weight. For cfs_rq, it is the
+ * aggregated such weights of all runnable and blocked sched_entities.
  * 2) util_avg factors frequency scaling into the amount of time
  * that a sched_entity is running on a CPU, in the range [0..SCHED_LOAD_SCALE].
  * For cfs_rq, it is the aggregated such times of all runnable and

kernel/sched/fair.c

@@ -2515,6 +2515,8 @@ static u32 __compute_runnable_contrib(u64 n)
 	return contrib + runnable_avg_yN_sum[n];
 }
 
+#define scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
 /*
  * We can represent the historical contribution to runnable average as the
  * coefficients of a geometric series.  To do this we sub-divide our runnable
@@ -2547,9 +2549,9 @@ static __always_inline int
 __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 		  unsigned long weight, int running, struct cfs_rq *cfs_rq)
 {
-	u64 delta, periods;
+	u64 delta, scaled_delta, periods;
 	u32 contrib;
-	int delta_w, decayed = 0;
+	int delta_w, scaled_delta_w, decayed = 0;
 	unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
 
 	delta = now - sa->last_update_time;
@@ -2585,13 +2587,16 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 		 * period and accrue it.
 		 */
 		delta_w = 1024 - delta_w;
+		scaled_delta_w = scale(delta_w, scale_freq);
 		if (weight) {
-			sa->load_sum += weight * delta_w;
-			if (cfs_rq)
-				cfs_rq->runnable_load_sum += weight * delta_w;
+			sa->load_sum += weight * scaled_delta_w;
+			if (cfs_rq) {
+				cfs_rq->runnable_load_sum +=
+						weight * scaled_delta_w;
+			}
 		}
 		if (running)
-			sa->util_sum += delta_w * scale_freq >> SCHED_CAPACITY_SHIFT;
+			sa->util_sum += scaled_delta_w;
 
 		delta -= delta_w;
 
@@ -2608,23 +2613,25 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 
 		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
 		contrib = __compute_runnable_contrib(periods);
+		contrib = scale(contrib, scale_freq);
 		if (weight) {
 			sa->load_sum += weight * contrib;
 			if (cfs_rq)
 				cfs_rq->runnable_load_sum += weight * contrib;
 		}
 		if (running)
-			sa->util_sum += contrib * scale_freq >> SCHED_CAPACITY_SHIFT;
+			sa->util_sum += contrib;
 	}
 
 	/* Remainder of delta accrued against u_0` */
+	scaled_delta = scale(delta, scale_freq);
 	if (weight) {
-		sa->load_sum += weight * delta;
+		sa->load_sum += weight * scaled_delta;
 		if (cfs_rq)
-			cfs_rq->runnable_load_sum += weight * delta;
+			cfs_rq->runnable_load_sum += weight * scaled_delta;
 	}
 	if (running)
-		sa->util_sum += delta * scale_freq >> SCHED_CAPACITY_SHIFT;
+		sa->util_sum += scaled_delta;
 
 	sa->period_contrib += delta;