[PATCH 2/2] sched: Make sched entity usage tracking scale-invariant

[Morten Rasmussen]

Apply frequency scale-invariance correction factor to usage tracking.
Each segment of the running_load_avg geometric series is now scaled by the
current frequency so the utilization_avg_contrib of each entity will be
invariant with frequency scaling. As a result, utilization_load_avg which is
the sum of utilization_avg_contrib, becomes invariant too. So the usage level
that is returned by get_cpu_usage, stays relative to the max frequency as the
cpu_capacity which is is compared against.
Then, we want the keep the load tracking values in a 32bits type, which implies
that the max value of {runnable|running}_avg_sum must be lower than
2^32/88761=48388 (88761 is the max weigth of a task). As LOAD_AVG_MAX = 47742,
arch_scale_freq_capacity must return a value less than
(48388/47742) << SCHED_CAPACITY_SHIFT = 1037 (SCHED_SCALE_CAPACITY = 1024).
So we define the range to [0..SCHED_SCALE_CAPACITY] in order to avoid overflow.

cc: Paul Turner <pjt@xxxxxxxxxx>
cc: Ben Segall <bsegall@xxxxxxxxxx>

Signed-off-by: Morten Rasmussen <morten.rasmussen@xxxxxxx>
Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
 kernel/sched/fair.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 60c3172..c09df87 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2471,6 +2471,8 @@ static u32 __compute_runnable_contrib(u64 n)
 	return contrib + runnable_avg_yN_sum[n];
 }
 
+unsigned long __weak arch_scale_freq_capacity(int cpu, unsigned long factor);
+
 /*
  * We can represent the historical contribution to runnable average as the
  * coefficients of a geometric series.  To do this we sub-divide our runnable
@@ -2499,7 +2501,7 @@ static u32 __compute_runnable_contrib(u64 n)
  *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
  *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
  */
-static __always_inline int __update_entity_runnable_avg(u64 now,
+static __always_inline int __update_entity_runnable_avg(u64 now, int cpu,
 							struct sched_avg *sa,
 							int runnable,
 							int running)
@@ -2542,7 +2544,8 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 		if (runnable)
 			sa->runnable_avg_sum += delta_w;
 		if (running)
-			sa->running_avg_sum += delta_w;
+			sa->running_avg_sum +=
+					arch_scale_freq_capacity(cpu, delta_w);
 		sa->avg_period += delta_w;
 
 		delta -= delta_w;
@@ -2563,7 +2566,8 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 		if (runnable)
 			sa->runnable_avg_sum += runnable_contrib;
 		if (running)
-			sa->running_avg_sum += runnable_contrib;
+			sa->running_avg_sum +=
+				arch_scale_freq_capacity(cpu, runnable_contrib);
 		sa->avg_period += runnable_contrib;
 	}
 
@@ -2571,7 +2575,7 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 	if (runnable)
 		sa->runnable_avg_sum += delta;
 	if (running)
-		sa->running_avg_sum += delta;
+		sa->running_avg_sum += arch_scale_freq_capacity(cpu, delta);
 	sa->avg_period += delta;
 
 	return decayed;
@@ -2679,8 +2683,8 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 {
-	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable,
-			runnable);
+	__update_entity_runnable_avg(rq_clock_task(rq), cpu_of(rq), &rq->avg,
+			runnable, runnable);
 	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
 }
 #else /* CONFIG_FAIR_GROUP_SCHED */
@@ -2758,6 +2762,7 @@ static inline void update_entity_load_avg(struct sched_entity *se,
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	long contrib_delta, utilization_delta;
+	int cpu = cpu_of(rq_of(cfs_rq));
 	u64 now;
 
 	/*
@@ -2769,7 +2774,7 @@ static inline void update_entity_load_avg(struct sched_entity *se,
 	else
 		now = cfs_rq_clock_task(group_cfs_rq(se));
 
-	if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq,
+	if (!__update_entity_runnable_avg(now, cpu, &se->avg, se->on_rq,
 					cfs_rq->curr == se))
 		return;
 
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/