[PATCH] sched/fair: Track peak per-entity utilization

[Morten Rasmussen]

When using PELT (per-entity load tracking) utilization to place tasks at
wake-up using the decayed utilization (due to sleep) leads to
under-estimation of true utilization of the task. This could mean
putting the task on a cpu with less available capacity than is actually
needed. This issue can be mitigated by using 'peak' utilization instead
of the decayed utilization for placement decisions, e.g. at task
wake-up.

The 'peak' utilization metric, util_peak, tracks util_avg when the task
is running and retains its previous value while the task is
blocked/waiting on the rq. It is instantly updated to track util_avg
again as soon as the task running again.

cc: Ingo Molnar <mingo@xxxxxxxxxx>
cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Signed-off-by: Morten Rasmussen <morten.rasmussen@xxxxxxx>
---
 include/linux/sched.h |  2 +-
 kernel/sched/fair.c   | 18 ++++++++++++++----
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4e0c47af9b05..40e427d1d378 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1281,7 +1281,7 @@ struct load_weight {
 struct sched_avg {
 	u64 last_update_time, load_sum;
 	u32 util_sum, period_contrib;
-	unsigned long load_avg, util_avg;
+	unsigned long load_avg, util_avg, util_peak;
 };
 
 #ifdef CONFIG_SCHEDSTATS
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 11b250531ed4..8462a3d455ff 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -692,6 +692,7 @@ void init_entity_runnable_average(struct sched_entity *se)
 	 * At this point, util_avg won't be used in select_task_rq_fair anyway
 	 */
 	sa->util_avg = 0;
+	sa->util_peak = 0;
 	sa->util_sum = 0;
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
@@ -744,6 +745,7 @@ void post_init_entity_util_avg(struct sched_entity *se)
 		} else {
 			sa->util_avg = cap;
 		}
+		sa->util_peak = sa->util_avg;
 		sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
 	}
 
@@ -2806,6 +2808,9 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 		sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
 	}
 
+	if (running || sa->util_avg > sa->util_peak)
+		sa->util_peak = sa->util_avg;
+
 	return decayed;
 }
 
@@ -5174,7 +5179,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	return 1;
 }
 
-static inline int task_util(struct task_struct *p);
+static inline int task_util_peak(struct task_struct *p);
 static int cpu_util_wake(int cpu, struct task_struct *p);
 
 static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
@@ -5257,10 +5262,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 	} while (group = group->next, group != sd->groups);
 
 	/* Found a significant amount of spare capacity. */
-	if (this_spare > task_util(p) / 2 &&
+	if (this_spare > task_util_peak(p) / 2 &&
 	    imbalance*this_spare > 100*most_spare)
 		return NULL;
-	else if (most_spare > task_util(p) / 2)
+	else if (most_spare > task_util_peak(p) / 2)
 		return most_spare_sg;
 
 	if (!idlest || 100*this_load < imbalance*min_load)
@@ -5423,6 +5428,11 @@ static inline int task_util(struct task_struct *p)
 	return p->se.avg.util_avg;
 }
 
+static inline int task_util_peak(struct task_struct *p)
+{
+	return p->se.avg.util_peak;
+}
+
 /*
  * cpu_util_wake: Compute cpu utilization with any contributions from
  * the waking task p removed.
@@ -5455,7 +5465,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 	/* Bring task utilization in sync with prev_cpu */
 	sync_entity_load_avg(&p->se);
 
-	return min_cap * 1024 < task_util(p) * capacity_margin;
+	return min_cap * 1024 < task_util_peak(p) * capacity_margin;
 }
 
 /*
-- 
1.9.1