[PATCH 09/13] sched/fair: Take into account runnable_avg to classify group

[Mel Gorman]

From: Vincent Guittot <vincent.guittot@xxxxxxxxxx>

Take into account the new runnable_avg signal to classify a group and to
mitigate the volatility of util_avg in face of intensive migration.

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
 kernel/sched/fair.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 39c3f67682cf..1e515ebe277d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5465,6 +5465,11 @@ static unsigned long cpu_load_without(struct rq *rq, struct task_struct *p)
 	return load;
 }
 
+static unsigned long cpu_runnable(struct rq *rq)
+{
+	return cfs_rq_runnable_avg(&rq->cfs);
+}
+
 static unsigned long capacity_of(int cpu)
 {
 	return cpu_rq(cpu)->cpu_capacity;
@@ -7748,7 +7753,8 @@ struct sg_lb_stats {
 	unsigned long avg_load; /*Avg load across the CPUs of the group */
 	unsigned long group_load; /* Total load over the CPUs of the group */
 	unsigned long group_capacity;
-	unsigned long group_util; /* Total utilization of the group */
+	unsigned long group_util; /* Total utilization over the CPUs of the group */
+	unsigned long group_runnable; /* Total runnable time over the CPUs of the group */
 	unsigned int sum_nr_running; /* Nr of tasks running in the group */
 	unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */
 	unsigned int idle_cpus;
@@ -7969,6 +7975,10 @@ group_has_capacity(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 	if (sgs->sum_nr_running < sgs->group_weight)
 		return true;
 
+	if ((sgs->group_capacity * imbalance_pct) <
+			(sgs->group_runnable * 100))
+		return false;
+
 	if ((sgs->group_capacity * 100) >
 			(sgs->group_util * imbalance_pct))
 		return true;
@@ -7994,6 +8004,10 @@ group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
 			(sgs->group_util * imbalance_pct))
 		return true;
 
+	if ((sgs->group_capacity * imbalance_pct) <
+			(sgs->group_runnable * 100))
+		return true;
+
 	return false;
 }
 
@@ -8088,6 +8102,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 		sgs->group_load += cpu_load(rq);
 		sgs->group_util += cpu_util(i);
+		sgs->group_runnable += cpu_runnable(rq);
 		sgs->sum_h_nr_running += rq->cfs.h_nr_running;
 
 		nr_running = rq->nr_running;
-- 
2.16.4