[PATCH 3/5] sched/fair: Wait before decaying max_newidle_lb_cost

[Vincent Guittot <vincent.guittot@linaro.org>]

Decay max_newidle_lb_cost only when it has not been updated for a while
and ensure to not decay a recently changed value.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 include/linux/sched/topology.h |  2 +-
 kernel/sched/fair.c            | 36 +++++++++++++++++++++++++---------
 kernel/sched/topology.c        |  2 +-
 3 files changed, 29 insertions(+), 11 deletions(-)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 2f9166f6dec8..c07bfa2d80f2 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -105,7 +105,7 @@ struct sched_domain {
 
 	/* idle_balance() stats */
 	u64 max_newidle_lb_cost;
-	unsigned long next_decay_max_lb_cost;
+	unsigned long last_decay_max_lb_cost;
 
 	u64 avg_scan_cost;		/* select_idle_sibling */
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c4c36865321b..e50fd751e1df 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10239,6 +10239,30 @@ void update_max_interval(void)
 	max_load_balance_interval = HZ*num_online_cpus()/10;
 }
 
+static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost)
+{
+	if (cost > sd->max_newidle_lb_cost) {
+		/*
+		 * Track max cost of a domain to make sure to not delay the
+		 * next wakeup on the CPU.
+		 */
+		sd->max_newidle_lb_cost = cost;
+		sd->last_decay_max_lb_cost = jiffies;
+	} else if (time_after(jiffies, sd->last_decay_max_lb_cost + HZ)) {
+		/*
+		 * Decay the newidle max times by ~1% per second to ensure that
+		 * it is not outdated and the current max cost is actually
+		 * shorter.
+		 */
+		sd->max_newidle_lb_cost = (sd->max_newidle_lb_cost * 253) / 256;
+		sd->last_decay_max_lb_cost = jiffies;
+
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * It checks each scheduling domain to see if it is due to be balanced,
  * and initiates a balancing operation if so.
@@ -10262,14 +10286,9 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 	for_each_domain(cpu, sd) {
 		/*
 		 * Decay the newidle max times here because this is a regular
-		 * visit to all the domains. Decay ~1% per second.
+		 * visit to all the domains.
 		 */
-		if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
-			sd->max_newidle_lb_cost =
-				(sd->max_newidle_lb_cost * 253) / 256;
-			sd->next_decay_max_lb_cost = jiffies + HZ;
-			need_decay = 1;
-		}
+		need_decay = update_newidle_cost(sd, 0);
 		max_cost += sd->max_newidle_lb_cost;
 
 		/*
@@ -10911,8 +10930,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 
 			t1 = sched_clock_cpu(this_cpu);
 			domain_cost = t1 - t0;
-			if (domain_cost > sd->max_newidle_lb_cost)
-				sd->max_newidle_lb_cost = domain_cost;
+			update_newidle_cost(sd, domain_cost);
 
 			curr_cost += domain_cost;
 			t0 = t1;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index e81246787560..30169c7685b6 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1568,7 +1568,7 @@ sd_init(struct sched_domain_topology_level *tl,
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
 		.max_newidle_lb_cost	= 0,
-		.next_decay_max_lb_cost	= jiffies,
+		.last_decay_max_lb_cost	= jiffies,
 		.child			= child,
 #ifdef CONFIG_SCHED_DEBUG
 		.name			= tl->name,
-- 
2.17.1