sched/balancing: Periodically decay max cost of idle balance

This patch builds on patch 2 and periodically decays that max value to
do idle balancing per sched domain by approximately 1% per second. Also
decay the rq's max_idle_balance_cost value.

Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1379096813-3032-4-git-send-email-jason.low2@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/metag/include/asm/topology.h

@@ -27,6 +27,7 @@
 	.balance_interval	= 1,			\
 	.nr_balance_failed	= 0,			\
 	.max_newidle_lb_cost	= 0,			\
+	.next_decay_max_lb_cost	= jiffies,		\
 }
 
 #define cpu_to_node(cpu)	((void)(cpu), 0)

include/linux/sched.h

@@ -810,7 +810,10 @@ struct sched_domain {
 	unsigned int nr_balance_failed; /* initialise to 0 */
 
 	u64 last_update;
+
+	/* idle_balance() stats */
 	u64 max_newidle_lb_cost;
+	unsigned long next_decay_max_lb_cost;
 
 #ifdef CONFIG_SCHEDSTATS
 	/* load_balance() stats */

include/linux/topology.h

@@ -107,6 +107,7 @@ int arch_update_cpu_topology(void);
 	.balance_interval	= 1,					\
 	.smt_gain		= 1178,	/* 15% */			\
 	.max_newidle_lb_cost	= 0,					\
+	.next_decay_max_lb_cost	= jiffies,				\
 }
 #endif
 #endif /* CONFIG_SCHED_SMT */
@@ -137,6 +138,7 @@ int arch_update_cpu_topology(void);
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
 	.max_newidle_lb_cost	= 0,					\
+	.next_decay_max_lb_cost	= jiffies,				\
 }
 #endif
 #endif /* CONFIG_SCHED_MC */
@@ -169,6 +171,7 @@ int arch_update_cpu_topology(void);
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
 	.max_newidle_lb_cost	= 0,					\
+	.next_decay_max_lb_cost	= jiffies,				\
 }
 #endif
 

kernel/sched/fair.c

@@ -5681,15 +5681,39 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	/* Earliest time when we have to do rebalance again */
 	unsigned long next_balance = jiffies + 60*HZ;
 	int update_next_balance = 0;
-	int need_serialize;
+	int need_serialize, need_decay = 0;
+	u64 max_cost = 0;
 
 	update_blocked_averages(cpu);
 
 	rcu_read_lock();
 	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.
+		 */
+		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;
+		}
+		max_cost += sd->max_newidle_lb_cost;
+
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;
 
+		/*
+		 * Stop the load balance at this level. There is another
+		 * CPU in our sched group which is doing load balancing more
+		 * actively.
+		 */
+		if (!continue_balancing) {
+			if (need_decay)
+				continue;
+			break;
+		}
+
 		interval = sd->balance_interval;
 		if (idle != CPU_IDLE)
 			interval *= sd->busy_factor;
@@ -5723,14 +5747,14 @@ out:
 			next_balance = sd->last_balance + interval;
 			update_next_balance = 1;
 		}
-
+	}
+	if (need_decay) {
 		/*
-		 * Stop the load balance at this level. There is another
-		 * CPU in our sched group which is doing load balancing more
-		 * actively.
+		 * Ensure the rq-wide value also decays but keep it at a
+		 * reasonable floor to avoid funnies with rq->avg_idle.
 		 */
-		if (!continue_balancing)
-			break;
+		rq->max_idle_balance_cost =
+			max((u64)sysctl_sched_migration_cost, max_cost);
 	}
 	rcu_read_unlock();