[PATCH 4/4] sched: bias to target cpu load to reduce task moving

[Alex Shi]

Task migration happens when target just a bit less then source cpu load.
To reduce such situation happens, aggravate the target cpu load with
sd->imbalance_pct/100 in wake_affine.

In find_idlest/busiest_group, change the aggravate to local cpu only
from old group aggravation.

on my pandaboard ES.

	latest kernel 527d1511310a89		+ whole patchset
hackbench -T -g 10 -f 40
	23.25"					21.99"
	23.16"					21.20"
	24.24"					21.89"
hackbench -p -g 10 -f 40
	26.52"					21.46"
	23.89"					22.96"
	25.65"					22.73"
hackbench -P -g 10 -f 40
	20.14"					19.72"
	19.96"					19.10"
	21.76"					20.03"

Signed-off-by: Alex Shi <alex.shi@xxxxxxxxxx>
---
 kernel/sched/fair.c | 35 ++++++++++++++++-------------------
 1 file changed, 16 insertions(+), 19 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bccdd89..3623ba4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -978,7 +978,7 @@ static inline unsigned long group_weight(struct task_struct *p, int nid)
 
 static unsigned long weighted_cpuload(const int cpu);
 static unsigned long source_load(int cpu);
-static unsigned long target_load(int cpu);
+static unsigned long target_load(int cpu, int imbalance_pct);
 static unsigned long power_of(int cpu);
 static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
 
@@ -3809,11 +3809,17 @@ static unsigned long source_load(int cpu)
  * Return a high guess at the load of a migration-target cpu weighted
  * according to the scheduling class and "nice" value.
  */
-static unsigned long target_load(int cpu)
+static unsigned long target_load(int cpu, int imbalance_pct)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long total = weighted_cpuload(cpu);
 
+	/*
+	 * without cpu_load decay, in most of time cpu_load is same as total
+	 * so we need to make target a bit heavier to reduce task migration
+	 */
+	total = total * imbalance_pct / 100;
+
 	if (!sched_feat(LB_BIAS))
 		return total;
 
@@ -4033,7 +4039,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	this_cpu  = smp_processor_id();
 	prev_cpu  = task_cpu(p);
 	load	  = source_load(prev_cpu);
-	this_load = target_load(this_cpu);
+	this_load = target_load(this_cpu, 100);
 
 	/*
 	 * If sync wakeup then subtract the (maximum possible)
@@ -4089,7 +4095,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 
 	if (balanced ||
 	    (this_load <= load &&
-	     this_load + target_load(prev_cpu) <= tl_per_task)) {
+	     this_load + target_load(prev_cpu, 100) <= tl_per_task)) {
 		/*
 		 * This domain has SD_WAKE_AFFINE and
 		 * p is cache cold in this domain, and
@@ -4112,7 +4118,6 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 {
 	struct sched_group *idlest = NULL, *group = sd->groups;
 	unsigned long min_load = ULONG_MAX, this_load = 0;
-	int imbalance = 100 + (sd->imbalance_pct-100)/2;
 
 	do {
 		unsigned long load, avg_load;
@@ -4132,10 +4137,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 
 		for_each_cpu(i, sched_group_cpus(group)) {
 			/* Bias balancing toward cpus of our domain */
-			if (local_group)
+			if (i == this_cpu)
 				load = source_load(i);
 			else
-				load = target_load(i);
+				load = target_load(i, sd->imbalance_pct);
 
 			avg_load += load;
 		}
@@ -4151,7 +4156,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 		}
 	} while (group = group->next, group != sd->groups);
 
-	if (!idlest || 100*this_load < imbalance*min_load)
+	if (!idlest || this_load < min_load)
 		return NULL;
 	return idlest;
 }
@@ -5476,9 +5481,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 		nr_running = rq->nr_running;
 
-		/* Bias balancing toward cpus of our domain */
-		if (local_group)
-			load = target_load(i);
+		/* Bias balancing toward dst cpu */
+		if (env->dst_cpu == i)
+			load = target_load(i, env->sd->imbalance_pct);
 		else
 			load = source_load(i);
 
@@ -5918,14 +5923,6 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 		if ((local->idle_cpus < busiest->idle_cpus) &&
 		    busiest->sum_nr_running <= busiest->group_weight)
 			goto out_balanced;
-	} else {
-		/*
-		 * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
-		 * imbalance_pct to be conservative.
-		 */
-		if (100 * busiest->avg_load <=
-				env->sd->imbalance_pct * local->avg_load)
-			goto out_balanced;
 	}
 
 force_balance:
-- 
1.8.1.2

--
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/