[PATCH 3/7] sched: select_idle_sibling optimization

[Alex Shi]

Current logical in this function will insist to wake up the task in a
totally idle group, otherwise it would rather back to previous cpu.

The new logical will try to wake up the task on any idle cpu in the same
cpu socket (in same sd_llc), while idle cpu in the smaller domain has
higher priority.

It should has some help on burst wake up benchmarks like aim7.

Original-patch-by: Preeti U Murthy <preeti@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Alex Shi <alex.shi@xxxxxxxxx>
---
 kernel/sched/fair.c |   40 +++++++++++++++++++---------------------
 1 files changed, 19 insertions(+), 21 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e116215..fa40e49 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3253,13 +3253,13 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 /*
  * Try and locate an idle CPU in the sched_domain.
  */
-static int select_idle_sibling(struct task_struct *p)
+static int select_idle_sibling(struct task_struct *p,
+				struct sched_domain *affine_sd, int sync)
 {
 	int cpu = smp_processor_id();
 	int prev_cpu = task_cpu(p);
 	struct sched_domain *sd;
 	struct sched_group *sg;
-	int i;
 
 	/*
 	 * If the task is going to be woken-up on this cpu and if it is
@@ -3281,27 +3281,25 @@ static int select_idle_sibling(struct task_struct *p)
 	/*
 	 * Otherwise, iterate the domains and find an elegible idle cpu.
 	 */
-	sd = rcu_dereference(per_cpu(sd_llc, prev_cpu));
-	for_each_lower_domain(sd) {
+	for_each_domain(prev_cpu, sd) {
 		sg = sd->groups;
 		do {
-			if (!cpumask_intersects(sched_group_cpus(sg),
-						tsk_cpus_allowed(p)))
-				goto next;
-
-			for_each_cpu(i, sched_group_cpus(sg)) {
-				if (!idle_cpu(i))
-					goto next;
-			}
-
-			prev_cpu = cpumask_first_and(sched_group_cpus(sg),
-					tsk_cpus_allowed(p));
-			goto done;
-next:
-			sg = sg->next;
-		} while (sg != sd->groups);
+			int nr_busy = atomic_read(&sg->sgp->nr_busy_cpus);
+			int i;
+
+			/* no idle cpu in the group */
+			if (nr_busy == sg->group_weight)
+				continue;
+			for_each_cpu_and(i, sched_group_cpus(sg),
+							tsk_cpus_allowed(p))
+				if (idle_cpu(i))
+					return i;
+		} while (sg = sg->next, sg != sd->groups);
+
+		/* only wake up task on the same cpu socket as prev cpu */
+		if (sd == per_cpu(sd_llc, prev_cpu))
+			break;
 	}
-done:
 	return prev_cpu;
 }
 
@@ -3355,7 +3353,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
 	}
 
 	if (affine_sd) {
-		new_cpu = select_idle_sibling(p, prev_cpu);
+		new_cpu = select_idle_sibling(p, affine_sd, sync);
 		goto unlock;
 	}
 
-- 
1.7.5.4

--
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/