sched: add avg-overlap support to RT tasks

We have the notion of tracking process-coupling (a.k.a. buddy-wake) via
the p->se.last_wake / p->se.avg_overlap facilities, but it is only used
for cfs to cfs interactions.  There is no reason why an rt to cfs
interaction cannot share in establishing a relationhip in a similar
manner.

Because PREEMPT_RT runs many kernel threads as FIFO priority, we often
times have heavy interaction between RT threads waking CFS applications.
This patch offers a substantial boost (50-60%+) in perfomance under those
circumstances.

Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Cc: npiggin@suse.de
Cc: rostedt@goodmis.org
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 16 insertions, 19 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index d99aeabeb72..bbc40c3a065 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1693,6 +1693,12 @@ static void set_load_weight(struct task_struct *p)
 	p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
 }
 
+static void update_avg(u64 *avg, u64 sample)
+{
+	s64 diff = sample - *avg;
+	*avg += diff >> 3;
+}
+
 static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
 {
 	sched_info_queued(p);
@@ -1702,6 +1708,12 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
 
 static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
 {
+	if (sleep && p->se.last_wakeup) {
+		update_avg(&p->se.avg_overlap,
+			   p->se.sum_exec_runtime - p->se.last_wakeup);
+		p->se.last_wakeup = 0;
+	}
+
 	p->sched_class->dequeue_task(rq, p, sleep);
 	p->se.on_rq = 0;
 }
@@ -2313,6 +2325,8 @@ out_running:
 		p->sched_class->task_wake_up(rq, p);
 #endif
 out:
+	current->se.last_wakeup = current->se.sum_exec_runtime;
+
 	task_rq_unlock(rq, &flags);
 
 	return success;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 2e43d4a748c..f2aa987027d 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -726,21 +726,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 		__enqueue_entity(cfs_rq, se);
 }
 
-static void update_avg(u64 *avg, u64 sample)
-{
-	s64 diff = sample - *avg;
-	*avg += diff >> 3;
-}
-
-static void update_avg_stats(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	if (!se->last_wakeup)
-		return;
-
-	update_avg(&se->avg_overlap, se->sum_exec_runtime - se->last_wakeup);
-	se->last_wakeup = 0;
-}
-
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -751,7 +736,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 
 	update_stats_dequeue(cfs_rq, se);
 	if (sleep) {
-		update_avg_stats(cfs_rq, se);
 #ifdef CONFIG_SCHEDSTATS
 		if (entity_is_task(se)) {
 			struct task_struct *tsk = task_of(se);
@@ -1196,9 +1180,9 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
 	 * a reasonable amount of time then attract this newly
 	 * woken task:
 	 */
-	if (sync && balanced && curr->sched_class == &fair_sched_class) {
+	if (sync && balanced) {
 		if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
-				p->se.avg_overlap < sysctl_sched_migration_cost)
+		    p->se.avg_overlap < sysctl_sched_migration_cost)
 			return 1;
 	}
 
@@ -1359,7 +1343,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 		return;
 	}
 
-	se->last_wakeup = se->sum_exec_runtime;
 	if (unlikely(se == pse))
 		return;