[PATCH v6 3/3] sched/rt: Check to push the task when changing its affinity

[Xunlei Pang]

From: Xunlei Pang <pang.xunlei@xxxxxxxxxx>

We may suffer from extra rt overload rq due to the affinity,
so when the affinity of any runnable rt task is changed, we
should check to trigger balancing, otherwise it will cause
some unnecessary delayed real-time response. Unfortunately,
current RT global scheduler does nothing about this.

For example: a 2-cpu system with two runnable FIFO tasks(same
rt_priority) bound on CPU0, let's name them rt1(running) and
rt2(runnable) respectively; CPU1 has no RTs. Then, someone sets
the affinity of rt2 to 0x3(i.e. CPU0 and CPU1), but after this,
rt2 still can't be scheduled until rt1 enters schedule(), this
definitely causes some/big response latency for rt2.

So, when doing set_cpus_allowed_rt(), if detecting such cases,
check to trigger a push behaviour.

Signed-off-by: Xunlei Pang <pang.xunlei@xxxxxxxxxx>
---
 kernel/sched/rt.c | 81 ++++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 71 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8679eff..846b59c 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1460,10 +1460,9 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
 	return next;
 }
 
-static struct task_struct *_pick_next_task_rt(struct rq *rq)
+static struct task_struct *peek_next_task_rt(struct rq *rq)
 {
 	struct sched_rt_entity *rt_se;
-	struct task_struct *p;
 	struct rt_rq *rt_rq  = &rq->rt;
 
 	do {
@@ -1472,7 +1471,14 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 		rt_rq = group_rt_rq(rt_se);
 	} while (rt_rq);
 
-	p = rt_task_of(rt_se);
+	return rt_task_of(rt_se);
+}
+
+static inline struct task_struct *_pick_next_task_rt(struct rq *rq)
+{
+	struct task_struct *p;
+
+	p = peek_next_task_rt(rq);
 	p->se.exec_start = rq_clock_task(rq);
 
 	return p;
@@ -2096,28 +2102,77 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 				const struct cpumask *new_mask)
 {
 	struct rq *rq;
-	int weight;
+	int old_weight, new_weight;
+	int preempt_push = 0, direct_push = 0;
 
 	BUG_ON(!rt_task(p));
 
 	if (!task_on_rq_queued(p))
 		return;
 
-	weight = cpumask_weight(new_mask);
+	old_weight = p->nr_cpus_allowed;
+	new_weight = cpumask_weight(new_mask);
 
+	rq = task_rq(p);
+
+	if (new_weight > 1 &&
+	    rt_task(rq->curr) &&
+	    rq->rt.rt_nr_total > 1 &&
+	    !test_tsk_need_resched(rq->curr)) {
+		/*
+		 * We own p->pi_lock and rq->lock. rq->lock might
+		 * get released when doing direct pushing, however
+		 * p->pi_lock is always held, so it's safe to assign
+		 * new_mask and new_weight to p below.
+		 */
+		if (!task_running(rq, p)) {
+			cpumask_copy(&p->cpus_allowed, new_mask);
+			p->nr_cpus_allowed = new_weight;
+			direct_push = 1;
+		} else if (cpumask_test_cpu(task_cpu(p), new_mask)) {
+			struct task_struct *next;
+
+			cpumask_copy(&p->cpus_allowed, new_mask);
+			p->nr_cpus_allowed = new_weight;
+			if (!cpupri_find(&rq->rd->cpupri, p, NULL))
+				goto update;
+
+			/*
+			 * At this point, current task gets migratable most
+			 * likely due to the change of its affinity, let's
+			 * figure out if we can migrate it.
+			 *
+			 * Can we find any task with the same priority as
+			 * current? To accomplish this, firstly we requeue
+			 * current to the tail and peek next, then restore
+			 * current to the head.
+			 */
+			requeue_task_rt(rq, p, 0);
+			next = peek_next_task_rt(rq);
+			requeue_task_rt(rq, p, 1);
+			if (next != p && next->prio == p->prio) {
+				/*
+				 * Target found, so let's reschedule to try
+				 * and push current away.
+				 */
+				requeue_task_rt(rq, next, 1);
+				preempt_push = 1;
+			}
+		}
+	}
+
+update:
 	/*
 	 * Only update if the process changes its state from whether it
 	 * can migrate or not.
 	 */
-	if ((p->nr_cpus_allowed > 1) == (weight > 1))
-		return;
-
-	rq = task_rq(p);
+	if ((old_weight > 1) == (new_weight > 1))
+		goto out;
 
 	/*
 	 * The process used to be able to migrate OR it can now migrate
 	 */
-	if (weight <= 1) {
+	if (new_weight <= 1) {
 		if (!task_current(rq, p))
 			dequeue_pushable_task(rq, p);
 		BUG_ON(!rq->rt.rt_nr_migratory);
@@ -2129,6 +2184,12 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 	}
 
 	update_rt_migration(&rq->rt);
+
+out:
+	if (direct_push)
+		push_rt_tasks(rq);
+	else if (preempt_push)
+		resched_curr(rq);
 }
 
 /* Assumes rq->lock is held */
-- 
1.9.1


--
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/