[patch 8/8] disable CFS RT load balancing.

[Steven Rostedt <rostedt@goodmis.org>]

Since we now take an active approach to load balancing, we don't need to
balance RT tasks via CFS. In fact, this code was found to pull RT tasks
away from CPUS that the active movement performed, resulting in
large latencies.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/sched_rt.c |   90 +-----------------------------------------------------
 1 file changed, 2 insertions(+), 88 deletions(-)

Index: linux-test.git/kernel/sched_rt.c
===================================================================
--- linux-test.git.orig/kernel/sched_rt.c	2007-10-19 12:36:07.000000000 -0400
+++ linux-test.git/kernel/sched_rt.c	2007-10-19 13:01:31.000000000 -0400
@@ -535,100 +535,14 @@ static void put_prev_task_rt(struct rq *
 	p->se.exec_start = 0;
 }
 
-/*
- * Load-balancing iterator. Note: while the runqueue stays locked
- * during the whole iteration, the current task might be
- * dequeued so the iterator has to be dequeue-safe. Here we
- * achieve that by always pre-iterating before returning
- * the current task:
- */
-static struct task_struct *load_balance_start_rt(void *arg)
-{
-	struct rq *rq = arg;
-	struct rt_prio_array *array = &rq->rt.active;
-	struct list_head *head, *curr;
-	struct task_struct *p;
-	int idx;
-
-	idx = sched_find_first_bit(array->bitmap);
-	if (idx >= MAX_RT_PRIO)
-		return NULL;
-
-	head = array->queue + idx;
-	curr = head->prev;
-
-	p = list_entry(curr, struct task_struct, run_list);
-
-	curr = curr->prev;
-
-	rq->rt.rt_load_balance_idx = idx;
-	rq->rt.rt_load_balance_head = head;
-	rq->rt.rt_load_balance_curr = curr;
-
-	return p;
-}
-
-static struct task_struct *load_balance_next_rt(void *arg)
-{
-	struct rq *rq = arg;
-	struct rt_prio_array *array = &rq->rt.active;
-	struct list_head *head, *curr;
-	struct task_struct *p;
-	int idx;
-
-	idx = rq->rt.rt_load_balance_idx;
-	head = rq->rt.rt_load_balance_head;
-	curr = rq->rt.rt_load_balance_curr;
-
-	/*
-	 * If we arrived back to the head again then
-	 * iterate to the next queue (if any):
-	 */
-	if (unlikely(head == curr)) {
-		int next_idx = find_next_bit(array->bitmap, MAX_RT_PRIO, idx+1);
-
-		if (next_idx >= MAX_RT_PRIO)
-			return NULL;
-
-		idx = next_idx;
-		head = array->queue + idx;
-		curr = head->prev;
-
-		rq->rt.rt_load_balance_idx = idx;
-		rq->rt.rt_load_balance_head = head;
-	}
-
-	p = list_entry(curr, struct task_struct, run_list);
-
-	curr = curr->prev;
-
-	rq->rt.rt_load_balance_curr = curr;
-
-	return p;
-}
-
 static unsigned long
 load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
 			unsigned long max_nr_move, unsigned long max_load_move,
 			struct sched_domain *sd, enum cpu_idle_type idle,
 			int *all_pinned, int *this_best_prio)
 {
-	int nr_moved;
-	struct rq_iterator rt_rq_iterator;
-	unsigned long load_moved;
-
-	rt_rq_iterator.start = load_balance_start_rt;
-	rt_rq_iterator.next = load_balance_next_rt;
-	/* pass 'busiest' rq argument into
-	 * load_balance_[start|next]_rt iterators
-	 */
-	rt_rq_iterator.arg = busiest;
-
-	nr_moved = balance_tasks(this_rq, this_cpu, busiest, max_nr_move,
-			max_load_move, sd, idle, all_pinned, &load_moved,
-			this_best_prio, &rt_rq_iterator);
-
-	return load_moved;
+	/* don't touch RT tasks */
+	return 0;
 }
 
 static void task_tick_rt(struct rq *rq, struct task_struct *p)

-- 
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/