SCHED_RR can context-switch many times without having changed the run-queue.
Therefore trying to push on each context switch can just be wasted effort
since if it failed the first time, it will likely fail any subsequent times
as well. Instead, set a flag when we have successfully pushed as many tasks
away as possible, and only clear it when the runqueue adds new tasks
(effectively becoming a run-queue "dirty bit"). If new tasks are added we
should try again. If any remote run-queues downgrade their priority in the
meantime, they will try to pull from us (as they always do).
This attempts to address a performance regression reported by Suresh Siddha,
et. al. in the 2.6.25 series. It applies to 2.6.25.
Signed-off-by: Gregory Haskins <ghaskins@xxxxxxxxxx>
CC: suresh.b.siddha@xxxxxxxxx
CC: mingo@xxxxxxx
CC: rostedt@xxxxxxxxxxx
CC: chinang.ma@xxxxxxxxx
CC: arjan@xxxxxxxxxxxxxxx
CC: willy@xxxxxxxxxxxxxxx
---
kernel/sched.c | 2 ++
kernel/sched_rt.c | 24 ++++++++++++++++++++++--
2 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/kernel/sched.c b/kernel/sched.c
index 0067fc8..d859649 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -462,6 +462,7 @@ struct rt_rq {
#ifdef CONFIG_SMP
unsigned long rt_nr_migratory;
int overloaded;
+ int pushed;
#endif
int rt_throttled;
u64 rt_time;
@@ -8073,6 +8074,7 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
#ifdef CONFIG_SMP
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
+ rt_rq->pushed = 0;
#endif
rt_rq->rt_time = 0;
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index c2730a5..3cc98be 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -515,6 +515,15 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
enqueue_rt_entity(rt_se);
inc_cpu_load(rq, p->se.load.weight);
+
+#ifdef CONFIG_SMP
+ /*
+ * Clear the "pushed" state since we have changed the run-queue and
+ * may need to migrate some of these tasks (see push_rt_tasks() for
+ * details)
+ */
+ rq->rt.pushed = 0;
+#endif
}
static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -913,7 +922,7 @@ static int push_rt_task(struct rq *rq)
int ret = 0;
int paranoid = RT_MAX_TRIES;
- if (!rq->rt.overloaded)
+ if (!rq->rt.overloaded || rq->rt.pushed)
return 0;
next_task = pick_next_highest_task_rt(rq, -1);
@@ -973,6 +982,15 @@ out:
}
/*
+ * push_rt_tasks()
+ *
+ * Push as many tasks away as possible. We only need to try once whenever
+ * one or more new tasks are added to our runqueue. After an inital attempt,
+ * further changes in remote runqueue state will be accounted for with pull
+ * operations. Therefore, we mark the run-queue as "pushed" here, and clear it
+ * during enqueue. This primarily helps SCHED_RR tasks which will tend to
+ * have a higher context-switch to enqueue ratio.
+ *
* TODO: Currently we just use the second highest prio task on
* the queue, and stop when it can't migrate (or there's
* no more RT tasks). There may be a case where a lower
@@ -987,6 +1005,8 @@ static void push_rt_tasks(struct rq *rq)
/* push_rt_task will return true if it moved an RT */
while (push_rt_task(rq))
;
+
+ rq->rt.pushed = 1;
}
static int pull_rt_task(struct rq *this_rq)
@@ -1091,7 +1111,7 @@ static void post_schedule_rt(struct rq *rq)
* the lock was owned by prev, we need to release it
* first via finish_lock_switch and then reaquire it here.
*/
- if (unlikely(rq->rt.overloaded)) {
+ if (unlikely(rq->rt.overloaded && !rq->rt.pushed)) {
spin_lock_irq(&rq->lock);
push_rt_tasks(rq);
spin_unlock_irq(&rq->lock);
--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
