Re: [tip:sched/core] sched: Push down pre_schedule() and idle_balance ()

[Michael wang <wangyun@linux.vnet.ibm.com>]

On 02/12/2014 06:22 PM, Peter Zijlstra wrote:
[snip]
> 
> Yes I think there might be a problem here because of how we re-arranged
> things. Let me brew of pot of tea and try to actually wake up.
> 
> I suspect we might be good if we clear the need_resched flags before
> calling pick_next_task. Then any RT/DL task that gets moved here will
> set need resched, and we'll retry the pick_next_task loop.

That sounds better, some thing like this?



diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fb9764f..56a2e1f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2688,8 +2688,8 @@ need_resched:
 	if (prev->on_rq || rq->skip_clock_update < 0)
 		update_rq_clock(rq);
 
-	next = pick_next_task(rq, prev);
 	clear_tsk_need_resched(prev);
+	next = pick_next_task(rq, prev);
 	clear_preempt_need_resched();
 	rq->skip_clock_update = 0;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 235cfa7..48a9500 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4784,7 +4784,18 @@ idle:
 	rq->idle_stamp = rq_clock(rq);
 	if (idle_balance(rq)) { /* drops rq->lock */
 		rq->idle_stamp = 0;
-		goto again;
+		/*
+		 * Before we start to pick one of the pulled fair entities, take
+		 * care if some RT/DL tasks has been enqueued during the time
+		 * we release rq-lock inside idle_balance().
+		 *
+		 * In such cases, since clear_tsk_need_resched() was done
+		 * already, need_resched() will imply the request to sched-in
+		 * the enqueued RT/DL tasks, so don't 'goto again' to make sure
+		 * the priority.
+		 */
+		if (rq->nr_running == rq->cfs.h_nr_running || !need_resched())
+			goto again;



I like tea BTW, drink every day :)

Regards,
Michael Wang

> --
> 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/
>