2014-06-25 08:19:56

by Kirill Tkhai

Subject: [PATCH v3 2/3] sched/rt: __disable_runtime: Enqueue just unthrottled rt_rq back on the stack

Make rt_rq available for pick_next_task(). Otherwise, their tasks
stay prisoned long time till dead cpu becomes alive again.

Signed-off-by: Kirill Tkhai <[email protected]>
CC: Konstantin Khorenko <[email protected]>
CC: Ben Segall <[email protected]>
CC: Paul Turner <[email protected]>
CC: Srikar Dronamraju <[email protected]>
CC: Mike Galbraith <[email protected]>
CC: Peter Zijlstra <[email protected]>
CC: Ingo Molnar <[email protected]>
---
kernel/sched/rt.c | 3 +++
1 file changed, 3 insertions(+)

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a490831..671a8b5 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -740,6 +740,9 @@ static void __disable_runtime(struct rq *rq)
rt_rq->rt_throttled = 0;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
raw_spin_unlock(&rt_b->rt_runtime_lock);
+
+ /* Make rt_rq available for pick_next_task() */
+ sched_rt_rq_enqueue(rt_rq);
}
}

2014-06-26 11:08:46

by Srikar Dronamraju

Subject: Re: [PATCH v3 2/3] sched/rt: __disable_runtime: Enqueue just unthrottled rt_rq back on the stack

* Kirill Tkhai <[email protected]> [2014-06-25 12:19:48]:

>
> Make rt_rq available for pick_next_task(). Otherwise, their tasks
> stay prisoned long time till dead cpu becomes alive again.
>
> Signed-off-by: Kirill Tkhai <[email protected]>
> CC: Konstantin Khorenko <[email protected]>
> CC: Ben Segall <[email protected]>
> CC: Paul Turner <[email protected]>
> CC: Srikar Dronamraju <[email protected]>
> CC: Mike Galbraith <[email protected]>
> CC: Peter Zijlstra <[email protected]>
> CC: Ingo Molnar <[email protected]>
> ---
looks good to me.

Reviewed-by: Srikar Dronamraju <[email protected]>

--
Thanks and Regards
Srikar Dronamraju

2014-06-26 11:09:38

by Srikar Dronamraju

Subject: Re: [PATCH v3 2/3] sched/rt: __disable_runtime: Enqueue just unthrottled rt_rq back on the stack

* Kirill Tkhai <[email protected]> [2014-06-25 12:19:48]:

>
> Make rt_rq available for pick_next_task(). Otherwise, their tasks
> stay prisoned long time till dead cpu becomes alive again.
>
> Signed-off-by: Kirill Tkhai <[email protected]>
> CC: Konstantin Khorenko <[email protected]>
> CC: Ben Segall <[email protected]>
> CC: Paul Turner <[email protected]>
> CC: Srikar Dronamraju <[email protected]>
> CC: Mike Galbraith <[email protected]>
> CC: Peter Zijlstra <[email protected]>
> CC: Ingo Molnar <[email protected]>
> ---

Reviewed-by: Srikar Dronamraju <[email protected]>

--
Thanks and Regards
Srikar Dronamraju

2014-07-05 10:47:17

by tip-bot for Vasyl Gomonovych

Subject: [tip:sched/core] sched/rt: Enqueue just unthrottled rt_rq back on the stack in __disable_runtime()

Commit-ID: 99b625670f1447ecf0739161efbe7f2f43c0e0b6
Gitweb: http://git.kernel.org/tip/99b625670f1447ecf0739161efbe7f2f43c0e0b6
Author: Kirill Tkhai <[email protected]>
AuthorDate: Wed, 25 Jun 2014 12:19:48 +0400
Committer: Ingo Molnar <[email protected]>
CommitDate: Sat, 5 Jul 2014 11:17:44 +0200

sched/rt: Enqueue just unthrottled rt_rq back on the stack in __disable_runtime()

Make rt_rq available for pick_next_task(). Otherwise, their tasks
stay prisoned long time till dead cpu becomes alive again.

Reviewed-by: Srikar Dronamraju <[email protected]>
Signed-off-by: Kirill Tkhai <[email protected]>
CC: Konstantin Khorenko <[email protected]>
CC: Ben Segall <[email protected]>
CC: Paul Turner <[email protected]>
CC: Mike Galbraith <[email protected]>
Cc: Linus Torvalds <[email protected]>
Signed-off-by: Peter Zijlstra <[email protected]>
Link: http://lkml.kernel.org/r/1403684388.3462.43.camel@tkhai
Signed-off-by: Ingo Molnar <[email protected]>
---
kernel/sched/rt.c | 3 +++
1 file changed, 3 insertions(+)

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a490831..671a8b5 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -740,6 +740,9 @@ balanced:
rt_rq->rt_throttled = 0;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
raw_spin_unlock(&rt_b->rt_runtime_lock);
+
+ /* Make rt_rq available for pick_next_task() */
+ sched_rt_rq_enqueue(rt_rq);
}
}