Re: [PATCH] sched/deadline: Always calculate end of period on sched_yield()

[Peter Zijlstra]

On Fri, Feb 12, 2016 at 06:10:20PM -0500, Steven Rostedt wrote:
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index cd64c979d0e1..1dd180cda574 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -735,7 +735,7 @@ static void update_curr_dl(struct rq *rq)
>        * approach need further study.
>        */
>       delta_exec = rq_clock_task(rq) - curr->se.exec_start;
> -     if (unlikely((s64)delta_exec <= 0))
> +     if (unlikely((s64)delta_exec <= 0 && !dl_se->dl_yielded))
>               return;
>  
>       schedstat_set(curr->se.statistics.exec_max,


Would something like this make sense instead?

It also retains the ->runtime while yielded, and would actually 'fix' a
case where, when we call yield, we would have had a negative runtime
after update_curr_dl().

The current code will 'gift' us extra runtime in that case.

---
 kernel/sched/deadline.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 57b939c81bce..c2bca80d3388 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -399,6 +399,9 @@ static void replenish_dl_entity(struct sched_dl_entity 
*dl_se,
                dl_se->runtime = pi_se->dl_runtime;
        }
 
+       if (dl_se->dl_yielded && dl_se->runtime > 0)
+               dl_se->runtime = 0;
+
        /*
         * We keep moving the deadline away until we get some
         * available runtime for the entity. This ensures correct
@@ -735,8 +738,11 @@ static void update_curr_dl(struct rq *rq)
         * approach need further study.
         */
        delta_exec = rq_clock_task(rq) - curr->se.exec_start;
-       if (unlikely((s64)delta_exec <= 0))
+       if (unlikely((s64)delta_exec <= 0)) {
+               if (unlikely(dl_se->dl_yielded))
+                       goto throttle;
                return;
+       }
 
        schedstat_set(curr->se.statistics.exec_max,
                      max(curr->se.statistics.exec_max, delta_exec));
@@ -749,8 +755,10 @@ static void update_curr_dl(struct rq *rq)
 
        sched_rt_avg_update(rq, delta_exec);
 
-       dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
-       if (dl_runtime_exceeded(dl_se)) {
+       dl_se->runtime -= delta_exec;
+
+throttle:
+       if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) {
                dl_se->dl_throttled = 1;
                __dequeue_task_dl(rq, curr, 0);
                if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr)))
@@ -1002,10 +1010,8 @@ static void yield_task_dl(struct rq *rq)
         * it and the bandwidth timer will wake it up and will give it
         * new scheduling parameters (thanks to dl_yielded=1).
         */
-       if (p->dl.runtime > 0) {
-               rq->curr->dl.dl_yielded = 1;
-               p->dl.runtime = 0;
-       }
+       rq->curr->dl.dl_yielded = 1;
+
        update_rq_clock(rq);
        update_curr_dl(rq);
        /*