Re: [PATCH V4 2/3] sched/deadline: Throttle a constrained deadline task activated after the deadline

[Wanpeng Li]

2017-03-02 22:10 GMT+08:00 Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>:
> During the activation, CBS checks if it can reuse the current task's
> runtime and period. If the deadline of the task is in the past, CBS
> cannot use the runtime, and so it replenishes the task. This rule
> works fine for implicit deadline tasks (deadline == period), and the
> CBS was designed for implicit deadline tasks. However, a task with
> constrained deadline (deadine < period) might be awakened after the
> deadline, but before the next period. In this case, replenishing the
> task would allow it to run for runtime / deadline. As in this case
> deadline < period, CBS enables a task to run for more than the
> runtime / period. In a very loaded system, this can cause a domino
> effect, making other tasks miss their deadlines.
>
> To avoid this problem, in the activation of a constrained deadline
> task after the deadline but before the next period, throttle the
> task and set the replenishing timer to the begin of the next period,
> unless it is boosted.
>
> Reproducer:
>
>  --------------- %< ---------------
>   int main (int argc, char **argv)
>   {
>         int ret;
>         int flags = 0;
>         unsigned long l = 0;
>         struct timespec ts;
>         struct sched_attr attr;
>
>         memset(&attr, 0, sizeof(attr));
>         attr.size = sizeof(attr);
>
>         attr.sched_policy   = SCHED_DEADLINE;
>         attr.sched_runtime  = 2 * 1000 * 1000;          /* 2 ms */
>         attr.sched_deadline = 2 * 1000 * 1000;          /* 2 ms */
>         attr.sched_period   = 2 * 1000 * 1000 * 1000;   /* 2 s */
>
>         ts.tv_sec = 0;
>         ts.tv_nsec = 2000 * 1000;                       /* 2 ms */
>
>         ret = sched_setattr(0, &attr, flags);
>
>         if (ret < 0) {
>                 perror("sched_setattr");
>                 exit(-1);
>         }
>
>         for(;;) {
>                 /* XXX: you may need to adjust the loop */
>                 for (l = 0; l < 150000; l++);
>                 /*
>                  * The ideia is to go to sleep right before the deadline
>                  * and then wake up before the next period to receive
>                  * a new replenishment.
>                  */
>                 nanosleep(&ts, NULL);
>         }
>
>         exit(0);
>   }
>   --------------- >% ---------------
>
> On my box, this reproducer uses almost 50% of the CPU time, which is
> obviously wrong for a task with 2/2000 reservation.
>
> Signed-off-by: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
> Cc: Ingo Molnar <mingo@xxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Cc: Juri Lelli <juri.lelli@xxxxxxx>
> Cc: Tommaso Cucinotta <tommaso.cucinotta@xxxxxxxx>
> Cc: Luca Abeni <luca.abeni@xxxxxxxxxxxxxxx>
> Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
> Cc: Mike Galbraith <efault@xxxxxx>
> Cc: Romulo Silva de Oliveira <romulo.deoliveira@xxxxxxx>
> Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
> Cc: linux-kernel@xxxxxxxxxxxxxxx

Reviewed-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>

> ---
>  kernel/sched/deadline.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 45 insertions(+)
>
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 3e3caae..b669f7f 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -694,6 +694,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
>         timer->function = dl_task_timer;
>  }
>
> +/*
> + * During the activation, CBS checks if it can reuse the current task's
> + * runtime and period. If the deadline of the task is in the past, CBS
> + * cannot use the runtime, and so it replenishes the task. This rule
> + * works fine for implicit deadline tasks (deadline == period), and the
> + * CBS was designed for implicit deadline tasks. However, a task with
> + * constrained deadline (deadine < period) might be awakened after the
> + * deadline, but before the next period. In this case, replenishing the
> + * task would allow it to run for runtime / deadline. As in this case
> + * deadline < period, CBS enables a task to run for more than the
> + * runtime / period. In a very loaded system, this can cause a domino
> + * effect, making other tasks miss their deadlines.
> + *
> + * To avoid this problem, in the activation of a constrained deadline
> + * task after the deadline but before the next period, throttle the
> + * task and set the replenishing timer to the begin of the next period,
> + * unless it is boosted.
> + */
> +static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
> +{
> +       struct task_struct *p = dl_task_of(dl_se);
> +       struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
> +
> +       if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
> +           dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
> +               if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
> +                       return;
> +               dl_se->dl_throttled = 1;
> +       }
> +}
> +
>  static
>  int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
>  {
> @@ -927,6 +958,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
>         __dequeue_dl_entity(dl_se);
>  }
>
> +static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
> +{
> +       return dl_se->dl_deadline < dl_se->dl_period;
> +}
> +
>  static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
>  {
>         struct task_struct *pi_task = rt_mutex_get_top_task(p);
> @@ -953,6 +989,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
>         }
>
>         /*
> +        * Check if a constrained deadline task was activated
> +        * after the deadline but before the next period.
> +        * If that is the case, the task will be throttled and
> +        * the replenishment timer will be set to the next period.
> +        */
> +       if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
> +               dl_check_constrained_dl(&p->dl);
> +
> +       /*
>          * If p is throttled, we do nothing. In fact, if it exhausted
>          * its budget it needs a replenishment and, since it now is on
>          * its rq, the bandwidth timer callback (which clearly has not
> --
> 2.9.3
>