Re: [RFC 4/8] Improve the tracking of active utilisation

[Peter Zijlstra]

On Thu, Jan 14, 2016 at 04:24:49PM +0100, Luca Abeni wrote:
> @@ -65,6 +67,62 @@ static void clear_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
>  	}
>  }
>  
> +static void task_go_inactive(struct task_struct *p)
> +{
> +	struct sched_dl_entity *dl_se = &p->dl;
> +	struct hrtimer *timer = &dl_se->inactive_timer;
> +	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
> +	struct rq *rq = rq_of_dl_rq(dl_rq);
> +	ktime_t now, act;
> +	s64 delta;
> +	u64 zerolag_time;
> +
> +	WARN_ON(dl_se->dl_runtime == 0);
> +
> +	/* If the inactive timer is already armed, return immediately */
> +	if (hrtimer_active(&dl_se->inactive_timer))
> +		return;
> +
> +
> +	/*
> +	 * We want the timer to fire at the "0 lag time", but considering
> +	 * that it is actually coming from rq->clock and not from
> +	 * hrtimer's time base reading.
> +	 */
> +        zerolag_time = dl_se->deadline - div64_long((dl_se->runtime * dl_se->dl_period), dl_se->dl_runtime);

whitespace damage

> @@ -530,9 +587,20 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
>  	 */
>  	if (dl_se->dl_new) {
>  		setup_new_dl_entity(dl_se, pi_se);
> +		add_running_bw(dl_se, dl_rq);
>  		return;
>  	}
>  
> +	/* If the "inactive timer" is still active, stop it adn leave
> +	 * the active utilisation unchanged.
> +	 * If it is running, increase the active utilisation
> +	 */
> +	if (hrtimer_active(&dl_se->inactive_timer)) {
> +		hrtimer_try_to_cancel(&dl_se->inactive_timer);

what if cancel fails?

> +	} else {
> +	        add_running_bw(dl_se, dl_rq);
> +	}
> +
>  	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
>  	    dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
>  		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;

> @@ -1248,8 +1370,6 @@ static void task_fork_dl(struct task_struct *p)
>  static void task_dead_dl(struct task_struct *p)
>  {
>  	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
> -	struct dl_rq *dl_rq = dl_rq_of_se(&p->dl);
> -	struct rq *rq = rq_of_dl_rq(dl_rq);
>  
>  	/*
>  	 * Since we are TASK_DEAD we won't slip out of the domain!
> @@ -1258,10 +1378,6 @@ static void task_dead_dl(struct task_struct *p)
>  	/* XXX we should retain the bw until 0-lag */
>  	dl_b->total_bw -= p->dl.dl_bw;
>  	raw_spin_unlock_irq(&dl_b->lock);
> -
> -	if (task_on_rq_queued(p)) {
> -		clear_running_bw(&p->dl, &rq->dl);
> -	}

what happens if the timer is still active here? then we get the timer
storage freed while enqueued?

> @@ -1742,12 +1858,12 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
>  	 * SCHED_DEADLINE until the deadline passes, the timer will reset the
>  	 * task.
>  	 */
> -	if (!start_dl_timer(p))
> +	if (task_on_rq_queued(p))
> +		task_go_inactive(p);
> +	if (!hrtimer_active(&p->dl.inactive_timer))
>  		__dl_clear_params(p);
> -
> -	if (task_on_rq_queued(p)) {
> +	else if (!hrtimer_callback_running(&p->dl.inactive_timer))
>  		clear_running_bw(&p->dl, &rq->dl);
> -	}
>  
>  	/*
>  	 * Since this might be the only -deadline task on the rq,

idem, what if the task dies while !dl but with timer pending?