Re: [RFC v3 2/6] Improve the tracking of active utilisation

[Juri Lelli]

Hi,

On 24/10/16 16:06, Luca Abeni wrote:
> This patch implements a more theoretically sound algorithm for
> thracking the active utilisation: instead of decreasing it when a

s/thracking/tracking/
s/the//

> task blocks, use a timer (the "inactive timer", named after the
> "Inactive" task state of the GRUB algorithm) to decrease the
> active utilisaation at the so called "0-lag time".

s/utilisaation/utilisation/

> 
> Signed-off-by: Luca Abeni <luca.abeni@xxxxxxxx>
> ---
>  include/linux/sched.h   |   1 +
>  kernel/sched/core.c     |   1 +
>  kernel/sched/deadline.c | 139 ++++++++++++++++++++++++++++++++++++++++++------
>  kernel/sched/sched.h    |   1 +
>  4 files changed, 126 insertions(+), 16 deletions(-)
> 
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 348f51b..22543c6 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1433,6 +1433,7 @@ struct sched_dl_entity {
>  	 * own bandwidth to be enforced, thus we need one timer per task.
>  	 */
>  	struct hrtimer dl_timer;
> +	struct hrtimer inactive_timer;
>  };
>  
>  union rcu_special {
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 94732d1..664c618 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -2217,6 +2217,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
>  
>  	RB_CLEAR_NODE(&p->dl.rb_node);
>  	init_dl_task_timer(&p->dl);
> +	init_inactive_task_timer(&p->dl);
>  	__dl_clear_params(p);
>  
>  	INIT_LIST_HEAD(&p->rt.run_list);
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 3d95c1d..80d1541 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -47,6 +47,7 @@ static void add_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
>  {
>  	u64 se_bw = dl_se->dl_bw;
>  
> +	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);

This and the one below go in 1/6.

>  	dl_rq->running_bw += se_bw;
>  }
>  
> @@ -54,11 +55,52 @@ static void sub_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
>  {
>  	u64 se_bw = dl_se->dl_bw;
>  
> +	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
>  	dl_rq->running_bw -= se_bw;
>  	if (WARN_ON(dl_rq->running_bw < 0))
>  		dl_rq->running_bw = 0;
>  }
>  
> +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);
> +	s64 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;
> +
> +	zerolag_time = dl_se->deadline -
> +		 div64_long((dl_se->runtime * dl_se->dl_period),
> +			dl_se->dl_runtime);
> +
> +	/*
> +	 * Using relative times instead of the absolute "0-lag time"
> +	 * allows to simplify the code
> +	 */
> +	zerolag_time -= rq_clock(rq);
> +
> +	/*
> +	 * If the "0-lag time" already passed, decrease the active
> +	 * utilization now, instead of starting a timer
> +	 */
> +	if (zerolag_time < 0) {
> +		sub_running_bw(dl_se, dl_rq);
> +		if (!dl_task(p))
> +			__dl_clear_params(p);
> +
> +		return;
> +	}
> +
> +	get_task_struct(p);
> +	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL);
> +}
> +
>  static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
>  {
>  	struct sched_dl_entity *dl_se = &p->dl;
> @@ -514,7 +556,20 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
>  	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
>  	struct rq *rq = rq_of_dl_rq(dl_rq);
>  
> -	add_running_bw(dl_se, dl_rq);
> +	if (hrtimer_is_queued(&dl_se->inactive_timer)) {
> +		hrtimer_try_to_cancel(&dl_se->inactive_timer);

Why we are OK with just trying to cancel the inactive timer?

> +		WARN_ON(dl_task_of(dl_se)->nr_cpus_allowed > 1);

What's wrong with nr_cpus_allowed > 1 tasks?

> +	} else {
> +		/*
> +		 * The "inactive timer" has been cancelled in
> +		 * select_task_rq_dl() (and the acvive utilisation has
> +		 * been decreased). So, increase the active utilisation.
> +		 * If select_task_rq_dl() could not cancel the timer,
> +		 * inactive_task_timer() will * find the task state as
> +		 * TASK_RUNNING, and will do nothing, so we are still safe.
> +		 */
> +		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))) {
> @@ -602,14 +657,8 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
>  
>  	rq = task_rq_lock(p, &rf);
>  
> -	/*
> -	 * The task might have changed its scheduling policy to something
> -	 * different than SCHED_DEADLINE (through switched_fromd_dl()).
> -	 */
> -	if (!dl_task(p)) {
> -		__dl_clear_params(p);
> +	if (!dl_task(p))
>  		goto unlock;
> -	}
>  
>  	/*
>  	 * The task might have been boosted by someone else and might be in the
> @@ -796,6 +845,44 @@ static void update_curr_dl(struct rq *rq)
>  	}
>  }
>  
> +static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
> +{
> +	struct sched_dl_entity *dl_se = container_of(timer,
> +						     struct sched_dl_entity,
> +						     inactive_timer);
> +	struct task_struct *p = dl_task_of(dl_se);
> +	struct rq_flags rf;
> +	struct rq *rq;
> +
> +	rq = task_rq_lock(p, &rf);
> +
> +	if (!dl_task(p)) {
> +		__dl_clear_params(p);
> +
> +		goto unlock;
> +	}
> +	if (p->state == TASK_RUNNING)
> +		goto unlock;
> +
> +	sched_clock_tick();
> +	update_rq_clock(rq);
> +
> +	sub_running_bw(dl_se, &rq->dl);
> +unlock:
> +	task_rq_unlock(rq, p, &rf);
> +	put_task_struct(p);
> +
> +	return HRTIMER_NORESTART;
> +}
> +
> +void init_inactive_task_timer(struct sched_dl_entity *dl_se)
> +{
> +	struct hrtimer *timer = &dl_se->inactive_timer;
> +
> +	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
> +	timer->function = inactive_task_timer;
> +}
> +
>  #ifdef CONFIG_SMP
>  
>  static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
> @@ -1000,7 +1087,7 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
>  		sub_running_bw(&p->dl, &rq->dl);
>  
>  	if (flags & DEQUEUE_SLEEP)
> -		sub_running_bw(&p->dl, &rq->dl);
> +		task_go_inactive(p);
>  }
>  
>  /*
> @@ -1074,6 +1161,14 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
>  	}
>  	rcu_read_unlock();
>  
> +	rq = task_rq(p);
> +	raw_spin_lock(&rq->lock);
> +	if (hrtimer_active(&p->dl.inactive_timer)) {
> +		sub_running_bw(&p->dl, &rq->dl);
> +		hrtimer_try_to_cancel(&p->dl.inactive_timer);

Can't we subtract twice if it happens that after we grabbed rq_lock the timer
fired, so it's now waiting for that lock and it goes ahead and sub_running_bw
again after we release the lock?

> +	}
> +	raw_spin_unlock(&rq->lock);
> +
>  out:
>  	return cpu;
>  }
> @@ -1244,6 +1339,11 @@ 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 (hrtimer_active(&p->dl.inactive_timer)) {
> +		raw_spin_lock_irq(&task_rq(p)->lock);
> +		sub_running_bw(&p->dl, dl_rq_of_se(&p->dl));

Don't we still need to wait for the 0-lag? Or maybe since the task is dying we
can release it's bw instantaneously? In this case I'd add a comment about it.

> +		raw_spin_unlock_irq(&task_rq(p)->lock);
> +	}
>  }
>  
>  static void set_curr_task_dl(struct rq *rq)
> @@ -1720,15 +1820,22 @@ void __init init_sched_dl_class(void)
>  static void switched_from_dl(struct rq *rq, struct task_struct *p)
>  {
>  	/*
> -	 * Start the deadline timer; if we switch back to dl before this we'll
> -	 * continue consuming our current CBS slice. If we stay outside of
> -	 * SCHED_DEADLINE until the deadline passes, the timer will reset the
> -	 * task.
> +	 * task_go_inactive() can start the "inactive timer" (if the 0-lag
> +	 * time is in the future). If the task switches back to dl before
> +	 * the "inactive timer" fires, it can continue to consume its current
> +	 * runtime using its current deadline. If it stays outside of
> +	 * SCHED_DEADLINE until the 0-lag time passes, inactive_task_timer()
> +	 * will reset the task parameters.
>  	 */
> -	if (!start_dl_timer(p))
> -		__dl_clear_params(p);
> +	if (task_on_rq_queued(p) && p->dl.dl_runtime)
> +		task_go_inactive(p);
>  
> -	if (task_on_rq_queued(p))
> +	/*
> +	 * We cannot use inactive_task_timer() to invoke sub_running_bw()
> +	 * at the 0-lag time, because the task could have been migrated
> +	 * while SCHED_OTHER in the meanwhile.

But, from a theoretical pow, we very much should, right?
Is this taken care of in next patch?

> +	 */
> +	if (hrtimer_is_queued(&p->dl.inactive_timer))
>  		sub_running_bw(&p->dl, &rq->dl);
>  

Thanks,

- Juri