[PATCH 1/2] sched/rt: Fix RT utilization tracking during policy change

[PATCH 1/2] sched/rt: Fix RT utilization tracking during policy change

[Vincent Donnefort]

RT keeps track of the utilization on a per-rq basis with the structure
avg_rt. This utilization is updated during task_tick_rt(),
put_prev_task_rt() and set_next_task_rt(). However, when the current
running task changes its policy, set_next_task_rt() which would usually
take care of updating the utilization when the rq starts running RT tasks,
will not see a such change, leaving the avg_rt structure outdated. When
that very same task will be dequeued later, put_prev_task_rt() will then
update the utilization, based on a wrong last_update_time, leading a huge
spike in the RT utilization signal.

The signal would eventually recover from this issue after few ms. Even if
no RT tasks are run, avg_rt is also updated in __update_blocked_others().
But as the CPU capacity depends partly on the avg_rt, this issue has
nonetheless a significant impact on the scheduler.

Fix this issue by ensuring a load update when a running task changes
its policy to RT.

Fixes: 371bf427 ("sched/rt: Add rt_rq utilization tracking")
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a525447..5ac0f31 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2341,10 +2341,8 @@ void __init init_sched_rt_class(void)
 static void switched_to_rt(struct rq *rq, struct task_struct *p)
 {
 	/*
-	 * If we are already running, then there's nothing
-	 * that needs to be done. But if we are not running
-	 * we may need to preempt the current running task.
-	 * If that current running task is also an RT task
+	 * If we are not running we may need to preempt the current
+	 * running task. If that current running task is also an RT task
 	 * then see if we can move to another run queue.
 	 */
 	if (task_on_rq_queued(p) && rq->curr != p) {
@@ -2355,6 +2353,13 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 		if (p->prio < rq->curr->prio && cpu_online(cpu_of(rq)))
 			resched_curr(rq);
 	}
+
+	/*
+	 * If we are running, update the avg_rt tracking, as the running time
+	 * will now on be accounted into the latter.
+	 */
+	if (task_current(rq, p))
+		update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
 }
 
 /*
-- 
2.7.4

[PATCH 2/2] sched/rt: Fix Deadline utilization tracking during policy change

[Vincent Donnefort]

DL keeps track of the utilization on a per-rq basis with the structure
avg_dl. This utilization is updated during task_tick_dl(),
put_prev_task_dl() and set_next_task_dl(). However, when the current
running task changes its policy, set_next_task_dl() which would usually
take care of updating the utilization when the rq starts running DL
tasks, will not see a such change, leaving the avg_dl structure outdated.
When that very same task will be dequeued later, put_prev_task_dl() will
then update the utilization, based on a wrong last_update_time, leading a
huge spike in the DL utilization signal.

The signal would eventually recover from this issue after few ms. Even
if no DL tasks are run, avg_dl is also updated in
__update_blocked_others(). But as the CPU capacity depends partly on the
avg_dl, this issue has nonetheless a significant impact on the scheduler.

Fix this issue by ensuring a load update when a running task changes
its policy to DL.

Fixes: 3727e0e ("sched/dl: Add dl_rq utilization tracking")
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 3829c5a..915227a 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2497,6 +2497,8 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 			check_preempt_curr_dl(rq, p, 0);
 		else
 			resched_curr(rq);
+	} else {
+		update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
 	}
 }
 
-- 
2.7.4

Re: [PATCH 1/2] sched/rt: Fix RT utilization tracking during policy change

[Vincent Guittot]

On Fri, 18 Jun 2021 at 15:32, Vincent Donnefort
<vincent.donnefort@arm.com> wrote:
>
> RT keeps track of the utilization on a per-rq basis with the structure
> avg_rt. This utilization is updated during task_tick_rt(),
> put_prev_task_rt() and set_next_task_rt(). However, when the current
> running task changes its policy, set_next_task_rt() which would usually
> take care of updating the utilization when the rq starts running RT tasks,
> will not see a such change, leaving the avg_rt structure outdated. When
> that very same task will be dequeued later, put_prev_task_rt() will then
> update the utilization, based on a wrong last_update_time, leading a huge
> spike in the RT utilization signal.
>
> The signal would eventually recover from this issue after few ms. Even if
> no RT tasks are run, avg_rt is also updated in __update_blocked_others().
> But as the CPU capacity depends partly on the avg_rt, this issue has
> nonetheless a significant impact on the scheduler.
>
> Fix this issue by ensuring a load update when a running task changes
> its policy to RT.
>
> Fixes: 371bf427 ("sched/rt: Add rt_rq utilization tracking")
> Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
>
> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
> index a525447..5ac0f31 100644
> --- a/kernel/sched/rt.c
> +++ b/kernel/sched/rt.c
> @@ -2341,10 +2341,8 @@ void __init init_sched_rt_class(void)
>  static void switched_to_rt(struct rq *rq, struct task_struct *p)
>  {
>         /*
> -        * If we are already running, then there's nothing
> -        * that needs to be done. But if we are not running
> -        * we may need to preempt the current running task.
> -        * If that current running task is also an RT task
> +        * If we are not running we may need to preempt the current
> +        * running task. If that current running task is also an RT task
>          * then see if we can move to another run queue.
>          */
>         if (task_on_rq_queued(p) && rq->curr != p) {
> @@ -2355,6 +2353,13 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
>                 if (p->prio < rq->curr->prio && cpu_online(cpu_of(rq)))
>                         resched_curr(rq);
>         }
> +
> +       /*
> +        * If we are running, update the avg_rt tracking, as the running time
> +        * will now on be accounted into the latter.
> +        */
> +       if (task_current(rq, p))

task_current(rq,p) equals the "rq->curr != p" above. Having 2
different ways to get the same value in the function is a bit
confusing.

And call it once

Otherwise, the fix looks good to me

> +               update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
>  }
>
>  /*
> --
> 2.7.4
>

Re: [PATCH 2/2] sched/rt: Fix Deadline utilization tracking during policy change

[Vincent Guittot]

On Fri, 18 Jun 2021 at 15:32, Vincent Donnefort
<vincent.donnefort@arm.com> wrote:
>
> DL keeps track of the utilization on a per-rq basis with the structure
> avg_dl. This utilization is updated during task_tick_dl(),
> put_prev_task_dl() and set_next_task_dl(). However, when the current
> running task changes its policy, set_next_task_dl() which would usually
> take care of updating the utilization when the rq starts running DL
> tasks, will not see a such change, leaving the avg_dl structure outdated.
> When that very same task will be dequeued later, put_prev_task_dl() will
> then update the utilization, based on a wrong last_update_time, leading a
> huge spike in the DL utilization signal.
>
> The signal would eventually recover from this issue after few ms. Even
> if no DL tasks are run, avg_dl is also updated in
> __update_blocked_others(). But as the CPU capacity depends partly on the
> avg_dl, this issue has nonetheless a significant impact on the scheduler.
>
> Fix this issue by ensuring a load update when a running task changes
> its policy to DL.
>
> Fixes: 3727e0e ("sched/dl: Add dl_rq utilization tracking")
> Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>

Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>

>
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 3829c5a..915227a 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -2497,6 +2497,8 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
>                         check_preempt_curr_dl(rq, p, 0);
>                 else
>                         resched_curr(rq);
> +       } else {
> +               update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
>         }
>  }
>
> --
> 2.7.4
>

Re: [PATCH 1/2] sched/rt: Fix RT utilization tracking during policy change

[Vincent Donnefort]

[...]

> >         /*
> > -        * If we are already running, then there's nothing
> > -        * that needs to be done. But if we are not running
> > -        * we may need to preempt the current running task.
> > -        * If that current running task is also an RT task
> > +        * If we are not running we may need to preempt the current
> > +        * running task. If that current running task is also an RT task
> >          * then see if we can move to another run queue.
> >          */
> >         if (task_on_rq_queued(p) && rq->curr != p) {
> > @@ -2355,6 +2353,13 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
> >                 if (p->prio < rq->curr->prio && cpu_online(cpu_of(rq)))
> >                         resched_curr(rq);
> >         }
> > +
> > +       /*
> > +        * If we are running, update the avg_rt tracking, as the running time
> > +        * will now on be accounted into the latter.
> > +        */
> > +       if (task_current(rq, p))
> 
> task_current(rq,p) equals the "rq->curr != p" above. Having 2
> different ways to get the same value in the function is a bit
> confusing.
> 
> And call it once
> 
> Otherwise, the fix looks good to me

I can change it to something like:

if (task_current(rq, p)) {
    update_rt_rq_load_avg()
    return;
}

if (task_on_rq_queued(p) {
        ...
	if (p->prio ...)
		resched_curr(rq);
}

?

> 
> > +               update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
> >  }
> >
> >  /*
> > --
> > 2.7.4
> >

Re: [PATCH 1/2] sched/rt: Fix RT utilization tracking during policy change

[Vincent Guittot]

On Mon, 21 Jun 2021 at 11:03, Vincent Donnefort
<vincent.donnefort@arm.com> wrote:
>
> [...]
>
> > >         /*
> > > -        * If we are already running, then there's nothing
> > > -        * that needs to be done. But if we are not running
> > > -        * we may need to preempt the current running task.
> > > -        * If that current running task is also an RT task
> > > +        * If we are not running we may need to preempt the current
> > > +        * running task. If that current running task is also an RT task
> > >          * then see if we can move to another run queue.
> > >          */
> > >         if (task_on_rq_queued(p) && rq->curr != p) {
> > > @@ -2355,6 +2353,13 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
> > >                 if (p->prio < rq->curr->prio && cpu_online(cpu_of(rq)))
> > >                         resched_curr(rq);
> > >         }
> > > +
> > > +       /*
> > > +        * If we are running, update the avg_rt tracking, as the running time
> > > +        * will now on be accounted into the latter.
> > > +        */
> > > +       if (task_current(rq, p))
> >
> > task_current(rq,p) equals the "rq->curr != p" above. Having 2
> > different ways to get the same value in the function is a bit
> > confusing.
> >
> > And call it once
> >
> > Otherwise, the fix looks good to me
>
> I can change it to something like:
>
> if (task_current(rq, p)) {
>     update_rt_rq_load_avg()
>     return;
> }
>
> if (task_on_rq_queued(p) {
>         ...
>         if (p->prio ...)
>                 resched_curr(rq);
> }
>
> ?

yes, looks good to me


>
> >
> > > +               update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
> > >  }
> > >
> > >  /*
> > > --
> > > 2.7.4
> > >