Re: [RFCv6 PATCH 10/10] sched: rt scheduler sets capacity requirement

[Juri Lelli]

On 08/12/15 22:19, Steve Muckle wrote:
> From: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
> 
> RT tasks don't provide any running constraints like deadline ones
> except their running priority. The only current usable input to
> estimate the capacity needed by RT tasks is the rt_avg metric. We use
> it to estimate the CPU capacity needed for the RT scheduler class.
> 
> In order to monitor the evolution for RT task load, we must
> peridiocally check it during the tick.
> 
> Then, we use the estimated capacity of the last activity to estimate
> the next one which can not be that accurate but is a good starting
> point without any impact on the wake up path of RT tasks.
> 
> Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
> Signed-off-by: Steve Muckle <smuckle@xxxxxxxxxx>
> ---
>  kernel/sched/rt.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 48 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
> index 8ec86ab..9694204 100644
> --- a/kernel/sched/rt.c
> +++ b/kernel/sched/rt.c
> @@ -1426,6 +1426,41 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
>  #endif
>  }
>  
> +#ifdef CONFIG_SMP

s/SMP/CPU_FREQ_GOV_SCHED/ ?

> +static void sched_rt_update_capacity_req(struct rq *rq)
> +{
> +	u64 total, used, age_stamp, avg;
> +	s64 delta;
> +
> +	if (!sched_freq())
> +		return;
> +
> +	sched_avg_update(rq);
> +	/*
> +	 * Since we're reading these variables without serialization make sure
> +	 * we read them once before doing sanity checks on them.
> +	 */
> +	age_stamp = READ_ONCE(rq->age_stamp);
> +	avg = READ_ONCE(rq->rt_avg);
> +	delta = rq_clock(rq) - age_stamp;
> +
> +	if (unlikely(delta < 0))
> +		delta = 0;
> +
> +	total = sched_avg_period() + delta;
> +
> +	used = div_u64(avg, total);
> +	if (unlikely(used > SCHED_CAPACITY_SCALE))
> +		used = SCHED_CAPACITY_SCALE;
> +
> +	set_rt_cpu_capacity(rq->cpu, 1, (unsigned long)(used));

Minor nitpick: s/1/true/ .

Thanks,

- Juri

> +}
> +#else
> +static inline void sched_rt_update_capacity_req(struct rq *rq)
> +{ }
> +
> +#endif
> +
>  static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
>  						   struct rt_rq *rt_rq)
>  {
> @@ -1494,8 +1529,17 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
>  	if (prev->sched_class == &rt_sched_class)
>  		update_curr_rt(rq);
>  
> -	if (!rt_rq->rt_queued)
> +	if (!rt_rq->rt_queued) {
> +		/*
> +		 * The next task to be picked on this rq will have a lower
> +		 * priority than rt tasks so we can spend some time to update
> +		 * the capacity used by rt tasks based on the last activity.
> +		 * This value will be the used as an estimation of the next
> +		 * activity.
> +		 */
> +		sched_rt_update_capacity_req(rq);
>  		return NULL;
> +	}
>  
>  	put_prev_task(rq, prev);
>  
> @@ -2212,6 +2256,9 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
>  
>  	update_curr_rt(rq);
>  
> +	if (rq->rt.rt_nr_running)
> +		sched_rt_update_capacity_req(rq);
> +
>  	watchdog(rq, p);
>  
>  	/*
> -- 
> 2.4.10
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/