Re: [PATCH v6 1/2] sched/deadline: Add support for SD_PREFER_SIBLING on find_later_rq()

[Steven Rostedt]

On Mon,  7 Aug 2017 12:50:33 +0900
Byungchul Park <byungchul.park@xxxxxxx> wrote:

> It would be better to avoid pushing tasks to other cpu within
> a SD_PREFER_SIBLING domain, instead, get more chances to check other
> siblings.
> 
> Signed-off-by: Byungchul Park <byungchul.park@xxxxxxx>
> ---
>  kernel/sched/deadline.c | 46 +++++++++++++++++++++++++++++++++++++++++++---
>  1 file changed, 43 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 0223694..2fd1591 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -1319,12 +1319,35 @@ static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu
>  
>  static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
>  
> +/*
> + * Find the first cpu in: mask & sd & ~prefer
> + */
> +static int find_cpu(const struct cpumask *mask,
> +		    const struct sched_domain *sd,
> +		    const struct sched_domain *prefer)
> +{
> +	const struct cpumask *sds = sched_domain_span(sd);
> +	const struct cpumask *ps  = prefer ? sched_domain_span(prefer) : NULL;
> +	int cpu = -1;
> +
> +	while ((cpu = cpumask_next(cpu, mask)) < nr_cpu_ids) {
> +		if (!cpumask_test_cpu(cpu, sds))
> +			continue;
> +		if (ps && cpumask_test_cpu(cpu, ps))
> +			continue;
> +		break;
> +	}
> +
> +	return cpu;
> +}
> +
>  static int find_later_rq(struct task_struct *task)
>  {
> -	struct sched_domain *sd;
> +	struct sched_domain *sd, *prefer = NULL;
>  	struct cpumask *later_mask = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
>  	int this_cpu = smp_processor_id();
>  	int cpu = task_cpu(task);
> +	int fallback_cpu = -1;
>  
>  	/* Make sure the mask is initialized first */
>  	if (unlikely(!later_mask))
> @@ -1376,8 +1399,7 @@ static int find_later_rq(struct task_struct *task)
>  				return this_cpu;
>  			}
>  
> -			best_cpu = cpumask_first_and(later_mask,
> -							sched_domain_span(sd));
> +			best_cpu = find_cpu(later_mask, sd, prefer);
>  			/*
>  			 * Last chance: if a cpu being in both later_mask
>  			 * and current sd span is valid, that becomes our
> @@ -1385,6 +1407,17 @@ static int find_later_rq(struct task_struct *task)
>  			 * already under consideration through later_mask.
>  			 */
>  			if (best_cpu < nr_cpu_ids) {
> +				/*
> +				 * If current domain is SD_PREFER_SIBLING
> +				 * flaged, we have to get more chances to
> +				 * check other siblings.
> +				 */
> +				if (sd->flags & SD_PREFER_SIBLING) {
> +					prefer = sd;

Is this how the SD_PREFER_SIBLING works? According to this, the
preferred sd is the next sd in for_each_domain(). Not to mention, the
prefer variable stays set if the next domain has no available CPUs. Is
that what we want?

-- Steve


> +					if (fallback_cpu == -1)
> +						fallback_cpu = best_cpu;
> +					continue;
> +				}
>  				rcu_read_unlock();
>  				return best_cpu;
>  			}
> @@ -1393,6 +1426,13 @@ static int find_later_rq(struct task_struct *task)
>  	rcu_read_unlock();
>  
>  	/*
> +	 * If fallback_cpu is valid, all our guesses failed *except* for
> +	 * SD_PREFER_SIBLING domain. Now, we can return the fallback cpu.
> +	 */
> +	if (fallback_cpu != -1)
> +		return fallback_cpu;
> +
> +	/*
>  	 * At this point, all our guesses failed, we just return
>  	 * 'something', and let the caller sort the things out.
>  	 */