Re: [PATCH v6 2/2] sched/rt: Add support for SD_PREFER_SIBLING on find_lowest_rq()

2017-08-10 Thread Byungchul Park
On Mon, Aug 07, 2017 at 12:50:34PM +0900, Byungchul Park 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.

I applied your suggestion. Could you let me know your opinions about
this?

> 
> Signed-off-by: Byungchul Park 
> ---
>  kernel/sched/rt.c | 47 ---
>  1 file changed, 44 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
> index 979b734..50639e5 100644
> --- a/kernel/sched/rt.c
> +++ b/kernel/sched/rt.c
> @@ -1618,12 +1618,35 @@ static struct task_struct 
> *pick_highest_pushable_task(struct rq *rq, int cpu)
>  
>  static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
>  
> +/*
> + * 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_lowest_rq(struct task_struct *task)
>  {
> - struct sched_domain *sd;
> + struct sched_domain *sd, *prefer = NULL;
>   struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
>   int this_cpu = smp_processor_id();
>   int cpu  = task_cpu(task);
> + int fallback_cpu = -1;
>  
>   /* Make sure the mask is initialized first */
>   if (unlikely(!lowest_mask))
> @@ -1668,9 +1691,20 @@ static int find_lowest_rq(struct task_struct *task)
>   return this_cpu;
>   }
>  
> - best_cpu = cpumask_first_and(lowest_mask,
> -  sched_domain_span(sd));
> + best_cpu = find_cpu(lowest_mask, sd, prefer);
> +
>   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;
> + if (fallback_cpu == -1)
> + fallback_cpu = best_cpu;
> + continue;
> + }
>   rcu_read_unlock();
>   return best_cpu;
>   }
> @@ -1679,6 +1713,13 @@ static int find_lowest_rq(struct task_struct *task)
>   rcu_read_unlock();
>  
>   /*
> +  * If fallback_cpu is valid, all our quesses failed *except* for
> +  * SD_PREFER_SIBLING domain. Now, we can return the fallback cpu.
> +  */
> + if (fallback_cpu != -1)
> + return fallback_cpu;
> +
> + /*
>* And finally, if there were no matches within the domains
>* just give the caller *something* to work with from the compatible
>* locations.
> -- 
> 1.9.1


[PATCH v6 2/2] sched/rt: Add support for SD_PREFER_SIBLING on find_lowest_rq()

2017-08-06 Thread Byungchul Park
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 
---
 kernel/sched/rt.c | 47 ---
 1 file changed, 44 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 979b734..50639e5 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1618,12 +1618,35 @@ static struct task_struct 
*pick_highest_pushable_task(struct rq *rq, int cpu)
 
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 
+/*
+ * 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_lowest_rq(struct task_struct *task)
 {
-   struct sched_domain *sd;
+   struct sched_domain *sd, *prefer = NULL;
struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
int this_cpu = smp_processor_id();
int cpu  = task_cpu(task);
+   int fallback_cpu = -1;
 
/* Make sure the mask is initialized first */
if (unlikely(!lowest_mask))
@@ -1668,9 +1691,20 @@ static int find_lowest_rq(struct task_struct *task)
return this_cpu;
}
 
-   best_cpu = cpumask_first_and(lowest_mask,
-sched_domain_span(sd));
+   best_cpu = find_cpu(lowest_mask, sd, prefer);
+
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;
+   if (fallback_cpu == -1)
+   fallback_cpu = best_cpu;
+   continue;
+   }
rcu_read_unlock();
return best_cpu;
}
@@ -1679,6 +1713,13 @@ static int find_lowest_rq(struct task_struct *task)
rcu_read_unlock();
 
/*
+* If fallback_cpu is valid, all our quesses failed *except* for
+* SD_PREFER_SIBLING domain. Now, we can return the fallback cpu.
+*/
+   if (fallback_cpu != -1)
+   return fallback_cpu;
+
+   /*
 * And finally, if there were no matches within the domains
 * just give the caller *something* to work with from the compatible
 * locations.
-- 
1.9.1