[PATCH] sched/deadline: Make find_later_rq() choose a closer cpu in topology

* [PATCH] sched/deadline: Make find_later_rq() choose a closer cpu in topology
@ 2017-03-21  1:38 Byungchul Park
  2017-03-21  6:29 ` Byungchul Park
  0 siblings, 1 reply; 3+ messages in thread
From: Byungchul Park @ 2017-03-21  1:38 UTC (permalink / raw)
  To: peterz, mingo; +Cc: linux-kernel, juri.lelli, rostedt, kernel-team

When cpudl_find() returns any among free_cpus, the cpu might not be
closer than others, considering sched domain. For example:

   this_cpu: 15
   free_cpus: 0, 1,..., 14 (== later_mask)
   best_cpu: 0

   topology:

   0 --+
       +--+
   1 --+  |
          +-- ... --+
   2 --+  |         |
       +--+         |
   3 --+            |

   ...             ...

   12 --+           |
        +--+        |
   13 --+  |        |
           +-- ... -+
   14 --+  |
        +--+
   15 --+

In this case, it would be best to select 14 since it's a free cpu and
closest to 15(this_cpu). However, currently the code select 0(best_cpu)
even though that's just any among free_cpus. Fix it.

Signed-off-by: Byungchul Park <byungchul.park@lge.com>
---
 kernel/sched/cpudeadline.c | 20 ++++++++------------
 kernel/sched/deadline.c    | 29 +++++++++++++++--------------
 2 files changed, 23 insertions(+), 26 deletions(-)

diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index fba235c..cb36727 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -119,7 +119,7 @@ static inline int cpudl_maximum(struct cpudl *cp)
  * @p: the task
  * @later_mask: a mask to fill in with the selected CPUs (or NULL)
  *
- * Returns: int - best CPU (heap maximum if suitable)
+ * Returns: (int)bool - CPUs were found
  */
 int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	       struct cpumask *later_mask)
@@ -127,21 +127,17 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	int best_cpu = -1;
 	const struct sched_dl_entity *dl_se = &p->dl;
 
-	if (later_mask &&
-	    cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) {
-		best_cpu = cpumask_any(later_mask);
-		goto out;
-	} else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
-			dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
-		best_cpu = cpudl_maximum(cp);
-		if (later_mask)
+	if (later_mask) {
+		if (!cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed) &&
+		    cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
+		    dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
+			best_cpu = cpudl_maximum(cp);
 			cpumask_set_cpu(best_cpu, later_mask);
+		}
 	}
 
-out:
 	WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
-
-	return best_cpu;
+	return best_cpu != -1;
 }
 
 /*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index a2ce590..45cc3d3 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1324,7 +1324,7 @@ static int find_later_rq(struct task_struct *task)
 	struct sched_domain *sd;
 	struct cpumask *later_mask = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
 	int this_cpu = smp_processor_id();
-	int best_cpu, cpu = task_cpu(task);
+	int cpu = task_cpu(task);
 
 	/* Make sure the mask is initialized first */
 	if (unlikely(!later_mask))
@@ -1337,17 +1337,14 @@ static int find_later_rq(struct task_struct *task)
 	 * We have to consider system topology and task affinity
 	 * first, then we can look for a suitable cpu.
 	 */
-	best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
-			task, later_mask);
-	if (best_cpu == -1)
+	if (!cpudl_find(&task_rq(task)->rd->cpudl, task, later_mask))
 		return -1;
 
 	/*
-	 * If we are here, some target has been found,
-	 * the most suitable of which is cached in best_cpu.
-	 * This is, among the runqueues where the current tasks
-	 * have later deadlines than the task's one, the rq
-	 * with the latest possible one.
+	 * If we are here, some targets have been found, including
+	 * the most suitable which is, among the runqueues where the
+	 * current tasks have later deadlines than the task's one, the
+	 * rq with the latest possible one.
 	 *
 	 * Now we check how well this matches with task's
 	 * affinity and system topology.
@@ -1367,6 +1364,7 @@ static int find_later_rq(struct task_struct *task)
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
 		if (sd->flags & SD_WAKE_AFFINE) {
+			int closest_cpu;
 
 			/*
 			 * If possible, preempting this_cpu is
@@ -1378,14 +1376,17 @@ static int find_later_rq(struct task_struct *task)
 				return this_cpu;
 			}
 
+			closest_cpu = cpumask_first_and(later_mask,
+							sched_domain_span(sd));
 			/*
-			 * Last chance: if best_cpu is valid and is
-			 * in the mask, that becomes our choice.
+			 * Last chance: if a cpu being in both later_mask
+			 * and current sd span is valid, that becomes our
+			 * choice. Of course, the latest possible cpu is
+			 * already under consideration through later_mask.
 			 */
-			if (best_cpu < nr_cpu_ids &&
-			    cpumask_test_cpu(best_cpu, sched_domain_span(sd))) {
+			if (closest_cpu < nr_cpu_ids) {
 				rcu_read_unlock();
-				return best_cpu;
+				return closest_cpu;
 			}
 		}
 	}
-- 
1.9.1

^ permalink raw reply related	[flat|nested] 3+ messages in thread