[PATCH v2 10/13] sched: Add per-cpu max capacity to sched_group_capacity

[Morten Rasmussen]

struct sched_group_capacity currently represents the compute capacity
sum of all cpus in the sched_group. Unless it is divided by the
group_weight to get the average capacity per cpu it hides differences in
cpu capacity for mixed capacity systems (e.g. high RT/IRQ utilization or
ARM big.LITTLE). But even the average may not be sufficient if the group
covers cpus of different capacities. Instead, by extending struct
sched_group_capacity to indicate max per-cpu capacity in the group a
suitable group for a given task utilization can easily be found such
that cpus with reduced capacity can be avoided for tasks with high
utilization (not implemented by this patch).

cc: Ingo Molnar <mingo@xxxxxxxxxx>
cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Signed-off-by: Morten Rasmussen <morten.rasmussen@xxxxxxx>
---
 kernel/sched/core.c  |  3 ++-
 kernel/sched/fair.c  | 17 ++++++++++++-----
 kernel/sched/sched.h |  3 ++-
 3 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5093765e9930..06cd7e4a81a2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5617,7 +5617,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		printk(KERN_CONT " %*pbl",
 		       cpumask_pr_args(sched_group_cpus(group)));
 		if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
-			printk(KERN_CONT " (cpu_capacity = %d)",
+			printk(KERN_CONT " (cpu_capacity = %lu)",
 				group->sgc->capacity);
 		}
 
@@ -6086,6 +6086,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		 * die on a /0 trap.
 		 */
 		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+		sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
 
 		/*
 		 * Make sure the first group of this domain contains the
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9c9b837742f6..4d10d022006d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6625,13 +6625,14 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 
 	cpu_rq(cpu)->cpu_capacity = capacity;
 	sdg->sgc->capacity = capacity;
+	sdg->sgc->max_capacity = capacity;
 }
 
 void update_group_capacity(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
-	unsigned long capacity;
+	unsigned long capacity, max_capacity;
 	unsigned long interval;
 
 	interval = msecs_to_jiffies(sd->balance_interval);
@@ -6644,6 +6645,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 	}
 
 	capacity = 0;
+	max_capacity = 0;
 
 	if (child->flags & SD_OVERLAP) {
 		/*
@@ -6668,11 +6670,12 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 			 */
 			if (unlikely(!rq->sd)) {
 				capacity += capacity_of(cpu);
-				continue;
+			} else {
+				sgc = rq->sd->groups->sgc;
+				capacity += sgc->capacity;
 			}
 
-			sgc = rq->sd->groups->sgc;
-			capacity += sgc->capacity;
+			max_capacity = max(capacity, max_capacity);
 		}
 	} else  {
 		/*
@@ -6682,12 +6685,16 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 
 		group = child->groups;
 		do {
-			capacity += group->sgc->capacity;
+			struct sched_group_capacity *sgc = group->sgc;
+
+			capacity += sgc->capacity;
+			max_capacity = max(sgc->max_capacity, max_capacity);
 			group = group->next;
 		} while (group != child->groups);
 	}
 
 	sdg->sgc->capacity = capacity;
+	sdg->sgc->max_capacity = max_capacity;
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3e9904ef224f..0cdb52168984 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -868,7 +868,8 @@ struct sched_group_capacity {
 	 * CPU capacity of this group, SCHED_CAPACITY_SCALE being max capacity
 	 * for a single CPU.
 	 */
-	unsigned int capacity;
+	unsigned long capacity;
+	unsigned long max_capacity; /* Max per-cpu capacity in group */
 	unsigned long next_update;
 	int imbalance; /* XXX unrelated to capacity but shared group state */
 	/*
-- 
1.9.1