@@ -5632,7 +5632,7 @@ 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);
}
@@ -6101,6 +6101,7 @@ 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->min_capacity = SCHED_CAPACITY_SCALE;
/*
* Make sure the first group of this domain contains the
@@ -6731,13 +6731,14 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
cpu_rq(cpu)->cpu_capacity = capacity;
sdg->sgc->capacity = capacity;
+ sdg->sgc->min_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, min_capacity;
unsigned long interval;
interval = msecs_to_jiffies(sd->balance_interval);
@@ -6750,6 +6751,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
}
capacity = 0;
+ min_capacity = ULONG_MAX;
if (child->flags & SD_OVERLAP) {
/*
@@ -6774,11 +6776,12 @@ 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;
+ min_capacity = min(capacity, min_capacity);
}
} else {
/*
@@ -6788,12 +6791,16 @@ 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;
+ min_capacity = min(sgc->min_capacity, min_capacity);
group = group->next;
} while (group != child->groups);
}
sdg->sgc->capacity = capacity;
+ sdg->sgc->min_capacity = min_capacity;
}
/*
@@ -869,7 +869,8 @@ 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 min_capacity; /* Min per-cpu capacity in group */
unsigned long next_update;
int imbalance; /* XXX unrelated to capacity but shared group state */
/*
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 min per-cpu capacity in the group a suitable group for a given task utilization can more 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@redhat.com> cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com> --- kernel/sched/core.c | 3 ++- kernel/sched/fair.c | 17 ++++++++++++----- kernel/sched/sched.h | 3 ++- 3 files changed, 16 insertions(+), 7 deletions(-) -- 1.9.1