For asymmetric cpu capacity systems it is counter-productive for
throughput if low capacity cpus are pulling tasks from non-overloaded
cpus with higher capacity. The assumption is that higher cpu capacity is
preferred over running alone in a group with lower cpu capacity.
This patch rejects higher cpu capacity groups with one or less task per
cpu as potential busiest group which could otherwise lead to a series of
failing load-balancing attempts leading to a force-migration.
cc: Ingo Molnar <mi...@redhat.com>
cc: Peter Zijlstra <pet...@infradead.org>
Signed-off-by: Morten Rasmussen <morten.rasmus...@arm.com>
---
kernel/sched/fair.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0dd2d9c..5213bb9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6822,6 +6822,17 @@ group_is_overloaded(struct lb_env *env, struct
sg_lb_stats *sgs)
return false;
}
+/*
+ * group_smaller_cpu_capacity: Returns true if sched_group sg has smaller
+ * per-cpu capacity than sched_group ref.
+ */
+static inline bool
+group_smaller_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
+{
+ return sg->sgc->max_capacity * capacity_margin <
+ ref->sgc->max_capacity * 1024;
+}
+
static inline enum
group_type group_classify(struct sched_group *group,
struct sg_lb_stats *sgs)
@@ -6925,6 +6936,19 @@ static bool update_sd_pick_busiest(struct lb_env *env,
if (sgs->avg_load <= busiest->avg_load)
return false;
+ if (!(env->sd->flags & SD_ASYM_CPUCAPACITY))
+ goto asym_packing;
+
+ /* Candidate sg has no more than one task per cpu and has
+ * higher per-cpu capacity. Migrating tasks to less capable
+ * cpus may harm throughput. Maximize throughput,
+ * power/energy consequences are not considered.
+ */
+ if (sgs->sum_nr_running <= sgs->group_weight &&
+ group_smaller_cpu_capacity(sds->local, sg))
+ return false;
+
+asym_packing:
/* This is the busiest node in its class. */
if (!(env->sd->flags & SD_ASYM_PACKING))
return true;
--
1.9.1
