[PATCH 2/6] sched/fair: Check whether active load balance is needed in busiest group

[Tim Chen]

From: Tim C Chen <tim.c.chen@xxxxxxxxxxxxxxx>

In the busiest group, we need to consider whether active load balance
to a local group is needed even when it is not overloaded.  For example,
when the busiest group is a SMT group that's fully busy and the destination group
is a cluster group with idle CPU.  Such condition is considered by
asym_active_balance() in load balancing but not when looking for busiest
group and load imbalance.  Add this consideration in find_busiest_group()
and calculate_imbalance().

Reviewed-by: Ricardo Neri <ricardo.neri-calderon@xxxxxxxxxxxxxxx>
Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
---
 kernel/sched/fair.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 87317634fab2..bde962aa160a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9433,6 +9433,17 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 				sgs->group_capacity;
 }
 
+/* One group is SMT while the other group is not */
+static inline bool asymmetric_groups(struct sched_group *sg1,
+				    struct sched_group *sg2)
+{
+	if (!sg1 || !sg2)
+		return false;
+
+	return (sg1->flags & SD_SHARE_CPUCAPACITY) !=
+		(sg2->flags & SD_SHARE_CPUCAPACITY);
+}
+
 /**
  * update_sd_pick_busiest - return 1 on busiest group
  * @env: The load balancing environment.
@@ -10079,6 +10090,31 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 	update_idle_cpu_scan(env, sum_util);
 }
 
+static inline bool asym_active_balance_busiest(struct lb_env *env, struct sd_lb_stats *sds)
+{
+	/*
+	 * Don't balance to a group without spare capacity.
+	 *
+	 * Skip non asymmetric sched group balancing. That check
+	 * is handled by code path handling imbalanced load between
+	 * similar groups.
+	 */
+	if (env->idle == CPU_NOT_IDLE ||
+	    sds->local_stat.group_type != group_has_spare ||
+	    !asymmetric_groups(sds->local, sds->busiest))
+		return false;
+
+	/*
+	 * For SMT source group, pull when there are two or more
+	 * tasks over-utilizing a core.
+	 */
+	if (sds->busiest->flags & SD_SHARE_CPUCAPACITY &&
+	    sds->busiest_stat.sum_h_nr_running > 1)
+		return true;
+
+	return false;
+}
+
 /**
  * calculate_imbalance - Calculate the amount of imbalance present within the
  *			 groups of a given sched_domain during load balance.
@@ -10164,6 +10200,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 			return;
 		}
 
+		if (asym_active_balance_busiest(env, sds)) {
+			env->migration_type = migrate_task;
+			env->imbalance = 1;
+			return;
+		}
+
 		if (busiest->group_weight == 1 || sds->prefer_sibling) {
 			unsigned int nr_diff = busiest->sum_nr_running;
 			/*
@@ -10371,6 +10413,9 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 			 */
 			goto out_balanced;
 
+		if (asym_active_balance_busiest(env, &sds))
+			goto force_balance;
+
 		if (busiest->group_weight > 1 &&
 		    local->idle_cpus <= (busiest->idle_cpus + 1))
 			/*
-- 
2.32.0