diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 56362ac036b2..2dc28766cf9a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5650,6 +5650,7 @@ struct lb_env {
 	int			new_dst_cpu;
 	enum cpu_idle_type	idle;
 	long			imbalance;
+	unsigned int		src_grp_nr_running;
 	/* The set of CPUs under consideration for load-balancing */
 	struct cpumask		*cpus;
 
@@ -6612,6 +6613,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 	if (env->sd->flags & SD_NUMA)
 		env->fbq_type = fbq_classify_group(&sds->busiest_stat);
 
+	env->src_grp_nr_running = sds->busiest_stat.sum_nr_running;
+
 	if (!env->sd->parent) {
 		/* update overload indicator if we are at root domain */
 		if (env->dst_rq->rd->overload != overload)
@@ -7240,7 +7243,8 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		 * excessive cache_hot migrations and active balances.
 		 */
 		if (idle != CPU_NEWLY_IDLE)
-			sd->nr_balance_failed++;
+			if (env.src_grp_nr_running > 1)
+				sd->nr_balance_failed++;
 
 		if (need_active_balance(&env)) {
 			raw_spin_lock_irqsave(&busiest->lock, flags);