diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 032b548be0fc81e0a9f2778bb16c3506656966ec..f1c615ff39d63dbab5c8327cb99002f1868bdcf8 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2554,9 +2554,14 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 		/*
 		 * In case the child domain prefers tasks go to siblings
 		 * first, lower the sg capacity to one so that we'll try
-		 * and move all the excess tasks away.
+		 * and move all the excess tasks away. We lower the capacity
+		 * of a group only if the local group has the capacity to fit
+		 * these excess tasks, i.e. nr_running < group_capacity. The
+		 * extra check prevents the case where you always pull from the
+		 * heaviest group when it is already under-utilized (possible
+		 * with a large weight task outweighs the tasks on the system).
 		 */
-		if (prefer_sibling)
+		if (prefer_sibling && !local_group && sds->this_has_capacity)
 			sgs.group_capacity = min(sgs.group_capacity, 1UL);
 
 		if (local_group) {