[PATCH 3/3 v2] sched/fair: reduce cases for active balance

[Vincent Guittot]

Active balance is triggered for a number of voluntary cases like misfit
or pinned tasks cases but also after that a number of load balance
attempts failed to migrate a task. There is no need to use active load
balance when the group is overloaded because an overloaded state means
that there is at least one waiting task. Nevertheless, the waiting task
is not selected and detached until the threshold becomes higher than its
load. This threshold increases with the number of failed lb (see the
condition if ((load >> env->sd->nr_balance_failed) > env->imbalance) in
detach_tasks()) and the waiting task will end up to be selected after a
number of attempts.

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
 kernel/sched/fair.c | 45 +++++++++++++++++++++++----------------------
 1 file changed, 23 insertions(+), 22 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a3515dea1afc..00ec5b901188 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9499,13 +9499,32 @@ asym_active_balance(struct lb_env *env)
 }
 
 static inline bool
-voluntary_active_balance(struct lb_env *env)
+imbalanced_active_balance(struct lb_env *env)
+{
+	struct sched_domain *sd = env->sd;
+
+	/*
+	 * The imbalanced case includes the case of pinned tasks preventing a fair
+	 * distribution of the load on the system but also the even distribution of the
+	 * threads on a system with spare capacity
+	 */
+	if ((env->migration_type == migrate_task) &&
+	    (sd->nr_balance_failed > sd->cache_nice_tries+2))
+		return 1;
+
+	return 0;
+}
+
+static int need_active_balance(struct lb_env *env)
 {
 	struct sched_domain *sd = env->sd;
 
 	if (asym_active_balance(env))
 		return 1;
 
+	if (imbalanced_active_balance(env))
+		return 1;
+
 	/*
 	 * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task.
 	 * It's worth migrating the task if the src_cpu's capacity is reduced
@@ -9525,16 +9544,6 @@ voluntary_active_balance(struct lb_env *env)
 	return 0;
 }
 
-static int need_active_balance(struct lb_env *env)
-{
-	struct sched_domain *sd = env->sd;
-
-	if (voluntary_active_balance(env))
-		return 1;
-
-	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
-}
-
 static int active_load_balance_cpu_stop(void *data);
 
 static int should_we_balance(struct lb_env *env)
@@ -9787,21 +9796,13 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			/* We've kicked active balancing, force task migration. */
 			sd->nr_balance_failed = sd->cache_nice_tries+1;
 		}
-	} else
+	} else {
 		sd->nr_balance_failed = 0;
+	}
 
-	if (likely(!active_balance) || voluntary_active_balance(&env)) {
+	if (likely(!active_balance) || need_active_balance(&env)) {
 		/* We were unbalanced, so reset the balancing interval */
 		sd->balance_interval = sd->min_interval;
-	} else {
-		/*
-		 * If we've begun active balancing, start to back off. This
-		 * case may not be covered by the all_pinned logic if there
-		 * is only 1 task on the busy runqueue (because we don't call
-		 * detach_tasks).
-		 */
-		if (sd->balance_interval < sd->max_interval)
-			sd->balance_interval *= 2;
 	}
 
 	goto out;
-- 
2.17.1