Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Vincent Guittot <vincent.guittot@linaro.org>
To:     linux-kernel@vger.kernel.org, mingo@redhat.com,
        peterz@infradead.org
Cc:     pauld@redhat.com, valentin.schneider@arm.com,
        srikar@linux.vnet.ibm.com, quentin.perret@arm.com,
        dietmar.eggemann@arm.com, Morten.Rasmussen@arm.com,
        hdanton@sina.com, Vincent Guittot <vincent.guittot@linaro.org>
Subject: [PATCH v3 05/10] sched/fair: use rq->nr_running when balancing load
Date:   Thu, 19 Sep 2019 09:33:36 +0200
Message-Id: <1568878421-12301-6-git-send-email-vincent.guittot@linaro.org>
In-Reply-To: <1568878421-12301-1-git-send-email-vincent.guittot@linaro.org>
References: <1568878421-12301-1-git-send-email-vincent.guittot@linaro.org>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

cfs load_balance only takes care of CFS tasks whereas CPUs can be used by
other scheduling class. Typically, a CFS task preempted by a RT or deadline
task will not get a chance to be pulled on another CPU because the
load_balance doesn't take into account tasks from other classes.
Add sum of nr_running in the statistics and use it to detect such
situation.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 kernel/sched/fair.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d33379c..7e74836 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7716,6 +7716,7 @@ struct sg_lb_stats {
 	unsigned long group_load; /* Total load over the CPUs of the group */
 	unsigned long group_capacity;
 	unsigned long group_util; /* Total utilization of the group */
+	unsigned int sum_nr_running; /* Nr of tasks running in the group */
 	unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */
 	unsigned int idle_cpus;
 	unsigned int group_weight;
@@ -7949,7 +7950,7 @@ static inline int sg_imbalanced(struct sched_group *group)
 static inline bool
 group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
 {
-	if (sgs->sum_h_nr_running < sgs->group_weight)
+	if (sgs->sum_nr_running < sgs->group_weight)
 		return true;
 
 	if ((sgs->group_capacity * 100) >
@@ -7970,7 +7971,7 @@ group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
 static inline bool
 group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
 {
-	if (sgs->sum_h_nr_running <= sgs->group_weight)
+	if (sgs->sum_nr_running <= sgs->group_weight)
 		return false;
 
 	if ((sgs->group_capacity * 100) <
@@ -8074,6 +8075,8 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->sum_h_nr_running += rq->cfs.h_nr_running;
 
 		nr_running = rq->nr_running;
+		sgs->sum_nr_running += nr_running;
+
 		if (nr_running > 1)
 			*sg_status |= SG_OVERLOAD;
 
@@ -8423,7 +8426,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 			 * groups.
 			 */
 			env->balance_type = migrate_task;
-			env->imbalance = (busiest->sum_h_nr_running - local->sum_h_nr_running) >> 1;
+			env->imbalance = (busiest->sum_nr_running - local->sum_nr_running) >> 1;
 			return;
 		}
 
@@ -8585,7 +8588,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 
 	/* Try to move all excess tasks to child's sibling domain */
 	if (sds.prefer_sibling && local->group_type == group_has_spare &&
-	    busiest->sum_h_nr_running > local->sum_h_nr_running + 1)
+	    busiest->sum_nr_running > local->sum_nr_running + 1)
 		goto force_balance;
 
 	if (busiest->group_type != group_overloaded &&
-- 
2.7.4