sched/fair: Use rq->nr_running when balancing load

CFS load_balance() only takes care of CFS tasks whereas CPUs can be used by
other scheduling classes. Typically, a CFS task preempted by an RT or deadline
task will not get a chance to be pulled by another CPU because
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
situations.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: hdanton@sina.com
Cc: parth@linux.ibm.com
Cc: pauld@redhat.com
Cc: quentin.perret@arm.com
Cc: riel@surriel.com
Cc: srikar@linux.vnet.ibm.com
Cc: valentin.schneider@arm.com
Link: https://lkml.kernel.org/r/1571405198-27570-6-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 76a2aa8db4714c3dfbff6f81c6d4e90ed744fcde..4e7396c97239f2a389e72a8192996f596cb23e35 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7694,6 +7694,7 @@ 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;
@@ -7928,7 +7929,7 @@ 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) >
@@ -7949,7 +7950,7 @@ 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) <
@@ -8053,6 +8054,8 @@ 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;
 
@@ -8410,13 +8413,13 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
                }
 
                if (busiest->group_weight == 1 || sds->prefer_sibling) {
-                       unsigned int nr_diff = busiest->sum_h_nr_running;
+                       unsigned int nr_diff = busiest->sum_nr_running;
                        /*
                         * When prefer sibling, evenly spread running tasks on
                         * groups.
                         */
                        env->migration_type = migrate_task;
-                       lsub_positive(&nr_diff, local->sum_h_nr_running);
+                       lsub_positive(&nr_diff, local->sum_nr_running);
                        env->imbalance = nr_diff >> 1;
                        return;
                }
@@ -8580,7 +8583,7 @@ 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 &&