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.guit...@linaro.org>
---
kernel/sched/fair.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5ae5281..e09fe12b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7704,6 +7704,7 @@ 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;
@@ -7938,7 +7939,7 @@ 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) >
@@ -7959,7 +7960,7 @@ 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) <
@@ -8063,6 +8064,8 @@ 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;
@@ -8420,13 +8423,13 @@ 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;
}
@@ -8590,7 +8593,7 @@ 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
