In
commmit 3b1baa6496e6 ("sched/fair: Add 'group_misfit_task' load-balance type")
we set rq->misfit_task_load whenever the current running task has a
utilization greater than 80% of rq->cpu_capacity. A non-zero value in
this field enables misfit load balancing.
However, if the task being looked at is already running on a CPU of
highest capacity, there's nothing more we can do for it. We can
currently spot this in update_sd_pick_busiest(), which prevents us
from selecting a sched_group of group_type == group_misfit_task as the
busiest group, but we don't do any of that in nohz_balancer_kick().
This means that we could repeatedly kick nohz CPUs when there's no
improvements in terms of load balance to be done.
Introduce a check_misfit_status() helper that returns true iff there
is a CPU in the system that could give more CPU capacity to a rq's
misfit task - IOW, there exists a CPU of higher capacity_orig or the
rq's CPU is severely pressured by rt/IRQ.
Signed-off-by: Valentin Schneider <[email protected]>
---
kernel/sched/fair.c | 22 +++++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7658f9d76a9a..291dfdb0183f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8012,6 +8012,18 @@ check_cpu_capacity(struct rq *rq, struct sched_domain
*sd)
(rq->cpu_capacity_orig * 100));
}
+/*
+ * Check whether a rq has a misfit task and if it looks like we can actually
+ * help that task: we can migrate the task to a CPU of higher capacity, or
+ * the task's current CPU is heavily pressured.
+ */
+static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
+{
+ return rq->misfit_task_load &&
+ (rq->cpu_capacity_orig < rq->rd->max_cpu_capacity ||
+ check_cpu_capacity(rq, sd));
+}
+
/*
* Group imbalance indicates (and tries to solve) the problem where balancing
* groups is inadequate due to ->cpus_allowed constraints.
@@ -9527,7 +9539,7 @@ static void nohz_balancer_kick(struct rq *rq)
if (time_before(now, nohz.next_balance))
goto out;
- if (rq->nr_running >= 2 || rq->misfit_task_load) {
+ if (rq->nr_running >= 2) {
flags = NOHZ_KICK_MASK;
goto out;
}
@@ -9561,6 +9573,14 @@ static void nohz_balancer_kick(struct rq *rq)
}
}
+ sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, cpu));
+ if (sd) {
+ if (check_misfit_status(rq, sd)) {
+ flags = NOHZ_KICK_MASK;
+ goto unlock;
+ }
+ }
+
sd = rcu_dereference(per_cpu(sd_asym_packing, cpu));
if (sd) {
for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask)
{
--
2.20.1
