Runnable load was originally introduced to take into account the case where
blocked load biases the wake up path which may end to select an overloaded
CPU with a large number of runnable tasks instead of an underutilized
CPU with a huge blocked load.
Tha wake up path now starts looking for idle CPUs before comparing
runnable load and it's worth aligning the wake up path with the
load_balance() logic.
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/1571405198-27570-10-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
}
group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
}
-static unsigned long cpu_runnable_load(struct rq *rq);
+static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
+
+static unsigned long cpu_runnable_load(struct rq *rq)
+{
+ return cfs_rq_runnable_load_avg(&rq->cfs);
+}
/* Cached statistics for all CPUs within a node */
struct numa_stats {
/* Cached statistics for all CPUs within a node */
struct numa_stats {
-static unsigned long cpu_runnable_load(struct rq *rq)
-{
- return cfs_rq_runnable_load_avg(&rq->cfs);
-}
-
static unsigned long cpu_load(struct rq *rq)
{
return cfs_rq_load_avg(&rq->cfs);
static unsigned long cpu_load(struct rq *rq)
{
return cfs_rq_load_avg(&rq->cfs);
s64 this_eff_load, prev_eff_load;
unsigned long task_load;
s64 this_eff_load, prev_eff_load;
unsigned long task_load;
- this_eff_load = cpu_runnable_load(cpu_rq(this_cpu));
+ this_eff_load = cpu_load(cpu_rq(this_cpu));
if (sync) {
unsigned long current_load = task_h_load(current);
if (sync) {
unsigned long current_load = task_h_load(current);
this_eff_load *= 100;
this_eff_load *= capacity_of(prev_cpu);
this_eff_load *= 100;
this_eff_load *= capacity_of(prev_cpu);
- prev_eff_load = cpu_runnable_load(cpu_rq(prev_cpu));
+ prev_eff_load = cpu_load(cpu_rq(prev_cpu));
prev_eff_load -= task_load;
if (sched_feat(WA_BIAS))
prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
prev_eff_load -= task_load;
if (sched_feat(WA_BIAS))
prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
max_spare_cap = 0;
for_each_cpu(i, sched_group_span(group)) {
max_spare_cap = 0;
for_each_cpu(i, sched_group_span(group)) {
- load = cpu_runnable_load(cpu_rq(i));
+ load = cpu_load(cpu_rq(i));
runnable_load += load;
avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
runnable_load += load;
avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
- load = cpu_runnable_load(cpu_rq(i));
+ load = cpu_load(cpu_rq(i));
if (load < min_load) {
min_load = load;
least_loaded_cpu = i;
if (load < min_load) {
min_load = load;
least_loaded_cpu = i;