Put upper and lower limit on cpu search of select_idle_cpu. The lower limit
is amount of cpus in a core while upper limit is twice that. This ensures
for any architecture we will usually search beyond a core. The upper limit
also helps in keeping the search cost low and constant.
Signed-off-by: subhra mazumdar <[email protected]>
---
kernel/sched/fair.c | 15 +++++++++++----
1 file changed, 11 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f35930f..b58f08f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6188,7 +6188,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
u64 avg_cost, avg_idle;
u64 time, cost;
s64 delta;
- int cpu, nr = INT_MAX;
+ int cpu, limit, floor, nr = INT_MAX;
this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
if (!this_sd)
@@ -6206,10 +6206,17 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
if (sched_feat(SIS_PROP)) {
u64 span_avg = sd->span_weight * avg_idle;
- if (span_avg > 4*avg_cost)
+ floor = cpumask_weight(topology_sibling_cpumask(target));
+ if (floor < 2)
+ floor = 2;
+ limit = floor << 1;
+ if (span_avg > floor*avg_cost) {
nr = div_u64(span_avg, avg_cost);
- else
- nr = 4;
+ if (nr > limit)
+ nr = limit;
+ } else {
+ nr = floor;
+ }
}
time = local_clock();
--
2.9.3