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 <subhra.mazum...@oracle.com>
---
 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 e497c05..9a6d28d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6372,7 +6372,7 @@ 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)
@@ -6389,11 +6389,18 @@ static int select_idle_cpu(struct task_struct *p, 
struct sched_domain *sd, int t
                return -1;
 
        if (sched_feat(SIS_PROP)) {
+               floor = cpumask_weight(topology_sibling_cpumask(target));
+               if (floor < 2)
+                       floor = 2;
+               limit = 2*floor;
                u64 span_avg = sd->span_weight * avg_idle;
-               if (span_avg > 4*avg_cost)
+               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

Reply via email to