sched: Rate-limit newidle
Rate limit newidle to migration_cost. It's a win for all
stages of sysbench oltp tests.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/sched.c b/kernel/sched.c
index ae026aa..f849212 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -589,6 +589,8 @@
u64 rt_avg;
u64 age_stamp;
+ u64 idle_stamp;
+ u64 avg_idle;
#endif
/* calc_load related fields */
@@ -2353,6 +2355,17 @@
if (rq != orig_rq)
update_rq_clock(rq);
+ if (rq->idle_stamp) {
+ u64 delta = rq->clock - rq->idle_stamp;
+ u64 max = 2*sysctl_sched_migration_cost;
+
+ if (delta > max)
+ rq->avg_idle = max;
+ else
+ update_avg(&rq->avg_idle, delta);
+ rq->idle_stamp = 0;
+ }
+
WARN_ON(p->state != TASK_WAKING);
cpu = task_cpu(p);
@@ -4389,6 +4402,11 @@
int pulled_task = 0;
unsigned long next_balance = jiffies + HZ;
+ this_rq->idle_stamp = this_rq->clock;
+
+ if (this_rq->avg_idle < sysctl_sched_migration_cost)
+ return;
+
for_each_domain(this_cpu, sd) {
unsigned long interval;
@@ -4403,8 +4421,10 @@
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
next_balance = sd->last_balance + interval;
- if (pulled_task)
+ if (pulled_task) {
+ this_rq->idle_stamp = 0;
break;
+ }
}
if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
/*