sched: adaptive scheduler granularity
Instead of specifying the preemption granularity, specify the wanted
latency. By fixing the granlarity to a constany the wakeup latency
it a function of the number of running tasks on the rq.
Invert this relation.
sysctl_sched_granularity becomes a minimum for the dynamic granularity
computed from the new sysctl_sched_latency.
Then use this latency to do more intelligent granularity decisions: if
there are fewer tasks running then we can schedule coarser. This helps
performance while still always keeping the latency target.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/kernel/sched.c b/kernel/sched.c
index 6798328..da26f46 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4911,14 +4911,18 @@
static inline void sched_init_granularity(void)
{
unsigned int factor = 1 + ilog2(num_online_cpus());
- const unsigned long gran_limit = 100000000;
+ const unsigned long limit = 100000000;
sysctl_sched_granularity *= factor;
- if (sysctl_sched_granularity > gran_limit)
- sysctl_sched_granularity = gran_limit;
+ if (sysctl_sched_granularity > limit)
+ sysctl_sched_granularity = limit;
- sysctl_sched_runtime_limit = sysctl_sched_granularity * 5;
- sysctl_sched_wakeup_granularity = sysctl_sched_granularity / 2;
+ sysctl_sched_latency *= factor;
+ if (sysctl_sched_latency > limit)
+ sysctl_sched_latency = limit;
+
+ sysctl_sched_runtime_limit = sysctl_sched_latency * 5;
+ sysctl_sched_wakeup_granularity = sysctl_sched_latency / 2;
}
#ifdef CONFIG_SMP
