summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorMike Galbraith <efault@gmx.de>2009-10-27 15:35:38 +0100
committerGreg Kroah-Hartman <gregkh@suse.de>2009-12-18 14:03:12 -0800
commitc2f1953231c6e99777633761c3bc0d2ca7ead20a (patch)
treeff609b6d242a97f0262ddbc9cd7baec077742016 /kernel
parent7f112f35f0da073a10d4d3bfdfcef2955555e4f7 (diff)
sched: Check for an idle shared cache in select_task_rq_fair()
commit a1f84a3ab8e002159498814eaa7e48c33752b04b upstream. When waking affine, check for an idle shared cache, and if found, wake to that CPU/sibling instead of the waker's CPU. This improves pgsql+oltp ramp up by roughly 8%. Possibly more for other loads, depending on overlap. The trade-off is a roughly 1% peak downturn if tasks are truly synchronous. Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> LKML-Reference: <1256654138.17752.7.camel@marge.simson.net> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched_fair.c33
1 files changed, 29 insertions, 4 deletions
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 37087a7fac22..32f06ed871b4 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1398,11 +1398,36 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
want_sd = 0;
}
- if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
- cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+ if (want_affine && (tmp->flags & SD_WAKE_AFFINE)) {
+ int candidate = -1, i;
- affine_sd = tmp;
- want_affine = 0;
+ if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
+ candidate = cpu;
+
+ /*
+ * Check for an idle shared cache.
+ */
+ if (tmp->flags & SD_PREFER_SIBLING) {
+ if (candidate == cpu) {
+ if (!cpu_rq(prev_cpu)->cfs.nr_running)
+ candidate = prev_cpu;
+ }
+
+ if (candidate == -1 || candidate == cpu) {
+ for_each_cpu(i, sched_domain_span(tmp)) {
+ if (!cpu_rq(i)->cfs.nr_running) {
+ candidate = i;
+ break;
+ }
+ }
+ }
+ }
+
+ if (candidate >= 0) {
+ affine_sd = tmp;
+ want_affine = 0;
+ cpu = candidate;
+ }
}
if (!want_sd && !want_affine)