From a1f84a3ab8e002159498814eaa7e48c33752b04b Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 27 Oct 2009 15:35:38 +0100 Subject: [PATCH] sched: Check for an idle shared cache in select_task_rq_fair() 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 Cc: Arjan van de Ven Cc: Peter Zijlstra Cc: LKML-Reference: <1256654138.17752.7.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched_fair.c | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 4e777b47eed..da87385683c 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1372,11 +1372,36 @@ 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) -- 2.39.5