From 911b2898b3c9fe0048e9485ad1629ed4fce330fd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 11 Nov 2013 18:21:56 +0100 Subject: [PATCH] sched: Optimize task_sched_runtime() Large multi-threaded apps like to hit this using do_sys_times() and then queue up on the rq->lock. Avoid when possible. Larry reported ~20% performance increase his test case. Reported-by: Larry Woodman Suggested-by: Paul Turner Signed-off-by: Peter Zijlstra Cc: KOSAKI Motohiro Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20131111172925.GG26898@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1deccd78be98..c1808606ee5f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2253,6 +2253,20 @@ unsigned long long task_sched_runtime(struct task_struct *p) struct rq *rq; u64 ns = 0; +#if defined(CONFIG_64BIT) && defined(CONFIG_SMP) + /* + * 64-bit doesn't need locks to atomically read a 64bit value. + * So we have a optimization chance when the task's delta_exec is 0. + * Reading ->on_cpu is racy, but this is ok. + * + * If we race with it leaving cpu, we'll take a lock. So we're correct. + * If we race with it entering cpu, unaccounted time is 0. This is + * indistinguishable from the read occurring a few cycles earlier. + */ + if (!p->on_cpu) + return p->se.sum_exec_runtime; +#endif + rq = task_rq_lock(p, &flags); ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); task_rq_unlock(rq, p, &flags); -- 2.30.2