From 782f0d9f62f0e8cb135e2991fdc71356d6c15e6b Mon Sep 17 00:00:00 2001
From: Dave Kleikamp <dave.kleikamp@oracle.com>
Date: Mon, 15 May 2017 14:14:13 -0500
Subject: [PATCH] sched/rt: Minimize rq->lock contention in
do_sched_rt_period_timer()
References: git fixes (sched)
Patch-mainline: v4.13-rc1
Git-commit: c249f255aab86b9b187ba319b9d2684841ac7c8d
With CONFIG_RT_GROUP_SCHED=y, do_sched_rt_period_timer() sequentially
takes each CPU's rq->lock. On a large, busy system, the cumulative time it
takes to acquire each lock can be excessive, even triggering a watchdog
timeout.
If rt_rq->rt_time and rt_rq->rt_nr_running are both zero, this function does
nothing while holding the lock, so don't bother taking it at all.
Signed-off-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/a767637b-df85-912f-ba69-c90ee00a3fb6@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
kernel/sched/rt.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index ba240da708bb..b28045f8a3a0 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -829,6 +829,17 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
int enqueue = 0;
struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
struct rq *rq = rq_of_rt_rq(rt_rq);
+ int skip;
+
+ /*
+ * When span == cpu_online_mask, taking each rq->lock
+ * can be time-consuming. Try to avoid it when possible.
+ */
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
+ skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ if (skip)
+ continue;
raw_spin_lock(&rq->lock);
if (rt_rq->rt_time) {