sched/fair: Don't push cfs_bandwith slack timers forward

When a cfs_rq sleeps and returns its quota, we delay for 5ms before
waking any throttled cfs_rqs to coalesce with other cfs_rqs going to
sleep, as this has to be done outside of the rq lock we hold.

The current code waits for 5ms without any sleeps, instead of waiting
for 5ms from the first sleep, which can delay the unthrottle more than
we want. Switch this around so that we can't push this forward forever.

This requires an extra flag rather than using hrtimer_active, since we
need to start a new timer if the current one is in the process of
finishing.

Signed-off-by: Ben Segall <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Xunlei Pang <[email protected]>
Acked-by: Phil Auld <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: [email protected]

kernel/sched/fair.c

@@ -4729,6 +4729,11 @@ static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b)
 	if (runtime_refresh_within(cfs_b, min_left))
 		return;
 
+	/* don't push forwards an existing deferred unthrottle */
+	if (cfs_b->slack_started)
+		return;
+	cfs_b->slack_started = true;
+
 	hrtimer_start(&cfs_b->slack_timer,
 			ns_to_ktime(cfs_bandwidth_slack_period),
 			HRTIMER_MODE_REL);
@@ -4782,6 +4787,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 
 	/* confirm we're still not at a refresh boundary */
 	raw_spin_lock_irqsave(&cfs_b->lock, flags);
+	cfs_b->slack_started = false;
 	if (cfs_b->distribute_running) {
 		raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 		return;
@@ -4945,6 +4951,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
 	cfs_b->distribute_running = 0;
+	cfs_b->slack_started = false;
 }
 
 static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)

kernel/sched/sched.h

@@ -338,8 +338,10 @@ struct cfs_bandwidth {
 	u64			runtime_expires;
 	int			expires_seq;
 
-	short			idle;
-	short			period_active;
+	u8			idle;
+	u8			period_active;
+	u8			distribute_running;
+	u8			slack_started;
 	struct hrtimer		period_timer;
 	struct hrtimer		slack_timer;
 	struct list_head	throttled_cfs_rq;
@@ -348,8 +350,6 @@ struct cfs_bandwidth {
 	int			nr_periods;
 	int			nr_throttled;
 	u64			throttled_time;
-
-	bool                    distribute_running;
 #endif
 };