[patch 14/15] sched: return unused runtime on voluntary sleep

[Paul Turner <pjt@google.com>]

[-- Attachment #1: sched-bwc-simple_return_quota.patch --]
[-- Type: text/plain, Size: 7424 bytes --]

When a local cfs_rq blocks we return the majority of its remaining quota to the
global bandwidth pool for use by other runqueues.

We do this only when the quota is current and there is more than 
min_cfs_rq_quota [1ms by default] of runtime remaining on the rq.

In the case where there are throttled runqueues and we have sufficient
bandwidth to meter out a slice, a second timer is kicked off to handle this
delivery, unthrottling where appropriate.

Using a 'worst case' antagonist which executes on each cpu
for 1ms before moving onto the next on a fairly large machine:

no quota generations:
 197.47 ms       /cgroup/a/cpuacct.usage
 199.46 ms       /cgroup/a/cpuacct.usage
 205.46 ms       /cgroup/a/cpuacct.usage
 198.46 ms       /cgroup/a/cpuacct.usage
 208.39 ms       /cgroup/a/cpuacct.usage
Since we are allowed to use "stale" quota our usage is effectively bounded by
the rate of input into the global pool and performance is relatively stable.

with quota generations [1s increments]:
 119.58 ms       /cgroup/a/cpuacct.usage
 119.65 ms       /cgroup/a/cpuacct.usage
 119.64 ms       /cgroup/a/cpuacct.usage
 119.63 ms       /cgroup/a/cpuacct.usage
 119.60 ms       /cgroup/a/cpuacct.usage
The large deficit here is due to quota generations (/intentionally/) preventing
us from now using previously stranded slack quota.  The cost is that this quota
becomes unavailable.

with quota generations and quota return:
 200.09 ms       /cgroup/a/cpuacct.usage
 200.09 ms       /cgroup/a/cpuacct.usage
 198.09 ms       /cgroup/a/cpuacct.usage
 200.09 ms       /cgroup/a/cpuacct.usage
 200.06 ms       /cgroup/a/cpuacct.usage
By returning unused quota we're able to both stably consume our desired quota
and prevent unintentional overages due to the abuse of slack quota from 
previous quota periods (especially on a large machine).

Signed-off-by: Paul Turner <pjt@google.com>

---
 kernel/sched.c      |   15 +++++++
 kernel/sched_fair.c |  102 ++++++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 113 insertions(+), 4 deletions(-)

Index: tip/kernel/sched.c
===================================================================
--- tip.orig/kernel/sched.c
+++ tip/kernel/sched.c
@@ -257,7 +257,7 @@ struct cfs_bandwidth {
 	s64 hierarchal_quota;
 
 	int idle;
-	struct hrtimer period_timer;
+	struct hrtimer period_timer, slack_timer;
 	struct list_head throttled_cfs_rq;
 
 	/* statistics */
@@ -414,6 +414,16 @@ static inline struct cfs_bandwidth *tg_c
 
 static inline u64 default_cfs_period(void);
 static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun);
+static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b);
+
+static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
+{
+	struct cfs_bandwidth *cfs_b =
+		container_of(timer, struct cfs_bandwidth, slack_timer);
+	do_sched_cfs_slack_timer(cfs_b);
+
+	return HRTIMER_NORESTART;
+}
 
 static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 {
@@ -446,6 +456,8 @@ static void init_cfs_bandwidth(struct cf
 	INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
 	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->period_timer.function = sched_cfs_period_timer;
+	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	cfs_b->slack_timer.function = sched_cfs_slack_timer;
 
 }
 
@@ -474,6 +486,7 @@ static void start_cfs_bandwidth(struct c
 static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 {
 	hrtimer_cancel(&cfs_b->period_timer);
+	hrtimer_cancel(&cfs_b->slack_timer);
 }
 #else
 #ifdef CONFIG_FAIR_GROUP_SCHED
Index: tip/kernel/sched_fair.c
===================================================================
--- tip.orig/kernel/sched_fair.c
+++ tip/kernel/sched_fair.c
@@ -1465,20 +1465,25 @@ static void throttle_cfs_rq(struct cfs_r
 	raw_spin_unlock(&cfs_b->lock);
 }
 
+static void return_cfs_rq_quota(struct cfs_rq *cfs_rq);
+
 /* conditionally throttle active cfs_rq's from put_prev_entity() */
 static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
-	if (!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0)
+	if (!cfs_rq->runtime_enabled)
 		return;
 
 	/*
 	 * it's possible active load balance has forced a throttled cfs_rq to
-	 * run again, we don't want to re-throttled in this case.
+	 * run again, we don't want to re-throttle in this case.
 	 */
 	if (cfs_rq_throttled(cfs_rq))
 		return;
 
-	throttle_cfs_rq(cfs_rq);
+	if (cfs_rq->runtime_remaining <= 0)
+		throttle_cfs_rq(cfs_rq);
+	else if (!cfs_rq->load.weight)
+		return_cfs_rq_quota(cfs_rq);
 }
 
 /*
@@ -1644,6 +1649,97 @@ out_unlock:
 out:
 	return idle;
 }
+
+/* a cfs_rq won't donate quota below this amount */
+static const u64 min_cfs_rq_quota = 1 * NSEC_PER_MSEC;
+/* minimum remaining period time to redistribute slack quota */
+static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC;
+/* how long we wait to gather additional slack before distributing */
+static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
+
+/* are we near the end of the current quota period? */
+static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
+{
+	struct hrtimer *refresh_timer = &cfs_b->period_timer;
+	u64 remaining;
+
+	/* if the call back is running a quota refresh is occurring */
+	if (hrtimer_callback_running(refresh_timer))
+		return 1;
+
+	/* is a quota refresh about to occur? */
+	remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer));
+	if (remaining < min_expire)
+		return 1;
+
+	return 0;
+}
+
+static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b)
+{
+	u64 min_left = cfs_bandwidth_slack_period + min_bandwidth_expiration;
+
+	/* if there's a quota refresh soon don't bother with slack */
+	if (runtime_refresh_within(cfs_b, min_left))
+		return;
+
+	start_bandwidth_timer(&cfs_b->slack_timer,
+				ns_to_ktime(cfs_bandwidth_slack_period));
+}
+
+static void return_cfs_rq_quota(struct cfs_rq *cfs_rq)
+{
+	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
+	s64 slack_runtime = cfs_rq->runtime_remaining - min_cfs_rq_quota;
+
+	if (!cfs_rq->runtime_enabled || cfs_rq->load.weight)
+		return;
+
+	if (slack_runtime <= 0)
+		return;
+
+	raw_spin_lock(&cfs_b->lock);
+	if (cfs_b->quota != RUNTIME_INF &&
+	    cfs_b->runtime_expires == cfs_rq->runtime_expires) {
+		cfs_b->runtime += slack_runtime;
+
+		if (cfs_b->runtime > sched_cfs_bandwidth_slice() &&
+		    !list_empty(&cfs_b->throttled_cfs_rq))
+			start_cfs_slack_bandwidth(cfs_b);
+	}
+	raw_spin_unlock(&cfs_b->lock);
+
+	cfs_rq->runtime_remaining -= slack_runtime;
+}
+
+static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
+{
+	u64 runtime = 0, slice = sched_cfs_bandwidth_slice();
+	u64 expires;
+
+	/* confirm we're still not at a refresh boundary */
+	if (runtime_refresh_within(cfs_b, min_bandwidth_expiration))
+		return;
+
+	raw_spin_lock(&cfs_b->lock);
+	if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) {
+		runtime = cfs_b->runtime;
+		cfs_b->runtime = 0;
+	}
+	expires = cfs_b->runtime_expires;
+	raw_spin_unlock(&cfs_b->lock);
+
+	if (!runtime)
+		return;
+
+	runtime = distribute_cfs_runtime(cfs_b, runtime, expires);
+
+	raw_spin_lock(&cfs_b->lock);
+	if (expires == cfs_b->runtime_expires)
+		cfs_b->runtime = runtime;
+	raw_spin_unlock(&cfs_b->lock);
+}
+
 #else
 static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
 		unsigned long delta_exec) {}