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 <bsegall@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Xunlei Pang <xlpang@linux.alibaba.com>
Acked-by: Phil Auld <pauld@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/xm26a7euy6iq.fsf_-_@bsegall-linux.svl.corp.google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4c8f45ed093c9a5dfda027ff014d5981ccdfde8d..3c11dcdedcbc6121df548088f853be0c1360dd77 100644 (file)
--- a/kernel/sched/fair.c
+++ b/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)

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 607859a18b2a3f947543cce7335cae6d04f35036..b08dee29ef5e834761e0f9254c7d5e89a7888fee 100644 (file)
--- a/kernel/sched/sched.h
+++ b/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
 };