sched/fair: Block nohz tick_stop when cfs bandwidth in use

CFS bandwidth limits and NOHZ full don't play well together.  Tasks
can easily run well past their quotas before a remote tick does
accounting.  This leads to long, multi-period stalls before such
tasks can run again. Currently, when presented with these conflicting
requirements the scheduler is favoring nohz_full and letting the tick
be stopped. However, nohz tick stopping is already best-effort, there
are a number of conditions that can prevent it, whereas cfs runtime
bandwidth is expected to be enforced.

Make the scheduler favor bandwidth over stopping the tick by setting
TICK_DEP_BIT_SCHED when the only running task is a cfs task with
runtime limit enabled. We use cfs_b->hierarchical_quota to
determine if the task requires the tick.

Add check in pick_next_task_fair() as well since that is where
we have a handle on the task that is actually going to be running.

Add check in sched_can_stop_tick() to cover some edge cases such
as nr_running going from 2->1 and the 1 remains the running task.

Reviewed-By: Ben Segall <bsegall@google.com>
Signed-off-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230712133357.381137-3-pauld@redhat.com

kernel/sched/core.c

@@ -1194,6 +1194,20 @@ static void nohz_csd_func(void *info)
 #endif /* CONFIG_NO_HZ_COMMON */
 
 #ifdef CONFIG_NO_HZ_FULL
+static inline bool __need_bw_check(struct rq *rq, struct task_struct *p)
+{
+	if (rq->nr_running != 1)
+		return false;
+
+	if (p->sched_class != &fair_sched_class)
+		return false;
+
+	if (!task_on_rq_queued(p))
+		return false;
+
+	return true;
+}
+
 bool sched_can_stop_tick(struct rq *rq)
 {
 	int fifo_nr_running;
@@ -1229,6 +1243,18 @@ bool sched_can_stop_tick(struct rq *rq)
 	if (rq->nr_running > 1)
 		return false;
 
+	/*
+	 * If there is one task and it has CFS runtime bandwidth constraints
+	 * and it's on the cpu now we don't want to stop the tick.
+	 * This check prevents clearing the bit if a newly enqueued task here is
+	 * dequeued by migrating while the constrained task continues to run.
+	 * E.g. going from 2->1 without going through pick_next_task().
+	 */
+	if (sched_feat(HZ_BW) && __need_bw_check(rq, rq->curr)) {
+		if (cfs_task_bw_constrained(rq->curr))
+			return false;
+	}
+
 	return true;
 }
 #endif /* CONFIG_NO_HZ_FULL */

kernel/sched/fair.c

@@ -6189,6 +6189,46 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 	rq_clock_stop_loop_update(rq);
 }
 
+bool cfs_task_bw_constrained(struct task_struct *p)
+{
+	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+
+	if (!cfs_bandwidth_used())
+		return false;
+
+	if (cfs_rq->runtime_enabled ||
+	    tg_cfs_bandwidth(cfs_rq->tg)->hierarchical_quota != RUNTIME_INF)
+		return true;
+
+	return false;
+}
+
+#ifdef CONFIG_NO_HZ_FULL
+/* called from pick_next_task_fair() */
+static void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p)
+{
+	int cpu = cpu_of(rq);
+
+	if (!sched_feat(HZ_BW) || !cfs_bandwidth_used())
+		return;
+
+	if (!tick_nohz_full_cpu(cpu))
+		return;
+
+	if (rq->nr_running != 1)
+		return;
+
+	/*
+	 *  We know there is only one task runnable and we've just picked it. The
+	 *  normal enqueue path will have cleared TICK_DEP_BIT_SCHED if we will
+	 *  be otherwise able to stop the tick. Just need to check if we are using
+	 *  bandwidth control.
+	 */
+	if (cfs_task_bw_constrained(p))
+		tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
+}
+#endif
+
 #else /* CONFIG_CFS_BANDWIDTH */
 
 static inline bool cfs_bandwidth_used(void)
@@ -6231,9 +6271,18 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
 static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
 static inline void update_runtime_enabled(struct rq *rq) {}
 static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
-
+#ifdef CONFIG_CGROUP_SCHED
+bool cfs_task_bw_constrained(struct task_struct *p)
+{
+	return false;
+}
+#endif
 #endif /* CONFIG_CFS_BANDWIDTH */
 
+#if !defined(CONFIG_CFS_BANDWIDTH) || !defined(CONFIG_NO_HZ_FULL)
+static inline void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p) {}
+#endif
+
 /**************************************************
  * CFS operations on tasks:
  */
@@ -8201,6 +8250,7 @@ done: __maybe_unused;
 		hrtick_start_fair(rq, p);
 
 	update_misfit_status(p, rq);
+	sched_fair_update_stop_tick(rq, p);
 
 	return p;
 

kernel/sched/features.h

@@ -101,3 +101,5 @@ SCHED_FEAT(LATENCY_WARN, false)
 
 SCHED_FEAT(ALT_PERIOD, true)
 SCHED_FEAT(BASE_SLICE, true)
+
+SCHED_FEAT(HZ_BW, true)

kernel/sched/sched.h

@@ -459,6 +459,7 @@ extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth
 extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
 extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
+extern bool cfs_task_bw_constrained(struct task_struct *p);
 
 extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 		struct sched_rt_entity *rt_se, int cpu,
@@ -494,6 +495,7 @@ static inline void set_task_rq_fair(struct sched_entity *se,
 #else /* CONFIG_CGROUP_SCHED */
 
 struct cfs_bandwidth { };
+static inline bool cfs_task_bw_constrained(struct task_struct *p) { return false; }
 
 #endif	/* CONFIG_CGROUP_SCHED */