Re: sched: Improve load balancing in the presence of idle CPUs

[Jason Low]

On Tue, 2015-04-07 at 16:28 -0700, Jason Low wrote:

> Okay, so perhaps we can also try continuing nohz load balancing if we
> find that there are overloaded CPUs in the system.

Something like the following.

---
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fdae26e..d636bf7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7620,6 +7620,16 @@ out:
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
+static inline bool nohz_kick_needed(struct rq *rq);
+
+static inline void pass_nohz_balance(struct rq *this_rq, int this_cpu)
+{
+	clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
+	nohz.next_balance = jiffies;
+	if (nohz_kick_needed(this_rq))
+		nohz_balancer_kick();
+}
+
 /*
  * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
  * rebalancing for all the cpus for whom scheduler ticks are stopped.
@@ -7631,8 +7641,10 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 	int balance_cpu;
 
 	if (idle != CPU_IDLE ||
-	    !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu)))
-		goto end;
+	    !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu))) {
+		pass_nohz_balance(this_rq, this_cpu);
+		return;
+	}
 
 	for_each_cpu(balance_cpu, nohz.idle_cpus_mask) {
 		if (balance_cpu == this_cpu || !idle_cpu(balance_cpu))
@@ -7643,8 +7655,10 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 		 * work being done for other cpus. Next load
 		 * balancing owner will pick it up.
 		 */
-		if (need_resched())
-			break;
+		if (need_resched()) {
+			pass_nohz_balance(this_rq, this_cpu);
+			return;
+		}
 
 		rq = cpu_rq(balance_cpu);
 
@@ -7664,7 +7678,6 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 			this_rq->next_balance = rq->next_balance;
 	}
 	nohz.next_balance = this_rq->next_balance;
-end:
 	clear_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu));
 }
 
@@ -7687,7 +7700,7 @@ static inline bool nohz_kick_needed(struct rq *rq)
 	int nr_busy, cpu = rq->cpu;
 	bool kick = false;
 
-	if (unlikely(rq->idle_balance))
+	if (unlikely(idle_cpu(cpu)))
 		return false;
 
        /*
@@ -7707,7 +7720,7 @@ static inline bool nohz_kick_needed(struct rq *rq)
 	if (time_before(now, nohz.next_balance))
 		return false;
 
-	if (rq->nr_running >= 2)
+	if (rq->nr_running >= 2 || rq->rd->overload)
 		return true;
 
 	rcu_read_lock();
@@ -7757,16 +7770,14 @@ static void run_rebalance_domains(struct softirq_action *h)
 	enum cpu_idle_type idle = this_rq->idle_balance ?
 						CPU_IDLE : CPU_NOT_IDLE;
 
+	rebalance_domains(this_rq, idle);
+
 	/*
 	 * If this cpu has a pending nohz_balance_kick, then do the
 	 * balancing on behalf of the other idle cpus whose ticks are
-	 * stopped. Do nohz_idle_balance *before* rebalance_domains to
-	 * give the idle cpus a chance to load balance. Else we may
-	 * load balance only within the local sched_domain hierarchy
-	 * and abort nohz_idle_balance altogether if we pull some load.
+	 * stopped.
 	 */
 	nohz_idle_balance(this_rq, idle);
-	rebalance_domains(this_rq, idle);
 }
 
 /*


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/