Re: [PATCH v2 3/4] sched/fair: Wait before decaying max_newidle_lb_cost

[Peter Zijlstra]

On Fri, Oct 15, 2021 at 02:46:53PM +0200, Vincent Guittot wrote:
> Decay max_newidle_lb_cost only when it has not been updated for a while
> and ensure to not decay a recently changed value.

I was more thinking something long these lines; ofcourse, no idea how
well it actually behaves.

Index: linux-2.6/include/linux/sched/topology.h
===================================================================
--- linux-2.6.orig/include/linux/sched/topology.h
+++ linux-2.6/include/linux/sched/topology.h
@@ -98,7 +98,6 @@ struct sched_domain {
 
 	/* idle_balance() stats */
 	u64 max_newidle_lb_cost;
-	unsigned long next_decay_max_lb_cost;
 
 	u64 avg_scan_cost;		/* select_idle_sibling */
 
Index: linux-2.6/kernel/sched/fair.c
===================================================================
--- linux-2.6.orig/kernel/sched/fair.c
+++ linux-2.6/kernel/sched/fair.c
@@ -10241,6 +10241,17 @@ void update_max_interval(void)
 }
 
 /*
+ * Asymmetric IIR filter, 1/4th down, 3/4th up.
+ */
+static void update_newidle_cost(u64 *cost, u64 new)
+{
+	s64 diff = new - *cost;
+	if (diff > 0)
+		diff *= 3;
+	*cost += diff / 4;
+}
+
+/*
  * It checks each scheduling domain to see if it is due to be balanced,
  * and initiates a balancing operation if so.
  *
@@ -10256,33 +10267,18 @@ static void rebalance_domains(struct rq
 	/* Earliest time when we have to do rebalance again */
 	unsigned long next_balance = jiffies + 60*HZ;
 	int update_next_balance = 0;
-	int need_serialize, need_decay = 0;
-	u64 max_cost = 0;
+	int need_serialize;
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		/*
-		 * Decay the newidle max times here because this is a regular
-		 * visit to all the domains. Decay ~1% per second.
-		 */
-		if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
-			sd->max_newidle_lb_cost =
-				(sd->max_newidle_lb_cost * 253) / 256;
-			sd->next_decay_max_lb_cost = jiffies + HZ;
-			need_decay = 1;
-		}
-		max_cost += sd->max_newidle_lb_cost;
 
 		/*
 		 * Stop the load balance at this level. There is another
 		 * CPU in our sched group which is doing load balancing more
 		 * actively.
 		 */
-		if (!continue_balancing) {
-			if (need_decay)
-				continue;
+		if (!continue_balancing)
 			break;
-		}
 
 		interval = get_sd_balance_interval(sd, busy);
 
@@ -10313,14 +10309,7 @@ out:
 			update_next_balance = 1;
 		}
 	}
-	if (need_decay) {
-		/*
-		 * Ensure the rq-wide value also decays but keep it at a
-		 * reasonable floor to avoid funnies with rq->avg_idle.
-		 */
-		rq->max_idle_balance_cost =
-			max((u64)sysctl_sched_migration_cost, max_cost);
-	}
+
 	rcu_read_unlock();
 
 	/*
@@ -10909,8 +10898,7 @@ static int newidle_balance(struct rq *th
 
 			t1 = sched_clock_cpu(this_cpu);
 			domain_cost = t1 - t0;
-			if (domain_cost > sd->max_newidle_lb_cost)
-				sd->max_newidle_lb_cost = domain_cost;
+			update_newidle_cost(&sd->max_newidle_lb_cost, domain_cost);
 
 			curr_cost += domain_cost;
 			t0 = t1;
@@ -10930,8 +10918,7 @@ static int newidle_balance(struct rq *th
 
 	raw_spin_rq_lock(this_rq);
 
-	if (curr_cost > this_rq->max_idle_balance_cost)
-		this_rq->max_idle_balance_cost = curr_cost;
+	update_newidle_cost(&this_rq->max_idle_balance_cost, curr_cost);
 
 	/*
 	 * While browsing the domains, we released the rq lock, a task could