Re: [PATCH 1/2] sched/fair: account update_blocked_averages in newidle_balance cost

[Peter Zijlstra]

On Mon, Oct 04, 2021 at 07:14:50PM +0200, Vincent Guittot wrote:
> The time spent to update the blocked load can be significant depending of
> the complexity fo the cgroup hierarchy. Take this time into account when
> deciding to stop newidle_balance() because it exceeds the expected idle
> time.
> 
> Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
> ---
>  kernel/sched/fair.c | 7 +++++--
>  1 file changed, 5 insertions(+), 2 deletions(-)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 8943dbb94365..1f78b2e3b71c 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -10810,7 +10810,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
>  	int this_cpu = this_rq->cpu;
>  	struct sched_domain *sd;
>  	int pulled_task = 0;
> -	u64 curr_cost = 0;
> +	u64 t0, domain_cost, curr_cost = 0;
>  
>  	update_misfit_status(NULL, this_rq);
>  
> @@ -10855,11 +10855,14 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
>  
>  	raw_spin_rq_unlock(this_rq);
>  
> +	t0 = sched_clock_cpu(this_cpu);
>  	update_blocked_averages(this_cpu);
> +	domain_cost = sched_clock_cpu(this_cpu) - t0;
> +	curr_cost += domain_cost;
> +
>  	rcu_read_lock();
>  	for_each_domain(this_cpu, sd) {
>  		int continue_balancing = 1;
> -		u64 t0, domain_cost;
>  
>  		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
>  			update_next_balance(sd, &next_balance);

Does this make sense? It avoids a bunch of clock calls (and thereby
accounts more actual time).

Also, perhaps we should some asymmetric IIR instead of a strict MAX
filter for max_newidle_lb_cost.

---
Index: linux-2.6/kernel/sched/fair.c
===================================================================
--- linux-2.6.orig/kernel/sched/fair.c
+++ linux-2.6/kernel/sched/fair.c
@@ -10759,9 +10759,9 @@ static int newidle_balance(struct rq *th
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;
+	u64 t0, t1, curr_cost = 0;
 	struct sched_domain *sd;
 	int pulled_task = 0;
-	u64 t0, domain_cost, curr_cost = 0;
 
 	update_misfit_status(NULL, this_rq);
 
@@ -10808,8 +10808,9 @@ static int newidle_balance(struct rq *th
 
 	t0 = sched_clock_cpu(this_cpu);
 	update_blocked_averages(this_cpu);
-	domain_cost = sched_clock_cpu(this_cpu) - t0;
-	curr_cost += domain_cost;
+	t1 = sched_clock_cpu(this_cpu);
+	curr_cost += t1 - t0;
+	t0 = t1;
 
 	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
@@ -10821,17 +10822,19 @@ static int newidle_balance(struct rq *th
 		}
 
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
-			t0 = sched_clock_cpu(this_cpu);
+			u64 domain_cost;
 
 			pulled_task = load_balance(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
 						   &continue_balancing);
 
-			domain_cost = sched_clock_cpu(this_cpu) - t0;
+			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;
 
 			curr_cost += domain_cost;
+			t0 = t1;
 		}
 
 		update_next_balance(sd, &next_balance);