Re: [PATCH] sched/fair: Optimize select_idle_cpu

["chengjian (D)" <cj.chengjian@huawei.com>]

On 2019/12/12 23:24, Peter Zijlstra wrote:
> On Thu, Dec 12, 2019 at 10:41:02PM +0800, Cheng Jian wrote:
>
>> Fixes: 1ad3aaf3fcd2 ("sched/core: Implement new approach to scale select_idle_cpu()")
> The 'funny' thing is that select_idle_core() actually does the right
> thing.
>
> Copying that should work:
>
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 08a233e97a01..416d574dcebf 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -5828,6 +5837,7 @@ static inline int select_idle_smt(struct task_struct *p, int target)
>    */
>   static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
>   {
> +	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
>   	struct sched_domain *this_sd;
>   	u64 avg_cost, avg_idle;
>   	u64 time, cost;
> @@ -5859,11 +5869,11 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
>   
>   	time = cpu_clock(this);
>   
> -	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
> +	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
> +
> +	for_each_cpu_wrap(cpu, cpus, target) {
>   		if (!--nr)
>   			return si_cpu;
> -		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
> -			continue;
>   		if (available_idle_cpu(cpu))
>   			break;
>   		if (si_cpu == -1 && sched_idle_cpu(cpu))
>
> .


in select_idle_smt()

/*
  * Scan the local SMT mask for idle CPUs.
  */
static int select_idle_smt(struct task_struct *p, int target)
{
     int cpu, si_cpu = -1;

     if (!static_branch_likely(&sched_smt_present))
         return -1;

     for_each_cpu(cpu, cpu_smt_mask(target)) {
         if (!cpumask_test_cpu(cpu, p->cpus_ptr))
             continue;
         if (available_idle_cpu(cpu))
             return cpu;
         if (si_cpu == -1 && sched_idle_cpu(cpu))
             si_cpu = cpu;
     }

     return si_cpu;
}


Why don't we do the same thing in this function,

although cpu_smt_present () often has few CPUs.

it is better to determine the 'p->cpus_ptr' first.