Re: [PATCH v3] sched/fair: Prefer fully idle cores for NOHZ balancing

Hello Vincent,

On 8/4/2026 2:12 PM, Vincent Guittot wrote:
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index 37001c63452e5..574b6b3ee922a 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -13965,28 +13965,66 @@ static inline int on_null_domain(struct rq *rq)
>>  static inline int find_new_ilb(void)
>>  {
>>         int this_cpu = smp_processor_id();
>> -       const struct cpumask *hk_mask;
>> -       int ilb_cpu;
>> +       struct cpumask *ilb_cpus;
>> +       int ilb_cpu, fallback = -1;
>> +
>> +       lockdep_assert_irqs_disabled();
>>
>> -       hk_mask = housekeeping_cpumask(HK_TYPE_KERNEL_NOISE);
>> +       /*
>> +        * Reuse the per-CPU select_rq_mask, which is protected from concurrent
>> +        * use on this CPU by having interrupts disabled.
>> +        */
>> +       ilb_cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
>> +       cpumask_and(ilb_cpus, nohz.idle_cpus_mask,
>> +                   housekeeping_cpumask(HK_TYPE_KERNEL_NOISE));
>>
>> -       for_each_cpu_and(ilb_cpu, nohz.idle_cpus_mask, hk_mask) {
>> +       for_each_cpu(ilb_cpu, ilb_cpus) {
>>                 if (ilb_cpu == this_cpu)
> 
> this_cpu is not idle so you can apply the same as below

Dumb question: nohz_balancer_kick() already does a
nohz_balance_exit_idle(rq) before trying to find the ilb_cpu via
find_new_ilb() so is it even possible for this_cpu to be set on the
nohz.idle_cpus_mask here?

Even on weakly ordered systems, reads and writes to the same location
(nohz.idle_cpus_mask) cannot get reordered right?

> 
> Other than that looks good to me
> 
>>                         continue;
>>
>> -               if (idle_cpu(ilb_cpu))
>> -                       return ilb_cpu;
>> +               if (!idle_cpu(ilb_cpu)) {
> 
> +               if (ilb_cpu == this_cpu || !idle_cpu(ilb_cpu)) {

Otherwise, this makes sense.

-- 
Thanks and Regards,
Prateek