Re: [PATCH v3 9/9] sched/topology: Define and use shortcut pointers for wakeup sd_flag scan

[Valentin Schneider]

On 16/04/20 16:58, Vincent Guittot wrote:
>> ---
>> if (wake_flags & WF_TTWU) {
>>         if (want_affine) {
>>                 // We can cache that at topology buildup
>>                 sd = highest_flag_domain(cpu, SD_WAKE_AFFINE);
>>
>>                 if (cpumask_test_cpu(prev_cpu, sched_domain_span(sd) &&
>>                     cpu != prev_cpu)
>>                         new_cpu = wake_affine();
>>
>>         }
>>         // Directly go to select_idle_sibling()
>>         goto sis;
>> }
>>
>> // !want_affine logic here
>> ---
>>
>> This in turns mean we could get rid of SD_BALANCE_WAKE entirely... I'm a
>> bit more reluctant to that only because the last SD_BALANCE_WAKE setter was
>
> For now, we should probably skip the additional test above: "if
> (wake_flags & WF_TTWU) {" and keep SD_BALANCE_WAKE so we will continue
> to loop in case of !want_affine.
>
> We can imagine that we might want at the end to be a bit more smart
> for SD_BALANCE_WAKE and the slow path... like with the latency nice
> proposal and latency-nice=19 as a example
>

Good point. I'll go for the first option and see where I end up; I'd like
to cache the other domain pointers if possible, I'll do some benchmarking
and see if I can do that without another switch case.

>> removed fairly recently, see
>>   a526d466798d ("sched/topology: Remove SD_BALANCE_WAKE on asymmetric capacity systems")