Re: [PATCH v3 2/3] sched/topology: Remove SD_BALANCE_WAKE on asymmetric capacity systems

[Valentin Schneider]

On 29/01/2020 16:27, Dietmar Eggemann wrote:
> On 26/01/2020 21:09, Valentin Schneider wrote:
>> From: Morten Rasmussen <morten.rasmussen@xxxxxxx>
> 
> [...]
> 
>> @@ -1374,18 +1374,9 @@ sd_init(struct sched_domain_topology_level *tl,
>>  	 * Convert topological properties into behaviour.
>>  	 */
>>  
>> -	if (sd->flags & SD_ASYM_CPUCAPACITY) {
>> -		struct sched_domain *t = sd;
>> -
>> -		/*
>> -		 * Don't attempt to spread across CPUs of different capacities.
>> -		 */
>> -		if (sd->child)
>> -			sd->child->flags &= ~SD_PREFER_SIBLING;
>> -
>> -		for_each_lower_domain(t)
> 
> It seems that with this goes the last use of for_each_lower_domain().
> 
> [...]
> 

Indeed, good catch. I see that was used at some point before the
select_idle_sibling() rework:

  10e2f1acd010 ("sched/core: Rewrite and improve select_idle_siblings()")

and our asymmetry policy saved it. I'll remove it in v4.