Re: [PATCH v2 3/4] sched/fair: Consider SMT in ASYM_PACKING load balance

[Ricardo Neri]

On Mon, May 03, 2021 at 11:52:25AM +0200, Peter Zijlstra wrote:
> On Tue, Apr 13, 2021 at 07:04:35PM -0700, Ricardo Neri wrote:
> > +static bool cpu_group_is_smt(int cpu, struct sched_group *sg)
> > +{
> > +#ifdef CONFIG_SCHED_SMT
> > +	if (!static_branch_likely(&sched_smt_present))
> > +		return false;
> > +
> > +	if (sg->group_weight == 1)
> > +		return false;
> > +
> > +	return cpumask_equal(sched_group_span(sg), cpu_smt_mask(cpu));
> > +#else
> > +	return false;
> > +#endif
> > +}
> > +
> > +/**
> > + * asym_can_pull_tasks - Check whether the load balancing CPU can pull tasks
> > + * @dst_cpu:	CPU doing the load balancing
> > + * @sds:	Load-balancing data with statistics of the local group
> > + * @sgs:	Load-balancing statistics of the candidate busiest group
> > + * @sg:		The candidate busiet group
> > + *
> > + * Check the state of the SMT siblings of both @sds::local and @sg and decide
> > + * if @dst_cpu can pull tasks. If @dst_cpu does not have SMT siblings, it can
> > + * pull tasks if two or more of the SMT siblings of @sg are busy. If only one
> > + * CPU in @sg is busy, pull tasks only if @dst_cpu has higher priority.
> > + *
> > + * If both @dst_cpu and @sg have SMT siblings. Even the number of idle CPUs
> > + * between @sds::local and @sg. Thus, pull tasks from @sg if the difference
> > + * between the number of busy CPUs is 2 or more. If the difference is of 1,
> > + * only pull if @dst_cpu has higher priority. If @sg does not have SMT siblings
> > + * only pull tasks if all of the SMT siblings of @dst_cpu are idle and @sg
> > + * has lower priority.
> > + */
> > +static bool asym_can_pull_tasks(int dst_cpu, struct sd_lb_stats *sds,
> > +				struct sg_lb_stats *sgs, struct sched_group *sg)
> > +{
> > +#ifdef CONFIG_SCHED_SMT
> > +	int cpu, local_busy_cpus, sg_busy_cpus;
> > +	bool local_is_smt, sg_is_smt;
> > +
> > +	if (!arch_asym_check_smt_siblings())
> > +		return true;
> > +
> > +	cpu = group_first_cpu(sg);
> > +	local_is_smt = cpu_group_is_smt(dst_cpu, sds->local);
> > +	sg_is_smt = cpu_group_is_smt(cpu, sg);
> 
> Would something like this make sense?
> 
> ---
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -8533,21 +8533,6 @@ static inline void update_sg_lb_stats(st
>  				sgs->group_capacity;
>  }
>  
> -static bool cpu_group_is_smt(int cpu, struct sched_group *sg)
> -{
> -#ifdef CONFIG_SCHED_SMT
> -	if (!static_branch_likely(&sched_smt_present))
> -		return false;
> -
> -	if (sg->group_weight == 1)
> -		return false;
> -
> -	return cpumask_equal(sched_group_span(sg), cpu_smt_mask(cpu));
> -#else
> -	return false;
> -#endif
> -}
> -
>  /**
>   * asym_can_pull_tasks - Check whether the load balancing CPU can pull tasks
>   * @dst_cpu:	CPU doing the load balancing
> @@ -8578,8 +8563,8 @@ static bool asym_can_pull_tasks(int dst_
>  		return true;
>  
>  	cpu = group_first_cpu(sg);
> -	local_is_smt = cpu_group_is_smt(dst_cpu, sds->local);
> -	sg_is_smt = cpu_group_is_smt(cpu, sg);
> +	local_is_smt = sds->local->flags & SD_SHARE_CPUCAPACITY;
> +	sg_is_smt = sg->flags & SD_SHARE_CPUCAPACITY;
>  
>  	sg_busy_cpus = sgs->group_weight - sgs->idle_cpus;
>  
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -1795,6 +1795,7 @@ struct sched_group {
>  	unsigned int		group_weight;
>  	struct sched_group_capacity *sgc;
>  	int			asym_prefer_cpu;	/* CPU of highest priority in group */
> +	int			flags;
>  
>  	/*
>  	 * The CPUs this group covers.
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -916,10 +916,12 @@ build_group_from_child_sched_domain(stru
>  		return NULL;
>  
>  	sg_span = sched_group_span(sg);
> -	if (sd->child)
> +	if (sd->child) {
>  		cpumask_copy(sg_span, sched_domain_span(sd->child));
> -	else
> +		sg->flags = sd->child->flags;
> +	} else {
>  		cpumask_copy(sg_span, sched_domain_span(sd));
> +	}
>  
>  	atomic_inc(&sg->ref);
>  	return sg;
> @@ -1169,6 +1171,7 @@ static struct sched_group *get_group(int
>  	if (child) {
>  		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
>  		cpumask_copy(group_balance_mask(sg), sched_group_span(sg));
> +		sg->flags = child->flags;
>  	} else {
>  		cpumask_set_cpu(cpu, sched_group_span(sg));
>  		cpumask_set_cpu(cpu, group_balance_mask(sg));

Thank you Peter! This code worked well and it looks better than what I
proposed. May I add your Originally-by: and Signed-off-by: tags in a
patch when I post v3?

BR,
Ricardo