Re: [PATCH 3/5] sched/fair: Make select_idle_cpu() proportional to cores

[Li, Aubrey]

On 2021/1/15 18:08, Mel Gorman wrote:
> From: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
> 
> Instead of calculating how many (logical) CPUs to scan, compute how
> many cores to scan.
> 
> This changes behaviour for anything !SMT2.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
> Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
> ---
>  kernel/sched/core.c  | 18 +++++++++++++-----
>  kernel/sched/fair.c  | 12 ++++++++++--
>  kernel/sched/sched.h |  2 ++
>  3 files changed, 25 insertions(+), 7 deletions(-)
> 
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 15d2562118d1..ada8faac2e4d 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -7444,11 +7444,19 @@ int sched_cpu_activate(unsigned int cpu)
>  	balance_push_set(cpu, false);
>  
>  #ifdef CONFIG_SCHED_SMT
> -	/*
> -	 * When going up, increment the number of cores with SMT present.
> -	 */
> -	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
> -		static_branch_inc_cpuslocked(&sched_smt_present);
> +	do {
> +		int weight = cpumask_weight(cpu_smt_mask(cpu));
> +
> +		if (weight > sched_smt_weight)
> +			sched_smt_weight = weight;
> +
> +		/*
> +		 * When going up, increment the number of cores with SMT present.
> +		 */
> +		if (weight == 2)
> +			static_branch_inc_cpuslocked(&sched_smt_present);
> +
> +	} while (0);
>  #endif
>  	set_cpu_active(cpu, true);
>  
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index c8d8e185cf3b..0811e2fe4f19 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6010,6 +6010,8 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
>  DEFINE_STATIC_KEY_FALSE(sched_smt_present);
>  EXPORT_SYMBOL_GPL(sched_smt_present);
>  
> +int sched_smt_weight __read_mostly = 1;
> +
>  static inline void set_idle_cores(int cpu, int val)
>  {
>  	struct sched_domain_shared *sds;
> @@ -6124,6 +6126,8 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
>  
>  #else /* CONFIG_SCHED_SMT */
>  
> +#define sched_smt_weight	1
> +
>  static inline int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
>  {
>  	return -1;
> @@ -6136,6 +6140,8 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd
>  
>  #endif /* CONFIG_SCHED_SMT */
>  
> +#define sis_min_cores		2
> +
>  /*
>   * Scan the LLC domain for idle CPUs; this is dynamically regulated by
>   * comparing the average scan cost (tracked in sd->avg_scan_cost) against the
> @@ -6166,10 +6172,12 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
>  		avg_cost = this_sd->avg_scan_cost + 1;
>  
>  		span_avg = sd->span_weight * avg_idle;
> -		if (span_avg > 4*avg_cost)
> +		if (span_avg > sis_min_cores*avg_cost)
>  			nr = div_u64(span_avg, avg_cost);
>  		else
> -			nr = 4;
> +			nr = sis_min_cores;
> +
> +		nr *= sched_smt_weight;

Is it better to put this into an inline wrapper to hide sched_smt_weight if !CONFIG_SCHED_SMT?

Thanks,
-Aubrey