[PATCH v4 2/2] sched/fair: Scan cluster before scanning LLC in wake-up path

[Tim Chen]

On Thu, 2022-06-09 at 20:06 +0800, Yicong Yang wrote:
> From: Barry Song <song.bao.hua at hisilicon.com>
> 
> For platforms having clusters like Kunpeng920, CPUs within the same cluster
> have lower latency when synchronizing and accessing shared resources like
> cache. Thus, this patch tries to find an idle cpu within the cluster of the
> target CPU before scanning the whole LLC to gain lower latency.
> 
> Note neither Kunpeng920 nor x86 Jacobsville supports SMT, so this patch
> doesn't consider SMT for this moment.
> 
> Testing has been done on Kunpeng920 by pinning tasks to one numa and two
> numa. On Kunpeng920, Each numa has 8 clusters and each cluster has 4 CPUs.
> 
> With this patch, We noticed enhancement on tbench within one numa or cross
> two numa.
> 
> On numa 0:
>                             5.19-rc1                patched
> Hmean     1        350.27 (   0.00%)      406.88 *  16.16%*
> Hmean     2        702.01 (   0.00%)      808.22 *  15.13%*
> Hmean     4       1405.14 (   0.00%)     1614.34 *  14.89%*
> Hmean     8       2830.53 (   0.00%)     3169.02 *  11.96%*
> Hmean     16      5597.95 (   0.00%)     6224.20 *  11.19%*
> Hmean     32     10537.38 (   0.00%)    10524.97 *  -0.12%*
> Hmean     64      8366.04 (   0.00%)     8437.41 *   0.85%*
> Hmean     128     7060.87 (   0.00%)     7150.25 *   1.27%*
> 
> On numa 0-1:
>                             5.19-rc1                patched
> Hmean     1        346.11 (   0.00%)      408.47 *  18.02%*
> Hmean     2        693.34 (   0.00%)      805.78 *  16.22%*
> Hmean     4       1384.96 (   0.00%)     1602.49 *  15.71%*
> Hmean     8       2699.45 (   0.00%)     3069.98 *  13.73%*
> Hmean     16      5327.11 (   0.00%)     5688.19 *   6.78%*
> Hmean     32     10019.10 (   0.00%)    11862.56 *  18.40%*
> Hmean     64     13850.57 (   0.00%)    17748.54 *  28.14%*
> Hmean     128    12498.25 (   0.00%)    15541.59 *  24.35%*
> Hmean     256    11195.77 (   0.00%)    13854.06 *  23.74%*

Yicong,

Have you tried any workload where tasks don't share data
with each other but have sleep/wakeup?  That's the case
where we actually want to spread the tasks out among the clusters
to void contention for L2 cache.

Will be nice to make sure there's no regression there for
such workload.

Code itself looks good.

Reviewed-by: Tim Chen <tim.c.chen at linux.intel.com>

> 
> Tested-by: Yicong Yang <yangyicong at hisilicon.com>
> Signed-off-by: Barry Song <song.bao.hua at hisilicon.com>
> Signed-off-by: Yicong Yang <yangyicong at hisilicon.com>
> ---
>  kernel/sched/fair.c | 44 +++++++++++++++++++++++++++++++++++++++++---
>  1 file changed, 41 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 77b2048a9326..6d173e196ad3 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6327,6 +6327,40 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd
>  
>  #endif /* CONFIG_SCHED_SMT */
>  
> +#ifdef CONFIG_SCHED_CLUSTER
> +/*
> + * Scan the cluster domain for idle CPUs and clear cluster cpumask after scanning
> + */
> +static inline int scan_cluster(struct task_struct *p, struct cpumask *cpus,
> +			       int target, int *nr)
> +{
> +	struct sched_domain *sd = rcu_dereference(per_cpu(sd_cluster, target));
> +	int cpu, idle_cpu;
> +
> +	/* TODO: Support SMT system with cluster topology */
> +	if (!sched_smt_active() && sd) {
> +		for_each_cpu_and(cpu, cpus, sched_domain_span(sd)) {
> +			if (!--*nr)
> +				break;
> +
> +			idle_cpu = __select_idle_cpu(cpu, p);
> +			if ((unsigned int)idle_cpu < nr_cpumask_bits)
> +				return idle_cpu;
> +		}
> +
> +		cpumask_andnot(cpus, cpus, sched_domain_span(sd));
> +	}
> +
> +	return -1;
> +}
> +#else
> +static inline int scan_cluster(struct task_struct *p, struct cpumask *cpus,
> +			       int target, int *nr)
> +{
> +	return -1;
> +}
> +#endif
> +
>  /*
>   * 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
> @@ -6375,6 +6409,10 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
>  		time = cpu_clock(this);
>  	}
>  
> +	idle_cpu = scan_cluster(p, cpus, target, &nr);
> +	if ((unsigned int)idle_cpu < nr_cpumask_bits)
> +		return idle_cpu;
> +
>  	for_each_cpu_wrap(cpu, cpus, target + 1) {
>  		if (has_idle_core) {
>  			i = select_idle_core(p, cpu, cpus, &idle_cpu);
> @@ -6382,7 +6420,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
>  				return i;
>  
>  		} else {
> -			if (!--nr)
> +			if (--nr <= 0)
>  				return -1;
>  			idle_cpu = __select_idle_cpu(cpu, p);
>  			if ((unsigned int)idle_cpu < nr_cpumask_bits)
> @@ -6481,7 +6519,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
>  	/*
>  	 * If the previous CPU is cache affine and idle, don't be stupid:
>  	 */
> -	if (prev != target && cpus_share_cache(prev, target) &&
> +	if (prev != target && cpus_share_resources(prev, target) &&
>  	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
>  	    asym_fits_capacity(task_util, prev))
>  		return prev;
> @@ -6507,7 +6545,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
>  	p->recent_used_cpu = prev;
>  	if (recent_used_cpu != prev &&
>  	    recent_used_cpu != target &&
> -	    cpus_share_cache(recent_used_cpu, target) &&
> +	    cpus_share_resources(recent_used_cpu, target) &&
>  	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
>  	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
>  	    asym_fits_capacity(task_util, recent_used_cpu)) {