Commit 0c3a4f98 authored by Barry Song's avatar Barry Song Committed by Jie Liu
Browse files

sched/fair: Scan cluster before scanning LLC in wake-up path 

kunpeng inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I5W44S
CVE: NA

Reference: https://lore.kernel.org/lkml/20220915073423.25535-1-yangyicong@huawei.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.

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:
                             6.0-rc1                patched
Hmean     1        351.20 (   0.00%)      396.45 *  12.88%*
Hmean     2        700.43 (   0.00%)      793.76 *  13.32%*
Hmean     4       1404.42 (   0.00%)     1583.62 *  12.76%*
Hmean     8       2833.31 (   0.00%)     3147.85 *  11.10%*
Hmean     16      5501.90 (   0.00%)     6089.89 *  10.69%*
Hmean     32     10428.59 (   0.00%)    10619.63 *   1.83%*
Hmean     64      8223.39 (   0.00%)     8306.93 *   1.02%*
Hmean     128     7042.88 (   0.00%)     7068.03 *   0.36%*

On numa 0-1:
                             6.0-rc1                patched
Hmean     1        363.06 (   0.00%)      397.13 *   9.38%*
Hmean     2        721.68 (   0.00%)      789.84 *   9.44%*
Hmean     4       1435.15 (   0.00%)     1566.01 *   9.12%*
Hmean     8       2776.17 (   0.00%)     3007.05 *   8.32%*
Hmean     16      5471.71 (   0.00%)     6103.91 *  11.55%*
Hmean     32     10164.98 (   0.00%)    11531.81 *  13.45%*
Hmean     64     17143.28 (   0.00%)    20078.68 *  17.12%*
Hmean     128    14552.70 (   0.00%)    15156.41 *   4.15%*
Hmean     256    12827.37 (   0.00%)    13326.86 *   3.89%*

Note neither Kunpeng920 nor x86 Jacobsville supports SMT, so the SMT branch
in the code has not been tested but it supposed to work.

Suggested-by: default avatarPeter Zijlstra <peterz@infradead.org>
[https://lore.kernel.org/lkml/Ytfjs+m1kUs0ScSn@worktop.programming.kicks-ass.net

]
Tested-by: default avatarYicong Yang <yangyicong@hisilicon.com>
Signed-off-by: default avatarBarry Song <song.bao.hua@hisilicon.com>
Signed-off-by: default avatarYicong Yang <yangyicong@hisilicon.com>
Reviewed-by: default avatarTim Chen <tim.c.chen@linux.intel.com>
Reviewed-by: default avatarChen Yu <yu.c.chen@intel.com>
Signed-off-by: default avatarJie Liu <liujie375@h-partners.com>
parent 53ad6bf7

kernel/sched/fair.c

+27 −3
Original line number Diff line number Diff line
@@ -6370,6 +6370,30 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t 
		}

	}



	if (static_branch_unlikely(&sched_cluster_active)) {

		struct sched_domain *sdc = rcu_dereference(per_cpu(sd_cluster, target));



		if (sdc) {

			for_each_cpu_wrap(cpu, sched_domain_span(sdc), target) {

				if (!cpumask_test_cpu(cpu, cpus))

					continue;



				if (smt) {

					i = select_idle_core(p, cpu, cpus, &idle_cpu);

					if ((unsigned int)i < nr_cpumask_bits)

						return i;

				} else {

					if (--nr <= 0)

						return -1;

					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(sdc));

		}

	}



	for_each_cpu_wrap(cpu, cpus, target) {

		if (smt) {

			i = select_idle_core(p, cpu, cpus, &idle_cpu);
@@ -6377,7 +6401,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t 
				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)
@@ -6487,7 +6511,7 @@ 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_lowest_cache(prev, target) &&

	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&

#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY

	    cpumask_test_cpu(prev, p->select_cpus) &&
@@ -6518,7 +6542,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) 
	recent_used_cpu = p->recent_used_cpu;

	if (recent_used_cpu != prev &&

	    recent_used_cpu != target &&

	    cpus_share_cache(recent_used_cpu, target) &&

	    cpus_share_lowest_cache(recent_used_cpu, target) &&

	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&

#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY

	    cpumask_test_cpu(p->recent_used_cpu, p->select_cpus) &&

kernel/sched/sched.h

+1 −0
Original line number Diff line number Diff line
@@ -1808,6 +1808,7 @@ DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa); 
DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);

DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);

extern struct static_key_false sched_asym_cpucapacity;

extern struct static_key_false sched_cluster_active;



struct sched_group_capacity {

	atomic_t		ref;

kernel/sched/topology.c

+11 −0
Original line number Diff line number Diff line
@@ -653,7 +653,9 @@ DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared); 
DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);

DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);

DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);



DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);

DEFINE_STATIC_KEY_FALSE(sched_cluster_active);



static void update_top_cache_domain(int cpu)

{
@@ -2200,6 +2202,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att 
	int i, ret = -ENOMEM;

	struct sched_domain_topology_level *tl_asym;

	bool has_asym = false;

	bool has_cluster = false;



	if (WARN_ON(cpumask_empty(cpu_map)))

		goto error;
@@ -2227,6 +2230,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att 


			sd = build_sched_domain(tl, cpu_map, attr, sd, dflags, i);



			has_cluster |= sd->flags & SD_CLUSTER;



			if (tl == sched_domain_topology)

				*per_cpu_ptr(d.sd, i) = sd;

			if (tl->flags & SDTL_OVERLAP)
@@ -2286,6 +2291,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att 
	if (has_asym)

		static_branch_inc_cpuslocked(&sched_asym_cpucapacity);



	if (has_cluster)

		static_branch_inc_cpuslocked(&sched_cluster_active);



	if (rq && sched_debug_enabled) {

		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",

			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
@@ -2385,6 +2393,9 @@ static void detach_destroy_domains(const struct cpumask *cpu_map) 
	if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu)))

		static_branch_dec_cpuslocked(&sched_asym_cpucapacity);



	if (rcu_access_pointer(per_cpu(sd_cluster, cpu)))

		static_branch_dec_cpuslocked(&sched_cluster_active);



	rcu_read_lock();

	for_each_cpu(i, cpu_map)

		cpu_attach_domain(NULL, &def_root_domain, i);