[PATCH v7 2/2] sched/fair: Scan cluster before scanning LLC in wake-up path

From: Yicong Yang
Date: Mon Aug 22 2022 - 03:38:32 EST

From: Barry Song <song.bao.hua@xxxxxxxxxxxxx>

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: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
[https://lore.kernel.org/lkml/Ytfjs+m1kUs0ScSn@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx]
Tested-by: Yicong Yang <yangyicong@xxxxxxxxxxxxx>
Signed-off-by: Barry Song <song.bao.hua@xxxxxxxxxxxxx>
Signed-off-by: Yicong Yang <yangyicong@xxxxxxxxxxxxx>
Reviewed-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
---
kernel/sched/fair.c | 30 +++++++++++++++++++++++++++---
kernel/sched/sched.h | 2 ++
kernel/sched/topology.c | 10 ++++++++++
3 files changed, 39 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 914096c5b1ae..6fa77610d0f5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6437,6 +6437,30 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
}
}

+ 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 + 1) {
+ if (!cpumask_test_cpu(cpu, cpus))
+ continue;
+
+ if (has_idle_core) {
+ 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 + 1) {
if (has_idle_core) {
i = select_idle_core(p, cpu, cpus, &idle_cpu);
@@ -6444,7 +6468,7 @@ 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)
@@ -6543,7 +6567,7 @@ 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)) &&
asym_fits_capacity(task_util, prev))
return prev;
@@ -6569,7 +6593,7 @@ 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_lowest_cache(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)) {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e9f0935605e2..60e8a91e29d1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1815,7 +1815,9 @@ DECLARE_PER_CPU(struct sched_domain __rcu *, sd_cluster);
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;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8ab27c0d6d1f..04ead3227201 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -670,7 +670,9 @@ 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)
{
@@ -2268,6 +2270,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
struct rq *rq = NULL;
int i, ret = -ENOMEM;
bool has_asym = false;
+ bool has_cluster = false;

if (WARN_ON(cpumask_empty(cpu_map)))
goto error;
@@ -2289,6 +2292,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
sd = build_sched_domain(tl, cpu_map, attr, sd, i);

has_asym |= sd->flags & SD_ASYM_CPUCAPACITY;
+ has_cluster |= sd->flags & SD_CLUSTER;

if (tl == sched_domain_topology)
*per_cpu_ptr(d.sd, i) = sd;
@@ -2399,6 +2403,9 @@ 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_verbose) {
pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
@@ -2498,6 +2505,9 @@ 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);
--
2.24.0