lkml.org 
[lkml]   [2020]   [Sep]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[RFC PATCH v1 1/1] sched/fair: select idle cpu from idle cpumask in sched domain
Date
Added idle cpumask to track idle cpus in sched domain. When a CPU
enters idle, its corresponding bit in the idle cpumask will be set,
and when the CPU exits idle, its bit will be cleared.

When a task wakes up to select an idle cpu, scanning idle cpumask
has low cost than scanning all the cpus in last level cache domain,
especially when the system is heavily loaded.

Signed-off-by: Aubrey Li <aubrey.li@linux.intel.com>
---
include/linux/sched/topology.h | 13 +++++++++++++
kernel/sched/fair.c | 4 +++-
kernel/sched/topology.c | 2 +-
3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index fb11091129b3..43a641d26154 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -65,8 +65,21 @@ struct sched_domain_shared {
atomic_t ref;
atomic_t nr_busy_cpus;
int has_idle_cores;
+ /*
+ * Span of all idle CPUs in this domain.
+ *
+ * NOTE: this field is variable length. (Allocated dynamically
+ * by attaching extra space to the end of the structure,
+ * depending on how many CPUs the kernel has booted up with)
+ */
+ unsigned long idle_cpus_span[];
};

+static inline struct cpumask *sds_idle_cpus(struct sched_domain_shared *sds)
+{
+ return to_cpumask(sds->idle_cpus_span);
+}
+
struct sched_domain {
/* These fields must be setup */
struct sched_domain __rcu *parent; /* top domain must be null terminated */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6b3b59cc51d6..3b6f8a3589be 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6136,7 +6136,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t

time = cpu_clock(this);

- cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
+ cpumask_and(cpus, sds_idle_cpus(sd->shared), p->cpus_ptr);

for_each_cpu_wrap(cpu, cpus, target) {
if (!--nr)
@@ -10182,6 +10182,7 @@ static void set_cpu_sd_state_busy(int cpu)
sd->nohz_idle = 0;

atomic_inc(&sd->shared->nr_busy_cpus);
+ cpumask_clear_cpu(cpu, sds_idle_cpus(sd->shared));
unlock:
rcu_read_unlock();
}
@@ -10212,6 +10213,7 @@ static void set_cpu_sd_state_idle(int cpu)
sd->nohz_idle = 1;

atomic_dec(&sd->shared->nr_busy_cpus);
+ cpumask_set_cpu(cpu, sds_idle_cpus(sd->shared));
unlock:
rcu_read_unlock();
}
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 9079d865a935..92d0aeef86bf 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1769,7 +1769,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map)

*per_cpu_ptr(sdd->sd, j) = sd;

- sds = kzalloc_node(sizeof(struct sched_domain_shared),
+ sds = kzalloc_node(sizeof(struct sched_domain_shared) + cpumask_size(),
GFP_KERNEL, cpu_to_node(j));
if (!sds)
return -ENOMEM;
--
2.25.1
\
 
 \ /
  Last update: 2020-09-11 17:46    [W:0.120 / U:0.480 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site