summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorWanpeng Li <wanpengli@tencent.com>2020-01-13 01:50:27 +0100
committerIngo Molnar <mingo@kernel.org>2020-01-28 21:36:57 +0100
commite938b9c94164e4d981039f1cf6007d7453883e5a (patch)
tree3ce4be9bc827fb32bd2ca38d71a5d6f601d5fe69 /kernel
parentsched/uclamp: Reject negative values in cpu_uclamp_write() (diff)
downloadlinux-e938b9c94164e4d981039f1cf6007d7453883e5a.tar.xz
linux-e938b9c94164e4d981039f1cf6007d7453883e5a.zip
sched/nohz: Optimize get_nohz_timer_target()
On a machine, CPU 0 is used for housekeeping, the other 39 CPUs in the same socket are in nohz_full mode. We can observe huge time burn in the loop for seaching nearest busy housekeeper cpu by ftrace. 2) | get_nohz_timer_target() { 2) 0.240 us | housekeeping_test_cpu(); 2) 0.458 us | housekeeping_test_cpu(); ... 2) 0.292 us | housekeeping_test_cpu(); 2) 0.240 us | housekeeping_test_cpu(); 2) 0.227 us | housekeeping_any_cpu(); 2) + 43.460 us | } This patch optimizes the searching logic by finding a nearest housekeeper CPU in the housekeeping cpumask, it can minimize the worst searching time from ~44us to < 10us in my testing. In addition, the last iterated busy housekeeper can become a random candidate while current CPU is a better fallback if it is a housekeeper. Signed-off-by: Wanpeng Li <wanpengli@tencent.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org> Link: https://lkml.kernel.org/r/1578876627-11938-1-git-send-email-wanpengli@tencent.com
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched/core.c19
1 files changed, 12 insertions, 7 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 55b9a9c53b91..a8a5d5b6f5cf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -552,27 +552,32 @@ void resched_cpu(int cpu)
*/
int get_nohz_timer_target(void)
{
- int i, cpu = smp_processor_id();
+ int i, cpu = smp_processor_id(), default_cpu = -1;
struct sched_domain *sd;
- if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER))
- return cpu;
+ if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
+ if (!idle_cpu(cpu))
+ return cpu;
+ default_cpu = cpu;
+ }
rcu_read_lock();
for_each_domain(cpu, sd) {
- for_each_cpu(i, sched_domain_span(sd)) {
+ for_each_cpu_and(i, sched_domain_span(sd),
+ housekeeping_cpumask(HK_FLAG_TIMER)) {
if (cpu == i)
continue;
- if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) {
+ if (!idle_cpu(i)) {
cpu = i;
goto unlock;
}
}
}
- if (!housekeeping_cpu(cpu, HK_FLAG_TIMER))
- cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+ if (default_cpu == -1)
+ default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+ cpu = default_cpu;
unlock:
rcu_read_unlock();
return cpu;