From: Wanpeng Li <wanpen...@tencent.com>

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.

Cc: Ingo Molnar <mi...@redhat.com> 
Cc: Peter Zijlstra <pet...@infradead.org>
Cc: Frederic Weisbecker <frede...@kernel.org>
Cc: Thomas Gleixner <t...@linutronix.de>
Signed-off-by: Wanpeng Li <wanpen...@tencent.com>
---
v1 -> v2:
 * current CPU is a better fallback if it is a housekeeper

 kernel/sched/core.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 102dfcf..04a0f6a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -539,27 +539,32 @@ 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;
-- 
1.8.3.1

Reply via email to