Automatically enable the rcu_normal_wake_from_gp parameter on
systems with a small number of CPUs. The activation threshold
is set to 16 CPUs.
This helps to reduce a latency of normal synchronize_rcu() API
by waking up GP-waiters earlier and decoupling synchronize_rcu()
callers from regular callback handling.
A benchmark running 64 parallel jobs invoking synchronize_rcu()
demonstrates a notable latency reduction with the setting enabled.
Latency distribution (microseconds):
<default>
0 - 9999 : 1
10000 - 19999 : 4
20000 - 29999 : 399
30000 - 39999 : 3197
40000 - 49999 : 10428
50000 - 59999 : 17363
60000 - 69999 : 15529
70000 - 79999 : 9287
80000 - 89999 : 4249
90000 - 99999 : 1915
100000 - 109999 : 922
110000 - 119999 : 390
120000 - 129999 : 187
...
<default>
<rcu_normal_wake_from_gp>
0 - 9999 : 1
10000 - 19999 : 234
20000 - 29999 : 6678
30000 - 39999 : 33463
40000 - 49999 : 20669
50000 - 59999 : 2766
60000 - 69999 : 183
...
<rcu_normal_wake_from_gp>
Signed-off-by: Uladzislau Rezki (Sony) <ure...@gmail.com>
---
kernel/rcu/tree.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 14d4499c6fc3..c0e0b38a08dc 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1625,7 +1625,9 @@ static void rcu_sr_put_wait_head(struct llist_node *node)
atomic_set_release(&sr_wn->inuse, 0);
}
-/* Disabled by default. */
+/* Enable rcu_normal_wake_from_gp automatically on small systems. */
+#define WAKE_FROM_GP_CPU_THRESHOLD 16
+
static int rcu_normal_wake_from_gp;
module_param(rcu_normal_wake_from_gp, int, 0644);
static struct workqueue_struct *sync_wq;
@@ -4847,6 +4849,9 @@ void __init rcu_init(void)
sync_wq = alloc_workqueue("sync_wq", WQ_MEM_RECLAIM, 0);
WARN_ON(!sync_wq);
+ if (num_possible_cpus() <= WAKE_FROM_GP_CPU_THRESHOLD)
+ WRITE_ONCE(rcu_normal_wake_from_gp, 1);
+
/* Fill in default value for rcutree.qovld boot parameter. */
/* -After- the rcu_node ->lock fields are initialized! */
if (qovld < 0)
--
2.39.5
