Re: [PATCH 2/3] rcu: Enable rcu_normal_wake_from_gp on small systems
On Tue, Jun 10, 2025 at 02:34:10PM -0400, Joel Fernandes wrote:
>
>
> On 6/10/2025 1:34 PM, Uladzislau Rezki (Sony) wrote:
> > 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):
> >
> >
> > 0 - : 1
> > 1 - 1 : 4
> > 2 - 2 : 399
> > 3 - 3 : 3197
> > 4 - 4 : 10428
> > 5 - 5 : 17363
> > 6 - 6 : 15529
> > 7 - 7 : 9287
> > 8 - 8 : 4249
> > 9 - 9 : 1915
> > 10 - 10 : 922
> > 11 - 11 : 390
> > 12 - 12 : 187
> > ...
> >
> >
> >
> > 0 - : 1
> > 1 - 1 : 234
> > 2 - 2 : 6678
> > 3 - 3 : 33463
> > 4 - 4 : 20669
> > 5 - 5 : 2766
> > 6 - 6 : 183
> > ...
> >
> >
> > Signed-off-by: Uladzislau Rezki (Sony)
> > ---
> > 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);
> > +
> I think this will get weird if user explictly specifies
> rcutree.rcu_normal_wake_from_gp=0 ? Then we're silently overriding the param.
> Maybe, initialize it to -1, and then if it was set 0 by user, don't override
> it.
> But otherwise, set it to 1. Per your third patch, '1' is a default, not a
> forced value.
>
Right. That case should be fixed.
--
Uladzislau Rezki
Re: [PATCH 2/3] rcu: Enable rcu_normal_wake_from_gp on small systems
On 6/10/2025 1:34 PM, Uladzislau Rezki (Sony) wrote:
> 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):
>
>
> 0 - : 1
> 1 - 1 : 4
> 2 - 2 : 399
> 3 - 3 : 3197
> 4 - 4 : 10428
> 5 - 5 : 17363
> 6 - 6 : 15529
> 7 - 7 : 9287
> 8 - 8 : 4249
> 9 - 9 : 1915
> 10 - 10 : 922
> 11 - 11 : 390
> 12 - 12 : 187
> ...
>
>
>
> 0 - : 1
> 1 - 1 : 234
> 2 - 2 : 6678
> 3 - 3 : 33463
> 4 - 4 : 20669
> 5 - 5 : 2766
> 6 - 6 : 183
> ...
>
>
> Signed-off-by: Uladzislau Rezki (Sony)
> ---
> 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);
> +
I think this will get weird if user explictly specifies
rcutree.rcu_normal_wake_from_gp=0 ? Then we're silently overriding the param.
Maybe, initialize it to -1, and then if it was set 0 by user, don't override it.
But otherwise, set it to 1. Per your third patch, '1' is a default, not a
forced value.
thanks,
- Joel
[PATCH 2/3] rcu: Enable rcu_normal_wake_from_gp on small systems
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):
0 - : 1
1 - 1 : 4
2 - 2 : 399
3 - 3 : 3197
4 - 4 : 10428
5 - 5 : 17363
6 - 6 : 15529
7 - 7 : 9287
8 - 8 : 4249
9 - 9 : 1915
10 - 10 : 922
11 - 11 : 390
12 - 12 : 187
...
0 - : 1
1 - 1 : 234
2 - 2 : 6678
3 - 3 : 33463
4 - 4 : 20669
5 - 5 : 2766
6 - 6 : 183
...
Signed-off-by: Uladzislau Rezki (Sony)
---
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
