* [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems
@ 2025-07-02 14:59 Uladzislau Rezki (Sony)
2025-07-02 14:59 ` [PATCH v3 2/2] Documentation/kernel-parameters: Update rcu_normal_wake_from_gp doc Uladzislau Rezki (Sony)
2025-07-03 15:35 ` [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems Uladzislau Rezki
0 siblings, 2 replies; 8+ messages in thread
From: Uladzislau Rezki (Sony) @ 2025-07-02 14:59 UTC (permalink / raw)
To: Paul E . McKenney, Neeraj upadhyay
Cc: Joel Fernandes, RCU, LKML, Frederic Weisbecker, Uladzislau Rezki,
Joel Fernandes
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(system with 64 CPUs) 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>
Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
---
kernel/rcu/tree.c | 14 +++++++++++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e8a4b720d7d2..b88ceb35cebd 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1625,8 +1625,10 @@ static void rcu_sr_put_wait_head(struct llist_node *node)
atomic_set_release(&sr_wn->inuse, 0);
}
-/* Disabled by default. */
-static int rcu_normal_wake_from_gp;
+/* Enable rcu_normal_wake_from_gp automatically on small systems. */
+#define WAKE_FROM_GP_CPU_THRESHOLD 16
+
+static int rcu_normal_wake_from_gp = -1;
module_param(rcu_normal_wake_from_gp, int, 0644);
static struct workqueue_struct *sync_wq;
@@ -3239,7 +3241,7 @@ static void synchronize_rcu_normal(void)
trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("request"));
- if (!READ_ONCE(rcu_normal_wake_from_gp)) {
+ if (READ_ONCE(rcu_normal_wake_from_gp) < 1) {
wait_rcu_gp(call_rcu_hurry);
goto trace_complete_out;
}
@@ -4843,6 +4845,12 @@ void __init rcu_init(void)
sync_wq = alloc_workqueue("sync_wq", WQ_MEM_RECLAIM, 0);
WARN_ON(!sync_wq);
+ /* Respect if explicitly disabled via a boot parameter. */
+ if (rcu_normal_wake_from_gp < 0) {
+ if (num_possible_cpus() <= WAKE_FROM_GP_CPU_THRESHOLD)
+ 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
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH v3 2/2] Documentation/kernel-parameters: Update rcu_normal_wake_from_gp doc
2025-07-02 14:59 [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems Uladzislau Rezki (Sony)
@ 2025-07-02 14:59 ` Uladzislau Rezki (Sony)
2025-07-03 15:36 ` Uladzislau Rezki
2025-07-03 15:35 ` [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems Uladzislau Rezki
1 sibling, 1 reply; 8+ messages in thread
From: Uladzislau Rezki (Sony) @ 2025-07-02 14:59 UTC (permalink / raw)
To: Paul E . McKenney, Neeraj upadhyay
Cc: Joel Fernandes, RCU, LKML, Frederic Weisbecker, Uladzislau Rezki,
Joel Fernandes
Update the documentation about rcu_normal_wake_from_gp parameter.
Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
---
Documentation/admin-guide/kernel-parameters.txt | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f1f2c0874da9..f7e4bee2b823 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5485,7 +5485,8 @@
echo 1 > /sys/module/rcutree/parameters/rcu_normal_wake_from_gp
or pass a boot parameter "rcutree.rcu_normal_wake_from_gp=1"
- Default is 0.
+ Default is 1 if num_possible_cpus() <= 16 and it is not explicitly
+ disabled by the boot parameter passing 0.
rcuscale.gp_async= [KNL]
Measure performance of asynchronous
--
2.39.5
^ permalink raw reply related [flat|nested] 8+ messages in thread
* Re: [PATCH v3 2/2] Documentation/kernel-parameters: Update rcu_normal_wake_from_gp doc
2025-07-02 14:59 ` [PATCH v3 2/2] Documentation/kernel-parameters: Update rcu_normal_wake_from_gp doc Uladzislau Rezki (Sony)
@ 2025-07-03 15:36 ` Uladzislau Rezki
2025-07-07 3:49 ` Neeraj Upadhyay
0 siblings, 1 reply; 8+ messages in thread
From: Uladzislau Rezki @ 2025-07-03 15:36 UTC (permalink / raw)
To: Neeraj upadhyay
Cc: Paul E . McKenney, Neeraj upadhyay, Joel Fernandes, RCU, LKML,
Frederic Weisbecker, Joel Fernandes
On Wed, Jul 02, 2025 at 04:59:37PM +0200, Uladzislau Rezki (Sony) wrote:
> Update the documentation about rcu_normal_wake_from_gp parameter.
>
> Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
> Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
> ---
> Documentation/admin-guide/kernel-parameters.txt | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index f1f2c0874da9..f7e4bee2b823 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -5485,7 +5485,8 @@
> echo 1 > /sys/module/rcutree/parameters/rcu_normal_wake_from_gp
> or pass a boot parameter "rcutree.rcu_normal_wake_from_gp=1"
>
> - Default is 0.
> + Default is 1 if num_possible_cpus() <= 16 and it is not explicitly
> + disabled by the boot parameter passing 0.
>
> rcuscale.gp_async= [KNL]
> Measure performance of asynchronous
> --
> 2.39.5
>
Same this one. Are you planning?
--
Uladzislau Rezki
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v3 2/2] Documentation/kernel-parameters: Update rcu_normal_wake_from_gp doc
2025-07-03 15:36 ` Uladzislau Rezki
@ 2025-07-07 3:49 ` Neeraj Upadhyay
2025-07-07 13:15 ` Uladzislau Rezki
0 siblings, 1 reply; 8+ messages in thread
From: Neeraj Upadhyay @ 2025-07-07 3:49 UTC (permalink / raw)
To: Uladzislau Rezki
Cc: Paul E . McKenney, Joel Fernandes, RCU, LKML, Frederic Weisbecker,
Joel Fernandes
On 7/3/2025 9:06 PM, Uladzislau Rezki wrote:
> On Wed, Jul 02, 2025 at 04:59:37PM +0200, Uladzislau Rezki (Sony) wrote:
>> Update the documentation about rcu_normal_wake_from_gp parameter.
>>
>> Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
>> Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
>> ---
>> Documentation/admin-guide/kernel-parameters.txt | 3 ++-
>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>
>> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
>> index f1f2c0874da9..f7e4bee2b823 100644
>> --- a/Documentation/admin-guide/kernel-parameters.txt
>> +++ b/Documentation/admin-guide/kernel-parameters.txt
>> @@ -5485,7 +5485,8 @@
>> echo 1 > /sys/module/rcutree/parameters/rcu_normal_wake_from_gp
>> or pass a boot parameter "rcutree.rcu_normal_wake_from_gp=1"
>>
>> - Default is 0.
>> + Default is 1 if num_possible_cpus() <= 16 and it is not explicitly
>> + disabled by the boot parameter passing 0.
>>
>> rcuscale.gp_async= [KNL]
>> Measure performance of asynchronous
>> --
>> 2.39.5
>>
> Same this one. Are you planning?
>
Yes, will be including these in the PR for next merge window.
- Neeraj
> --
> Uladzislau Rezki
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v3 2/2] Documentation/kernel-parameters: Update rcu_normal_wake_from_gp doc
2025-07-07 3:49 ` Neeraj Upadhyay
@ 2025-07-07 13:15 ` Uladzislau Rezki
0 siblings, 0 replies; 8+ messages in thread
From: Uladzislau Rezki @ 2025-07-07 13:15 UTC (permalink / raw)
To: Neeraj Upadhyay
Cc: Uladzislau Rezki, Paul E . McKenney, Joel Fernandes, RCU, LKML,
Frederic Weisbecker, Joel Fernandes
On Mon, Jul 07, 2025 at 09:19:38AM +0530, Neeraj Upadhyay wrote:
>
>
> On 7/3/2025 9:06 PM, Uladzislau Rezki wrote:
> > On Wed, Jul 02, 2025 at 04:59:37PM +0200, Uladzislau Rezki (Sony) wrote:
> >> Update the documentation about rcu_normal_wake_from_gp parameter.
> >>
> >> Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
> >> Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
> >> ---
> >> Documentation/admin-guide/kernel-parameters.txt | 3 ++-
> >> 1 file changed, 2 insertions(+), 1 deletion(-)
> >>
> >> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> >> index f1f2c0874da9..f7e4bee2b823 100644
> >> --- a/Documentation/admin-guide/kernel-parameters.txt
> >> +++ b/Documentation/admin-guide/kernel-parameters.txt
> >> @@ -5485,7 +5485,8 @@
> >> echo 1 > /sys/module/rcutree/parameters/rcu_normal_wake_from_gp
> >> or pass a boot parameter "rcutree.rcu_normal_wake_from_gp=1"
> >>
> >> - Default is 0.
> >> + Default is 1 if num_possible_cpus() <= 16 and it is not explicitly
> >> + disabled by the boot parameter passing 0.
> >>
> >> rcuscale.gp_async= [KNL]
> >> Measure performance of asynchronous
> >> --
> >> 2.39.5
> >>
> > Same this one. Are you planning?
> >
>
> Yes, will be including these in the PR for next merge window.
>
Appreciate it and thank you!
--
Uladzislau Rezki
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems
2025-07-02 14:59 [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems Uladzislau Rezki (Sony)
2025-07-02 14:59 ` [PATCH v3 2/2] Documentation/kernel-parameters: Update rcu_normal_wake_from_gp doc Uladzislau Rezki (Sony)
@ 2025-07-03 15:35 ` Uladzislau Rezki
2025-07-07 3:49 ` Neeraj Upadhyay
1 sibling, 1 reply; 8+ messages in thread
From: Uladzislau Rezki @ 2025-07-03 15:35 UTC (permalink / raw)
To: Neeraj upadhyay
Cc: Paul E . McKenney, Neeraj upadhyay, Joel Fernandes, RCU, LKML,
Frederic Weisbecker, Joel Fernandes
On Wed, Jul 02, 2025 at 04:59:36PM +0200, 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(system with 64 CPUs) 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>
>
> Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
> Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
> ---
> kernel/rcu/tree.c | 14 +++++++++++---
> 1 file changed, 11 insertions(+), 3 deletions(-)
>
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index e8a4b720d7d2..b88ceb35cebd 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -1625,8 +1625,10 @@ static void rcu_sr_put_wait_head(struct llist_node *node)
> atomic_set_release(&sr_wn->inuse, 0);
> }
>
> -/* Disabled by default. */
> -static int rcu_normal_wake_from_gp;
> +/* Enable rcu_normal_wake_from_gp automatically on small systems. */
> +#define WAKE_FROM_GP_CPU_THRESHOLD 16
> +
> +static int rcu_normal_wake_from_gp = -1;
> module_param(rcu_normal_wake_from_gp, int, 0644);
> static struct workqueue_struct *sync_wq;
>
> @@ -3239,7 +3241,7 @@ static void synchronize_rcu_normal(void)
>
> trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("request"));
>
> - if (!READ_ONCE(rcu_normal_wake_from_gp)) {
> + if (READ_ONCE(rcu_normal_wake_from_gp) < 1) {
> wait_rcu_gp(call_rcu_hurry);
> goto trace_complete_out;
> }
> @@ -4843,6 +4845,12 @@ void __init rcu_init(void)
> sync_wq = alloc_workqueue("sync_wq", WQ_MEM_RECLAIM, 0);
> WARN_ON(!sync_wq);
>
> + /* Respect if explicitly disabled via a boot parameter. */
> + if (rcu_normal_wake_from_gp < 0) {
> + if (num_possible_cpus() <= WAKE_FROM_GP_CPU_THRESHOLD)
> + 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
>
Neeraj, are you planning to take this for next merge window?
--
Uladzislau Rezlo
^ permalink raw reply [flat|nested] 8+ messages in thread* Re: [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems
2025-07-03 15:35 ` [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems Uladzislau Rezki
@ 2025-07-07 3:49 ` Neeraj Upadhyay
2025-07-07 13:15 ` Uladzislau Rezki
0 siblings, 1 reply; 8+ messages in thread
From: Neeraj Upadhyay @ 2025-07-07 3:49 UTC (permalink / raw)
To: Uladzislau Rezki
Cc: Paul E . McKenney, Joel Fernandes, RCU, LKML, Frederic Weisbecker,
Joel Fernandes
On 7/3/2025 9:05 PM, Uladzislau Rezki wrote:
> On Wed, Jul 02, 2025 at 04:59:36PM +0200, 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(system with 64 CPUs) 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>
>>
>> Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
>> Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
>> ---
>> kernel/rcu/tree.c | 14 +++++++++++---
>> 1 file changed, 11 insertions(+), 3 deletions(-)
>>
>> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
>> index e8a4b720d7d2..b88ceb35cebd 100644
>> --- a/kernel/rcu/tree.c
>> +++ b/kernel/rcu/tree.c
>> @@ -1625,8 +1625,10 @@ static void rcu_sr_put_wait_head(struct llist_node *node)
>> atomic_set_release(&sr_wn->inuse, 0);
>> }
>>
>> -/* Disabled by default. */
>> -static int rcu_normal_wake_from_gp;
>> +/* Enable rcu_normal_wake_from_gp automatically on small systems. */
>> +#define WAKE_FROM_GP_CPU_THRESHOLD 16
>> +
>> +static int rcu_normal_wake_from_gp = -1;
>> module_param(rcu_normal_wake_from_gp, int, 0644);
>> static struct workqueue_struct *sync_wq;
>>
>> @@ -3239,7 +3241,7 @@ static void synchronize_rcu_normal(void)
>>
>> trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("request"));
>>
>> - if (!READ_ONCE(rcu_normal_wake_from_gp)) {
>> + if (READ_ONCE(rcu_normal_wake_from_gp) < 1) {
>> wait_rcu_gp(call_rcu_hurry);
>> goto trace_complete_out;
>> }
>> @@ -4843,6 +4845,12 @@ void __init rcu_init(void)
>> sync_wq = alloc_workqueue("sync_wq", WQ_MEM_RECLAIM, 0);
>> WARN_ON(!sync_wq);
>>
>> + /* Respect if explicitly disabled via a boot parameter. */
>> + if (rcu_normal_wake_from_gp < 0) {
>> + if (num_possible_cpus() <= WAKE_FROM_GP_CPU_THRESHOLD)
>> + 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
>>
> Neeraj, are you planning to take this for next merge window?
>
Yes, I have queued v2 of these for testing here:
https://git.kernel.org/pub/scm/linux/kernel/git/neeraj.upadhyay/linux-rcu.git/log/?h=dev.01.07.2025
Will include them in PR for next merge window.
- Neeraj
> --
> Uladzislau Rezlo
^ permalink raw reply [flat|nested] 8+ messages in thread* Re: [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems
2025-07-07 3:49 ` Neeraj Upadhyay
@ 2025-07-07 13:15 ` Uladzislau Rezki
0 siblings, 0 replies; 8+ messages in thread
From: Uladzislau Rezki @ 2025-07-07 13:15 UTC (permalink / raw)
To: Neeraj Upadhyay
Cc: Uladzislau Rezki, Paul E . McKenney, Joel Fernandes, RCU, LKML,
Frederic Weisbecker, Joel Fernandes
On Mon, Jul 07, 2025 at 09:19:03AM +0530, Neeraj Upadhyay wrote:
>
>
> On 7/3/2025 9:05 PM, Uladzislau Rezki wrote:
> > On Wed, Jul 02, 2025 at 04:59:36PM +0200, 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(system with 64 CPUs) 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>
> >>
> >> Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
> >> Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
> >> ---
> >> kernel/rcu/tree.c | 14 +++++++++++---
> >> 1 file changed, 11 insertions(+), 3 deletions(-)
> >>
> >> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> >> index e8a4b720d7d2..b88ceb35cebd 100644
> >> --- a/kernel/rcu/tree.c
> >> +++ b/kernel/rcu/tree.c
> >> @@ -1625,8 +1625,10 @@ static void rcu_sr_put_wait_head(struct llist_node *node)
> >> atomic_set_release(&sr_wn->inuse, 0);
> >> }
> >>
> >> -/* Disabled by default. */
> >> -static int rcu_normal_wake_from_gp;
> >> +/* Enable rcu_normal_wake_from_gp automatically on small systems. */
> >> +#define WAKE_FROM_GP_CPU_THRESHOLD 16
> >> +
> >> +static int rcu_normal_wake_from_gp = -1;
> >> module_param(rcu_normal_wake_from_gp, int, 0644);
> >> static struct workqueue_struct *sync_wq;
> >>
> >> @@ -3239,7 +3241,7 @@ static void synchronize_rcu_normal(void)
> >>
> >> trace_rcu_sr_normal(rcu_state.name, &rs.head, TPS("request"));
> >>
> >> - if (!READ_ONCE(rcu_normal_wake_from_gp)) {
> >> + if (READ_ONCE(rcu_normal_wake_from_gp) < 1) {
> >> wait_rcu_gp(call_rcu_hurry);
> >> goto trace_complete_out;
> >> }
> >> @@ -4843,6 +4845,12 @@ void __init rcu_init(void)
> >> sync_wq = alloc_workqueue("sync_wq", WQ_MEM_RECLAIM, 0);
> >> WARN_ON(!sync_wq);
> >>
> >> + /* Respect if explicitly disabled via a boot parameter. */
> >> + if (rcu_normal_wake_from_gp < 0) {
> >> + if (num_possible_cpus() <= WAKE_FROM_GP_CPU_THRESHOLD)
> >> + 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
> >>
> > Neeraj, are you planning to take this for next merge window?
> >
>
> Yes, I have queued v2 of these for testing here:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/neeraj.upadhyay/linux-rcu.git/log/?h=dev.01.07.2025
>
> Will include them in PR for next merge window.
>
Thank you! I asked because i did not see both in our common RCU tree.
--
Uladzislau Rezki
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2025-07-07 13:15 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-07-02 14:59 [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems Uladzislau Rezki (Sony)
2025-07-02 14:59 ` [PATCH v3 2/2] Documentation/kernel-parameters: Update rcu_normal_wake_from_gp doc Uladzislau Rezki (Sony)
2025-07-03 15:36 ` Uladzislau Rezki
2025-07-07 3:49 ` Neeraj Upadhyay
2025-07-07 13:15 ` Uladzislau Rezki
2025-07-03 15:35 ` [PATCH v3 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems Uladzislau Rezki
2025-07-07 3:49 ` Neeraj Upadhyay
2025-07-07 13:15 ` Uladzislau Rezki
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).