Re: [PATCH v2 1/2] rcu: Enable rcu_normal_wake_from_gp on small systems

[Uladzislau Rezki <urezki@gmail.com>]

On Wed, Jun 11, 2025 at 05:48:57PM -0400, Joel Fernandes wrote:
> 
> 
> On 6/11/2025 1:56 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(system with 64 CPUs) invoking
> > synchronize_rcu() demonstrates a notable latency reduction with the
> > setting enabled.
> 
> Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
> 
Thank you for review!

> Just one nit below:
> 
> > 
> > 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) <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;
> > +	}
> 
> nit: better to just do:
> 
> 	if (rcu_normal_wake_from_gp < 0 &&
> 	    num_possible_cpus() <= WAKE_FROM_GP_CPU_THRESHOLD)
>  		rcu_normal_wake_from_gp = 1;
> 	}
> 
Two lines anyway :)

--
Uladzislau Rezki