Re: [PATCH 15/16] rcu: Check for a nocb cpu before trying to spawn nocb threads

From: Pranith Kumar
Date: Wed Jul 23 2014 - 09:15:28 EST


On Wed, Jul 23, 2014 at 8:28 AM, Paul E. McKenney
<paulmck@xxxxxxxxxxxxxxxxxx> wrote:
> On Wed, Jul 23, 2014 at 01:09:52AM -0400, Pranith Kumar wrote:
>> This commit tries to spawn nocb kthreads only when the CPU is marked as a nocb
>> cpu. This is a minor optimization.
>>
>> Signed-off-by: Pranith Kumar <bobby.prani@xxxxxxxxx>
>
> This only happens once at boot time, so I am happier with the single check
> at the bottom. So sorry, but no.
>


Actually this happens whenever a CPU is coming online, but yes, it is
a minor optimization for hotplug.

> Thanx, Paul
>
>> ---
>> kernel/rcu/tree_plugin.h | 3 ++-
>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>
>> diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
>> index 541c776..8abff0a 100644
>> --- a/kernel/rcu/tree_plugin.h
>> +++ b/kernel/rcu/tree_plugin.h
>> @@ -1490,7 +1490,8 @@ static void rcu_prepare_kthreads(int cpu)
>> return;
>>
>> rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
>> - rcu_spawn_all_nocb_kthreads(cpu);
>> + if (rcu_is_nocb_cpu(cpu))
>> + rcu_spawn_all_nocb_kthreads(cpu);
>> }
>>
>> #else /* #ifdef CONFIG_RCU_BOOST */
>> --
>> 2.0.0.rc2
>>
>



--
Pranith
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/