[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20181101232518.GA12385@linux.ibm.com>
Date: Thu, 1 Nov 2018 16:25:18 -0700
From: "Paul E. McKenney" <paulmck@...ux.ibm.com>
To: bigeasy@...utronix.de
Cc: linux-rt-users@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: rcu: make RCU_BOOST default on RT
> Since it is no longer invoked from the softirq people run into OOM more
> often if the priority of the RCU thread is too low. Making boosting
> default on RT should help in those case and it can be switched off if
> someone knows better.
>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
>
> diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
> index 644264be90f0..0be2c96fb640 100644
> --- a/kernel/rcu/Kconfig
> +++ b/kernel/rcu/Kconfig
> @@ -36,7 +36,7 @@ config TINY_RCU
>
> config RCU_EXPERT
> bool "Make expert-level adjustments to RCU configuration"
> - default n
> + default y if PREEMPT_RT_FULL
Would it work to leave this as is, and ...
> help
> This option needs to be enabled if you wish to make
> expert-level adjustments to RCU configuration. By default,
> @@ -191,7 +191,7 @@ config RCU_FAST_NO_HZ
> config RCU_BOOST
> bool "Enable RCU priority boosting"
> depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
... make the above line instead be:
depends on (RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT) || PREEMPT_RT_FULL
Or am I missing something?
I agree that the risk might currently seem small, but if Linus ever
starts building PREEMPT_RT_FULL kernels, I really really do not want
RCU_EXPERT to be set. ;-)
Thanx, Paul
> - default n
> + default y if PREEMPT_RT_FULL
> help
> This option boosts the priority of preempted RCU readers that
> block the current preemptible RCU grace period for too long.
Powered by blists - more mailing lists