From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Paul E. McKenney" Subject: Re: rcu: enable rcu_normal_after_boot by default for RT Date: Thu, 8 Nov 2018 08:12:25 -0800 Message-ID: <20181108161225.GK4170@linux.ibm.com> References: <20181101230235.GA8757@linux.ibm.com> <20181108155225.d2m6sx5z7tvzurft@linutronix.de> Reply-To: paulmck@linux.ibm.com Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: lcapitulino@redhat.com, julia@ni.com, linux-rt-users@vger.kernel.org, linux-kernel@vger.kernel.org To: Sebastian Andrzej Siewior Return-path: Content-Disposition: inline In-Reply-To: <20181108155225.d2m6sx5z7tvzurft@linutronix.de> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-rt-users.vger.kernel.org On Thu, Nov 08, 2018 at 04:52:26PM +0100, Sebastian Andrzej Siewior wrote: > On 2018-11-01 16:02:35 [-0700], Paul E. McKenney wrote: > > > The forcing of an expedited grace period is an expensive and very > > > RT-application unfriendly operation, as it forcibly preempts all running > > > tasks on CPUs which are preventing the gp from expiring. > > > > > > By default, as a policy decision, disable the expediting of grace > > > periods (after boot) on configurations which enable PREEMPT_RT_FULL. > > > > > > Suggested-by: Luiz Capitulino > > > Signed-off-by: Julia Cartwright > > > Signed-off-by: Sebastian Andrzej Siewior > > > > In case it matters: > > > > Acked-by: Paul E. McKenney > > > > Alternatively, any reason that I should not pull this into -rcu? > because we don't have CONFIG_PREEMPT_RT_FULL yet. Fair enough. This particular case works without CONFIG_PREEMPT_RT_FULL defined, but up to you guys. Thanx, Paul