linux-rt-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Luiz Capitulino <lcapitulino@redhat.com>
To: Julia Cartwright <julia@ni.com>
Cc: linux-rt-users@vger.kernel.org, bigeasy@linutronix.de,
	mst@redhat.com, paulmck@linux.vnet.ibm.com
Subject: Re: Making rcu_normal=1 in RT
Date: Wed, 12 Oct 2016 12:49:56 -0400	[thread overview]
Message-ID: <20161012124956.3cb5f988@redhat.com> (raw)
In-Reply-To: <20161012162114.GA9362@jcartwri.amer.corp.natinst.com>

On Wed, 12 Oct 2016 11:21:14 -0500
Julia Cartwright <julia@ni.com> wrote:

> On Wed, Oct 12, 2016 at 11:12:51AM -0400, Luiz Capitulino wrote:
> > Hi,
> > 
> > We have the following patch applied to the RT tree:
> > 
> >   commit a9d3cc781a3306bfa332fa7cb6134b70696058d5
> >   Author: Josh Cartwright <joshc@ni.com>
> >   Date:   Tue Oct 27 07:31:53 2015 -0500
> >   
> >       net: Make synchronize_rcu_expedited() conditional on !RT_FULL
> > 
> > However, as noted by Michael, making rcu_normal=1 default in the
> > RT kernel should have the same effect (ie.  not calling
> > synchronize_sched_expedited()).
> > 
> > So, honest question, is there a reason not to:
> > 
> >  1. Drop the patch above
> >  2. Make rcu_normal=1 default?  
> 
> I think this is probably a cleaner way to fix the problems which
> motivated this patch in the first place.  In my defense, the above patch
> predates rcu_normal :).

No need to defend yourself! We debugged this very spike in one of
our kernels that don't have rcu_normal. We decided to do exactly
what you're doing before looking at upstream. Your patch helped
us confirm that we were in the right track.

> Something like this, perhaps?

Looks good, but (honest question) what does it buy us using
rcu_normal_after_boot vs rcu_normal? Is the boot process
improved someway?

As long as we're rcu_normal=1 before launching user-space,
this should be fine.

> 
>    Julia
> 
> -- 8< --
> Subject: [PATCH] rcu: enable rcu_normal_after_boot by default for RT
> 
> 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 <lcapitulino@redhat.com>
> Signed-off-by: Julia Cartwright <julia@ni.com>
> ---
>  kernel/rcu/update.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
> index b40d346..4975917 100644
> --- a/kernel/rcu/update.c
> +++ b/kernel/rcu/update.c
> @@ -63,7 +63,7 @@ MODULE_ALIAS("rcupdate");
>  #ifndef CONFIG_TINY_RCU
>  module_param(rcu_expedited, int, 0);
>  module_param(rcu_normal, int, 0);
> -static int rcu_normal_after_boot;
> +static int rcu_normal_after_boot = IS_ENABLED(CONFIG_PREEMPT_RT_FULL);
>  module_param(rcu_normal_after_boot, int, 0);
>  #endif /* #ifndef CONFIG_TINY_RCU */
>  


  parent reply	other threads:[~2016-10-12 16:56 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-10-12 15:12 Making rcu_normal=1 in RT Luiz Capitulino
2016-10-12 16:21 ` Julia Cartwright
2016-10-12 16:39   ` Paul E. McKenney
2016-10-12 16:49   ` Luiz Capitulino [this message]
2016-10-12 17:15     ` Julia Cartwright
2016-10-12 20:32       ` Paul E. McKenney
2016-10-13 16:25         ` Michael S. Tsirkin
2016-10-14  9:20           ` Paul E. McKenney
2016-10-16  1:45             ` Michael S. Tsirkin
2016-10-16 11:28               ` Paul E. McKenney
2016-10-31 17:38                 ` Sebastian Andrzej Siewior
2016-10-31 18:15                   ` Paul E. McKenney
2016-10-31 22:37                     ` Michael S. Tsirkin
2016-11-01  2:19                       ` Paul E. McKenney
2016-11-01  2:36                         ` Michael S. Tsirkin
2016-11-01  2:52                           ` Paul E. McKenney
2016-11-01  3:31                             ` Michael S. Tsirkin
2016-11-02 16:05                               ` Sebastian Andrzej Siewior
2016-11-03 16:26                                 ` Paul E. McKenney
2016-11-02 16:30                     ` [PATCH] rcu: update: make RCU_EXPEDITE_BOOT default Sebastian Andrzej Siewior
2016-11-03 16:22                       ` Paul E. McKenney
2016-11-03 16:33                         ` Sebastian Andrzej Siewior
2016-11-03 16:59                           ` Paul E. McKenney
2016-11-07 17:19                             ` Steven Rostedt
2016-11-07 17:30                               ` Sebastian Andrzej Siewior
2016-11-07 17:35                                 ` Josh Triplett
2016-11-07 18:05                                   ` Paul E. McKenney
2016-11-07 18:08                                     ` Josh Triplett
2016-11-07 19:04                                       ` Paul E. McKenney
2016-11-02 16:51   ` Making rcu_normal=1 in RT Sebastian Andrzej Siewior
2016-11-02 17:41     ` Luiz Capitulino

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20161012124956.3cb5f988@redhat.com \
    --to=lcapitulino@redhat.com \
    --cc=bigeasy@linutronix.de \
    --cc=julia@ni.com \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=paulmck@linux.vnet.ibm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).