Re: [RFC 06/10] rcu/hotplug: Make rcutree_dead_cpu() parallel

[Pingfan Liu]

On Tue, Aug 23, 2022 at 11:01 AM Paul E. McKenney <paulmck@xxxxxxxxxx> wrote:
>
> On Tue, Aug 23, 2022 at 09:50:56AM +0800, Pingfan Liu wrote:
> > On Sun, Aug 21, 2022 at 07:45:28PM -0700, Paul E. McKenney wrote:
> > > On Mon, Aug 22, 2022 at 10:15:16AM +0800, Pingfan Liu wrote:
> > > > In order to support parallel, rcu_state.n_online_cpus should be
> > > > atomic_dec()
> > > >
> > > > Signed-off-by: Pingfan Liu <kernelfans@xxxxxxxxx>
> > >
> > > I have to ask...  What testing have you subjected this patch to?
> > >
> >
> > This patch subjects to [1]. The series aims to enable kexec-reboot in
> > parallel on all cpu. As a result, the involved RCU part is expected to
> > support parallel.
>
> I understand (and even sympathize with) the expectation.  But results
> sometimes diverge from expectations.  There have been implicit assumptions
> in RCU about only one CPU going offline at a time, and I am not sure
> that all of them have been addressed.  Concurrent CPU onlining has
> been looked at recently here:
>
> https://docs.google.com/document/d/1jymsaCPQ1PUDcfjIKm0UIbVdrJAaGX-6cXrmcfm0PRU/edit?usp=sharing
>
> You did us atomic_dec() to make rcu_state.n_online_cpus decrementing be
> atomic, which is good.  Did you look through the rest of RCU's CPU-offline
> code paths and related code paths?
>

I went through those codes at a shallow level, especially at each
cpuhp_step hook in the RCU system.

But as you pointed out, there are implicit assumptions about only one
CPU going offline at a time, I will chew the google doc which you
share.  Then I can come to a final result.

> > [1]: https://lore.kernel.org/linux-arm-kernel/20220822021520.6996-3-kernelfans@xxxxxxxxx/T/#mf62352138d7b040fdb583ba66f8cd0ed1e145feb
>
> Perhaps I am more blind than usual today, but I am not seeing anything
> in this patch describing the testing.  At this point, I am thinking in
> terms of making rcutorture test concurrent CPU offlining parallel
>

Yes, testing results are more convincing in this area.

After making clear the implicit assumptions, I will write some code to
bridge my code and rcutorture test. Since the series is a little
different from parallel cpu offlining. It happens after all devices
are torn down, and there is no way to rollback.

> Thoughts?
>

Need a deeper dive into this field. Hope to bring out something soon.


Thanks,

    Pingfan