Re: [PATCH tip/core/rcu 1/2] rcu: Parallelize and economize NOCB kthread wakeups

["Paul E. McKenney" <paulmck@linux.vnet.ibm.com>]

On Wed, Aug 27, 2014 at 10:13:50AM +0530, Amit Shah wrote:
> On (Sat) 23 Aug 2014 [03:43:38], Pranith Kumar wrote:
> > On Fri, Aug 22, 2014 at 5:53 PM, Paul E. McKenney
> > <paulmck@linux.vnet.ibm.com> wrote:
> > >
> > > Hmmm...  Please try replacing the synchronize_rcu() in
> > > __sysrq_swap_key_ops() with (say) schedule_timeout_interruptible(HZ / 10).
> > > I bet that gets rid of the hang.  (And also introduces a low-probability
> > > bug, but should be OK for testing.)
> > >
> > > The other thing to try is to revert your patch that turned my event
> > > traces into printk()s, then put an ftrace_dump(DUMP_ALL); just after
> > > the synchronize_rcu() -- that might make it so that the ftrace data
> > > actually gets dumped out.
> > >
> > 
> > I was able to reproduce this error on my Ubuntu 14.04 machine. I think
> > I found the root cause of the problem after several kvm runs.
> > 
> > The problem is that earlier we were waiting on nocb_head and now we
> > are waiting on nocb_leader_wake.
> > 
> > So there are a lot of nocb callbacks which are enqueued before the
> > nocb thread is spawned. This sets up nocb_head to be non-null, because
> > of which the nocb kthread used to wake up immediately after sleeping.
> > 
> > Now that we have switched to nocb_leader_wake, this is not being set
> > when there are pending callbacks, unless the callbacks overflow the
> > qhimark. The pending callbacks were around 7000 when the boot hangs.
> > 
> > So setting the qhimark using the boot parameter rcutree.qhimark=5000
> > is one way to allow us to boot past the point by forcefully waking up
> > the nocb kthread. I am not sure this is fool-proof.
> > 
> > Another option to start the nocb kthreads with nocb_leader_wake set,
> > so that it can handle any pending callbacks. The following patch also
> > allows us to boot properly.
> > 
> > Phew! Let me know if this makes any sense :)
> > 
> > diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
> > index 00dc411..4c397aa 100644
> > --- a/kernel/rcu/tree_plugin.h
> > +++ b/kernel/rcu/tree_plugin.h
> > @@ -2386,6 +2386,9 @@ static int rcu_nocb_kthread(void *arg)
> >         struct rcu_head **tail;
> >         struct rcu_data *rdp = arg;
> > 
> > +       if (rdp->nocb_leader == rdp)
> > +               rdp->nocb_leader_wake = true;
> > +
> >         /* Each pass through this loop invokes one batch of callbacks */
> >         for (;;) {
> >                 /* Wait for callbacks. */
> 
> Yes, this patch helps my case as well.

Very good!!!

Pranith, I can take this patch, but would you be willing to invert
the sense of ->nocb_leader_wake (e.g., call it ->nocb_leader_sleep or
some such)?  This field is only used in eight places in the source code.

The idea is that inverting the sense of the field allows the normal C
initialization of zero to properly initialize this field, plus it gets
rid of a few lines of code.

							Thanx, Paul