Re: [PATCH -tip] v9 scalable classic RCU implementation

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

On Fri, Dec 19, 2008 at 02:29:35AM +0100, Andi Kleen wrote:
> On Thu, Dec 18, 2008 at 02:54:03PM -0800, Paul E. McKenney wrote:
> > On Tue, Dec 02, 2008 at 05:36:59PM -0800, Paul E. McKenney wrote:
> > > On Wed, Dec 03, 2008 at 02:10:42AM +0100, Andi Kleen wrote:
> > > > > On Power, I see a hang in all three flavors of RCU when CPU hotplug
> > > > > is enabled and dynticks is not.  I have not yet seen this hang on x86.
> > > > > On Power, the hang occurs in the CPU-offline code, and is identical to
> > > > > the hangs I was seeing in 2.6.27, except that "sleep 1" does not hang
> > > > > in recent 2.6.28 versions.  So the timeout is apparently failing to fire
> > > > > (or being ignored) for some other reason.
> > > > > 
> > > > > Is this similar to what you are seeing on x86?
> > > > 
> > > > Yes it is.
> > > 
> > > OK, then I will consider them to be the same bug for the moment.
> > 
> > Question based on some further testing over here...
> > 
> > Do you still get failures if you refrain from offlining CPU 0?
> 
> Yes, i never offlined cpu 0 in fact.

Hmmm...  Then you are most likely seeing a different failure than I see
on Power.

Could you please retry with v10 of the patch, setting CONFIG_TREE_RCU?

							Thanx, Paul