Messages in this thread | | | Date | Thu, 18 Dec 2008 17:49:46 -0800 | From | "Paul E. McKenney" <> | Subject | Re: [PATCH -tip] v9 scalable classic RCU implementation |
| |
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
| |