Messages in this thread | | | Subject | Re: [PATCH tip/core/rcu 2/3] rcu: make hot-unplugged CPU relinquish its own RCU callbacks | From | Steven Rostedt <> | Date | Wed, 07 Oct 2009 09:16:12 -0400 |
| |
Paul,
Still suffering jetlag? ;-)
On Tue, 2009-10-06 at 21:48 -0700, Paul E. McKenney wrote: > From: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > The current interaction between RCU and CPU hotplug requires that > RCU block in CPU notifiers waiting for callbacks to drain. This can > be greatly simplified by haing each CPU relinquish its own callbacks, having
> and for both _rcu_barrier() and CPU_DEAD notifiers to adopt all callbacks > that were previously relinquished. This change also eliminates the > possibility of certain types of hangs due to the previous practice of > waiting for callbacks to be invoked from within CPU notifiers. If you > don't every wait, you cannot hang. ever
;-)
> > Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-- Steve
| |