Hi, On Wed, Dec 23, 2009 at 05:50:57PM +0100, Bernd Schubert wrote: > On Wednesday 23 December 2009, Dejan Muhamedagic wrote: > > Hi, > > > > On Tue, Dec 22, 2009 at 06:52:34PM +0100, Michael Schwartzkopff wrote: > > > Hi, > > > > > > The Lustre Filesystem uses a feature called Multiple Mount Protection to > > > make sure that one device is really only mounted by one node. > > > > > > My question now: Is this feature really needed in a pacemaker cluster? > > > > > > In a pacemaker cluster with correctly enables STONITH the cluster manager > > > takes care that the resource is only mounted on one node, isn't it? At > > > least in my understanding it should. Only after getting the positive > > > feedback that the resource was stopped on the other node or the other > > > node was fenced pacemaker starts the resource on the second node, or? > > > > Right. But I guess you knew that. > > The problem are those annoying bugs that tell you the device is umounted > although it is not.
If the RA lies all bets are off, of course. > My lustre server agent, which I will submit here once I > find some time to review it again, will protect you from this. I least I hope > I did catch all Lustre bugs... > And then pacemaker does not protect you to mount a filesystem, for which > presently e2fsck is running. I guess that the start action would fail in this case. Please file a bugzilla if the RA does something unexpected. Thanks, Dejan > > Cheers, > Bernd > > -- > Bernd Schubert > DataDirect Networks _______________________________________________ Pacemaker mailing list Pacemaker@oss.clusterlabs.org http://oss.clusterlabs.org/mailman/listinfo/pacemaker
