Failover Cluster Installation and Configuration Guide, Windows Server 2008 SP2 and Windows Server 2008 R2 SP1

Figure 1-3 Node and File Share Majority example
• Node and Disk Majority – This type of quorum is optimal for clusters having an even
number of nodes. Each node and the witness disk gets a vote, and it requires that each node
can communicate with the disk. This cluster can survive the loss of any one vote.
Figure 1-4 Node and Disk Majority example
The concept of quorum in Windows Server 2008 moves away from the requirement for a shared
storage resource. The concept of quorum now refers to a number of votes which must equate to
a majority of nodes. All nodes and disk resources get a vote. This helps eliminate failure points
in the old model, where it was assumed that the disk would always be available. If the disk failed,
the cluster would fail.
In Windows Server 2008 failover clustering the disk resource that gets a vote is no longer referred
to as a quorum disk; now it is called the witness disk. With the new quorum models, the cluster
can come online even if the witness disk resource is not available.
The No Majority Disk Only model behaves similarly to the old quorum disk model. If the
quorum disk failed, the cluster would not come online, thus representing a single point of failure.
The Node Majority model behaves similarly to the Majority Node Set model. This model requires
three or more nodes and there is no dependence on witness-disk availability. The disadvantage
of this model is that you cannot run two server clusters, because a majority of nodes is not possible
in a two-node cluster scenario.
The Node and File Share Majority and the Node and Disk Majority models are similar. In the
Node and Disk Majority model, both the nodes and the disk resource are allowed to vote. The
Cluster Terminology 15