A managed disk (MDisk) that contains quorum data is a quorum disk. A cluster uses a quorum disk to break a tie and achieve a quorum. The cluster automatically chooses three MDisks as quorum disk candidates. Each disk is assigned an index number, either 0, 1, or 2 that identifies the MDisk as a quorum disk to the cluster.
Quorum disks are used when there is a problem in the SAN fabric or when nodes are shut down, leaving half of the nodes remaining in the cluster. This type of problem causes a loss of communication between the nodes that remain in the cluster and those that do not. The nodes are split into groups where the nodes in each group can communicate with each other, but not with the other group of nodes that were formerly part of the cluster.
In this situation, some nodes must stop operating and processing I/O requests from hosts to preserve data integrity while maintaining data access. If a group contains less than half the nodes that were active in the cluster, the nodes in that group stop operating and processing I/O requests from hosts.
It is possible for a cluster to split into two groups with each group containing half the original number of nodes in the cluster. A quorum disk determines which group of nodes stops operating and processing I/O requests. In this tie-break situation, the first group of nodes that accesses the quorum disk marks their ownership of the quorum disk and as a result continues to operate as the cluster, handling all I/O requests. If the other group of nodes cannot access the quorum disk or finds it owned by another group of nodes, it stops operating as the cluster and does not handle I/O requests.
A quorum disk is formed by taking a small amount of space from a managed disk (MDisk). There is only one active quorum disk that is used to determine which nodes operate as the cluster. However, up to three candidate quorum disks are maintained. The purpose of the other quorum disks is to provide redundancy if a quorum disk fails prior to the cluster being split into two equal groups of nodes. The SAN Volume Controller automatically chooses up to three MDisk as quorum disk candidates and then automatically selects one of these as the active quorum disk. You can also manually set quorum disk candidates and the active quorum disk.
You must set quorum disks on multiple controllers to avoid the possibility of losing all of the quorum disks with a single failure. Mirrored virtual disks (VDisks) also are taken offline when all the quorum disks are on a single controller that experiences a failure. Mirrored VDisks are taken offline because synchronization data is stored on the quorum disks. To protect against mirrored VDisks being taken offline, follow these guidelines for changing the MDisk that are assigned as quorum disk candidates: