Although this architecture should work with the maximum number
of nodes allowed in an MC/ServiceGuard cluster, this cluster architecture has
been tested with a maximum of 4 nodes. Therefore, the configuration currently
supported is 2 nodes per data center as shown in Figure 2-1 “Two Data Centers with FibreChannel
Hubs”.
This configuration can be implemented using any HP-supported FibreChannel
devices. Disks must be available from all nodes using redundant
links. Not all links are shown in Figure 2-1 “Two Data Centers with FibreChannel
Hubs”. The
two cluster lock disks should be located on separate FibreChannel
loops to guard against single point of failure.
The lock disks can also be used as data disks. They must be
connected to all nodes using redundant links. Not all links are
shown in Figure 2-1 “Two Data Centers with FibreChannel
Hubs”. If you do choose to use High
Availability Model 30 disk arrays as cluster lock disks, you must
disable the AutoTrespass function for all LUNs, which
prevents you from using PV links thus introducing a single point of
failure.
Nodes can connect to disks in the same data center using short
wave ports, and hubs can connect between data centers using long-wave
ports. This gives you a maximum distance of 3 kilometers between
data centers, making it possible to locate data centers in different
buildings. Therefore this configuration can be used to create either
campus or metropolitan clusters.
This architecture is also possible using FibreChannel switches.
Printable version
