Building a Disaster-proof Data Center with HP Serviceguard for Linux, June 2007

Figure 2. Disaster tolerant architecture
Understanding types of disaster-tolerant clusters
To protect against multiple points of failure, cluster components must be geographically dispersed:
nodes can be put in different rooms, on different floors of a building, or even in separate buildings or
cities. The distance between the nodes is dependent on the types of disaster from which you need
protection and on the technology used to replicate data. Two types of disaster-tolerant clusters are
described in this white paper:
• HP Serviceguard Extended Distance Cluster for Linux
• HP StorageWorks XP Cluster Extension Software
These types of disaster-tolerant clusters differ from a simple local cluster in many ways. Extended
distance clusters and
metropolitan clusters often require right-of-way from local governments or utilities
to lay network and data replication cables or connect to DWDMs. This can complicate the design
and implementation. These clusters also require a different kind of control mechanism such as a
quorum server, to prevent data integrity issues. Typically, extended distance and metropolitan clusters
use an arbitrator site containing a computer running a quorum application.
5