HP Surestore NAS - Manual (Page 69)

69
High Availability
Clustering Overview
For mission critical environments, NAS head clustering is a requirement. The NAS VA is an ideal
fit for this environment due to its modular nature. The high performance NAS head used in the
NAS VA can be clustered to provide an extremely dense highly available NAS solution. In
addition to high availability, clustering technologies provide scalable performance. Unlike other
ways to increase performance, clustering provides an almost linear performance curve as more
nodes are added to the cluster.
A high availability system allows file services to continue in spite of a hardware or software
failure. Highly availiable systems protect users from software failures as well as ffrom failure of a
NAS head, disk, or local area network (LAN) component via redundancy.
An MC/ServiceGuard cluster is a networked group of HP approved NAS heads having sufficient
redundancy of software and hardware that a single point of failure will not significantly disrupt
service. Application services (individual HP -UX processes) are grouped together in packages. In
the event of a single service, node, network, or other resource failure, MC/ServiceGuard can
automatically transfer control of the package to another node within the NAS cluster, allowing
service to remain available with minimal interruption.
The NAS web interface provides basic functionality for both single headed and clustered NAS VA
solutions. MC/ServiceGuard provides the clustering and failover specific functionality. Command
line functions will also apply. For more information on managing clustered NAS heads please
refer to your MC/ServiceGuard User's Manual.