White Papers
7 Dell Storage PS Series Architecture: Load Balancers | TR1070
3 Why automatically balance SAN resources
The IT resources available to most organizations are limited. The realities of budgets, staffing, knowledge,
and the business needs of the organization are often competing and conflicting, forcing IT managers to
optimize the environment for the proper balance of these items. The usual result is that tuning for optimal
performance is deprioritized in favor of more pressing items. Unfortunately, the demands that are placed on a
SAN after installation are rarely the same as those that were anticipated at the time the SAN was installed.
For example, applications may have been added or removed from the environment, and user loads may have
increased or decreased based on the evolving needs of the business. Typically, due to data growth, the
number of disks or other storage devices has increased, often dramatically.
For a classic non-virtualized storage architecture, there are typically only two options to optimize performance
once these inevitable changes have occurred, and neither of them simple: Re-layout all of the data on the
storage array manually, or replace the old array in its entirety and begin the process of performance tuning
from scratch.
PS Series storage provides an alternative strategy for tuning that does not strain IT resources in either of
those ways. Because of the virtualized scale-out architecture of the PS Series arrays, adding resources to
meet the demands of the business is easy — administrators simply add an array to an existing PS Series
Group and more space is immediately available. The system will automatically rebalance the load with no
downtime and in a way that is completely transparent to the servers, applications, and users. Re-deploying or
retiring older equipment is equally simple, just choose a member to remove, and it will automatically offload its
data to other members in its pool and extract itself from the Group and be immediately ready for re-
deployment or retirement. This, too, occurs seamlessly with no downtime.