Server virtualization has become a popular method for increasing a Data Center’s IT application capacity, without making additional investments in physical infrastructure. This approach allows rapid provisioning, as multiple applications can be supported by a single server. While virtualization solves a number of IT challenges, it also creates problems for the underlying Data Center infrastructure which is often failing to keep pace with these developments. Power, cooling and floor plans widely in use were designed for an older generation of servers, and are usually inadequate to support current and future data demands and advances in technology.
For instance, blade servers pack significantly more processing power in a server rack than traditional non-blade servers and emit a lot more heat. As a result, blade servers have much greater power and cooling requirements per rack. This makes traditional room based cooling ineffective and requires Data Centers to overhaul their cooling systems in favour of row or rack oriented architectures (such as cold aisle containment).
The issues arising from virtualization are addressed by the Data Centre Infrastructure Management (DCIM) approach, which enables Data Center owners to manage physical assets such as chillers in tandem with IT assets. This streamlines capacity planning, eases day-to-day operations and increases efficiency.