They say there’s no use cracking a walnut with a sledge hammer. Likewise, when it comes to data centers, it makes sense to fit the task to the tool. Yet facilities are typically engineered with a one-size-fits-all mindset. A monolithic level of mechanical, electrical and plumbing infrastructure is employed to support all systems and applications regardless of their criticality or business risk if unplanned downtime occurs. High redundancy designs are being used to accommodate growing demand for highly available operational frameworks. They are designed to support dense technology systems, “always-on” applications, and aggressive business-service delivery models. However in many instances this results in unnecessary expense both in upfront construction and ongoing operation of the data center.
At a time when CIOs and facility managers are operating within tight budgetary constraints they should be looking towards the next-generation of data center design. A facility needs to incorporate multiple operational environments, each aligned with business priorities and the criticality of specific technology systems and applications. A multi-tiered data center can typically reduce capital costs by 15 to 25 percent. This architecture conserves energy, requires fewer support resources, and operates more efficiently, cutting total cost of ownership (TCO) as well.
The Uptime Institute has defined a four tier system for identifying different data center infrastructure design topologies. Tier 1 offers the lowest availability at 99.671 percent, while Tier 4 provides the highest level of availability at 99.995 percent. The dilemma that facilities managers and designers have faced until now is that the majority of data centers are mixed technology environments populated with systems and applications of varying criticality and business priorities.
For example, a bank’s ATM technology must be available 24x7, and therefore requires a Tier 4 environment, composed of multiple active power and cooling distribution paths, redundant components, and is fault tolerant. On the other hand, applications sharing the same facility such as check processing or funds transfer—may not be severely affected by some downtime instances and could therefore be accommodated by lower-tier redundancy operational levels.
However, conventional data centers are designed monolithically, with technology systems and applications located together and designed to operate within a single tier level. The high redundancy levels that the most critical application processes require are extended across the data center. Single-tiered designs do not offer any way to easily segment mission-critical applications from less-critical applications. As a result the entire facilities infrastructure has to be continuously operating at “full throttle,” with unnecessary redundancy continuously driving down energy efficiency and driving up costs.
The next step for data centers is a multi-tiered hybrid design that designs a single data center to deliver multiple operational environments. Under this methodology, data centers can contain tiers of varying capabilities to meet specific technology and business requirements. For example, the model can be applied to design a data center to approximate both a Tier 2 and Tier 4 facility. This enables the appropriate level of the facility’s resources to be assigned to each designated pod (below). Each pod would be engineered to match the availability requirements of the specific technology systems/applications tiers deployed within it. This tier is determined by a structured business priority analysis process. Business-critical applications, for example, would be deployed only within pods designated for high-uptime Tier 4 facilities’ operational models.
HP Multi-tiered Hybrid Design Model
Various tiered applications are deployed within designated pods that provide the required operational levels.Right-sizing the design of each pod’s redundancy infrastructure delivers substantial capital (CAPEX) and operational (OPEX) cost savings. Upfront data center construction costs can be reduced by 15 to 25 percent. A multi-tiered data center also allows for increased adaptability and scalability. Modular “blocks” in the power and cooling systems can be readily reconfigured to change various pods’ redundancy levels. This same system reduces business continuity risk as systems and equipment failures are contained within smaller areas of the data center.
A multi-tiered design fits the needs of today’s economy by helping companies work within tightened budgetary constraints but it also positions them to meet evolving business and operational requirements for years to come.
Related Articles: 3D 'weather maps' to increase datacenter energy efficiency at TelecityGroup TelecityGroup to house Proofpoint infrastructure in Europe Datacentre Leaders’ Awards recognize sustainability, efficiency and true innovation across the industry
Keywords: HP, data center, environments, technology systems, Uptime Institute, active power and cooling, energy efficieny.
