Skip navigation

Understanding “Uptime” and Data Center Tier Levels

The data center industry is laden with inter-related terms such as Uptime, Tier Levels, Availability, Redundancy and Reliability. In order to make an informed decision it is important to understand what they mean and what is the actual significance for any proposals you are considering in your “Build vs Buy” analysis.

The data center industry is laden with inter-related terms such as Uptime, Tier Levels, Availability, Redundancy and Reliability. In order to make an informed decision it is important to understand what they mean and what is the actual significance for any proposals you are considering in your “Build vs Buy” analysis.

The concept of “Uptime” was pioneered by the Uptime Institute which was founded in 1993 and introduced its well defined Tier Classification system: I, II, III and IV, of which Tier IV represents the highest level of projected availability. Today, its Tier Certification system is globally recognized and its members are mostly Fortune 100-sized companies having multiple data centers averaging 50,000 square feet. And while not everyone subscribes to the Uptime Institute officially, marketing references to *Tier 2,3 or 4 are common among those seeking to ascribe a certain level of design or construction to a data center’s overall availability or system redundancy, which may, or may not be totally accurate.

The terms “N, N+1 and 2N”, typically refer to the number of power and cooling components that comprise the entire data center infrastructure systems. Wherein “N” is the minimum rating of any component (such as a UPS, generator or cooling unit) required to support the critical load. An “N” system is not redundant at all, and the failure of any component will cause an outage, effectively describing a tier 1 type facility. N+1 and 2N, represent increasing levels of component redundancies and power paths, roughly mapping to the tiers 2-4, however it is important to understand that redundant components in themselves do not guarantee continuous availability, nor insure compliance with an Uptime Institute certified data center tier level.

Moreover, besides redundancy, the ability to do planned maintenance or emergency repairs on systems may involve the necessity to take them offline. This involves the key concept of “concurrent maintainability” which permits systems to be bypassed, without impacting the availability of the computing equipment. The Uptime Institute is well recognized in clearly defining concurrent maintainability in their Tier Level system. This is one of the key criteria in the design or certification of Tier III and Tier IV data centers.

Besides the level of infrastructure redundancy at the facility level, consistency of procedures for operations, maintenance and support of the critical infrastructure systems are key to ensuring continuous availability. Moreover, the Uptime Institute has now also established a related sub-category called Operational Sustainability to define and evaluate data center’s operational procedures, as an addition to their well recognized Tier Classification rating system.

Whether you chose to build or buy, you should examine all of these factors very closely to understand what is being promised if it is a brand new building and/or what the operating history of a proposed data center facility provider has been. You can download the complete Data Center Knowledge – Data Center Build vs Buy report, which includes all the articles in the series plus additional sidebars and analysis, compliments of Digital Realty Trust.

Julius Neudorfer is the CTO and founder of North American Access Technologies, Inc. and writes for Data Center Knowledge on issues and strategies relevant to seniors business executives.

Hide comments

Comments

  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
Publish