Data center classifications or ratings. Uptime Institute has defined four levels of classification. The levels describe the availability of data from.

data center classifications or ratings

Uptime Institute has defined four levels of classification. The levels describe the availability of data from the hardware at a location. The higher the tier, the greater the availability.

The tier classification system measures the performance of a site's operating infrastructure, which includes power, cooling, emergency backup, and fire suppression. The power and cooling capabilities of a facility are delivered by its Mechanical, Electrical, and Plumbing (MEP) infrastructure.

Tier-1 Basic Data Center Infrastructure Tier-2 Data Center with Redundant Capacity Components Tier-3 Concurrently Maintainable Data Center Tier-4 Fault-tolerant Data Center

TIER IV – requirements

The fundamental requirements:

A Fault Tolerant data center has multiple, independent, physically isolated systems that provide redundant capacity components and multiple, independent, diverse, active distribution paths simultaneously serving the computer equipment. The redundant capacity components and diverse distribution paths shall be configured such that “N” capacity is providing power and cooling to the computer equipment after any infrastructure failure.All IT equipment is dual powered and installed properly to be compatible with the topology of the site’s architecture. Complementary systems and distribution paths must be physically isolated from one another (compartmentalized) to prevent any single event from simultaneously impacting both systems or distribution paths.Continuous Cooling is required.

TIER IV – requirements

The operational impacts:

The site is not susceptible to disruption from a single unplanned event.The site is not susceptible to disruption from any planned work activities.The site infrastructure maintenance can be performed by using the redundant capacity components and distribution paths to safely work on the remaining equipment.During maintenance activity where redundant capacity components or a distribution path shut down, the computer equipment is exposed to an increased risk of disruption in the event a failure occurs on the remaining path.Operation of the fire alarm, fire suppression, or the emergency power off (EPO) feature may cause a data center disruption.

TIER IV – requirements

Engine-Generator Systems

Tier IV engine-generator systems are considered the primary power source for the data center. The local power utility is an economic alternative.

A Tier IV engine-generator system, along with its power paths and other supporting elements, shall meet the Concurrently Maintainable performance confirmation tests while they are carrying the site on engine-generator power.

Engine generators for Tier IV sites shall not have a limitation on consecutive hours of operation when loaded to “N” demand.

TIER Certification of Design Documents

Ensure the site infrastructure solutions, as represented in the design documents, are consistent with the Tier objective of the project.

TIER Certification of Constructed Facility

Ensure the facility has been constructed as designed and has the demonstrated capability to meet the target Tier objective.

TIER Operational Sustainability Certification

Ensure that the Operational Sustainability behaviors and risks are consistent with the business Tier objectives.

Site risk factors and enhancements are evaluated to determine if the appropriate mitigation is in place. Assessed in accordance with the Tier Standard: Operational Sustainability in terms of potential impact.

Some common data center design requirements

Primary data center must be X km away from secondary.

Raised floor is required.

Gas fire suppression is required.

IT security rooms are best solution.

Physical security is a prime.

Data Center – how to do it

USE YOUR COMMON SENSE!

Fault tolerant data center is not just:

coolingelectricityfire suppressionphysical security etc.

All bits and pieces must be constantly real-time monitored.

The system itself MUST automatically respond (‘self heals’) to a failure to prevent further impact to the site.

Some figures on an example TIER IV data center:

120 server racks3.2MW power300+ PDU’s800+ electric switches, fuses...1500+ actuators, sensors, pumps, PLC’s...20000+ SNMP managable ports+ thousands of other pieces

All mentioned above must be constantly and automaticaly managed – no human error allowed – by a proper IT system in place.

Detailed statistics of all events must be held for years – self learning system, management decisions, optimisations, dispute management etc.

Living persons and IT system analogy – part one:

Data centers general manager drops dead – what now? Some tears, deputy general manager takes over and life is going on – no real interruptions with business impact.

Primary domain controller (AD) goes down – what now? No tears at all – Microsoft has a nice solution handy – secondary or backup domain controller – no interruptions at all.

Please note: keep all primary and all redundant (secondary) components in separate server rooms (requirement of compartmenization)

Living persons and IT system analogy – part two:

Data centers system administrator is working for days with no break but he still can’t do all the job – what now? Get a second, third etc. sysadmin.

SNMP pooling server can’t handle all the reuqests. Microsoft has a nice solution handy – server clustering with load balancing, redundancy etc.

Please note: there is no wizzard who will tell you in advance a fairly exact computing power needed to run a data center – be prepared to scale up and scale out ALL parts of the IT system and buy additional hardware when needed and not on stock in advance.

Living persons and IT system analogy – part three:

Chillers have a cooling liquid leakage. Operator is running downstairs to shut down the valve, but unfortunately he is clumsy and breaks his leg. Second operator is on the way, getting verbal information from the first one to co-ordinate the task needed to shut down that valve. By that time data center can be already flooded.

Here comes the MAGIC

Microsoft has a nice solution handy – virtualized active-active clustering – no downtime, no real HW limitations (scale up and scale out)

Something to recall:

Within all management standards (that includes ISO/IEC 27001 too) PROPER documentation and record tracks is a REQUIREMENT.

Microsoft has every product well documented, thus suitable to implement into every standardized environment.

The system itself MUST automatically respond (‘self heals’) to a failure to prevent further impact to the site.

Using Microsoft Windows 2012 Servers, SQL 2012 Servers, Exchange etc. it is not rocket science anymore to set up a real fault tolerant IT system which is totaly compliant to TIER IV requirements in every aspect – redundancy, reliability, sustainabilty etc. – with zero downtime.

Running data center easier:

design stage – Microsoft Visio implementation stage – Microsoft Visio, Excell, PowerPointdocumentation stage - Microsoft SharePoint, Visio, Excell

using some third party add-on products based on Microsoft will make your life easier (AssetGen, Solarwinds, Sanbolic etc.)