Home > Data Center News > Uptime Institute warns against tier standard misuse
Data Center News:
EMAIL THIS

Uptime Institute warns against tier standard misuse

By Matt Stansberry, Site Editor
27 Apr 2006 | SearchDataCenter.com

Digg This!    StumbleUpon Toolbar StumbleUpon    Bookmark with Delicious Del.icio.us   

ORLANDO, Fla. -- Data center executives and Uptime Institute Inc. directors say the IT community is misappropriating Uptime's tier classification system for data center performance. Institute president Ken Brill attempted to set the record straight this week at the Uptime's Symposium on high-density computing.
For more information:

Industry standard tier classifications define site infrastructure performance

Enviro-friendly data center cuts costs

The Institute created a four-tier rating system that applied the IT concepts of high availability and concurrent maintainability to the underlying data center infrastructure. Tier-1 data centers are the most basic while a Tier-4 is fundamentally immune to planned and unplanned downtime.

But when the research firm developed its classifications over 10 years ago, its directors had no idea the tier system would become a standard used far beyond its circle of influence.

"It's evolved -- it was never intended to be what it is," Brill said. "We did it in response to a customer who wanted to explain to his management why he was spending the money he was spending. It answered a fundamental need and has become a default standard. I'm pleased that it happened, but we didn't set out to do that."

But as the Uptime tier standard spread, terms like "near Tier-3 data center" and "Tier-3 plus" started cropping up at conferences and in boardrooms. So the Institute revised its standards to better explain that those classifications don't actually exist.

"You either are or you aren't -- the definitions are very simple," Brill said. "Are you concurrently maintainable? There's not a 'maybe' answer to that."

Concurrent maintenance is a big part of the Tier-3 and Tier-4 classifications. In server hardware terms, it means you can replace power supplies or upload software without turning it off. The Institute's definition extends that idea to infrastructure -- you need to be able to shut down any component of your power distribution or cooling systems and have a redundant system working -- uninterrupted by the maintenance.

"The fact that you may never need to do it isn't part of the definition," Brill said.

Paul Schumann, vice president and manager of distributed systems for TD Banknorth in Lewiston, Maine, took that message to heart. He agreed that there is a big risk in misusing the standard.

"There's a risk when people try to interpret where they are," Schumann said. "It's an absolute system and people get a false self-confidence saying 'I'm a near Tier-3.' You're a Tier-2. The risk is that you have infrastructure somewhere in your data center that you're not paying attention to that one day will pop up and bite you."

Schumann is wrapping up a two-year renovation of his data center, a mainframe shop with 460 distributed servers. He has upgraded power, cooling and UPS to redundant levels, all on a production data center without taking systems down.

The goal for TD Banknorth is to have a Tier-3 data center, but Schumann is wary to call it that yet. "Our organization has pride in our improvements -- and rightly so -- but we're talking about being near Tier-3. I've got to go back once our project is done this summer and find out what's keeping us from being a full Tier-3. I know where some of those points are, but if all of a sudden I lose part of the center because some piece hasn't been addressed, we're in for an ugly surprise."

Schumann is planning to audit his project soon, and until that's done, he's not going to call it Tier-3.

"[The Institute] is making it very clear that you're only as good as your weakest link. I think that's a place where people can get confused and get their executives confused," Schumann said. "It's nicer to say near Tier-3 than say Tier-2. But who are you fooling?"

Let us know what you think about the story; e-mail: Matt Stansberry, Site Editor

Tags: Data center standards and metricsData center backup powerData center disaster recovery planningVIEW ALL TAGS

Digg This!    StumbleUpon Toolbar StumbleUpon    Bookmark with Delicious Del.icio.us   



RELATED CONTENT
Data center standards and metrics
IT wish list: Better ways to analyze data center environmental metrics
Buyout could boost Uptime Institute
IT pros weigh Gartner Magic Quadrant lawsuit
SPECpower benchmark has flaws, says analyst
Uptime Institute opens data center availability tiers
Healthcare data centers face deadline pressure
In measuring data center power use, more (info) is more
Apps testing key in upgrade to six-core processors
L.L. Bean data center earns silver LEED certification: News in brief
Group works toward energy-efficient high-performance computing

Data center backup power
How will ultra-low sulfur diesel affect data center generator performance?
Backup power in a shipping container: Active Power's PowerHouse
Using flywheel power for data center uninterruptible power supply backup
Uninterruptible power supply load bus synchronization: Yes or no?
Do dual-power supply servers increase redundancy?
Flywheel UPS, not batteries, for data center company's backup power
Data center shaves 10% off yearly electric bill
Weighing centralized versus modular UPS in the data center
UPS maintenance outage
More on power supplies

Data center disaster recovery planning
Data center pros must prepare for increased space weather
Are you wasting disaster recovery budget to avoid employee inconvenience?
Four ways to extend data center UPS battery life
Why SunGard uses flywheel UPSes in its data centers
Lower disaster recovery costs with open source replication tools
Apple updates Xserve, Symantec ships DR monitoring software: News in brief
Data center disaster recovery planning
Google opts for battery backup over UPS: News in brief
Avoiding disaster recovery pitfalls in VMware and Linux: Rejecting default settings
Make IT change management part of your disaster recovery plan
Data center disaster recovery planning Research

RELATED GLOSSARY TERMS
Terms from Whatis.com − the technology online dictionary
ASHRAE  (SearchDataCenter.com)
CADE (Corporate Average Data center Efficiency)  (SearchDataCenter.com)
data center infrastructure efficiency (DCIE)  (SearchDataCenter.com)
data center services  (SearchDataCenter.com)
EDI  (SearchDataCenter.com)
ISO 9000  (SearchDataCenter.com)
ITIL  (SearchDataCenter.com)
Linpack benchmark  (SearchDataCenter.com)
TIA-942  (SearchDataCenter.com)
workload  (SearchDataCenter.com)

RELATED RESOURCES
2020software.com, trial software downloads for accounting software, ERP software, CRM software and business software systems
Search Bitpipe.com for the latest white papers and business webcasts
Whatis.com, the online computer dictionary



Efficient Management for Data Centers
HomeNewsTopicsITKnowledge ExchangeTipsBlogsMultimediaWhite PapersEvents
About Us  |  Contact Us  |  For Advertisers  |  For Business Partners  |  Site Index  |  RSS
SEARCH 
TechTarget provides technology professionals with the information they need to perform their jobs - from developing strategy, to making cost-effective purchase decisions and managing their organizations' technology projects - with its network of technology-specific websites, events and online magazines.

TechTarget Corporate Web Site  |  Media Kits  |  Site Map




All Rights Reserved, Copyright 2005 - 2009, TechTarget | Read our Privacy Policy
  TechTarget - The IT Media ROI Experts