Microsoft’s datacenters – top 10 best practices

Microsoft’s datacenters – top 10 best practices

  • Comments 1


I’ve written a little bit already on this blog about Microsoft’s datacenters and it’s something I suspect you’ll hear a lot more about over the next year. I’ll happily predict that Wired, the NY Times and The Financial Times will write on the topic more over the coming year. Why? Partly because it’s the new battleground for computing and the mainstream media will enjoy pitting the old (Microsoft) against the new (Google) and some other significant players like HP, EMC and Amazon. It’ll also be a hot topic because of the energy consumption of these massive datacenters.

You can relatively easily put the X axis on the charts above but if you need some guidance, check out the Wired Information Factories article from 2006.

The total of electricity consumed by major search engines in 2006 approaches 5 gigawatts. That's an impressive quantity of electricity. Five gigawatts is almost enough to power the Las Vegas metropolitan area – with all its hotels, casinos, restaurants, and convention centers – on the hottest day of the year.

What I found even more intriguing about that article was that a third of the incoming power is lost to the grid's inefficiencies, and half of what's left lost to power supplies, transformers, and converters. Wow….that’s pretty expensive when you’re running several large datacenters and you biggest cost (to you and the environment) is power. There, efficient datacenters are worth their weight in kw’s. Back in February Microsoft mentioned it was publishing a whitepaper on Best Practices for Energy Efficiency in Microsoft Data Center Operations and I finally tracked down the paper, and a cool video.

The 10 best practices are below and can be found on the Microsoft Environment site too.

  1. Engineer the data center for cost and energy efficiency.
  2. Optimize the design to assess multiple factors.
  3. Optimize provisioning for maximum efficiency and productivity.
  4. Monitor and control data center performance in real time.
  5. Make data center operational excellence part of organizational culture.
  6. Measure power usage effectiveness (PUE).
  7. Use temperature control and airflow distribution.
  8. Eliminate the mixing of hot and cold air.
  9. Use effective air-side or water-side economizers.
  10. Share and learn from industry partners.