What features does a server absolutely positively have to have to be a candidate for a big cloud data center? What features would put it ahead of other servers in the eyes of the manager writing the checks for that cloud computing data center?
There’s an interesting article out about how Rackable Systems (and presumably others) are building machines inpsired by Google that answer those questions better than ever before. We’re talking about features like heat-resistant processors, motherboards that contain 2 servers, and that only need one power supply voltage instead of 2 or 3.
One thing the cloud does, is it will force standardization and penny shaving at the hardware (and software) end. When Amazon, Google, or one of the others is building a big cloud data center, they want utility-grade computing. It has to be dense on MIPS value, meaning it is really compact and cheap for the amount of cpu power delivered. Designs that add 25% to the cost to deliver an extra 10% in power won’t cut it. The Cloud will be too concerned about simply delivering more cores and enough memory, disk, and network speed to keep them happy. Closing a deal to build standard hardware for a big cloud vendor will be hugely valuable, and in fact, Rackable started out life building systems for Google.
It’s going to be interesting to watch the Cloud Server market evolve. Reading these articles reminds me of Southwest Airlines, which dramatically improved its cost savings by standardizing on just one kind of airplane, the 737. Not only did that one-size-fit-all for Southwest, but it made their maintenance costs dramatically lower becaues they can standardize on spare parts for one aircraft, mechanics trained on one, and so on.
Cool beans!
Related Articles
James Urquhart, one of the top cloud bloggers, has given us mention in his related post. There’s some further great analysis from James as well, so check him out!