Is Building a Data Center on Your Bucket List? some items should be skipped

I was reading this NBCNews article on the foolish things people do to check off their bucket lists.

Bucket lists gone bad: When senior thrills become life threatening

7 hours ago

Laverne Everett's skydiving partner holds onto her after she fell out of her harness.
Laverne Everett's skydiving partner holds onto her after she fell out of her harness.

An 80-year-old woman on a tandem skydive slipped from her instructor’s harness then held on for life while rocketing toward Earth. An Alabama man busted his ankles trying to ride a bull. A Missouri man smashed his body – and his new motorcycle – minutes after buying the bike.

And it reminded me of a story I was telling of an IT executive I know who was convinced he needed to build a data center to support his company's move out of colocation spaces scattered around the world.  He was thrilled to build and when i told him he should go the route of three wholesale sites scattered around the US and Europe he said he had on good expensive advice from Gartner that he was doing the right thing.  Three years later, the data center is not operating yet,  he has changed companies. 

I found the public disclosure of the company finally breaking ground on a 10-15MW data center in Dec 2012.  If they had followed my advice, they would probably be on their fifth wholesale deployment by now with 25 MW of capacity and spent a fraction of the capital.  There were all kinds of people telling the executive building a data center is something he should do.  Now that he is at a new company and the strategy is cloud, hopefully the executives will keep him from continue to focus on his bucket list item of building a data center.  A high availability service needs at least 3 and ideally 5 locations.  Why 5?  Because at some point you'll have major maintenance events and going from 5 to 4 is much better than going from 3  to 2.