Robert X. Cringely has an interesting theory about why Google has been buying all that dark fibre everyone says it has been acquiring: to take over the Internet — but in a good way.
“The probable answer lies in one of Google’s underground parking garages in Mountain View,” he says. “There, in a secret area off-limits even to regular GoogleFolk, is a shipping container. But it isn’t just any shipping container. This shipping container is a prototype data center. Google hired a pair of very bright industrial designers to figure out how to cram the greatest number of CPUs, the most storage, memory and power support into a 20- or 40-foot box. We’re talking about 5000 Opteron processors and 3.5 petabytes of disk storage that can be dropped-off overnight by a tractor-trailer rig. The idea is to plant one of these puppies anywhere Google owns access to fiber, basically turning the entire Internet into a giant processing and storage grid.”
This idea makes a lot of sense. Google’s specialty consists of taking vast amounts of data and analyzing, collating, searching, sorting and displaying it. It does all this with in excess of 60,000 or so servers running as a giant distributed computer. So why not distribute nodes to where the they can jack right into the high-speed backbone of the Internet? That makes running things such as a Google distributed Office suite — or any other feature, service or application Google feels like providing — both easier and faster. Cringley figures the company could do it for about $1-billion. Considering the company is worth about $110-billion or so at the moment, and has $7.5-billion in cash, that shouldn’t be very tough.
Dan Dodge points to Cringley’s take as well, as does Michael Parekh.