Jonathan Schwartz weighed in on the future of the datacenter today, saying:
where’s computing headed? …into the real world, certainly.
Perhaps a more interesting question should be – why bother with datacenters at all? Surely it’s time we all started revisiting some basic assumptions…
Schwartz’s message is clear: the datacenter as we know it will die. That’s a pretty shocking prognostication to come from the lips of one of the founders of Sun Microsystems, a company whose bread and butter has always been the traditional datacenter. But of course there is little new in this prophecy. Many of us have been predicting the demise, or at least decline, of the datacenter for many years now. And it’s not hard to see why.
The center of gravity of computing has been moving away from centralization for several decades. Mainframes gave way to minicomputers. Minicomputers gave way to Personal Computers. Desktops proliferated. Portable computers such as the Palm, the iPod, dashboard GPS navigators, and cell phones clearly have an importance that increases every day.
And it’s not just the hardware. Software has followed a similar trend, from the gluing together of diverse electronic mail systems by sendmail to form what we now regard singly as email, to the creation of the Internet itself, to the incredible popularity and seeming indestructibility of today’s most used p2p filesharing applications. All of these decentralized computing resources provide an incredibly diverse and resilient platform for creating the next generation of software and services.
Will the datacenter as we know it today cease to exist in ten years? Probably not. But will important services continue to move to the edges of the network? Yes. Will decentralization be able to provide services at costs that blow datacenter solutions out of the water? Yes. Will these new applications provide a new level of reliabilty? Yes.