Google spotlights data center inner workings

CNET brings us this story that peels back the curtain on Google’s secretive datacenters:
“Google doesn’t reveal exactly how many servers it has, but I’d estimate it’s easily in the hundreds of thousands. It puts 40 servers in each rack, Dean said, and by one reckoning, Google has 36 data centers across the globe. With 150 racks per data center, that would mean Google has more than 200,000 servers, and I’d guess it’s far beyond that and growing every day.” Full Story


About Rich
FlexRex began his life as a cartoon character I created a Sun Microsystems. As the world's first "fictional blogger," he appeared in numerous parody films that made fun of the whole work-from-home thing. Somewhere along the line, the Sun IT department adopted FlexRex as their spokesman in a half-dozen security awareness films for employees. So when I left Sun recently, I started FlexRex Communications, a Marketing company in Portland, Oregon.

One Response to Google spotlights data center inner workings

  1. Sean Donovan says:

    There’s a fascination with Google’s server installations.
    The problem, is that Google’s server arrangement only lends itself to certain application types. I find it very hard to believe that you could reuse the infrastructure for computational type applications, without hugely affecting the current run-time dynamic of the system. To that extent, and excepting the applications it’s **good** at, but how is this good for anything else (such as heavy computation?).
    Even if you go ‘cloud’, the framework required would be stunningly complex. Also, for computational apps you’d need C/C++ (or at a VERY minimum Java). Such vendor’s (Google, Microsoft, etc) are unlikely to support these — as it could destroy the efficiency of the design. Though, it will be interesting to see if/how MS supports .NET.
    How can models such as Google’s become general purpose? It strikes me (and I’m not zealot here) that Sun’s Compute Grid seems a more practical arrangement.
    What is interesting, is having to think about how you’d package data + handle results for cloud execution.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: