Every since the revelation that US spooks are spying on the internet activities of citizens around the world, the attention has focused on a new government database being built in Utah.
The site is supposed to be the place which will house and process data collected from telephone and ISPs, satellites, fiber-optic cables and bugs
When it opens in September it is supposed to hold “yottabytes” of data, according to Wired or five “zettabytes” according to NPR, in other words more data than puny human brains are really able to comprehend.
But Forbes has got its paws on the blueprints of the data centre and is starting to work out that the actual storage capacity is comparatively low. It’s still pretty big.
After all the administration buildings, power sources and back-up generators are factored out, spooks have room for 100,000 square feet of servers. Impressive, but perhaps not enough room for a yottabyte of data.
Brewster Kahle is the engineering genius behind the Internet Archive, and Kahle estimates that a space of that size could hold 10,000 racks of about a billion dollars’ worth of servers.
Kahle thinks each rack would be capable of storing 1.2 petabytes of data. Kahle says that voice recordings of all the phone calls made in the US in a year would take up about 272 petabytes, or just over 200 of those 10,000 racks. This means that the facility can potentially hold up to 12,000 petabytes, or 12 exabytes.
Internet infrastructure expert Paul Vixie told Forbes that Kahle’s calculations were a little on the high side.
Assuming larger 13 square feet racks would be used, factoring in space between the racks, and assuming a lower amount of data storage per rack, he came up with an estimate of less than 3 exabytes of data capacity for the facility.
This would limit the US spying to 24-hour recordings of what every one of Philadelphia’s 1.5 million residents was up to for a year.
The defence from the US government is that it is only collecting metadata. But this data can tell you a lot about people and all of their social connections and habits, like who they talk to and where they go. While it may be technically unlikely that the NSA is storing every communication exactly, it can help the state decide who, when and where to target before zooming in on them through other back doors.
As the numbers are speculation, to put it into perspective, the Utah facility would still hold a lot of data. Google uses multiple data centres for a single exabyte of info.