ABSTRACT

In 2006, Kevin Kelly estimated that the whole of humanity’s existing published knowledge could be digitized onto a 50 petabyte disk. A single petabyte is an incredible amount of data, but far more remarkable than Kelly’s 2006 estimate is the rate of change since 2006. Two years later, a group of Google engineers published a white paper that showed that Google processed 20 petabytes of data a day (Dean & Ghemawat, 2008). Google is not the only company dealing with massive amounts of data: AT&T carries 16 petabytes of data and IP traffic a day, “the equivalent of a 2.5-megabyte music download for every man, woman and child on the planet” (AT&T, 2008).