The Internet Archive is moving into a Blackbox. Sun Microsystems says part of the digital archive of Internet pages, known as the Wayback Machine, will now be housed in a Sun MD data center container. More than two petabytes of data from the archive will be consolidated in a single 20-foot long shipping container, which will be on display when the system is unveiled next week at Sun’s Santa Clara campus.
The Internet Archive had previously developed its infrastructure in a custom enclosure known as the PetaBox, which can be packaged in a shipping container. The PetaBox, which has since been commercialized, has often been cited as an inspiration for data center containers to follow. That includes the oft-rumored but never-seen Google container as well as Sun’s container, which was launched in 2006 as Project Blackbox but now known as the Sun MD S20.
The Internet Archive will now move from the PetaBox filled with standard Linux servers into a Blackbox filled with Sun Fire X4500 “Thumper” storage units running Solaris 10, which will be able to support 500 requests per second.
The Internet Archive is a non-profit founded to build an Internet library to offer researchers, historians, and scholars permanent access to Internet content. Today the Archive also records content from TV channels worldwide, as well as movies, music, and books, all with storage requirements that are growing exponentially. You can read more about the Internet Archive and its work.
Image of Internet Archive infrastructure by MysteryBee.