In my last post I talked about how the Panasas parallel file system (PanFS) achieves extreme performance for big data sets. It also provides redundancy without the need for hardware RAID controllers. In the attached video, Garth Gibson, Panasas founder and CTO, digs deep into the specifics of file system RAID and how PanFS delivers redundancy as part of the file system itself. He compares this innovative approach to most other parallel file systems which push reliability down to the storage device layer, usually to hardware RAID controllers. Watch Garth as he explains the problems with the traditional RAID controller approach to redundancy, which include: cost and long reconstruction times, among other things. He concludes by talking about the various technologies essential to making reconstruction as parallel as are applications.