This resource is no longer available
The explosion of unstructured data and the advent of scale out NAS systems has caused backup of these systems to be an ever growing concern. This is of particular concern for customers using technical applications where the data is often generated with computer models or digital sensors of ever-increasing precision. Traditional NAS systems use a central server or "filer head" which must manage the user traffic as well as the backup traffic through a single choke point. The Panasas scale out NAS system uses distributed intelligence to break the “backup bottleneck” by delivering high throughput with many concurrent backup IO streams to standard backup applications. However, file system performance is just one aspect of implementing an effective backup and restore process. This white paper describes the overall strategy for backup and restore taking into account the tape subsystem, networking, file system workload and administrative policy.