Once datasets grow into the petabyte realm, a whole new level of availability, management, and protection challenges arise. At this magnitude, given the law of large numbers with the sheer quantity of components involved, one or more components will almost always be in a degraded state at any one time within the storage infrastructure. As such, guarding against single points of failure and bottlenecks becomes a critical and highly complex issue. Other challenges that quickly become apparent at the petabyte scale include the following:

• File System Limitations: How much capacity and how many files can a file system accommodate?
• Disaster Recovery: How do you duplicate the data off site and then how do you retrieve it?
• Scalability of Tools: How do you take snapshots of massive datasets?
• Software Upgrades and Hardware Refresh: How do you upgrade software and replace outdated hardware with new?
• Performance Issues: How long will searches and tree-walks take with large, complex datasets?
• Backup and Restore: How do you back up a large dataset and how long will it take to restore?

Given these challenges, the requirement for a new approach to file storage is clear. Fortunately, when done correctly, scale-out NAS can fulfill this need.