Abstract: A method of data management for efficiently storing and retrieving data in response to user access requests. The method includes receiving a request from at least one client for a title not resident in a storage server, where the title includes a play track having a plurality of chapters. The retrieval from a secondary storage device of play track portions proximate chapter delineation points is initiated, and bandwidth capacity and quality-of-service (QoS) parameters associated with the secondary storage device is determined. In the case of a client request to begin presentation of the title at one of the chapters, streaming of retrieved portions of the play track chapter to the client is initiated, masking latency associated with the secondary storage device is provided, and retrieval of at least unretrieved portions of the play track chapter and subsequent play track portions from the secondary storage device is initiated.

Abstract: A storage server for efficiently retrieving data from a plurality of disks in response to user access requests. The server comprises a plurality of processors coupled to disjoint subsets of disks, and a custom non-blocking packet switch for routing data from the processors to users. By tightly coupling the processors to disks and employing an application-specific switch, congestion and disk scheduling bottlenecks are minimized. By making efficient use of bandwidth, the architecture is also capable of receiving real-time data streams from a remote source and distributing these data streams to requesting users. The architecture is particularly well suited to video-on-demand systems in which a video server stores a library of movies and users submit requests to view particular movies.