A method of data management for efficiently storing and retrieving data in response to user access requests. The architecture comprises a plurality of disk drives over which data is distributed, and a plurality of processors, each of which is assigned to a subset of the disk drives in a modular fashion. The server architecture employs dynamic data management methods and load-balancing methods to assign user requests to processors. The modular server architecture, in combination with the dynamic data management and load balancing methods, provides both good performance (i.e., low expected-case access times and high disk bandwidth), and fault-tolerance. 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 programs.