"On Periodic Resource Scheduling for Continuous Media Databases"

by Minos N. Garofalakis, Banu Özden, and Avi Silberschatz.
Proceedings of IEEE RIDE'98, Orlando, Florida, February 1998, pp. 111-120.



Abstract

The Enhanced Pay-Per-View (EPPV) service model provides an effective way of delivering continuous media (CM) data clips to a large number of different clients. The aim is to share CM streams among various clients, thereby increasing the level of concurrency beyond the capacity limitations of available resources (e.g., disk bandwidth, RAM, and network bandwidth), while guaranteeing an upper bound on the clients' waiting time. In the EPPV service model, waiting time guarantees are provided by means of a regular playback schedule, where each continuous media clip is displayed periodically with a frequency that depends on factors such as the clip's popularity. Efficiency is achieved by sharing these periodic CM streams among multiple clients. The EPPV model offers a number of advantages over other schemes (e.g., batching), which makes it more attractive to large-scale service providers. The purpose of this paper is twofold: (1) to provide an overview of our recent results on the resource scheduling problems associated with supporting EPPV for continuous media clips with (possibly) different display rates, frequencies, and lengths; and, (2) to outline a number of open research problems related to the EPPV service model. A major contribution of our work is the introduction of a robust scheduling framework that, we believe, can provide solutions for a variety of realistic EPPV resource scheduling scenarios, as well as any scheduling problem involving regular, periodic use of a shared resource. Based on this framework, we propose various interesting research directions for extending the results presented in this paper.

[ paper (ps.gz) | journal version (in The VLDB Journal) ]


Copyright © 1998, IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.