An evaluation of alternative disk scheduling techniques in support of variable bit rate continuous media
A number of recent studies have investigated scheduling techniques in support of variable bit rate (VBR) video. When compared with constant bit rate (CBR) video, VBR has a lower storage and bandwidth requirement while providing the same quality of images. However, a VBR video clip might exhibit a significant variance in the bit rate required to support its continuous display. The previous studies have proposed techniques to support the display of a VBR clip from two different perspectives: disk storage subsystem and the network. In this study, we propose a taxonomy of VBR disk scheduling techniques that includes those proposed for the network. The results demonstrate that a new class of disk scheduling techniques, termed Atomic — VR 2 VITAL, is superior. Algorithms used to represent this class were adopted from the networking literature.
KeywordsAverage Bandwidth Universal Object Simultaneous Display Client Buffer Startup Latency
Unable to display preview. Download preview PDF.
- 1.J. A. Al-Marri and S. Ghandeharizadeh. An evaluation of alternative disk scheduling techniques in support of variable bit rate continuous media. Technical Report USC-CS-TR98-666, USC, 1997.Google Scholar
- 2.E. Chang and A. Zakhor. Admissions control and data placement for vbr video servers. In Proceedings of the IEEE International Conference on Images Processing (ICIP), volume 1, pages 278–282, Austin, Texas, November 1994.Google Scholar
- 3.E. Chang and A. Zakhor. Variable bit rate mpeg video storage on parallel disk arrays. In First International Workshop on Community Networking Integrated Multimedia Services to the Home, pages 127–137, San Francisco, July 1994.Google Scholar
- 4.W. Feng. Rate-constrained bandwidth smoothing for the delivery of stored video. To appear in IS&T/SPIE Multimedia Networking and Computing, February 1997.Google Scholar
- 5.W. Feng, F. Jahanian, and S. Sechrest. Optimal buffering for the delivery of compressed prerecorded video. In Proceedings of the IASTED/ISMM International Conference on Networks, January 1995.Google Scholar
- 7.W. Feng and S. Sechrest. Smoothing and buffering for delivery of prerecorded compressed video. In Proceedings of the IS&T/SPIE Symposium on Multimedia Computing and Networking, pages 234–242, February 1995.Google Scholar
- 8.M. Grossglauser, S. Keshav, and D. Tse. Rcbr: A simple and efficient service for multiple time-scale traffic. In Proceedings of the ACM SIGCOMM, pages 219–230, August 1995.Google Scholar
- 9.E. W. Knightly, D. E. Wrege, J. Liebeherr, and H. Zhang. Fundamental limits and tradeoffs of providing deterministic guarantees to vbr video traffic. In Proceedings of the ACM SIGMETRICS, pages 98–107, May 1995.Google Scholar
- 10.J. M. McManus and K. W. Ross. Prerecorded vbr sources in atm networks: Piecewise-constant-rate transmission and transport. Submitted for publication, September 1995.Google Scholar
- 11.J. M. McManus and K. W. Ross. Video on demand over atm: Constant-rate transmission and transport. In Proceedings of IEEE INFOCOM, pages 1357–1362, March 1996.Google Scholar
- 12.G. Nerjes, P. Muth, and G. Weikum. Stochastic service guarantees for continuous data on multi-zone disks. In Proceedings of the 16th Symposium on Principles of Database Systems, Tucson, Arizona, May 1997.Google Scholar
- 13.J. D. Salehi, Z. L. Zhang, J. F. Kurose, and D. Towsley. Supporting stored video: Reducing rate variability and end-to-end resource requirements through optimal smoothing. In Proceedings of ACM SIGMETRICS, pages 222–231, May 1996.Google Scholar