Advertisement

Abstract

Mirroring-based reliability as compared to parity-based reliability significantly simplifies the design and the implementation of video servers, since in case of failure mirroring does not require any synchronization of reads or decoding to reconstruct the lost video data. While mirroring doubles the amount of storage volume required, the steep decrease of the cost of magnetic disk storage makes it more and more attractive as a reliability mechanism. We present in this paper a novel data layout strategy for replicated data on a video server. In contrast to classical replica placement schemes that store original and replicated data separately, our approach stores replicated data adjacent to original data and thus does not require additional seek overhead when operating with disk failure. We show that our approach considerably improves the server performance compared to classical replica placement schemes such as the interleaved declustering scheme and the scheme used by the Microsoft Tiger video server. Our performance metric is the maximum number of users that a video server can simultaneously support (server throughput).

Keywords

Video Servers Data Replication Performance Analysis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    A. Mourad, “Doubly-striped disk mirroring: Reliable storage for video servers,” Multimedia, Tools and Applications, vol. 2, pp. 253–272, May 1996.Google Scholar
  2. 2.
    W. Bolosky et al., “The tiger video fileserver,” in 6th Workshop on Network and Operating System Support for Digital Audio and Video, (Zushi, Japan), Apr. 1996.Google Scholar
  3. 3.
    W. Bolosky, R. F. Fritzgerald, and J. R. Douceur, “Distributed schedule management in the tiger video server,” in Proc. Symp. on Operating System Principles, pp. 212–223, Oct. 1997.Google Scholar
  4. 4.
    D. A. Patterson, G. Gibson, and R. H. Katz, “A Case for Redundant Arrays of Inexpensive Disks (RAID),” in Proceedings of the 1988 ACM Conference on Management of Data (SIGMOD), (Chicago, IL), pp. 109–116, June 1988.Google Scholar
  5. 5.
    F. A. Tobagi, J. Pang, R. Baird, and M. Gang, “Streaming raid(tm) — a disk array management system for video files,” in Proceedings of the 1st ACM International Conference on Multimedia, (Anaheim, CA), August 1993.Google Scholar
  6. 6.
    S. Berson, L. Golubchik, and R. R. Muntz, “Fault tolerant design of multimedia servers,” in Proceedings of SIGMOD’95, (San Jose, CA), pp. 364–375, May 1995.Google Scholar
  7. 7.
    S. Ghandeharizadeh and H. K. Seon, “Striping in multi-disk video servers,” in Proceedings in the SPIE International Symposium on Photonics Technologies and Systems for Voice, Video, and Data Communications, 1995.Google Scholar
  8. 8.
    J. Gafsi and E. W. Biersack, “Data striping and reliablity aspects in distributed video servers,” In Cluster Computing: Networks, Software Tools, and Applications, February 1999.Google Scholar
  9. 9.
    B. Ozden et al., “Fault-tolerant architectures for continuous media servers,” in SIGMOD International Conference on Management of Data 96, pp. 79–90, June 1996.Google Scholar
  10. 10.
    B. Ozden et al., “Disk striping in video server environments,” in Proc. of the IEEE Conf. on Multimedia Systems, (Hiroshima, Japan), pp. 580–589, jun 1996.Google Scholar
  11. 11.
    R. Tewari, D. M. Dias, W. Kish, and H. Vin, “Design and performance tradeoffs in clustered video servers,” in Proceedings IEEE International Conference on Multimedia Computing and Systems (ICMCS’96), (Hiroshima), pp. 144–150, June 1996.Google Scholar
  12. 12.
    S. A. Barnett, G. J. Anido, and P. Beadle, “Predictive call admission control for a disk array based video server,” in Proceedings in Multimedia Computing and Networking, (San Jose, California, USA), pp. 240, 251, February 1997.Google Scholar
  13. 13.
    H. I. Hsiao and D. J. DeWitt, “Chained declustering: A new availability strategy for multiprocessor database machines.,” in In Proceedings of the Int. Conference of Data Engeneering (ICDE), 1990, pp. 456–465, 1990.Google Scholar
  14. 14.
    L. Golubchik, J. C. Lui, and R. R. Muntz, “Chained declustering: Load balancing and robustness to skew and failures,” in In Proceedings of the Second International Workshop on Research Issues in Data Engineering: Transaction and Query Processing, Tempe, Arizona, (Tempe, Arizona), pp. 88–95, February 1992.Google Scholar
  15. 15.
    J. L. Hennessy and D. A. Patterson, Computer Arcitecture A Quantative Approach. Morgan Kaufmann Publishers, Inc., 1990.Google Scholar
  16. 16.
  17. 17.
    C. Ruemmler and J. Wilkes, “An introduction to disk drive modeling,” IEEE Computer, vol. 27, pp. 17–28, Mar. 1994.Google Scholar
  18. 18.
    B. L. Worthington, G. Ganger, Y. N. Patt, and J. Wilkes, “On-line extraction of scis drive characteristics,” in Proc. 1995 ACM SIGMETRICS, (Ottawa, Canada), pp. 146–156, May 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Jamel Gafsi
    • 1
  • Ernst W. Biersack
    • 1
  1. 1.Institut EURECOMSophia Antipolis CedexFrance

Personalised recommendations