Adaptive Caching Management for Multimedia Suppor

  • Frederic Andres
  • Kinji Ono
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1677)

Abstract

The Active HYpermedia Delivery System (AHYDS) within the NACSIS R&D department is an experimental advanced platform developed for delivering hypermedia documents over distributed and heterogeneous systems. The evolution of the network technology and the requirements of multimedia applications suggest that hypermedia and multimedia delivery systems need to be improved in terms of media caching to guarantee data delivery to a large scale of users and also to reduce information traffic within large scale multimedia information systems. Remote main-memory accesses require combining main memory access in a same LAN.

In this article, we address the main memory caching capabilities of the AHYDS platform used in a multi-server/multi-client architecture, to optimize the use of the uniform storage management of the underlying data structure. It provides a high performance support in terms of distributed and heterogeneous hypermedia management. We propose two cache algorithms: the “Temperature Adaptation Cache”, and the “States Adaptation Cache” for distributed information systems. Performance evaluations show that our proposal reduces the data access latency and increase the hit ratio of accessing data in main memory in a rate between 10 and 20%. The caching algorithms also eliminate the CPU overhead in a range of 50-95% maintaining a high hit ratio.

Keywords

Application Oriented Database Systems Caching Management Access Optimization Distributed Multimedia Systems 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1. [ABO96]
    Andres F., Boulos J., and Ono K. “Accessing Active Applicationoriented DBMS from the World Wide Web” in the Proceedings of the Intern. Symp. on COoperative DAtabase Systems for Advanced Applications (CODAS), Dec 1996, pp 232–234.Google Scholar
  2. 2. [AO97]
    Andres F., and Ono K. “Phasme Un Systeme parallele de Gestion de Bases de Donnees Oriente Application” F. Andres, K. Ono, in the French Journal Calculateurs Paralleles Edition speciale BD paralleles et distribuees, 1997.Google Scholar
  3. 3. [AO98]
    Andres F., and Ono K. “The Active HYpermedia Delivery System”, in the Proceedings of ICDE98, Orlando, USA, 1998, pp 600.Google Scholar
  4. 4. [AO99]
    Andres F., and Ono K. “Caching Management in the AHYDS platform: optimisation and tuning”, NACSIS, Technical report 99/1, March 1999.Google Scholar
  5. 5. [BMK99]
    Boncz P., Manegold S., and Kersten M. “Database Architecture Optimized for the new Bottleneck: Memory Access”, to appear in Proceeding of the 25th VLDB Conference, Edinburg, Scotland, 1999.Google Scholar
  6. 6. [CALM97]
    Castro M., Adya A., Liskov B., and Myers A.C. “HAC: Hybrid Adaptive Caching for distributed Storage Systems” in The Proceedings of the ACM Symposium on Operating System Principles (SOSP’97), Saint Malo, France, October 1997.Google Scholar
  7. 7. [CG97]
    Chang E., and Garcia-Molina H. “Effective Memory Use in a Media Server” in Proceedings of the 23rd VLDB Conference, Athens, Greece, 1997, pp 496–505.Google Scholar
  8. 8. [CI97]
    Cao P., and Irani S. “Costáware WWW Proxy Caching Algorithms” in The Proceedings of the 1997 USENIX Symposium on the Internet Technology and Systems, Dec 1997, pp 193–206.Google Scholar
  9. 9. [FCAB98]
    Fan L., Cao P., Almeida J., and Broder A. Z. “Summary Cache: A Scalable Wide-Area Web Cache Sharing Protocol” in SIGCOMM’98, 1998.Google Scholar
  10. 10. [JAC95]
    Van Jacobson “How to kill the internet”, in SIGCOMM’95 Middleware workshop, August 1995, ftp://ftp.ee.lhl.gov/talks/vj-webflame.ps.Z.
  11. 11. [LC97]
    Liu C., and Cao P. “Maintaining Strong Cache Consistency in the World Wide Web”, in The Proceedings of ICDCS’97, May 1997, pp 12–21.Google Scholar
  12. 12. [QUA99]
    Quantify 4.2, Rational Software, http://www.rational.com/products/quantify.
  13. 13. [SRB97]
    Stathatos K., Roussopoulos N., Baras J. S. “Adaptive Data Broadcast in Hybrid Networks”, in Proceedings of the 23rd VLDB Conference, Athens, Greece, 1997, pp 326–335.Google Scholar
  14. 14. [VNL95]
    Venkataraman S., Livny M., Naughton J., “The Impact of Data Placement on Memory Management for Multi-Server OODBMS”, International ICDE, 1995, pp 355–364.Google Scholar
  15. 15. [VNL98]
    Venkataraman S., Naughton J.F., Livny M. “Remote Load Sensitive Caching for Multi-Server Database Systems”, in Proceedings of the ICDE, Florida, USA, 1998, pp 514–521.Google Scholar
  16. 16. [VR97]
    Verghese B., and Rosenblum M. “Remote Memory Access in Workstation Clusters”, Technical Report CSL-TR-97-729, Computer Systems Laboratory, Stanford University, Stanford, CA, July 1997.Google Scholar
  17. 17. [WPB98]
    Wisconsin Proxy Benchmark 1.0, http://www.cs.wisc.edu/∼cao/wpb1.0.html
  18. 18. [ZFJ97]
    Zhang L., Floyd S., and Jacobson V. “Adaptive Web Caching” in The Proceedings of the 2nd Boulder Cache Workshop’97, Colorado, June 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Frederic Andres
    • 1
  • Kinji Ono
    • 1
  1. 1.R&D DepartmentNational Center for Science Information SystemsBunkyo-ku, TokyoJapan

Personalised recommendations