ABSTRACT
As the number of World Wide Web users grows, so does the number of connections made to servers. This increases both network load and server load. Caching can reduce both loads by migrating copies of server files closer to the clients that use those files. Caching can either be done at a client or in the network (by a proxy server or gateway). We assess the potential of proxy servers to cache documents retrieved with the HTTP, GOPHER, FTP, and WAIS protocols using World Wide Web browsers. We monitored traffic corresponding to three types of educational workloads over a one-semester period, and used this as input to a cache simulation. Our main findings are (1) that with our workloads a proxy has a 30--50% maximum possible hit rate no matter how it is designed; (2) that when the cache is full and a document is replaced, classic least recently used (LRU) is a poor policy, but simple variations can dramatically improve hit rate and reduce cache size; (3) that a proxy server really functions as a second-level cache, and its hit rate may tend to decline with time after initial loading, given a more or less constant set of users; and (4) that certain modifications to proxy-server configuration parameters for a cache may have little benefit.
- M. Abrams, S. Williams, G. Abdulla, S. Patel, R. Ribler, E. A. Fox, "Multimedia Traffic Analysis Using Chitra95," to appear in ACM Multimedia 95, San Francisco, Nov. 1995; URL http://www.cs.vt.edu/~chitra/docs/95multimediaAWAFPR/95multimediaAWAFPR.html.Google Scholar
- K. Andrews, F. Kappe, H. Maurer, K. Schmaranz, "On Second Generation Network Hypermedia Systems," Proc. ED-MEDIA 95, World Conference on Educational Multimedia and Hypermedia, Graz, Austria, June 17--21, 1995.Google Scholar
- H. Braun and K. Claffy, "Web Traffic Characterization: An Assessment of the Impact of Caching Documents from NCSA's Web Server," Proc. 2nd Int. WWW Conference, Chicago, Oct. 1994; URL http://www.ncsa.uiuc.edu/SDG/IT94/Proceedings/DDay/claffy/main.htmlGoogle Scholar
- S. Glassman, "A Caching Relay for the World Wide Web," In First International World Wide Web Conference, pages 69--76, May 1994; also appeared in Computer Networks and ISDN Systems 27, No. 2, 1994; URL http://www1.cern.ch/PapersWWW94/steveg.ps/Google Scholar
- T.T. Kwan, R.E. McGrath, and D.A. Reed, "User Access Patterns to NCSA's World Wide Web Server," NCSA and University of Illinois Computer Science Technical Report, 1994.Google Scholar
- A. Luotonen, Configuration File of CERN httpd, 1994; URL http://www.w3.org/hypertext/WWW/Daemon/User/Config/Overview.htmlGoogle Scholar
- A. Luotonen and K. Altis, "World Wide Web Proxies", 1st Inter. Conf. on the WWW, Geneva, May 1994; also appeared in Computer Networks and ISDN Systems 27, No. 2, 1994; URL http://www1.cern.ch/PapersWWW94/luotonen.psGoogle ScholarDigital Library
- J. E. Pitkow and M. M. Recker, "A Simple Yet Robust Caching Algorithm Based on Dynamic Access Patterns," in Proc. 2nd Int. WWW Conf., 1994; URL ftp://ftp.gvu.gatech.edu/pub/gvu/techreports/94-39.ps.ZGoogle Scholar
- Pritsker, A. A. B., Introduction to Simulation and SLAM II, 3rd ed., Halsted, New York, 1987.Google Scholar
- M. M. Recker and J. Pitkow, Predicting Document Access in Large, Multimedia Repositories, Graphics, Visualization, and Usability Center Tech. Rep. VU-GIT-94-39, Georgia Tech, August, 1994; URL ftp://ftp.gvu.gatech.edu/pub/gvu/tech-reports/94-35a.ps.Z and 94-35b.ps.ZGoogle Scholar
- N.Smith, What Can Archives Offer the World-Wide Web, University of Kent at Canterbury, 22 March 1994.Google ScholarCross Ref
- A. S. Tanenbaum, Modern Operating Systems, Prentice-Hall, 1992, pp. 111--112.Google Scholar
Index Terms
- Caching Proxies: Limitations and Potentials
Recommendations
Pass down class-LRU caching algorithm for WWW proxies
ICN'05: Proceedings of the 4th international conference on Networking - Volume Part ICaching has been recognized as one of the most important techniques to reduce Internet bandwidth consumption caused by the tremendous growth of the WWW. Class-based LRU (C-LRU) delivers better results for the hit rate than most of the existing ...
Integrating Web Caching and Web Prefetching in Client-Side Proxies
Web caching and Web prefetching are two important techniques used to reduce the noticeable response time perceived by users. Note that by integrating Web caching and Web prefetching, these two techniques can complement each other since the Web caching ...
Comments