Cache na WWW: Limitações e Potencial
Resumo
WWW caching systems are essential for Web performance and scalability. Web cache workloads and goals show important differences when compared with traditional caching systems, such as memory caches. This article points out and discusses these differences. In order to illustrate our discussion, we present characterization of ten workloads from Web caches. The analysis focuses on the parameters response size and access patterns. We discuss the influence of the characterized parameters in cache performance according to relevant metrics for the WWW and we show directions for the design of Web cache replacement policies.
Palavras-chave:
WWW, Caching, Internet performance
Referências
Esoterica. "http://www.esoterica.pt", 1998.
Martin F. Arlitt and Carey L. Williamson. Web Server Workload Characterization: The Search for Invariants. Proceedings of the 1996 ACM Sigmetrics Conference, pp 126-137, 1996.
Mark E. Crovella and Murad S. Taqqu. Estimating the Heavy Tail Index from Scaling Properties. Methodology and Computing in Applied Probability, V. 1, N. 1, 1999.
Mark E. Crovella, Murad S. Taqqu and Azer Bestravos. A Practical Guide to Heavy Tails. in Heavy-Tailed Probability Distributions in the World Wide Web, chapter 1, pp 3-26, Chapman & Hall, New York, 1998.
NLANR. "http://ircache.nlanr.net", 1999.
Paul Basford and Mark E. Crovella. Generating Representative Web Workloads for Network and Server Perfonnance Evaluation. Proceedings of Performance '98/ACM SIGMETRICS'98, pp. 151-160, 1998.
D. A. Patterson and J. L. Hennessy. Computer Arquitecture: A Quantitative Approach, 2nd Edition. Morgan Kaufmann Publishers, California, 1996.
POP-MG. Ponto de Presença da RNP em Minas Gerais. "http://www.po-mg.rnp.br/index.html", 1998.
Virgínia Tech. Traces from Virgínia Polytechnic Institute. "http://www.cs.vtech.edu", 1995.
Martin F. Arlitt and Carey L. Williamson. Web Server Workload Characterization: The Search for Invariants. Proceedings of the 1996 ACM Sigmetrics Conference, pp 126-137, 1996.
Mark E. Crovella and Murad S. Taqqu. Estimating the Heavy Tail Index from Scaling Properties. Methodology and Computing in Applied Probability, V. 1, N. 1, 1999.
Mark E. Crovella, Murad S. Taqqu and Azer Bestravos. A Practical Guide to Heavy Tails. in Heavy-Tailed Probability Distributions in the World Wide Web, chapter 1, pp 3-26, Chapman & Hall, New York, 1998.
NLANR. "http://ircache.nlanr.net", 1999.
Paul Basford and Mark E. Crovella. Generating Representative Web Workloads for Network and Server Perfonnance Evaluation. Proceedings of Performance '98/ACM SIGMETRICS'98, pp. 151-160, 1998.
D. A. Patterson and J. L. Hennessy. Computer Arquitecture: A Quantitative Approach, 2nd Edition. Morgan Kaufmann Publishers, California, 1996.
POP-MG. Ponto de Presença da RNP em Minas Gerais. "http://www.po-mg.rnp.br/index.html", 1998.
Virgínia Tech. Traces from Virgínia Polytechnic Institute. "http://www.cs.vtech.edu", 1995.
Publicado
29/09/1999
Como Citar
MURTA, Cristina Duarte; ALMEIDA, Virgílio A. F..
Cache na WWW: Limitações e Potencial. In: INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING (SBAC-PAD), 11. , 1999, Natal.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
1999
.
p. 313-318.
DOI: https://doi.org/10.5753/sbac-pad.1999.19806.
