Workload Characterization in Web Caching Hierarchies

  • Authors:
  • G. Bai;C. Williamson

  • Affiliations:
  • -;-

  • Venue:
  • MASCOTS '02 Proceedings of the 10th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper uses trace-driven simulation and syntheticWeb workloads to study the request arrival process at eachlevel of a simple Web proxy caching hierarchy. The simulationresults show that a Web cache reduces both the peakand the mean request arrival rate for Web traffic workloads.However, the variability of the request arrival pro-cessmay either increase, decrease, or remain the same afterthe cache, depending on the input arrival process andthe configuration of the cache. If the input request arrivalprocess is self-similar, then the filtered request arrival processremains self-similar, though with reduced mean. Furthermore,the superposition of Web request streams frommultiple child caches results in a bursty aggregate requeststream. Finally, we find that a Gamma distribution providesa flexible means of modeling the request arrival count distributionin hierarchical Web caching architectures.