Approximate Models for General Cache Networks

Many systems employ caches to improve performance. While isolated caches have been studied in-depth, multi-cache systems are not well understood, especially in networks with arbitrary topologies. In order to gain insight into and manage these systems, a low-complexity algorithm for approximating their behavior is required. We propose a new algorithm, termed a-Net, that approximates the behavior of multi-cache networks by leveraging existing approximation algorithms for isolated LRU caches. We demonstrate the utility of a-Net using both per- cache and network-wide performance measures. We also perform factor analysis of the approximation error to identify system parameters that determine the precision of a-Net.

I. Introduction

Many systems employ caching as a means to reduce the load on access links and shorten access time to selected content. While the basic caching unit is a single cache, equipped with management policies, some systems make use of several caches linked together, allowing each cache to also forward requests to its neighbors when needed. Common examples of such systems are hierarchical web and file system caches. Recently [1] [2] [3], there have been proposals for multi-cache designs over networks of Internet-like scale and structure.