An Analytical Approach to File Prefetching

File prefetching is an eeective technique for improving le access performance. In this paper, we present a le prefetching mechanism that is based on on-line analytic modeling of interesting system events and is transparent to higher levels. The mechanism, incorporated into a client's le cache manager, seeks to build semantic structures, called access trees, that capture the correlations between le accesses. It then heuristically uses these structures to represent distinct le usage patterns and exploits them to prefetch les from a le server. We show results of a simulation study and of a working implementation. Measurements suggest that our method can predict future le accesses with an accuracy around 90%, that it can reduce cache miss rate by up to 47% and application latency by up to 40%. Our method imposes little overhead, even under antagonistic circumstances.