A Study of Parallel Prefetching Algorithms Using Trace-Driven Simulation

I/O for parallel and distributed systems has drawn increasing attention over the past decade as it has become apparent that I/O performance, rather than CPU performance, may be the key limiting factor in the performance of future systems. Prefetch is the fundamental approach for improving the overall read performance. In this paper, we study three parallel prefetching algorithms-LRU-Lookahead, Fixed Horizon, and Greedy algorithmin, and explore the performance characteristics of each of the algorithms using the trace-driven simulation.