Reducing file system latency using a predictive approach

TLDR

Despite advances in file system throughput from high‑bandwidth networks and disk arrays, file system latency has not improved and remains a major bottleneck to operating system performance. The paper investigates an automated predictive approach to reduce file latency by pre‑providing data in advance to mask access delays. Automatic prefetching predicts future file system requests from past accesses, and the authors implemented a system to evaluate its performance. Trace‑driven simulation shows that prefetching can improve performance by up to 280% over LRU for small caches and reduce required cache size by up to 50%.

Abstract

Despite impressive advances in file system through put resulting from technologies such as high-bandwidth networks and disk arrays, file system latency has not improved and in many cases has become worse. Consequently, file system I/O remains one of the major bottlenecks to operating system performance [10]. This paper investigates an automated predictive approach towards reducing file latency. Automatic Prefetching uses past file accesses to predict future file systemrequests. The objective is to provide data in advance of the request for the data, effectively masking access latencies. We have designed and implement a system to measure the performance benefits of automatic prefetching. Our current results, obtained from a trace-driven simulation, show that prefetching results in as much as a 280% improvement over LRU especially for smaller caches. Alternatively, prefetching can reduce cache size by up to 50%.