MITHRIL: Mining Sporadic Associations for Cache Prefetching

TL;DR

MITHRIL is a cache prefetching method that uses sporadic association rule mining to exploit historical request patterns, significantly improving cache hit ratios in cloud storage systems.

Contribution

MITHRIL introduces a novel prefetching layer based on sporadic association rules that efficiently leverages request timestamps, enhancing cache performance.

Findings

55% average hit ratio increase over LRU

36% gain over AMP in cache hit ratio

Effective in capturing mid-frequency blocks

Abstract

The growing pressure on cloud application scalability has accentuated storage performance as a critical bottle- neck. Although cache replacement algorithms have been extensively studied, cache prefetching - reducing latency by retrieving items before they are actually requested remains an underexplored area. Existing approaches to history-based prefetching, in particular, provide too few benefits for real systems for the resources they cost. We propose MITHRIL, a prefetching layer that efficiently exploits historical patterns in cache request associations. MITHRIL is inspired by sporadic association rule mining and only relies on the timestamps of requests. Through evaluation of 135 block-storage traces, we show that MITHRIL is effective, giving an average of a 55% hit ratio increase over LRU and PROBABILITY GRAPH, a 36% hit ratio gain over AMP at reasonable cost. We further show that MITHRIL can supplement any cache replacement algorithm and be readily integrated into existing systems. Furthermore, we demonstrate the improvement comes from MITHRIL being able to capture mid-frequency blocks.