Virtual I/O caching: Dynamic storage cache management for concurrent workloads

Abstract

A leading cause of reduced or unpredictable application performance in distributed systems is contention at the storage layer, where resources are multiplexed among many concurrent data intensive workloads. We target the shared storage cache, used to alleviate disk I/O bottlenecks, and propose a new caching paradigm to both improve performance and reduce memory requirements for HPC storage systems. We present the virtual I/O cache, a dynamic scheme to manage a limited storage cache resource. Application behavior and the corresponding performance of a chosen replacement policy are observed at run time, and a mechanism is designed to mitigate suboptimal behavior and increase cache efficiency. We further use the virtual I/O cache to isolate concurrent workloads and globally manage physical resource allocation towards system level performance objectives. We evaluate our scheme using twenty I/O intensive applications and benchmarks. Average hit rate gains over 17% were observed for isolated workloads, as well as cache size reductions near 80% for equivalent performance levels. Our largest concurrent workload achieved hit rate gains over 23%, and an over 80% iso-performance cache reduction.