HACache: Leveraging Read Performance with Cache in a Heterogeneous Array

TL;DR

HACache is a novel caching mechanism designed to improve read performance in heterogeneous SSD RAID arrays by dynamically balancing request distribution and cache quotas.

Contribution

It formalizes the request diversion problem and introduces a two-phase adjustment mechanism for optimal request routing in heterogeneous SSD environments.

Findings

HACache achieves approximately 35% bandwidth improvement in mixed SSD configurations.

The proposed method effectively balances request diversion to maximize bandwidth utilization.

Experimental results validate the effectiveness of HACache in heterogeneous RAID setups.

Abstract

In cost-sensitive deployments, RAID arrays may combine SSDs with different performance levels. Such heterogeneity arises when aging SSDs degrade yet remain usable, or when failed drives are replaced with new devices of explicitly better performance. While this reduces procurement cost, it creates performance challenges: traditional striping mecahnism distributes requests evenly, but slower SSDs become bottlenecks, leaving faster ones underutilized and limiting overall bandwidth to the slowest drive. To address this, we propose HACache (Heterogeneity Adaptive Cache) for read-intensive workloads. HACache introduces high-performance SSDs as read caches to rebalance request distribution. First, we formalize the request diversion problem and solve it formally. Second, to support optimal diversion ratios searching at runtime, HACache adopts a two-phase request diversion ratio adjustment mechanism. Finally, a cache capacity regulation is adopted to adapt quotas for each backend SSD based on hit rates and request diversion needs. This design maximizes bandwidth utilization. Experiments show HACache improves heterogeneous RAID read performance significantly, with bandwidth gains of about 35\% in typical mixed configurations.