Exploiting Data Similarity to Improve SSD Read Performance

Abstract

Although NAND (Not And) flash-based Solid-State Drive (SSD) has recently demonstrated a significant performance advantage against hard disk, it still suffers from non-negligible performance under-utilization issues as the access conflict often occurs during servicing IO requests due to the share mechanism (e.g., several chips share one channel bus, several planes share one data register inside the die). Many research works have been devoted to minimizing access conflict by redesigning IO scheduling, cache replacement, and so on. These works have achieved reasonable results; however, the potential data similarity characterization is not utilized fully in prior works to alleviate access conflict. The basic idea is that, as data duplication is common in many workloads where data with the same content from different requests could be distributed to the address with minimized access conflict (i.e., the address does not share the same channel or chip), the logic address is mapped to more than one physical address. Therefore, the data can be read out from candidate pages when the channel or chip of its original address is busy. Motivated by this idea, we propose Data Similarity aware Flash Translation Layer (DS-FTL), which mainly includes a content-aware page allocation scheme and a multi-path read scheme. The DS-FTL enables maximization of the channel-level and chip-level parallelism and avoids the read stall induced by bus-shared mechanisms. We also conducted a series of experiments on SSDsim, with the subsequent results depicting the effectiveness of our scheme. Compared with the state-of-art, our scheme reduces read latency by 35.3% on average in our workloads.