CFTL: An Adaptive Hybrid Flash Translation Layer with Efficient Caching Strategies

The Flash Translation Layer (FTL) is a software/hardware layer inside NAND flash memory that allows existing diskbased applications to use it without any significant modifications. Since FTL has a critical impact on the performance and reliability of the flash-based storage, a variety of FTL schemes have been proposed. The existing FTLs, however, are designed to perform well for either a read intensive workload or a write intensive workload, but not for both due to their internal address mapping schemes. To overcome this limitation, in this paper we propose a novel hybrid FTL scheme named Convertible Flash Translation Layer (CFTL). CFTL is adaptive to data access patterns with the help of our unique hot data identification algorithm. Thus, CFTL can dynamically switch its mapping scheme to either a page level mapping or a block level mapping in order to fully exploit the benefits of both schemes. By judiciously taking advantage of both schemes, CFTL resolves the intrinsic problems of the existing FTLs. In addition to this convertible scheme, we propose an efficient caching strategy and adaptive partitioning of mapping tables to further improve the CFTL performance. Consequently, both the convertible feature and the caching strategies empower CFTL to achieve good read performance as well as good write performance. Our experimental evaluation with a variety of realistic workloads demonstrates that CFTL outperforms other existing FTLs. In particular, our new caching strategy remarkably improves a cache hit ratio, by an average of 245%, and achieves much higher hit ratios, especially for randomly read intensive workloads.