Research on the Flash Translation Layer Based on Grouping Pages

Flash Translation Layer (FTL) is a key technology in a Solid-State Disk (SSD) system to manage the data transfer. Different mapping granularity in FTL will cause a change in the read/write performance and the size of mapping table. For the scenario that big capacity storage needs to hold high performance, on the basis of former mapping algorithms, this paper design a mapping method based on grouping pages granularity, and a SSD system architecture based on the parallelism of flash chip array. Besides, considering the features of the mapping method, we implement the corresponding wear-leveling algorithm and garbage collection algorithm. By computer simulation verifying, under four kinds of workload, the method proposed in this paper can decrease the size of mapping table and keep excellent read/write performance at the same time.