重复数据删除存储系统的可靠性关键技术研究

重复数据删除技术已被应用于备份存储系统和闪存存储系统中，但其对存储系统可靠性的影响仍是一个开放性的问题。本项目拟基于闪存存储系统，研究基于文件的内部校验冗余保护技术，既保护单个文件的所有数据块，也通过文件间迭代恢复技术进一步保护引用率高的关键数据块，解决重复数据删除技术对闪存存储系统可靠性影响，以基于重复数据删除技术的闪存存储系统的可靠性，进一步推动重复数据删除技术在闪存存储系统中的更广泛应用。

Data deduplication technology has been widely deployed in backup storage systems and flash-based storage systems. However, the impact of data deduplication on the reliability of flash-based storage systems is still an open problem. To address this issue, we propose a per-file-based scheme which provides parity redundancy protection for all files and higher-level protection for data chunks with high reference counts, thus alleviating the common reliability issues introduced by data deduplication. Based on the study, the reliability of deduplication-based flash storage systems is improved, thus further promoting the applications of data deduplication in flash-based storage systems.