块备份数据多版本融合方法  

Multi-version consolidation method for block-level backup data

作　　者：王树鹏[1,2] 吴广君[1] 吴志刚[3] 云晓春[1] 

机构地区：[1]中国科学院计算技术研究所,北京100190 [2]灾备技术国家工程实验室,北京100876 [3]北京邮电大学网络技术研究院,北京100876

出　　处：《通信学报》2011年第12期114-121,共8页Journal on Communications

基　　金：国家自然科学基金资助项目(61003260;61003261);国家高技术研究发展计划("863"计划)基金资助项目(2009AA01A403;2007AA010501;2007AA01Z467;2007AA01Z474)~~

摘　　要：在多版本备份数据存储系统中,版本链的长度直接影响着历史版本的检索效率。针对该问题提出了一种块备份数据多版本融合方法,通过增量备份数据版本序列之间的融合产生任意时间点的全量快照备份数据。理论分析表明:该方法可以有效提高版本链中目标版本的检索效率。进一步根据块备份数据的分布特点,提出变长数据块版本融合算法,降低快照版本融合的计算复杂度。最后给出了版本融合技术在多版本备份数据管理中的具体应用和性能分析。模拟实验结果表明:使用版本融合技术在相同版本链长度下,可以大量减少冗余版本备份数据量,有效提高多版本条件下全量数据的恢复效率。Historical version backup data query efficiency was dependent on the version chain length in a multi-version backup data storage system. A novel block-level backup data multi-version consolidation method was presented for this problem. Any version of a historical full system snapshot could be generated within the incremental backup data version sequence. Theoretical analysis showed that it could increase the target snapshot version query efficiency significantly in the version chain. A variable-length block version merging algorithm was presented to decrease the computing complexity in the process of snapshot version merging, according to the block-level backup data distribution features. Finally, the concrete applications and performance analysis for block-level version consolidation method was also introduced. The simulated experiments results expose that the version consolidation method can eliminate redundant version of backup data with the same version chain length, and it can increase full system recovery efficiency than traditional methods significantly.

关 键 词：版本融合 块备份数据 容灾备份 数据存储 快照 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]