An Effective RAID Data Layout for Object-Based De-duplication Backup System  

作　　者：YAN Fang TAN Yu'an ZHANG Quanxin WU Fei CHENG Zijing ZHENG Jun 

机构地区：[1]School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China [2]School of Information, Beijing Wuzi University, Beijing 101149, China [3]Beijing Engineering Research Center of Massive Language Information Processing and Cloud Computing Application, Beijing 100081, China [4]Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan 430074, China [5]Space Star Technology CO., Ltd, China Academy of Space Technology, Beijing 100086, China

出　　处：《Chinese Journal of Electronics》2016年第5期832-840,共9页电子学报（英文版）

基　　金：supported by the National High Technology Research and Development Program of China(No.2013AA01A212);National Natural Science Foundation of China(No.61272511,No.61370063,No.61300047,No.91438117,No.91538202);SRF for ROC,SEM,Open fund of China State Key Laboratory of Virtual Reality Technology and Systems(No.BUAA-VR-16KF-20);Beijing Intelligent Logistics System Collaborative Innovation Center

摘　　要：We propose an alternative Redundant array of independent disks(RAID) data layout, Asymmetrical grouping data organization(AGDO), for object-based data de-duplication backup system. Object-based data deduplication is an effective solution for detecting duplicate data for compound files. We designed an asymmetrical grouping strategy, the disk in the array are partitioned into different groups, and in each group parallelism data access scheme is adopted, different types of objects are stored in different groups with maybe different group size, it can set and manage dynamic group size by using dynamic disk group adjustment algorithms. The performance of AGDO is evaluated and proved to be sufficient for the continuous storage application. The result is that disk accesses are concentrated in a part of the disks over a long time period and reduces the power consumption to 25% in a 10-disk configuration. Moreover, object-based de-duplication combined with AGDO has great potential in increasing data restoration speed for compound files. We have shown that this combination makes average restoration speed improved 11%.We propose an alternative Redundant array of independent disks（RAID） data layout, Asymmetrical grouping data organization（AGDO）, for object-based data de-duplication backup system. Object-based data deduplication is an effective solution for detecting duplicate data for compound files. We designed an asymmetrical grouping strategy, the disk in the array are partitioned into different groups, and in each group parallelism data access scheme is adopted, different types of objects are stored in different groups with maybe different group size, it can set and manage dynamic group size by using dynamic disk group adjustment algorithms. The performance of AGDO is evaluated and proved to be sufficient for the continuous storage application. The result is that disk accesses are concentrated in a part of the disks over a long time period and reduces the power consumption to 25% in a 10-disk configuration. Moreover, object-based de-duplication combined with AGDO has great potential in increasing data restoration speed for compound files. We have shown that this combination makes average restoration speed improved 11%.

关 键 词：Data layout Object-based deduplication Backup Energy aware Redundant array of independent disks（RAID） 

分 类 号：TP309.3[自动化与计算机技术—计算机系统结构]