双容错数据布局算法DP-RAID扩展研究  

Research on Double-Error Tolerance Data Placement Scheme DP-RAID

作　　者：刘卫平[1] 蔡皖东[1] 任建奇[1] 

机构地区：[1]西北工业大学计算机学院,西安710072

出　　处：《计算机科学》2006年第4期122-125,共4页Computer Science

基　　金：航空基础科学基金项目(项目号:03F53031);西安市工业攻关项目(项目号:GG200312)的资助

摘　　要：基于单容错编码的数据布局已经不能满足存储系统对可靠性越来越高的要求。对基于多容错编码的数据布局的研究受到了广泛的关注,并且出现了一些多容错的布局算法,如多维 Parity,DH1,DH2等。但这些布局算法普遍存在冗余度较差、计算负载大等缺点。DP-RAID 是一种基于水平方向和对角方向双重奇偶校验的双容错数据布局算法。该布局计算负载小,实现简单,但该布局要求校验条纹长度为素数。本文对 DP-RAID 进行扩展,使其能够应用于校验条纹长度为素数减一的环境。与其他双容错布局算法比较表明,该布局算法在保证同样可靠性的情况下,性能有了明显的提高。As the data placement scheme based on single-erasure correcting codes can not satisfy the requirement of storage system on reliability. Now there are more and more researches on the data placement scheme based on multi-erasure correcting codes such as multi-dimension parity, DH1, DH2. But these data placement schemes have some disadvantages such as poor redundancy, heavy computing scheme based on horizontal parity and diagonal parity. workload. DP-RAID is a double error tolerating data placement Its computing load is low, and easy to implement. But it requires that the length of parity stripe is prime number. This paper extends the data placement scheme to the environment that the length of parity stripe is prime number minus 1. The performance of the new data placement scheme improves obviously and reliability of the new data placement scheme doesn＇t change, comparing with other double-error tolerance data placement scheme.

关 键 词：RAID35 奇偶校验 双容错编码 可靠性 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论] TN929.533[自动化与计算机技术—计算机科学与技术]