DCR^2S:分布式协作冗余复制存储机制  

DCR^2S: Distributed Cooperative Redundancy Replication Storage Mechanism

作　　者：周旭[1] 卢显良[1] 魏青松[1] 

机构地区：[1]电子科技大学计算机学院,成都610054

出　　处：《计算机科学》2004年第12期207-209,213,共4页Computer Science

基　　金：国家95重点攻关项目支持

摘　　要：文件复制和编码校验是分布式文件容错中常用的方法。结合两者的优点,本文提出了一种分布式协作冗余复制存储机制(DCR^2S)。DCR^2S通过XOR校验文件实现了分布在不同主机上的多个文件之间的相互协作。使得各个文件不仅可以通过复制冗余复本来提高自身的容错抗毁性能,并且可以通过检验文件协助其他文件提高容错性,既提高了单个文件的客错性能,更大大提高了一组文件的整体客错性能。本文对DCR^1S的原理进行了图论表述,给出了概率计算公式,定量地分析了DCR^2S的容错性能。通过计算比较,DCR^2S的容错性能远高于完全复制。File replication and coding are two common method used in fault-tolerance of distributed file systems. Combining the advantage of replication and coding, this paper presents a novel distributed cooperative redundancy replication storage mechanism (DCR^2S). By using XOR coding, DCR^2S makes a group of files which distributed among different hosts cooperative, so that not only a single file in the group can using XOR files to improve its own availability, but also the total availability of the whole group can be improved greatly. Under the graph theory description of DCR^2S, author gives a quantitative analysis to DCR^2S' performance. Comparing to complete replication method, DCR^2S has much higher fault-tolerance performance.

关 键 词：文件复制 分布式 冗余 复制 协作 存储 容错性能 DCR 抗毁性 编码 

分 类 号：TP316[自动化与计算机技术—计算机软件与理论] TN946[自动化与计算机技术—计算机科学与技术]