摘要
在海量云存储系统中,提高存储利用率,降低冗余方案的计算复杂度是热点研究问题.分组校验纠删码冗余算法能够减少在数据重构时所需的纠删码片段,从而减少对存储网络带宽以及系统I/O的需求,降低存储系统的负载.介绍了分组校验纠删码的编码规则,参数设置,通过实验分析算法具有良好的容错能力与空间利用率,能够满足云存储系统需要的编解码性能.
In the massive cloud storage system,the hot research problem is to improve storage utilization and reduce the computation complexity of redundancy scheme.Redundancy algorithm of group parity erasure code can reduce the erasure code fragments required for data reconstruction,thereby decreasing the demand for storage network bandwidth and system I/O,and reducing the load of the storage system.Coding rules and parameter settings of group parity erasure code are described in this paper.Good fault tolerance and space utilization are verified through experimental analysis algorithm,meeting the codec performance required for cloud storage system.
引文
[1]罗亮,吴文峻,张飞.面向云计算数据中心的能耗建模方法[J].软件学报,2014,25(7):1371-1387.
[2]张松,杜庆伟.基于预测的云计算热点数据副本因子决策算法[J].计算机与现代化,2015(2):62-67.
[3]张乐.云计算环境下的分布存储关键技术研究[J].电子技术与工程,2015(23):185-189.
[4]L.Xu.and J.Bruck.X-code.MDS Array Codes with Optimal Encoding[J].IEEE Trans.on Information Theory.Jan,1999,45(1):272-276.