摘要
在分布式存储中,由于网络与存储节点的不稳定性,会导致文件存储过程失败。通过对文件进行适当的分割存储可以提高文件存储过程成功的概率。建立了网络存储节点可用性概率模型和文件块网络存储成功的概率模型,给出了文件分割存储策略,比较了在不同分割粒度下文件网络存储成功的概率,提出了分布式存储中文件分割的最优化模型,通过该模型可计算出大小为X的文件进行分布式存储时最优的分割块数。该模型对大文件的分布式存储具有一定的参考价值。
In the distributed storage environment,network and storage nodes are unstable,which may lead to failure of the storage process.The probability of a success file uploading/downloading can be improved by the rational partition of the file .The probability model of the storage node availability and the success file block storage process were established.The store-after-partition strategy was proposed,and the probabilities of a success file storage process at different partition granularities were compared to finally put forward the optimization model of file partition in distributed storage environment. This model can find the most suitable partition copy for the file＇s distributed storage at the size of X,and it is valuable for distributed storage of massive files.
出处
《解放军理工大学学报（自然科学版）》
EI
北大核心
2010年第4期413-416,共4页
Journal of PLA University of Science and Technology(Natural Science Edition)
基金
国家863计划资助项目(2008AA01A309)
国家自然科学基金资助项目(60603029)
关键词
分布式存储
存储节点可用性
文件分割
最优化分割
distributed storage
storage node availability
file partition
optimizing file partition
