中文摘要：

结合虚拟节点技术和均分存储区域技术,提出了嵌套循环式数据一致性哈希优化分布式集群存储的多副本放置策略.按照此优化策略,能够有序选择数据副本机架,确定数据节点存储位置,保证数据存储的均衡性分布,可以针对集群的实际要求开展扩展,并按照扩展情况制定使数据存储完成自适应优化调整,加快数据处理的速度.有效实验表明存储优化后算例的执行速度得到很大提升,能够保证解决负载均衡问题;而针对实际情况中可能出现的扩展与删减问题进行测试后表明,使用优化存储策略处理此类问题时,振荡对整体负载均衡影响不大,且执行时间与负载占比变化趋势一致.

英文摘要：

We present a consistent Hash data-optimized multiple-copy distributed clustered storage placement strategy using technology to determine the storage location and rack selection to ensure a balanced distribution of data storage. The new strategy is able to complete the expansion according to the actual requirement of the clusters, and to complete the development of adaptive optimization based on the expansion, thus accelerating the speed of data processing. Experiments show that the execution speed has been effectively improved, ensuring the load balance. Extensions and reducing problems are situations possible to occur in real circumstances. The new strategy is utilized and tested in these situations. The results show that the oscillation has little impact on the load balancing, and the execution time is consistent with the proportion of the load trends as well.