私有云下基于相似度聚类的重删算法研究

发布时间：2018-04-05 15:16

本文选题：私有云　切入点：主存储　出处：《微电子学与计算机》2017年09期

【摘要】：随着虚拟化技术的日趋成熟与发展,越来越多的企业采用私有云平台来替代传统PC办公.然而,虚拟磁盘数据的高度重复与超大容量导致了存储空间与系统能耗的巨大浪费.为解决这一问题,首先提出了基于特征标签粗归类算法,将重删操作分散到云平台计算结点,有效地避免了传统重删算法的性能瓶颈;然后,提出了基于指纹ID相似度聚类算法,提高了各计算结点上的重删率;最后,通过实验对两种子算法进行分析,并验证了其有效性.
[Abstract]:With the development of virtualization technology, more and more enterprises use private cloud platform to replace traditional PC office.However, the high repetition and large capacity of virtual disk data lead to a huge waste of storage space and system energy consumption.In order to solve this problem, a rough categorization algorithm based on feature tags is proposed to disperse the redelete operations to cloud platform computing nodes, which effectively avoids the performance bottleneck of traditional redelete algorithms.A fingerprint ID similarity clustering algorithm is proposed to improve the rescheduling rate on each computing node. Finally, the two algorithms are analyzed through experiments, and the validity of the algorithm is verified.
【作者单位】：电子科技大学电子科学技术研究院;
【分类号】：TP333

【相似文献】