本文選題：私有云　切入點：主存儲　出處：《微電子學與計算機》2017年09期

【摘要】：隨著虛擬化技術的日趨成熟與發(fā)展,越來越多的企業(yè)采用私有云平臺來替代傳統(tǒng)PC辦公.然而,虛擬磁盤數(shù)據(jù)的高度重復與超大容量導致了存儲空間與系統(tǒng)能耗的巨大浪費.為解決這一問題,首先提出了基于特征標簽粗歸類算法,將重刪操作分散到云平臺計算結點,有效地避免了傳統(tǒng)重刪算法的性能瓶頸;然后,提出了基于指紋ID相似度聚類算法,提高了各計算結點上的重刪率;最后,通過實驗對兩種子算法進行分析,并驗證了其有效性.
[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.
【作者單位】： 電子科技大學電子科學技術研究院;
【分類號】：TP333

【相似文獻】

相關期刊論文 前1條

1 黃石華;盧珍菊;李曉樂;李海茗;;教育資源服務下海量云存儲優(yōu)化機制的研究[J];中國教育信息化;2014年13期

，

本文編號：1715326