一种自适应文件系统元数据服务负载均衡策略

发布时间：2018-01-12 10:15

本文关键词：一种自适应文件系统元数据服务负载均衡策略　出处：《软件学报》2017年08期 　论文类型：期刊论文

【摘要】：随着大数据时代的到来,全球信息存储量呈现爆发式的增长,传统的存储系统在存储性能、存储容量、数据可靠性和成本等方面存在诸多不足.近年来,以云计算平台为依托的存储技术得到了飞速发展,成为处理海量数据的重要工具.针对分布式文件系统元数据管理的问题,提出了一种自适应元数据服务负载均衡策略.该策略主要包括以下3点内容:介绍了一种实时的元数据服务器的性能评价模型;提出了一种基于服务器负载变化的检测周期自适应调整机制;提出了一种基于元数据服务器性能指标的自适应负载均衡算法.实验结果证明了该方法的可行性、有效性和稳定性.
[Abstract]:With the arrival of big data era, the global information storage capacity presents explosive growth, the traditional storage system in storage performance, storage capacity, data reliability and cost, and so on, there are many shortcomings in recent years. The storage technology based on cloud computing platform has been developed rapidly, and has become an important tool to deal with massive data, aiming at the problem of metadata management in distributed file system. In this paper, an adaptive load balancing strategy for metadata service is proposed, which mainly includes the following three aspects: a real-time metadata server performance evaluation model is introduced. In this paper, an adaptive adjustment mechanism of detection cycle based on server load change is proposed. An adaptive load balancing algorithm based on metadata server performance index is proposed. The experimental results show that the proposed method is feasible, effective and stable.
【作者单位】：中山大学数据科学与计算机学院;中山大学-卡内基梅隆大学国际联合研究院;广东财经大学数学与统计学院;
【基金】：广东省科技计划(2014B010114002,2015B010108004)~~
【分类号】：TP333
【正文快照】： 随着云计算技术的逐步成熟,存储系统作为云计算中重要的组成部分,同样需要满足当下新的需求.在云计算环境下,存储系统通常要求支持PB级的数据存储,同时需要满足高可用性、高扩展性、高性能等多种需求.文件系统作为存储系统中重要的一种类型,被业界广泛地应用.不同于传统环境

【相似文献】