论文部分内容阅读
针对云存储系统节点在数据分布策略和系统响应时间方面的综合负载计算问题,提出了一种云存储系统的负载均衡算法,并对该算法进行了验证。算法基于层次分析法(Analytic Hierarchy Process,AHP),通过建立综合评估指标体系,从可用存储空间、可用CPU、可用内存和访问热度四个方面,计算各个存储节点的综合负载,并据此对数据存取进行均衡调度。验证结果表明,通过调整不同指标的权重,算法能够很好地满足不同的应用需求,同时,该算法能够很好地反应各节点的综合负载,实现云存储系统整机性能的优化,尤其适用于一些高并发的大数据存储。
Aiming at the problem of comprehensive load calculation of cloud storage system node in data distribution strategy and system response time, a load balancing algorithm for cloud storage system was proposed and verified. Based on Analytic Hierarchy Process (AHP), the algorithm calculates the comprehensive load of each storage node from the available storage space, available CPU, available memory and access heat by establishing an integrated evaluation index system. Based on this, the data Access for balanced scheduling. The verification results show that the algorithm can meet different application requirements well by adjusting the weight of different indicators. Meanwhile, the algorithm can well reflect the comprehensive load of each node and optimize the overall performance of cloud storage system, especially for Some high-concurrency big data storage.