摘要
现有的动态负载均衡算法通常对服务器上的负载进行监测,然而大多数负载均衡算法不能区分用户请求服务的类别,且对于监控时间间隔之间的负载很难实时获得。针对此种情况,文中提出了一种预测动态负载均衡算法。该算法对用户请求服务进行分类,同时可对每台服务器节点的资源利用率进行实时预测。在实验室搭建的Web服务器集群(WSC)上,对该算法的两种PSDLB模型、WLC以及QSC-LB负载均衡算法在异构环境中安全传输服务、数据库服务、大小文件下载服务的请求失败率、系统响应时间进行了对比测试。结果表明,在高负载情况下该算法优于另外两种算法。
The present dynamic load balancing algorithms usually monitor load on servers,however,most of them cannot differentiate the types of the request services and the load between monitoring intervals is so difficult to achieve in real-time. Based on this situation,pres-ent a predictive dynamic load balancing algorithm PSDLB. This algorithm takes the users’ services types into consideration,as well as, the resource utilization of each server node between monitoring intervals can be predicted in real-time. On the Web Server Cluster ( WSC) of the lab,the proposed algorithm’ s two models are compared with WLC algorithm and QSC-LB algorithm in the heterogeneous environment. The content of the comparison is the failed requests rate and the system response time of the four request service types, such as,secure transaction service,database service,small file downloading service and big file downloading service. Results of the experi-ments show that the proposed algorithm is better than the other two algorithms under high system loading condition.
出处
《计算机技术与发展》
2015年第6期96-100,105,共6页
Computer Technology and Development
基金
国家科技重大专项(2012ZX03001008-003
2011ZX03005-004-03)
国家"973"重点基础研究发展计划项目(2013CB329005)
关键词
动态负载均衡算法
预测
服务分类
WEB服务器集群
dynamic load balancing algorithm
predictive
service differentiation
Web server cluster