首页> 中文期刊> 《长春理工大学学报(自然科学版)》 >基于动态反馈的负载均衡方法研究

基于动态反馈的负载均衡方法研究

         

摘要

With the recent growth of Internet-based application services,the concurrent accessing requests arriving at the particular servers offering application services are growing significantly. It is one of the critical strategies that em-ploying load balancing to cope with the massive concurrent accessing requests and improve the access performance is. To build up a better online service to users,load balancing solutions achieve to deal with the massive incoming concur-rent requests in parallel through assigning and scheduling the work executed by the members within one server cluster. In this paper,we propose a dynamic feedback-based load balancing methodology. The method analyzes the real-time load and response status of each single cluster member through periodically collecting its work condition information to evaluate the current load pressure by comparing the learned load balancing performance with the preset threshold. In this way,since the load arriving at the cluster could be distributed dynamically with the optimized manner,the load balancing performance could thus be maintained so that the service throughput capacity would correspondingly be im-proved and the response delay to service requests would be reduced. The proposed result is contributed to strengthening the concurrent access capacity of server clusters. According to the experiment report,the overall performance of server system employing the proposed solution is better.%随着基于互联网的应用服务快速发展,网络上提供应用服务支撑的服务器(集群)所面临的并发性访问激增,运用负载均衡是应对处理大量并发访问及提高服务请求接入性能的重要策略之一.负载均衡通过对服务器集群中的逻辑/物理单机进行规划实现负载任务分配调度,实现对大量并发访问的并行化处理,从而提高应用服务的请求接入和服务处理性能.提出了一种基于动态反馈的负载均衡方法,其通过周期性的获取集群中单机节点的工况信息,然后分析单机节点的实时负载和响应情况,并将其与保持负载均衡性能的决策参考阈值相比对,通过负载任务再分配达成动态负载调整并保持集群工作性能均衡的目的,进而提升集群系统的服务吞吐能力,降低服务请求的响应延迟,能够为开展海量数据高并发处理提供技术基础和保障.实验结果表明,该算法使系统的整体性能得到了改善.

著录项

相似文献

  • 中文文献
  • 外文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号