一种动态的客户端负载均衡机制

A dynamic client-side load balancing mechanism

互联网应用的并发用户数量不仅多变并且这种变化常常不可预测.将系统容量配置为固定值的惯用做法在面临多变的请求时常常会导致两种结果,一种是因为配置过低而引起用户的不满,另一种则因为配置过高而造成计算资源的浪费.而通过运用云架构按需提供、按使用收费的能力,系统具有了实时地按需配置计算资源的能力.然而静态的客户端负载均衡方法作为一种主要的负载均衡技术很难适应云架构条件下更加易变的集群结构.本文提出了一种动态的客户端负载均衡机制.通过引入分布式的集群视图更新、控制流等技术,该机制在保持客户端负载均衡机制分布式、可伸缩性强的基础上,又为集群节点的动态加入与退出和负载均衡策略的动态调整提供了有效的支持.同时,本文分析了该机制在一个开源JEE应用服务器PKUAS中的关键实现问题,并通过实验从多方面验证了该机制的有效性.

Web applications＇ traffic demand fluctuates widely and usually unpredictably. The common practice of provisioning a fixed capacity would either result in unsatisfied customers （when the resources allocated to a specific customer are too low） or waste valuable capital investment （when the resources allocated to a specific customer are too much）. By leveraging an infrastructure cloud＇s on-demand, pay-per-use capabilities, we finally can match the system＇s capacity with the demand in real time. Although the static client-side load balancing mechanism has been used by many clusters, it does not suit the cluster which needs to change nodes and load balancing policies in runtime. This paper proposes a dynamic client-side load balancing mechanism. By integrating technologies such as distributed cluster-view maintenance and control flow, this mechanism not only has good scalability but also introduces many dynamic features into the client-side load balancing, providing effective support for the nodes＇ dynamic join and exit as well as the adaptive adjustment of the load balancing policies. Since the framework has been implemented in an open-source JEE application server named PKUAS, this paper also describes some key implementation features and analyzes the evaluation results of the experiments to show the effectiveness of the mechanism from different aspects.