考虑虚拟机间性能互扰基于排队网的多层Web应用性能分析模型  

Queueing Network Based Performance Model for Multi-tiered Web Application with Consideration of Performance Interference among Virtual Machines

作　　者：杨雷[1] 代钰[2] 张斌[1] 王昊[1] 

机构地区：[1]东北大学信息科学与工程学院,沈阳110819 [2]东北大学软件学院,沈阳110819

出　　处：《计算机科学》2015年第1期47-49,共3页Computer Science

基　　金：国家自然科学基金(60903218;61073062);中央高校基本科研业务费专项资金(N110404008;N110417003;N110804002)资助

摘　　要：多层Web应用性能分析是实现资源动态分配和管理、保证多层Web应用性能的重要因素之一。传统的多层Web应用性能分析模型往往假设服务器部署在无性能互扰的服务器环境中且忽略了逻辑资源服务能力对多层Web应用性能的影响。随着云计算的发展,底层物理资源可以通过虚拟化方式形成虚拟资源并向外提供服务,这为多层Web应用的性能保证提供了有效支撑。因此,如何考虑虚拟机性能互扰以及逻辑资源服务能力对多层Web应用性能的影响已经成为云计算环境中多层Web应用性能分析所需解决的关键问题。为此,构建了一个基于排队网的多层Web应用性能分析模型,该模型通过丢弃队列来对目前多层Web应用性能分析模型在并发数限制方面进行扩展,在考虑虚拟机间性能互扰的基础上,提出了多层Web应用性能分析模型参数求解方法。实验结果验证了所提出的多层Web应用性能分析模型的有效性。Performance analysis for multi-tiered application is one of the important factors to achieve dynamic resource allocation and management,and insure the better performance of the application.Traditional performance models assume the availability of dedicated hardware for the application and neglect the effect caused by logic resource.With the development of cloud computing,hardware resources can be virtualized as virtual resource to provide service which can support the performance insurance of the multi-tiered application effectively.Then,how to take the performance interference between virtual machines and the logic resource into consideration becomes a key issue when building the performance model for a multi-tiered application.For this,this paper built a performance model for multi-tiered application based on queuing network.This model extends the current performance model with a drop queue to support concurrent connection limit.With the consideration of the performance interference between virtual machines,this paper presented the parameter solving method of the proposed performance model.The experiments show the better performance of the performance model.

关 键 词：性能分析 虚拟机间性能互扰 多层应用 

分 类 号：TP393.1[自动化与计算机技术—计算机应用技术]