期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

多租户Web应用的CPU资源动态评估方法 被引量：5

Dynamically Estimating Approach for CPU Consumption of Multi-Tenancy Web Applications
在线阅读 下载PDF
导出
摘要 中间件共享是云计算模式中一种重要的资源共享方式.但是,这种方式容易导致宿主在同一中间件服务器上的多个租户间产生性能干扰.因此,需要为租户提供性能隔离的服务实例.在线度量租户对系统资源的使用情况是实现性能隔离的前提条件,但是,在共享中间件服务器中直接度量CPU资源需要注入探针,将引起性能开销,并依赖于操作系统的支持.最近,一些工作利用回归分析进行资源使用情况的间接评估,但仍难以对动态Web系统的时变资源状态进行有效评估.文中针对普遍使用的Java中间件服务器,提出一种基于Kalman滤波的多租户Web应用CPU资源动态评估方法,并通过两个实验案例分析方法的评估效果、影响因素和面临的挑战.实验结果表明,通过适当的参数设置,该方法可动态适应持续变化的负载环境,并且与直接度量方法相比,具有可接受的评估误差.实验还表明该方法可用于检测侵占型租户,并避免共享中间件服务器CPU过载. Middleware sharing is one of the important resource sharing approaches in cloud computing.However,a shared middleware server easily causes interference in performance between multiple hosted tenants.This interference affects infrastructure resources as well as applications and services that are hosted on shared resources but that need to be made available in multiple performance isolated instances.A key requirement in performance isolation of the shared Java middleware server is the knowledge of the resource consumption of the various tenants.However,direct measurement of CPU resource consumption requires instrumentation,incurs overhead,and assumes OS support.Recently,regression analysis has been applied to indirectly approximate resource consumption,but challenges still remain in estimating time-varying states in dynamic systems.In this paper,we propose a Kalman filter-based approach to offer a solution to the problem of dynamically estimating the CPU consumption of a multi-tenancy Web application in a shared Java middleware server,and we discuss the challenges involved in this approach.We investigate factors that impact the efficiency and accuracy of the approach in estimating time-varying states via two case studies.Experimental results show that,even under continuously changing workload conditions,estimation results are in agreement with the corresponding measurements with acceptable estimation errors,especially with appropriately tuned filter settings taken into account.Our experiments also demonstrate the utility of our approach in identifying the aggressive tenants and in avoiding shared middleware server CPU overloading.
作者 王伟 黄翔 张文博 魏峻 钟华 黄涛
机构地区 中国科学院软件研究所软件工程技术研究中心 武汉大学软件工程国家重点实验室 中国科学院研究生院
出处 《计算机学报》 EI CSCD 北大核心 2011年第12期2292-2304,共13页 Chinese Journal of Computers
基金 国家自然科学基金(61100068 61173003) 国家"九七三"重点基础研究发展规划项目基金(2009CB320704) 国家"八六三"高技术研究发展计划项目基金(2011AA040504) 国家科技重大专项(2010ZX01045-001-010-4) 武汉大学软件工程国家重点实验室开放基金项目资助~~
关键词 CPU资源评估 性能隔离 KALMAN滤波 多租户 CPU consumption estimation performance isolation Kalman filter multi-tenancy
分类号 TP311 [自动化与计算机技术—计算机软件与理论]
  • 相关文献

参考文献19

  • 1Zhang Q, Cheng L, Boutaba R. Cloud computing: State-of- the-art and research challenges. Journal of Internet Services and Applications, 2010, 1(1) : 7-18.
  • 2林海略,韩燕波.多租户应用的性能管理关键问题研究[J].计算机学报,2010,33(10):1881-1895. 被引量：45
  • 3GuoCJ, SunW, Huang Y, Wang Z H, Gao B. A frame work for native multi tenancy application development and management//Proceedings of the 9th International Confer ence on E-Commerce Technology and the 4th IEEE International Conference on Enterprise Computing, E-commerce and E-Services. 2007.. 551-558.
  • 4Li X H, Liu T C, Li Y, Chen Y. SPIN: Service performance isolation infrastructure in multi-tenancy environment//Proceedings of the 6th International Conference on Service-Oriented Computing. Sydney, Australia, 2008:649-663.
  • 5Binder W, Hulaas J. A portable CPU-management frame- work for Java. IEEE Internet Computing, 2004, 8(5) : 74-83.
  • 6Hulaas J, Binder W. Program transformations for portable CPU accounting and control in Java//Proceedings of ACM SIGPLAN Symposium on Partial Evaluation & Program Manipulation. Verona, Italy, 2004:169-177.
  • 7Zhang Q, Cherkasova L, Mathews G, Greene W, Smirni E. R capriccio: A capacity planning and anomaly detection tool for enterprise services with live workloads//Proceedings of the Middleware. Newport Beach, CA, 2007:244-265.
  • 8Cherkasova L, Ozonat K. Automated anomaly detection and performance modeling of enterprise applications. ACM Transactions on Computer Systems, 2009, 27(3) : 1-32.
  • 9Kalman R E. A new approach to linear filtering and prediction problems. Transactions of the ASME Journal of Basic Engineering, 1960, 82(D):35-45.
  • 10Lazowska E D, Zahorjan J, Graham G S, Sevcik K C. Quan- Titative System Performance: Computer System Analysis Using Queueing Network Models. Upper Saddle River: Prentice-Hall, Inc. , 1984.

二级参考文献55

  • 1EJ Technologies. JProfiler ej-technologies, http://www.ej-technologies.com/products/jprofiler/overview.html.
  • 2NetBeans Community. NetBeans profiler, Version 5.5.2007. http://www.netbeans.org/produets/profiler/index.html.
  • 3Murray H, Engineer S, Associates I. Rules-of-Thumb for monitoring windows NT/2000 and domino statistics, http://www.ibm. com/developerworks/lotus/library/ls-Rules_WinNT2000/.
  • 4Barham P, Donnelly A, Isaacs R, Mortier R. Using magpie for request extraction and workload modeling. In: Proc. of the 6th Symp. on Operating Systems Design and Implementation (OSDI 2004). Berkeley: USENIX Association, 2004. 18.
  • 5Bodden E, Hendren LJ, Lam P, Lhotak O, Naeem NA. Collaborative runtime verification with tracematches. In: Proc. of the 7th Int'l Workshop on Runtime Verification (RV). LNCS 4839, Berlin: Springer-Verlag, 2007.22-37.
  • 6Cohen I, Goldszmidt M, Kelly T, Symons J, Chase J. Correlating instrumentation data to system states: A building block for automated diagnosis and control. In: Proc. of the 6th Symp. on Operating Systems Design and Implementation (OSDI 2004). Berkeley: USENIX Association, 2004. 16.
  • 7Zhang S, Cohen I, Symons J, Fox A. Ensembles of models for automated diagnosis of system performance problems. In: Proc. of the 2005 Int'l Conf. on Dependable Systems and Networks (DSN 2005). Washington: IEEE Computer Society Press, 2005. 644-653.
  • 8Cohen I, Zhang S, Goldszmidt M, Symons J, Kelly T, Fox A. Capturing, indexing, clustering, and retrieving system history. In: Proc. of the 20th ACM Symp. on Operating Systems Principles. New York: ACM Press, 2005. 105-118.
  • 9Kelly T. Detecting performance anomalies in global applications. In: Proc. of the 2nd Workshop on Real, Large Distributed Systems (WORLDS 2005). Berkeley: USENIX Association, 2005.42-47.
  • 10Chen M, Kcman E, Fratkin E, Brewer E, Fox A. Pinpoint: Problem determination in large, dynamic Internet services. In: Proc. of the Symp. on Dependable Networks and Systems (IPDS Track). Washington: IEEE Computer Society Press, 2002. 595-604.

共引文献50

同被引文献47

  • 1BACIGALUPO D A, VAN H, USMANI J A. Resource management of enterprise cloud systems using layered queuing andhistorical performance models[ C ]//Proceedings of 2010 IEEE International Symposium on Parallel & Distributed Process- ing, Workshops and Phd Forum (IPDPSW). Washington,DC: IEEE Computer Society, 2010:1-8.
  • 2SOROR A, MINHAS U F, ABOULNAGA A, et al. Automatic virtual maehine configuration for database workloads [ J ]. ACM Transactions on Database Systems, 2010,35 ( 1 ) :953-966.
  • 3JOHN J, PREVOST,KRANTHI M N, t al. Load prediction algorithm for multi-tenant virtual machine environments[ C]// Proceedings of World Automation Congress (WAC). Washington, DC : IEEE Computer Society, 2012 : 1-6.
  • 4WEI T, SUN T X, SHAO Q H, et al. Two-tier multi-tenancy scaling and load balancing[ C ]//Proceedings of 2010 IEEE 7th International Conference on E-Business Engineering (ICEBE). Washington, DC : IEEE Computer Society 2010 : 483- 489.
  • 5BROSIG F, HUBER N, SAMUEL K. Automated extraction of architecture-level performance models of distributed compo- nent-based systems[ C l// Proceedings of 2011 26th IEEE/ACM International Conference on Automated Software Engi- neering (ASE). Washington, DC : IEEE Computer Society, 2011 : 183-192.
  • 6KOUNEV S. Performance modeling and evaluation of distributed component-based systems using queueing Petri nets [ J ]. IEEE Transactions on Software Engineering, 2006, 32 (7) :486-502.
  • 7ZHANG Q, CHERKASOVA L, MI N F. A regression-based analytic model for capacity planning of multi-tier applications [ J ]. Journal of Cluster Computing, 2008, 11 ( 3 ) : 197-211.
  • 8GIOVANNI P, WOLFGANG S, MIKE S. CPU demand for web serving: Measurement analysis and dynamic estimation [ J ]. Performance Evaluation. 2008,65 ( 6-7 ) : 531-553.
  • 9SIMON D. Optimal state estimation: Kalman, H Infinity and Nonlinear Approaches [ M ]. Hoboken, NJ: Wiley-Inter- science, 2006.
  • 10SPINNER S, KOUNEV S, MEIER P. Stochastic Modeling and Analysis using QPME:Queueing Petri Net Modeling Environ- ment v2. 0[ C]//Proceedings of the 33rd International Conference on Application and Theory of Petri Nets and Concurren- cy ( Petri Nets 2012). Berlin : Springer Berlin Heidelberg,2012:234-253.

引证文献5

二级引证文献5

计算机学报
2011年 第12期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部