资源敏感的分布式系统性能建模方法

摘要/Abstract

摘要： 早期的性能预测可帮助设计人员有效地评估和改进系统设计,降低性能风险,提高软件制品满足性能需求的可信程度。但复杂低效的性能模型构造过程,严重阻碍了它在软件开发过程中的应用。为简化建模复杂度,以典型的UML模型为基础,研究了一种面向分布式系统的性能模型方法,并提出了一种中间模型——资源场景模型(Resource Scenario Model,RSM),解决了多UML视图转化为多性能模型的问题,使设计人员可以根据自身偏好选择熟悉的工具进行性能建模和性能分析。最后,以UML活动图和序列图到分层排队网和通用随机Petri网模型的转换为例,说明了本方法的可行性和有效性。

关键词: 资源,分布式系统,性能模型,模型转换中图法分类号TP32文献标识码A

Abstract: Performance prediction of software at early stage makes benefit to improve the quality of designs and reduce the performance problems．However,the huge costs of performance modeling approaches make it impossible to integrate the approach into the software development processes．In order to develop a cost effective modeling approach,we used the widely accepted UML model to support our work for distributed systems,and designed an intermediate model named Resource Scenario Model(RSM)for multi architecture model to multi performance model transformations．Therefore,designers can use their preferred tools to build and analyze software’s performance．To illustrate the effectiveness of our method,we given a case study,in which UML models can be easily transformed into performance models,such as LQN and LGSPN.

Key words: Resource,Distributed system,Performance model,Model transformation

黄翔,陈志刚. 资源敏感的分布式系统性能建模方法[J]. 计算机科学, 2013, 40(9): 174-181. https://doi.org/

HUANG Xiang and CHEN Zhi-gang. Performance Modeling Approach for Resource Sensitive Distributed Systems[J]. Computer Science, 2013, 40(9): 174-181. https://doi.org/

参考文献

[1] Koziole H．Performance evaluation of component-based software systems:A survey[J]．Performance Evaluation,2010,67:634-658
[2] Balsamo S,Marco D．Model based performance prediction insoftware development:a survey[J]．IEEE Trans．Softw．Eng．,2004,30(5),295-310
[3] Object Management Group:Unified modeling language:super-structure,version 2[R]．OMG Adopted Specification,formal/05-07-04,2005
[4] Object Management Group:UML profile for schedulability,performance,and time specification[S]．OMG Adopted Specification ptc/05-01-02,July 2005
[5] D’Ambrogio A,Bocciarelli P．A model-driven approach to describe and predict the performance of composite services[C]∥Cortellessa V,Uchitel S,Yankelevich D,eds．WOSP．ACM,2007:78-89
[6] Hillston J,Wang Y．Performance evaluation of UML models via automatically generated simulation models[C]∥Jarvis S A,ed．Proceedings of the 19th Annual UKPerformance Engineering Workshop．Warwick,UK,2003:64-78
[7] Tribastone M,Gilmore S．Automatic Extraction of PEPA Per-formance Models from UML Activity Diagrams Annotated with the MARTE Profile[C]∥Princeton,WOSP．ACM,New Jersey,USA,2008:67-78
[8] Bernardi S,Donatelli S,Merseguer J．From UML sequence diagrams and statecharts to analysable Petri net models[C]∥Proc．3rd Int．Workshop on Software and Performance(WOSP02)．Rome,July 2002:35-45
[9] Lo’pez-Grao J P,Merseguer J,Campos J．From UML Activity Diagrams To Stochastic Petri Nets[C]∥Fourth Int．Workshop on Software and Performance(WOSP 2004)．Redwood City,CA,Jan．2004:25-36
[10] Merseguer J．Software performance engineering based on UML and Petri nets[D]．University of Zaragoza,Spain,March 2003
[11] Petriu D C,Shen H．Applying the UML performance profile:Graph grammar-based derivation of LQN models from UML specifications[C]∥Computer Performance Evaluation / TOOLS．Lecture Notes in Computer Science,Springer,2002:159-177
[12] Gu G P,Petriu D C．XSLT transformation from UML models to LQN performance models[C]∥WOSP’02．Rome,Italy,July 2002
[13] Koziolek H,Reussner R．A Model Transformation from the Palladio Component Model to Layered Queueing Networks[C]∥Kounev S,Gorton I,Sachs K,eds.SIPEW 2008．LNCS 5119,2008:58-78
[14] Woodside C M,Petriu D C．Performance by unified model analysis(PUMA)[C]∥Proceedings of the Fifth International Workshop on Software and Performance,WOSP．ACM,2005:1-12
[15] Woodside C M．From Annotated Software Designs(UML SPT/MARTE)to Model Formalisms[C]∥Bernardo M,Hillston J,eds.SFM 2007．LNCS 4486,2007:429-467
[16] Mizan A,Franks G．An Automatic Trace Based Performance Evaluation Model Building for Parallel Distributed Systems [C]∥Proceedings of the second joint WOSP/SIPEW international conference on performance engineering(ICPE 2011)．2011
[17] Jiang De-jun,Pierre G,Chi C-H．Autonomous Resource Provisioning for Multi-Service Web Applications [C]∥19th procee-ding:International World Wide Web Conference．2010
[18] Zhang Wen-bo,Huang Xiang,Wei Jun．An Aspect-orientedModeling Approach to Predict Performance of JCA-based Systems[C]∥International Conference on Interoperability for Enterprise Software and Applications,I-ESA2009．2009:140-146
[19] http://oncepd.sourceforge.net/
[20] Woodside M．Software Resource Architecture[J]．Journal ofSoftware Engineering and Knowledge Engineering,2001,11(4)
[21] Woodside M．Resource Architecture and Continuous Perfor-mance Engineering[C]∥Overhage S,et al.,eds.QoSA 2007．LNCS 4880,2007:1-14
[22] Welsh M,Culler D,Brewer E．SEDA:An architecture for well-conditioned,scalable Internet services[C]∥ Proceedings of the 18th Symposium on Operating Systems Principles(SOSP)．October 2001
[23] Cherkasova L,Fu Y,Tang W,et al.Measuring and Characterizing End-to-End Internet Service Performance[J]．Journal ACM/IEEE Transactions on Internet Technology(TOIT),2003,3(4):347-391
[24] Woodside M,Frank G．The Future of Software Performance Engineering[C]∥IEEE Future of Software Engineering(FOSE’07)．2007:171-187
[25] Woodside M,Franks G．Tutorial Introduction to Layered Mode-ling of Software Performance．http://www.sce.carleton.ca/rads/lqns/lqn-documentation
[26] Marsan M A,Balbo G,Conte G．Modelling with generalized stochastic Petri nets[J]．ACM SIGMETRISS Performance Evaluation Review,1998,6(2)
[27] Krogmann K,Kuperberg M,Reussner R．Using Genetic Search for Reverse Engineering of Parametric Behavior Models for Performance Prediction[J]．IEEE Transaction on Software Engineering,2010,36
[28] Woodside M,Li J,Chinneck J,et al.Performance Model Driven QoS Guarantees and Optimization in Clouds [C]∥ACM/IEEE ICSE Workshop on Cloud Computing．Vancouver,May 2009

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed