Rule-based automatic software performance diagnosis and improvement

ABSTRACT

Performance of a software system is the result of many interacting factors. This paper describes a rule-based framework to identify root causes of performance limits, to untangle the effects of the system configuration (such as the allocation of processors) from limits imposed by the software design, and to recommend both configuration and design improvements. The framework uses a performance model which represents (and is derived from) a UML design model, and applies transformations to the given performance model to obtain another improved one. The improvements imply configuration and design changes which can be applied to the system. This paper describes the approach and demonstrates feasibility by applying a small set of rules to the design of a web application.

REFERENCES

• 1: Asogawa, M., Shiramizu, A., Kubo, H., "A computer system performance analysis expert system (EXPERFORM)", Ninth Annual Int. Phoenix Conf. on Computers and Communications, 1990, pp. 785--765.
• 2: Alberto Avritzer , Elaine J. Weyuker, The Role of Modeling in the Performance Testing of E-Commerce Applications, IEEE Transactions on Software Engineering, v.30 n.12, p.1072-1083, December 2004 [doi>10.1109/TSE.2004.107]
• 3: Benoit, A., Cole, M., Gilmore, S., Hillston, J., "Evaluating the Performance of Skeleton-Based High Level Parallel Programs", Int. Conf. on Computational Science (ICCS 2004), LNCS 3038, pp. 299--306. Springer, 2004.
• 4: Darcy Gerard Benoit , Patrick Martin, Automatic diagnosis of performance problems in database management systems, Queen's University, Kingston, Ont., Canada, 2003
• 5: Simona Bernardi , Susanna Donatelli , José Merseguer, From UML sequence diagrams and statecharts to analysable petri net models, Proceedings of the 3rd international workshop on Software and performance, July 24-26, 2002, Rome, Italy [doi>10.1145/584369.584376]
• 6: Cortellessa, V., Frittella, L., "A Framework for Automated Generation of Architectural Feedback from Software Performance Analysis." Proc. of European Performance Engineering Workshop (EPEW 2007), September 27-28, 2007, Berlin (Germany).
• 7: Espinosa, A., Margalef, T., and Luque, E., Automatic Performance Evaluation of Parallel Programs, Proc Euromicro 98, pp. 365 -- 377, 1998.
• 8: Espinoza, H., Dubois, H., Gerard, S., Medina, J., Petriu, D.C., Woodside, M., "Annotating UML Models with Non-Functional Properties for Quantitative Analysis", Proc. of MoDELS'2005 Satellite Events: Revised Selected Papers ed J.M. Bruel, Lecture Notes in Computer Science, V. 3844, pp. 79 -- 90, Springer, 2006.
• 9: Roy Gregory Franks , C. Murray Woodside, Performance analysis of distributed server systems, Carleton University, Ottawa, Ont., Canada, 2000
• 10: Franks, G., Maly, P., Woodside, M., Petriu, D.C., Hubbard, A., Layered Queueing Network Solver and Simulator User Manual, Carleton Univ., Dec. 2005, http://www.sce.carleton. ca/rads/software/ LQNSUserMan.pdf,
• 11: Greg Franks , Dorina Petriu , Murray Woodside , Jing Xu , Peter Tregunno, Layered Bottlenecks and Their Mitigation, Proceedings of the 3rd international conference on the Quantitative Evaluation of Systems, p.103-114, September 11-14, 2006 [doi>10.1109/QEST.2006.23]
• 12: Ernest Friedman Hill, Jess in Action: Java Rule-Based Systems, Manning Publications Co., Greenwich, CT, 2003
• 13: Friedman-Hill, E., Jess, the Rule Engine for the Java Platform, http://herzberg.ca.sandia.gov/jess/
• 14: Gordon P. Gu , Dorina C. Petriu, From UML to LQN by XML algebra-based model transformations, Proceedings of the 5th international workshop on Software and performance, p.99-110, July 12-14, 2005, Palma, Illes Balears, Spain [doi>10.1145/1071021.1071031]
• 15: B. Robert Helm , Allen D. Malony , Stephen Fickas, Capturing and automating performance diagnosis: the Poirot approach, Proceedings of the 9th International Symposium on Parallel Processing, p.606-613, April 25-28, 1995
• 16: Hoogenboom, P. J., "System performance advisor: An expert system for unix system performance management," Dept. Computer Science, University of Utah, Salt Lake City, 1992, p. 144.
• 17: Karen L. Karavanic , Barton P. Miller, Improving online performance diagnosis by the use of historical performance data, Proceedings of the 1999 ACM/IEEE conference on Supercomputing (CDROM), p.42-es, November 14-19, 1999, Portland, Oregon, United States [doi>10.1145/331532.331574]
• 18: Li, L., Malony, A.D., "Model-Based Performance Diagnosis of Master-Worker Parallel Computations", Proc Euro-Par 2006 Parallel Processing, LNCS 4128, pp 35--46, 2006.
• 19: Barton P. Miller , Mark D. Callaghan , Jonathan M. Cargille , Jeffrey K. Hollingsworth , R. Bruce Irvin , Karen L. Karavanic , Krishna Kunchithapadam , Tia Newhall, The Paradyn Parallel Performance Measurement Tool, Computer, v.28 n.11, p.37-46, November 1995 [doi>10.1109/2.471178]
• 20: Anna Morajko , Tomàs Margalef , Emilio Luque, Design and implementation of a dynamic tuning environment, Journal of Parallel and Distributed Computing, v.67 n.4, p.474-490, April, 2007 [doi>10.1016/j.jpdc.2007.01.001]
• 21: J. E. Neilson , C. M. Woodside , D. C. Petriu , S. Majumdar, Software Bottlenecking in Client-Server Systems and Rendezvous Networks, IEEE Transactions on Software Engineering, v.21 n.9, p.776-782, September 1995 [doi>10.1109/32.464543]
• 22: Object Management Group, UML Profile for Schedulability, Performance, and Time Specification, OMG Adopted Specification ptc/02-03-02, July 1, 2002.
• 23: Object Management Group, UML 2.1.1 Superstructure Specification, Document formal/07-02-03, Feb. 2007.
• 24: Petriu, D.B., and Woodside, M., "An intermediate metamodel with scenarios and resources for generating performance models from UML designs", Software and Systems Modeling, issue 2007/02, pp. 163--184.
• 25: Petriu, D.C., Sabetta, A., "From UML to Performance Analysis Models by Abstraction-raising Transformation", In From MDD Concepts to Experiments and Illustrations, (eds. J.P. Babau, J. Champeau, S. Gerard), ISTE Ltd., pp.53--70, 2006.
• 26: Dorin Petriu , Murray Woodside, Analysing software requirements specifications for performance, Proceedings of the 3rd international workshop on Software and performance, July 24-26, 2002, Rome, Italy [doi>10.1145/584369.584371]
• 27: PUMA (Performance from Unified Model Analysis), www.sce.carleton.ca/rads/puma/.
• 28: Smith, C. U., Williams, L. G., Performance Solutions, Addison-Wesley, 2002.
• 29: Connie U. Smith , Lloyd G. Williams, Software performance antipatterns, Proceedings of the 2nd international workshop on Software and performance, p.127-136, September 2000, Ottawa, Ontario, Canada [doi>10.1145/350391.350420]
• 30: Jeffrey Vetter, Performance analysis of distributed applications using automatic classification of communication inefficiencies, Proceedings of the 14th international conference on Supercomputing, p.245-254, May 08-11, 2000, Santa Fe, New Mexico, United States [doi>10.1145/335231.335255]
• 31: Woodside, M., "From Annotated Software Designs (UML SPT/MARTE) to Model Formalisms", in SFM 2007, eds M. Bernardo and J. Hillston, LNCS 4486, pp. 429 -- 467, Springer, 2007
• 32: Murray Woodside , Dorina C. Petriu , Dorin B. Petriu , Hui Shen , Toqeer Israr , Jose Merseguer, Performance by unified model analysis (PUMA), Proceedings of the 5th international workshop on Software and performance, p.1-12, July 12-14, 2005, Palma, Illes Balears, Spain [doi>10.1145/1071021.1071022]
• 33: Woodside, C.M., Petriu, D., "Performance Analysis with UML", Chapter 11 in UML for Real: Design of Embedded Real-Time Systems, eds L. Lavagno, G. Martin, and B. Selic, Kluwer, 2003.
• 34: C. M. Woodside, A Three-View Model for Performance Engineering of Concurrent Software, IEEE Transactions on Software Engineering, v.21 n.9, p.754-767, September 1995 [doi>10.1109/32.464545]
• 35: Woodside, M., "Software Resource Architecture", Int. Journal on Software Engineering and Knowledge Engineering (IJSEKE), v 11, no 4, pp 407--429, 2001.
• 36: Murray Woodside , Dorin Petriu , Khalid Siddiqui, Performance-related completions for software specifications, Proceedings of the 24th International Conference on Software Engineering, May 19-25, 2002, Orlando, Florida [doi>10.1145/581339.581346]
• 37: Xu, J., Woodside, M., Petriu, D.C., "Performance Analysis of a Software Design using the UML Profile for Schedulability, Performance and Time", Proc. 13th Int. Conf. on Computer Performance Evaluation, Modelling Techniques and Tools, Urbana, Illinois, USA, Sept 2003, pp 291 -- 310, vol. LNCS 2794, Springer-Verlag, 2003.

INDEX TERMS

Primary Classification:
  D. Software
  D.2 SOFTWARE ENGINEERING
      D.2.2 Design Tools and Techniques
          Subjects: Computer-aided software engineering (CASE)

General Terms:
Design, Experimentation, Measurement, Performance

Keywords:
bottleneck., design improvement, layered queuing networks, performance diagnosis, rules