Performance Evaluation

Introduction

Resource Sharing Models

Measurement Framework

Middleware Benchmarking

Performance Prediction Validation

Regression Benchmarking

Acknowledgments

Archive

Publications

Picture of Tools

Introduction

Our performance evaluation research focuses on measuring and analyzing software performance. Our activities include performance evaluation of middleware implementations, performance analysis of modern hardware architectures, and methods and tools for integrating performance evaluation into software development. We intensively participate in research projects with both academia and industry.

Resource Sharing Models

Executing software components share resources. Modeling software performance thus means modeling resource sharing, which is commonly done for resources such as processors or disks, but rarely done for resources such as memory caches or collected heaps. We investigate resource sharing within the Q-ImPrESS project.

We maintain two generic benchmarking frameworks for investigating performance related effects due to sharing of resources such as the processor core, memory architecture (memory caches, translation buffers) or file system among multiple software components.

List of the measurements of the performance related effects due to sharing of resources:

Measurement Framework

Our activities involve collecting performance related observations from heterogeneous systems. We therefore develop an extensible framework for performance measurement that allows aggregating configurable amount of data from configurable sources during configurable events. The framework is part of the Q-ImPrESS project.

More details can be found in the Ph.D. Thesis of Lubomír Bulej. You can also inspect the development version of the framework.

Performance Prediction Validation on Random Systems

Validation of performance prediction models is typically done on a few case studies, due to a lot of manual work needed to create the model and measure the implementation, in order to compare the predicted and actual performance. We have proposed an approach where systems for validation are generated together with their models, allowing validation on many systems without manual intervention.

Middleware Benchmarking

  • Comprehensive CORBA Benchmarks (Xampler)
    Comprehensive benchmarking suite for CORBA, focus on extensibility of the suite and breadth and depth of the evaluation, suitable for vendor level benchmarks. See project home page for more information, latest results and downloads.

  • Simplified CORBA Benchmarks (Sampler)
    Simplified benchmarking suite for CORBA, focus on automated execution of the suite, suitable for user level benchmarks. See project home page for more information, latest results, downloads, or for uploading your own results.

  • Generic Results Repository (SkladR)
    For storing benchmark results, we have also implemented a generic results repository. The repository can be configured to parse, store and plot arbitrary results. The implementation is available for download.

Regression Benchmarking

BEEN logo

Regression benchmarking stands as an analogy to regression testing. By running and evaluating unit benchmarks on every version of software under development, performance regressions can be discovered, pretty much the same way as running and evaluating unit tests can discover functional regressions.

Acknowledgments

Borland

Borland Software Corporation has kindly provided a research grant for developing and running some of the benchmarks.

Intel

Intel Corporation has kindly provided an equipment grant for developing and running some of the benchmarks.

IONA

IONA Technologies has kindly provided a research grant for developing and running some of the benchmarks.

Archive

2007

Linux Virtual Memory Tuning
Performance of memory intensive applications is influenced by virtual to physical memory mapping. We have developed an interface through which applications with special mapping requirements can influence the mapping strategies, implemented as kernel modules. More details.
Common Component Modeling Example
We have used our tools and models in the CoCoME modeling contest.

2004

OOPSLA'04
OOPSLA 2004 Workshop
We have organized the Workshop on Component and Middleware Performance during OOPSLA on October 25, 2004 in Vancouver, British Columbia, Canada.

2003

OOPSLA'03
OOPSLA 2003 Workshop
We have organized the Workshop on Middleware Benchmarking: Approaches, Results, Experiences during OOPSLA on October 26, 2003 in Anaheim, California, USA.

2002

CORBA Comparison Project, Part 3
We have done a benchmarking project for Borland International, USA. The final report containing the results of the measurements:
IDL Tester
A tester for CORBA IDL compilers. Generates random IDL interfaces of preset complexity and code that links with the generated stubs. More details on the tool page.
IIOP Tester
A tester for CORBA IIOP engines. Replaces a remote object reference with a remote object proxy that intercepts IIOP messages and applies configurable damage before forwarding the IIOP messages to the original object. More details on the tool page.

2000

IONA benchmarking
In March 2000, we have done a benchmarking project for IONA Technologies, PLC, Ireland. The project report is not publicly available.
Automated CORBA Benchmark Suite
In June 2000, the Automated CORBA Benchmark Suite was released. It is now deprecated by our newer CORBA benchmark suites.

1999

EJB Comparison Project
Our group launched the EJB Comparison Project for MLC Systeme GmbH, later a part of Deutsche Post under the name DP Com. The purpose of the project is to devise a sensible set of criteria for comparing Enterprise Java Beans implementations and to apply this criteria to compare four EJB servers selected by MLC (WebLogic, WebSphere, NetDynamics, GemStone/J, all of them based on EJB 1.0).
To avoid any potentially misleading extrapolation of the results relevant to the EJB 1.0 products, we only make available for a download the part of the report which outlines and describes the methodology designed for the EJB server evaluation and the results for NetDynamics, which is not evolving anymore.
CORBA Comparison Project, Part 2
In June 1999, an extension of the CORBA Comparison Project was concluded. The extension covers three more ORBs, namely omniORB 2.7.1, ORBacus 3.1.2 and Orbix 3.0, and also slightly extends the set of applied benchmarks.
The final report containing the results of the measurements, structured as an appendix to the original project report from August 16, 1999.

1998

CORBA Comparison Project, Part 1
In February 1998, our group launched a CORBA Comparison Project for MLC Systeme GmbH. The purpose of the project is to devise a sensible set of criteria for comparing ORB implementations and to apply this criteria to compare three ORBs selected by MLC (omniORB, Orbix, VisiBroker).
The final report containing the results of the measurements as PS, PS.GZ, PDF. Also results and sources of the throughput test.
The experience gained during this project lead us to sent a response to OMG Benchmarking RFI. Our response is available as an OMG document or as a technical report.

Publications

2012 (1)

Accepted

Samuel Kounev, Philipp Reinecke, Fabian Brosig, Jeremy Bradley, Kaustubh Joshi, Babka V., Anton Stefanek, Stephen Gilmore: Providing Dependability and Resilience in the Cloud: Challenges and Opportunities,
Accepted as Book Chapter in A. Avritzer, A. van Moorsel, K. Wolter, and M. Vieira: Resilience Assessment and Evaluation, Dagstuhl Seminar 10292, Springer Verlag, 2012

2011 (4)

Refereed (journals/proceedings)

PDF, Link Babka V., Tůma P.: Can Linear Approximation Improve Performance Prediction ?,
Proceedings of EPEW 2011, Borrowdale, UK, Springer-Verlag LNCS 6977, ISBN 978-3-642-24748-4, ISSN 0302-9743, pp. 250-264, October 2011

Technical Reports

PDF Keznikl J., Malohlava M., Marek L., Tůma P.: Ferdinand Project Middleware List,
Tech. Report No. 2011/2, Dep. of Distributed and Dependable Systems, Charles University in Prague, January 2011
PDF Babka V., Bulej L., Libič P., Marek L., Martinec T., Podzimek A., Tůma P.: Resource Impact Analysis,
Q-ImPrESS Project Deliverable D3.4, January 2011

Nonrefereed

Kofroň J., Plášil F.: Evolving SOA in the Q-ImPrESS Project,
Invited talk at WADT 2010, Proceedings of WADT 2010, Springer Verlag, LNCS 7137, November 2011
(preliminary version available here)

2010 (8)

Refereed (journals/proceedings)

PDF Parízek P., Yuldashev N.: Extraction of Component-Environment Interaction Model Using State Space Traversal,
In Proceedings of the 25th ACM Symposium on Applied Computing (SAC 2010), SE track, ACM, March 2010
PDF Parízek P., Plášil F.: Assume-Guarantee Verification of Software Components in SOFA 2 Framework,
In IET Software, volume 4, issue 3, ISSN 1751-8806, June 2010
PDF Kolb E., Šerý O., Weiss R.: Applicability of the BLAST Model Checker: An Industrial Case Study,
In Proceedings of PSI'09, LNCS 5947, ISBN 978-3-642-11485-4, pp. 218-229, January 2010
Link Becker S., Hauck M., Trifu M., Krogmann K., Kofroň J.: Reverse Engineering Component Models for Quality Predictions,
in Proceedings of the 14th European Conference on Software Maintenance and Reengineering, European Projects Track, (c) IEEE, ISBN: 978-0-7695-4321-5, March 2010
(preliminary version available here)
PDF, Link Babka V., Tůma P., Bulej L.: Validating Model-Driven Performance Predictions On Random Software Systems,
In the Proceedings of the Sixth International Conference on the Quality of Software Architectures (QoSA 2010, federate event of CompArch 2010), Springer-Verlag, LNCS 6093, ISBN 978-3-642-13820-1, ISSN 0302-9743, pp. 3-19, June 2010

Ph.D. Theses

PDF Šerý O.: Automated Verification of Software,
Ph.D. thesis, advisor: Frantisek Plasil, September 2010
PDF Poch T.: Towards Thread Aware Component Specifications,
Ph.D. thesis, advisor: Frantisek Plasil, September 2010

Technical Reports

PDF Babka V., Bulej L., Ciancone A., Filieri A., Hauck M., Libič P., Marek L., Stammel J., Tůma P.: Prediction Validation,
Q-ImPrESS Project Deliverable D4.2, July 2010

2009 (9)

Refereed (journals/proceedings)

PDF, Link Babka V., Tůma P.: Investigating Cache Parameters of x86 Family Processors,
In Proceedings of SPEC Benchmark Workshop 2009, Austin, TX, USA, Awarded with Kaivalya Dixit Award. Springer-Verlag, LNCS 5419, ISBN 978-3-540-93798-2, ISSN 0302-9743, pp. 77-96, January 2009
PDF, Link Libič P., Tůma P., Bulej L.: Issues in Performance Modeling of Applications with Garbage Collection,
In Proceedings of QUASOSS 2009, Amsterdam, Netherlands, ACM, ISBN 978-1-60558-709-7, pp. 3-10, August 2009
PDF, PDF, Link Babka V., Libič P., Tůma P.: Timing Penalties Associated with Cache Sharing,
In Proceedings of MASCOTS 2009, London, UK, IEEE, ISBN: 978-1-4244-4926-2, ISSN: 1526-7539, pp. 583-586, September 2009
PDF Kofroň J., Poch T., Šerý O.: TBP: Code-Oriented Component Behavior Specification,
In Proceedings of SEW-32, IEEE, ISBN 978-0-7695-3617-0, pp. 75-83, Greece, January 2009
PDF Kebrt M., Šerý O.: UnitCheck: Unit Testing and Model Checking Combined,
In Proceedings of the 7th International Symposium on Automated Technology for Verification and Analysis (ATVA'09), LNCS 5799, ISBN 978-3-642-04760-2, pp. 97-103, October 2009
PDF, Link Babka V., Marek L., Tůma P.: When Misses Differ: Investigating Impact of Cache Misses on Observed Performance,
In Proceedings of ICPADS 2009, Shenzhen, China, IEEE, ISBN: 978-0-7695-3900-3, ISSN: 1521-9097, pp. 112-119, December 2009
PDF Hocko M., Kalibera T.: Reducing Performance Non-determinism via Cache-aware Page Allocation Strategies,
Accepted at First Joint WOSP/SIPEW International Conference on Performance Engineering, September 2009

Technical Reports

PDF Bulej L., Marek L., Tůma P.: Object Instance Profiling,
Tech. Report No. 2009/7, Dep. of SW Engineering, Charles University in Prague, November 2009

Master Theses

PDF Marek L.: Parallel Processing and Software Performance,
Master thesis, advisor: Petr Tuma, January 2009

2008 (3)

Refereed (journals/proceedings)

PDF Bureš T., Děcký M., Hnětynka P., Kofroň J., Parízek P., Plášil F., Poch T., Šerý O., Tůma P.: CoCoME in SOFA,
Chapter in The Common Component Modeling Example: Comparing Software Component Models, Springer-Verlag, LNCS 5153, August 2008
PDF Bulej L., Bureš T., Coupaye T., Děcký M., Ježek P., Parízek P., Plášil F., Poch T., Rivierre N., Šerý O., Tůma P.: CoCoME in Fractal,
Chapter in The Common Component Modeling Example: Comparing Software Component Models, Springer-Verlag, LNCS 5153, August 2008

Technical Reports

PDF Babka V., Bulej L., Děcký M., Kraft J., Libič P., Marek L., Seceleanu C., Tůma P.: Resource Usage Modeling,
Q-ImPrESS Project Deliverable D3.3, September 2008

2007 (3)

Master Theses

PDF Hocko M.: Tuning Virtual Memory for Performance,
Master Thesis, advisor: Tomas Kalibera, July 2007

Nonrefereed

PDF Bureš T., Děcký M., Hnětynka P., Kofroň J., Parízek P., Plášil F., Poch T., Šerý O., Tůma P.: CoCoME in SOFA 2.0,
Poster, Intel 12th EMEA Academic Forum, Intel Corporation, 2200 Mission College Blvd., Santa Clara, CA, USA, June 2007
PDF Babka V., Děcký M., Tůma P.: Performance in CoCoME,
Poster, Intel 12th EMEA Academic Forum, Intel Corporation, 2200 Mission College Blvd., Santa Clara, CA, USA, June 2007

2006 (3)

Refereed (journals/proceedings)

PDF, PDF, Link Kalibera T., Tůma P.: Precise Regression Benchmarking with Random Effects: Improving Mono Benchmark Results,
in proceedings of Third European Performance Engineering Workshop (EPEW 2006), Budapest, Hungary, Copyright (C) Springer-Verlag, Berlin, LNCS 4054, ISBN 3-540-35362-3, ISSN 0302-9743, pp. 63-77., June 2006
PDF Kalibera T., Lehotsky J., Majda D., Repcek B., Tomcanyi M., Tomecek A., Tůma P., Urban J.: Automated Benchmarking and Analysis Tool,
in proceedings of First International Conference on Performance Evaluation Methodologies and Tools (VALUETOOLS 2006), Pisa, Italy, Copyright (C) ACM, ISBN 1-59593-504-5, October 2006

Technical Reports

PDF Kalibera T., Lehotsky J., Majda D., Repcek B., Tomcanyi M., Tomecek A., Tůma P., Urban J.: Automated Benchmarking and Analysis Tool,
Tech. Report No. 2006/8. Dept. of SW Engineering, Charles University,Prague, June 2006

2005 (4)

Refereed (journals/proceedings)

PDF, PDF Kalibera T., Bulej L., Tůma P.: Benchmark Precision and Random Initial State,
in Proceedings of the 2005 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS 2005), Cherry Hill, NJ, USA, Copyright (C) SCS, San Diego, CA, USA, pp. 853-862, ISBN 1-56555-300-4, July 2005
PDF, PDF, PDF Kalibera T., Bulej L., Tůma P.: Automated Detection of Performance Regressions: The Mono Experience,
in proceedings of the 13th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS 2005), Atlanta, GA, USA, Copyright (C) IEEE, Piscataway, New Jersey, USA, ISBN 0-7695-2458-3, ISSN 1526-7539, pp. 183-190, September 2005
PDF, Link Bulej L., Kalibera T., Tůma P.: Repeated Results Analysis for Middleware Regression Benchmarking,
in Performance Evaluation: An International Journal, Performance Modeling and Evaluation of High-Performance Parallel and Distributed Systems, vol. 60, pg. 345-358, Elsevier B.V., ISSN 0166-5316, May 2005
PDF, Link Kalibera T., Bulej L., Tůma P.: Quality Assurance in Performance: Evaluating Mono Benchmark Results,
in proceedings of the Second International Workshop on Software Quality (SOQUA 2005), Erfurt, Germany, Copyright (C) Springer-Verlag, Berlin, LNCS3712, ISBN 3-540-29033-8, ISSN 0302-9743, pp. 271-288, September 2005

2004 (2)

Refereed (journals/proceedings)

PDF, PDF, Link Kalibera T., Bulej L., Tůma P.: Generic Environment for Full Automation of Benchmarking,
in proceedings of Net.ObjectDays 2004, First International Workshop on Software Quality (SOQUA 2004), Erfurt, Germany, Copyright (C) 2004 tranSIT GmbH Ilmenau, Germany, pp. 35-41, ISBN 3-9808628-3-6 ; also in Testing of Component-Based Systems and Software Quality, Proceedings of SOQUA 2004 and TECOS 2004, LNI 58, GI 2004, pp. 125-132, ISBN 3-88579-387-3, ISSN 1617-5468, September 2004
PDF, PDF, Link Bulej L., Kalibera T., Tůma P.: Regression Benchmarking with Simple Middleware Benchmarks,
in proceedings of the 2004 International Performance Computing and Communications Conference (IPCCC 2004), International Workshop on Middleware Performance, Phoenix, AZ, USA, Copyright (C) 2004 IEEE, Piscataway, New Jersey, USA, pp. 771-776, ISBN 0-7803-8396-6, ISSN 1097-2641, April 2004

2003 (1)

Refereed (journals/proceedings)

PDF, PDF Buble A., Bulej L., Tůma P.: CORBA Benchmarking: A Course With Hidden Obstacles,
In the Proceedings of the 2003 Internation Parallel & Distributed Processing Symposium (IPDPS 2003), Workshop on Performance Modeling, Evaluation and Optimization of Parallel and Distributed Systems (PMEOPDS 2003), Nice, France, Copyright (C) 2003 IEEE, Piscataway, New Jersey, USA, ISBN 0-7695-1926-1, ISSN 1530-2075, pp. 279, CDROM DATA/W18_PMEO_11.PDF, April 2003

2002 (3)

Refereed (journals/proceedings)

PDF Tůma P., Buble A.: Overview of the CORBA Performance,
Proceedings of the 2002 EurOpen.CZ Conference, Znojmo, Czech Republic, September 2002

Master Theses

PDF, Link Strnad P.: IDL Source Generator and IDL Compiler Testing Tool,
Master Thesis, advisor: Petr Tuma, April 2002
PDF, Link Kuhn J.: IIOP Engine For Testing CORBA Implementation Robustness,
Master Thesis, advisor: Petr Tuma, September 2002

2001 (2)

Refereed (journals/proceedings)

PDF Tůma P., Buble A.: Open CORBA Benchmarking,
Proceedings of the 2001 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS 2001), Orlando, FL, Copyright (C) SCS, San Diego, CA, USA, July 2001

Technical Reports

PDF Tůma P., Buble A.: Technical Report on Open CORBA Benchmarking,
Tech. Report No. 2001/1, Dep. of SW Engineering, Charles University, Prague (slightly modified form appears in the SPECTS '01 conference proceedings), March 2001

2000 (4)

Refereed (journals/proceedings)

PDF Procházka M.: Advanced Transactions in Enterprise JavaBeans,
Proceedings of EDO 2000, Davis (CA), USA, Springer Verlag, LNCS, October 2000

Technical Reports

PDF Distributed Systems Research Group: EJB Comparison Project,
Final Project Report, Public Distribution Version, February 2000
PDF Procházka M.: Extending Transactions in Enterprise JavaBeans,
Tech. Report No. 2000/3, Dep. of SW Engineering, Charles University, Prague, 2000
PDF Procházka M., Tůma P., Pospíšil R.: Enterprise JavaBeans Benchmarking,
Tech. Report No. 2000/4, Dep. of SW Engineering, Charles University, Prague, 2000

1999 (2)

Technical Reports

PDF Distributed Systems Research Group: CORBA Comparison Project,
Project Extension Final Report, August 1999

Master Theses

PDF, PDF Buble A.: Comparing CORBA Implementations,
Master Thesis, advisor: Petr Tuma, August 1999

1998 (2)

Technical Reports

PDF Distributed Systems Research Group: CORBA Comparison Project,
Final Project Report, June 1998
PDF Plášil F., Tůma P., Buble A.: CORBA Benchmarking,
Tech. Report No. 98/7, Dep. of SW Engineering, Charles University, Prague (in a slightly modified form submitted to OMG as the Charles University Response to ORBOS Benchmark RFI as the OMG document bench/98-10-04), October 1998
Modified on 2011-10-25