Freiberger Statistical Computer Performance Evaluation

1. Auflage 2014
ISBN: 978-1-4832-6094-5
Verlag: Elsevier Science & Techn.
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 530 Seiten, Web PDF

Statistical Computer Performance Evaluation contains the proceedings of a Conference on Statistical Computer Performance Evaluation held at Brown University in Providence, Rhode Island, on November 22-23, 1971, under the auspices of the Division of Applied Mathematics and the Center for Computer and Information Sciences. The papers review the application of quantitative, and particularly statistical, methods to the study of computer performance. Comprised of 19 chapters, this book begins with an overview of the state of the art of computer system evaluation and some quantitative methods (analytical, simulation, and empirical methods) that are applicable to the problem. A utility theoretic approach to evaluation of a time-sharing system is then described, followed by a discussion on the results of a multi-factor paging experiment. Subsequent chapters focus on statistical quantification of instruction and operand traces; measurement and improvement of program behavior under paging systems; free-storage algorithms; and probabilistic models for predicting software reliability. This monograph will be of interest to practitioners in the fields ofcomputer science and applied mathematics.

Autoren/Hrsg.

Freiberger, Walter

Inhaltsverzeichnis

1;Front Cover;1
2;Statistical Computer Performance Evaluation;4
3;Copyright Page;5
4;Table of Contents;6
5;AUTHORS, DISCUSSANTS, AND SESSION CHAIRMEN;10
6;PREFACE;14
7;FOREWORD;16
8;SESSION I: GENERAL APPROACHES;20
8.1;CHAPTER 1. QUANTITATIVE METHODS FOR EVALUATING COMPUTER SYSTEM PERFORMANCE: A REVIEW AND PROPOSALS;22
8.1.1;ABSTRACT;22
8.1.2;I. INTRODUCTION: STATE OF THE ART;22
8.1.3;II. THE QUANTITATIVE APPROACH;26
8.1.4;III. CONCLUSION: THE ASSESSMENT;41
8.1.5;Acknowledgment;42
8.1.6;REFERENCES;42
8.2;CHAPTER 2. A UTILITY THEORETIC APPROACH TO EVALUATION OF A TIME-SHARING SYSTEM;44
8.2.1;INTRODUCTION;44
8.2.2;THE METHOD OF ANALYSIS;44
8.2.3;UTILITY THEORY;45
8.2.4;EXPERIMENTAL DETERMINATION OF A MULTI-DIMENSIONAL UTILITY FUNCTION;47
8.2.5;AN EXAMPLE;49
8.2.6;A UTILITY FUNCTION;52
8.2.7;OBSERVATIONS AND CONCLUSIONS;54
8.2.8;FURTHER RESEARCH;55
8.2.9;SUMMARY;56
8.2.10;BIBLIOGRAPHY;57
8.2.11;APPENDIX;66
8.3;DISCUSSION OF SESSION I;70
9;SESSION II: EVALUATION OF CURRENT SYSTEMS;74
9.1;CHAPTER 3. MODELLING THE PERFORMANCE OF THE OS/360 TIME-SHARING OPTION (TSO);76
9.1.1;ABSTRACT;76
9.1.2;INTRODUCTION;76
9.1.3;THE MODEL;78
9.1.4;USE OF THE MODEL TO PROJECT PERFORMANCE;81
9.1.5;USE OF THE MODEL FOR PERFORMANCE PREDICTION;81
9.1.6;SYSTEM MEASUREMENT;83
9.1.7;MEASUREMENT VERSUS PREDICTIONS;84
9.1.8;SUMMARY;86
9.1.9;REFERENCES;87
9.2;CHAPTER 4. A STATISTICAL EVALUATION OF THE SCHEDULER OF AN EXPERIMENTAL INTERACTIVE COMPUTING SYSTEM;92
9.2.1;ABSTRACT;92
9.2.2;INTRODUCTION;92
9.2.3;THE EXPERIMENTAL IBM APL\360 SYSTEM;93
9.2.4;CHARACTERIZATION OF THE USERS' COMPUTER SERVICE TIME DEMANDS;95
9.2.5;DESIGN OF EXPERIMENT CONSIDERATIONS;98
9.2.6;RESULTS OF THE 32 FACTORIAL DESIGN OF EXPERIMENTS;101
9.2.7;REGRESSION MODELS FOR THE PERFORMANCE MEASURES;102
9.2.8;CONCLUSIONS;106
9.2.9;Acknowledgements;107
9.2.10;BIBLIOGRAPHY;107
9.3;DISCUSSION OF SESSION II;118
10;SESSION III: DESIGN OF EXPERIMENTS;120
10.1;CHAPTER 5. A MULTI-FACTOR PAGING EXPERIMENT: I. THE EXPERIMENT AND THE CONCLUSIONS;122
10.1.1;ABSTRACT;122
10.1.2;1. INTRODUCTION;122
10.1.3;2. PROBLEMS UNDER INVESTIGATION;124
10.1.4;3. EXPERIMENTAL ENVIRONMENT;124
10.1.5;4. DESCRIPTION OF THE EXPERIMENT;125
10.1.6;5. CONCLUSIONS;130
10.1.7;Acknowledgements;132
10.1.8;REFERENCES;133
10.1.9;APPENDIX I: FREQUENCY DISTRIBUTION OF AC, f(x);136
10.1.10;APPENDIX II: FREQUENCY DISTRIBUTION OF IC, g(y;145
10.2;CHAPTER 6. A MULTI-FACTOR PAGING EXPERIMENT: II. STATISTICAL METHODOLOGY;154
10.2.1;ABSTRACT;154
10.2.2;1. INTRODUCTION;154
10.2.3;2. METHODOLOGICAL CONSIDERATIONS;154
10.2.4;3. PLANNING OF THE EXPERIMENT;157
10.2.5;4. INDICATION: PRELIMINARY DATA SCANNING;157
10.2.6;5. EMPIRICAL MODEL BUILDING;160
10.2.7;6. CALIBRATION OF THE FITTED MODEL;162
10.2.8;7. QUANTIFICATION OF EXPERIMENTAL CONCLUSIONS;166
10.2.9;8. FINAL REMARKS;168
10.2.10;REFERENCES;168
10.2.11;APPENDIX A;172
10.2.12;APPENDIX B: DISCUSSION OF INTERACTION;177
10.3;DISCUSSION OF SESSION III;178
11;SESSION IV: INPUT ANALYSIS;182
11.1;CHAPTER 7. A COMPUTER PERFORMANCE MONITOR AND MARKOV ANALYSIS FOR MULTIPROCESSOR SYSTEM EVALUATION;184
11.1.1;1. INTRODUCTION;184
11.1.2;2. GENERAL DISCUSSION;194
11.1.3;3. DATA SUMMARIZATION AND RESULTS;198
11.1.4;4. MATHEMATICAL MODEL OF THE EXEC 8 NINE-MODULE SYSTEM;202
11.1.5;REFERENCES;213
11.2;CHAPTER 8. STATISTICAL QUANTIFICATION OF INSTRUCTION AND OPERAND TRACES;246
11.2.1;ABSTRACT;246
11.2.2;INTRODUCTION;247
11.2.3;STATISTICAL ANALYSIS OF A TRACE;249
11.2.4;EXTRAPOLATION TO MULTIPROGRAMMING AND MULTIPROCESSING MODES FROM UNIPROGRAMMING MODE;251
11.2.5;ILLUSTRATION OF STATISTICS FROM A SAMPLE DATA STREAM;251
11.2.6;SUMMARY;253
11.2.7;REFERENCES;253
11.3;CHAPTER 9. MEASUREMENT AND IMPROVEMENT OF PROGRAM BEHAVIOR UNDER PAGING SYSTEMS;260
11.3.1;I. INTRODUCTION;260
11.3.2;II. PARAMETERS OF A PAGING SYSTEM. APPROPRIATE MEASUREMENTS;260
11.3.3;III. A SOFTWARE PAGING SYSTEM;264
11.3.4;IV. EXPERIMENTS;267
11.3.5;V. CONCLUSION;270
11.3.6;Acknowledgments;270
11.3.7;REFERENCES;270
11.4;CHAPTER 10. STATISTICAL ANALYSIS OF SERIES OF EVENTS IN COMPUTER SYSTEMS;284
11.4.1;SUMMARY;284
11.4.2;I. INTRODUCTION: THE SASE IV PROGRAM;284
11.4.3;II. RECENT DEVELOPMENTS;287
11.4.4;III. ANALYSIS OF ARRIVAL DATA;291
11.4.5;DISCUSSION;293
11.4.6;REFERENCES;293
11.5;DISCUSSION OF SESSION IV;300
12;SESSION V: REGRESSION ANALYSIS;304
12.1;CHAPTER 11. AN APPLICATION OF STATISTICAL METHODOLOGY IN THE STUDY OF COMPUTER SYSTEM PERFORMANCE;306
12.1.1;ABSTRACT;306
12.1.2;1. INTRODUCTION;306
12.1.3;2. METHODOLOGY;307
12.1.4;3. RESULTS, DISCUSSION, VALIDATION AND PHYSICAL INTERPRETATION OF THE MODEL;311
12.1.5;4. POSSIBLE APPLICATIONS OF THE MODEL AND GENERAL CONCLUSIONS;313
12.1.6;5. FUTURE DIRECTIONS;315
12.1.7;Acknowledgments;316
12.1.8;REFERENCES;316
12.1.9;APPENDIX I: DESCRIPTION OF SYSTEM A;334
12.1.10;APPENDIX II;335
12.1.11;APPENDIX III;340
12.1.12;APPENDIX IV: DESCRIPTION OF SYSTEM B;343
12.1.13;APPENDIX V: CPU/CH OVERLAP MODEL;343
12.2;CHAPTER 12. ON THE STRUCTURE OF CP-67 OVERHEAD;348
12.2.1;INTRODUCTION;348
12.2.2;THE VARIABLES;348
12.2.3;THE DATA;350
12.2.4;REGRESSION ON PRIMARY VARIABLES;350
12.2.5;REGRESSION ON ALL VARIABLES;351
12.2.6;PRINCIPAL COMPONENT ANALYSIS;352
12.2.7;REGRESSION ON MODIFIED VARIABLES;354
12.2.8;CONCLUSIONS;355
12.2.9;Acknowledgement;355
12.2.10;Disclaimer;356
12.2.11;REFERENCES;356
12.3;CHAPTER 13. THE USE OF PURE AND MODIFIED REGRESSION TECHNIQUES FOR DEVELOPING SYSTEMS PERFORMANCE ALGORITHMS;366
12.3.1;ABSTRACT;366
12.3.2;THE MODELS;374
12.3.3;Acknowledgements;378
12.3.4;APPENDIX A;381
12.3.5;APPENDIX B;384
12.4;DISCUSSION OF SESSION V;390
13;SESSION VI: SYSTEMS MANAGEMENT;394
13.1;CHAPTER 14. ANALYSIS OF FREE-STORAGE ALGORITHMS;396
13.1.1;ABSTRACT;396
13.1.2;BACKGROUND;397
13.1.3;DATA GATHERING;399
13.1.4;DYNAMIC CHAINS AND POOLING STUDIES;406
13.1.5;ON-LINE EXPERIMENTATION;412
13.1.6;Acknowledgement;414
13.1.7;REFERENCES;414
13.2;CHAPTER 15. LOCALITY: WORKING SET, REQUEST STRING, DISTANCE FUNCTION AND REPLACEMENT STACK;426
13.2.1;REFERENCES;434
13.3;CHAPTER 16. STATISTICAL METHODOLOGY FOR CALIBRATING A TRACE-DRIVEN SIMULATOR OF A BATCH COMPUTER SYSTEM;442
13.3.1;ABSTRACT;442
13.3.2;1. INTRODUCTION;442
13.3.3;2. THE PROJECT: A BRIEF DESCRIPTION;444
13.3.4;3. GOODNESS OF FIT AND FIGURES OF MERIT;445
13.3.5;4. METHODS FOR TUNING THE MODEL;448
13.3.6;5. A DECISION METHOD: VALIDATING IMPROVEMENT IN THE GOODNESS OF FIT;453
13.3.7;6. THE CALIBRATION PROCESS IN DETAIL;454
13.3.8;7. PLANS;457
13.3.9;Acknowledgments;459
13.3.10;REFERENCES;460
13.3.11;APPENDIX A;470
13.3.12;APPENDIX B;476
13.4;DISCUSSION OF SESSION VI;480
14;SESSION VII: SOFTWARE RELIABILITY;482
14.1;CHAPTER 17. SOFTWARE RELIABILITY RESEARCH;484
14.1.1;INTRODUCTION AND SUMMARY;484
14.1.2;STATE-OF-THE-ART REVIEW;484
14.1.3;DEFINITIONS;487
14.1.4;IMPORTANCE OF SOFTWARE RELIABILITY;487
14.1.5;PROGRAM TESTING TRANSLATOR;489
14.1.6;SOFTWARE RELIABILITY RESEARCH OBJECTIVES;489
14.1.7;SOURCES OF DATA;490
14.1.8;MODEL DEVELOPMENT;491
14.1.9;APPLICATION;494
14.1.10;REFINEMENTS;496
14.1.11;MODULARITY AND RELIABILITY;498
14.1.12;CONCLUSION;498
14.1.13;REFERENCES;499
14.2;CHAPTER 18. PROBABILISTIC MODELS FOR SOFTWARE RELIABILITY PREDICTION;504
14.2.1;Summary;504
14.2.2;INTRODUCTION;504
14.2.3;ERROR MODEL;506
14.2.4;RELIABILITY MODEL;508
14.2.5;EXPONENTIAL ERROR RATE MODEL;511
14.2.6;VARYING-MANPOWER MODEL;512
14.2.7;EVALUATION OF MODEL CONSTANTS;514
14.2.8;CONCLUSIONS;515
14.2.9;REFERENCES;516
14.3;CHAPTER 19. AN INTRODUCTION TO GROWTH DYNAMICS;522
14.3.1;1. PROJECT STATISTIC;522
14.3.2;2. GROWTH DYNAMICS;523
14.3.3;3. THE MACRO-MODEL;524
14.3.4;4. THE MICRO-MODEL;525
14.3.5;5. CITIES AND OTHER SYSTEMS;526
14.3.6;REFERENCES;526
14.4;DISCUSSION OF SESSION VII;532