Solving Enterprise Applications Performance Puzzles: Queuing Models to the Rescue

Leonid Grinshpan Ph.D. (Stamford, CT) has been working for Oracle Corporation for more than 14 years as Consulting Technical Director. His customers include Dell, Citibank, Verizon, Clorox, Bank of America, AT&T, Best Buy, Aetna and many other major enterprises. He obtained Ph.D. in queuing models of computer systems from Russian Academy of Science.

Acknowledgments ix Preface xi 1. Queuing Networks as Applications Models 1 1.1. Enterprise Applications-What Do They Have in Common?, 1 1.2. Key Performance Indicator-Transaction Time, 6 1.3. What Is Application Tuning and Sizing?, 8 1.4. Queuing Models of Enterprise Application, 9 1.5. Transaction Response Time and Transaction Profi le, 19 1.6. Network of Highways as an Analogy of the Queuing Model, 22 Take Away from the Chapter, 24 2. Building and Solving Application Models 25 2.1. Building Models, 25 Hardware Specification, 26 Model Topology, 28 A Model's Input Data, 29 Model Calibration, 31 2.2. Essentials of Queuing Networks Theory, 34 2.3. Solving Models, 39 2.4. Interpretation of Modeling Results, 47 Hardware Utilization, 47 Server Queue Length, Transaction Time, System Throughput, 51 Take Away from the Chapter, 54 3. Workload Characterization and Transaction Profiling 57 3.1. What Is Application Workload?, 57 3.2. Workload Characterization, 60 Transaction Rate and User Think Time, 61 Think Time Model, 65 Take Away from the Think Time Model, 68 Workload Deviations, 68 "Garbage in, Garbage out" Models, 68 Realistic Workload, 69 Users' Redistribution, 72 Changing Number of Users, 72 Transaction Rate Variation, 75 Take Away from "Garbage in, Garbage out" Models, 78 Number of Application Users, 78 User Concurrency Model, 80 Take Away from User Concurrency Model, 81 3.3. Business Process Analysis, 81 3.4. Mining Transactional Data from Production Applications, 88 Profi ling Transactions Using Operating System Monitors and Utilities, 88 Application Log Files, 90 Transaction Monitors, 91 Take Away from the Chapter, 93 4. Servers, CPUs, and Other Building Blocks of Application Scalability 94 4.1. Application Scalability, 94 4.2. Bottleneck Identification, 95 CPU Bottleneck, 97 CPU Bottleneck Models, 97 CPU Bottleneck Identification, 97 Additional CPUs, 100 Additional Servers, 100 Faster CPUs, 100 Take Away from the CPU Bottleneck Model, 104 I/O Bottleneck, 105 I/O Bottleneck Models, 106 I/O Bottleneck Identification, 106 Additional Disks, 107 Faster Disks, 108 Take Away from the I/O Bottleneck Model, 111 Take Away from the Chapter, 113 5. Operating System Overhead 114 5.1. Components of an Operating System, 114 5.2. Operating System Overhead, 118 System Time Models, 122 Impact of System Overhead on Transaction Time, 123 Impact of System Overhead on Hardware Utilization, 124 Take Away from the Chapter, 125 6. Software Bottlenecks 127 6.1. What Is a Software Bottleneck?, 127 6.2. Memory Bottleneck, 131 Memory Bottleneck Models, 133 Preset Upper Memory Limit, 133 Paging Effect, 138 Take Away from the Memory Bottleneck Model, 143 6.3. Thread Optimization, 144 Thread Optimization Models, 145 Thread Bottleneck Identification, 145 Correlation Among Transaction Time, CPU Utilization, and the Number of Threads, 148 Optimal Number of Threads, 150 Take Away from Thread Optimization Model, 151 6.4. Other Causes of Software Bottlenecks, 152 Transaction Affinity, 152 Connections to Database; User Sessions, 152 Limited Wait Time and Limited Wait Space, 154 Software Locks, 155 Take Away from the Chapter, 155 7. Performance and Capacity of Virtual Systems 157 7.1. What Is Virtualization?, 157 7.2. Hardware Virtualization, 160 Non-Virtualized Hosts, 161 Virtualized Hosts, 165 Queuing Theory Explains It All, 167 Virtualized Hosts Sizing After Lesson Learned, 169 7.3. Methodology of Virtual Machines Sizing, 171 Take Away from the Chapter, 172 8. Model-Based Application Sizing: Say Good-Bye to Guessing 173 8.1. Why Model-Based Sizing?, 173 8.2. A Model's Input Data, 177 Workload and Expected Transaction Time, 177 How to Obtain a Transaction Profile, 179 Hardware Platform, 182 8.3. Mapping a System into a Model, 186 8.4. Model Deliverables and What-If Scenarios, 188 Take Away from the Chapter, 193 9. Modeling Different Application Configurations 194 9.1. Geographical Distribution of Users, 194 Remote Office Models, 196 Users' Locations, 196 Network Latency, 197 Take Away from Remote Offi ce Models, 198 9.2. Accounting for the Time on End-User Computers, 198 9.3. Remote Terminal Services, 200 9.4. Cross-Platform Modeling, 201 9.5. Load Balancing and Server Farms, 203 9.6. Transaction Parallel Processing Models, 205 Concurrent Transaction Processing by a Few Servers, 205 Concurrent Transaction Processing by the Same Server, 209 Take Away from Transaction Parallel Processing Models, 213 Take Away from the Chapter, 214 Glossary 215 References 220 Index 223