Solving Enterprise Applications Performance Puzzle Puzzles – Queuing Models to the Rescue

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