Performance Engineering: Learning Through Applications Using JMT

This open access book improves the users' skills needed to implement models for performance evaluation of digital infrastructures. Building a model is usually a relatively easy task, but making it an accurate representation of the phenomenon to be reproduced is a completely different matter. It is well-known that to increase the ability to build reliable models it is necessary to accumulate experience. The book addresses this need by presenting a collection of case studies of increasing complexity. Readers are introduced to the modeling process gradually, learning the basic concepts step-by-step as they go through the case studies. Queueing Networks are used to design the models solved with simulation and analytical techniques from the open source Java Modelling Tools (JMT). Among the models analyzed there are systems for optimizing performance, identifying bottlenecks, evaluating the impact of the variability of traffic and service demands, analyzing the effects of synchronization policies in parallel computing. Four case studies derived from real-life scenarios are also presented: a surveillance system, autoscaling load fluctuations, web app workflow simulation, and crowd computing platform. This book serves as a reference tool for graduate and senior-level computer science students in courses of performance evaluation and modeling, as well as for researchers and practitioners. 603597_1_En_OFC 603597_1_En_BookFrontmatter_OnlinePDF Preface Acknowledgments Contents 603597_1_En_1_Chapter_OnlinePDF 1 The Process of Modeling 1.1 Model Implementation 1.2 Inputs and Outputs of Models 1.3 Parameterization of Simulation Models 1.4 Parameterization of Analytical Models 603597_1_En_2_Chapter_OnlinePDF 2 Systems with Homogeneous Workloads 2.1 A Web Server with External Workload 2.1.1 Problem Description 2.1.2 Model Implementation 2.1.3 Results 2.2 A Computing Infrastructure with a Closed Workload 2.2.1 Problem Description 2.2.2 Model Implementation 2.2.3 Results 2.3 Equivalent Model with Service Demands 2.3.1 Problem Description 2.3.2 Model Implementation 2.3.3 Results 2.4 Optimal Operating Point of a Server 2.4.1 Problem Description 2.4.2 Model Implementation 2.4.3 Results 2.4.4 Limitations and Improvements 603597_1_En_3_Chapter_OnlinePDF 3 Systems with Heterogeneous Workloads 3.1 Parameterization of Heterogeneous Workloads 3.2 Motivating Example of Multiclass Models 3.2.1 Problem Description 3.2.2 Model Implementation 3.2.3 Results 3.3 Performance Optimization of a Data Center 3.3.1 Problem Description 3.3.2 Model Implementation 3.3.3 Results 603597_1_En_4_Chapter_OnlinePDF 4 Impact of Variability of Interarrival and Service Times 4.1 Importance of Distributions: A Motivating Example 4.2 Variability of Interarrival Times 4.2.1 Problem Description 4.2.2 Model Implementation 4.2.3 Results 4.3 Variability of Service Times 4.3.1 Problem Description 4.3.2 Model Implementation 4.3.3 Results 603597_1_En_5_Chapter_OnlinePDF 5 Parallel Computing 5.1 Synchronization of All Parallel Tasks 5.1.1 Problem Description 5.1.2 Model Implementation 5.1.3 Results 5.1.4 Limitations and Improvements 5.2 Impact of Variance on Synchronization 5.2.1 Problem Description 5.2.2 Model Implementation 5.2.3 Results 5.2.4 Limitations and Improvements 5.3 Synchronization on the Fastest Task 5.3.1 Problem Description 5.3.2 Model Implementation 5.3.3 Results 603597_1_En_6_Chapter_OnlinePDF 6 Reference Models 6.1 A Facial Recognition Surveillance System 6.1.1 Problem Description 6.1.2 Model Implementation 6.1.3 Results 6.1.4 Limitations and Improvements 6.2 Autoscaling Load Fluctuations 6.2.1 Problem Description 6.2.2 Model Implementation 6.2.3 Results 6.2.4 Limitations and Improvements 6.3 Simulation of the Workflow of a Web App 6.3.1 Problem Description 6.3.2 Model Implementation 6.3.3 Results 6.3.4 Limitations and Improvements 6.4 A Crowd Computing Platform 6.4.1 Problem Description 6.4.2 Model Implementation 6.4.3 Results 603597_1_En_BookBackmatter_OnlinePDF Appendix A What May Be Useful to Know A.1 Routing Probabilities Versus Visits to Resources A.2 Confidence Intervals A.3 Details on Reliability Models of Chap. 5 A.4 Models Described in the Book Appendix References