Performance by Design: Computer Capacity Planning by Example

Individual organizations and society as a whole could face major breakdowns if IT systems do not meet their Quality of Service (QoS) requirements on performance, availability, security, and maintainability. Corporations stand to lose valuable income, and public interests could be put at great risk. System designers and analysts usually do not take QoS requirements into account when designing and/or analyzing computer systems, due mainly to their lack of awareness about the issues that affect performance and the lack of a framework to reason about performance. This book describes how to map real-life systems (e.g., databases, data centers, e-commerce applications) into analytic performance models. The authors elaborate upon these models, and use them to help the reader thoroughly analyze and better understand potential performance issues.

•	Table of Contents

Performance by Design: Computer Capacity Planning by Example
By Daniel A. Menasc, Virgilio A.F. Almeida, Lawrence W. Dowdy
Publisher	: Prentice Hall PTR
Pub Date	: January 05, 2004
ISBN	: 0-13-090673-5
Pages	: 552
Slots	: 2.0
				Copyright
		Preface
			Goal, Theme, and Approach
		Part I:  The Practice of Performance Engineering
			Chapter 1.  Computer System Lifecycle
				Section 1.1.  Introduction
				Section 1.2.  QoS in IT Systems
				Section 1.3.  System Life Cycle
				Section 1.4.  A Reference Model for IT Systems
				Section 1.5.  Concluding Remarks
				Section 1.6.  Exercises
				Bibliography
			Chapter 2.  From Systems to Descriptive Models
				Section 2.1.  Introduction
				Section 2.2.  Modeling
				Section 2.3.  A Simple Database Server Example
				Section 2.4.  The Database Server Example: Multiple Classes
				Section 2.5.  The Database Server Example: Open and Closed Classes
				Section 2.6.  The Database Server Example: a Mixed Model
				Section 2.7.  The Database Server Example: Types of Resources
				Section 2.8.  The Database Server Example: Blocking
				Section 2.9.  The Database Server Example: Software Contention
				Section 2.10.  Database Example: Simultaneous Resource Possession
				Section 2.11.  Database Example: Class Switching
				Section 2.12.  Database Example: Queuing Disciplines
				Section 2.13.  QN Models
				Section 2.14.  Concluding Remarks
				Section 2.15.  Exercises
				Bibliography
			Chapter 3.  Quantifying Performance Models
				Section 3.1.  Introduction
				Section 3.2.  Basic Performance Results
				Section 3.3.  Bounds on Performance
				Section 3.4.  Using QN Models
				Section 3.5.  Concluding Remarks
				Section 3.6.  Exercises
				Bibliography
			Chapter 4.  Performance Engineering Methodology
				Section 4.1.  Introduction
				Section 4.2.  Performance Engineering
				Section 4.3.  Motivating Example
				Section 4.4.  A Model-based Methodology
				Section 4.5.  Workload Model
				Section 4.6.  Performance Models
				Section 4.7.  Specifying Performance Objectives
				Section 4.8.  Concluding Remarks
				Section 4.9.  Exercises
				Bibliography
			Chapter 5.  Case Study I: A Database Service
				Section 5.1.  Introduction
				Section 5.2.  Database Service Example
				Section 5.3.  Building a Performance Model
				Section 5.4.  Using the Model
				Section 5.5.  Monitoring Tools
				Section 5.6.  Measurements Techniques
				Section 5.7.  Obtaining Input Parameters
				Section 5.8.  Concluding Remarks
				Section 5.9.  Exercises
				Bibliography
			Chapter 6.  Case Study II: A Web Server
				Section 6.1.  Introduction
				Section 6.2.  The Web Server
				Section 6.3.  Preliminary Analysis of the Workload
				Section 6.4.  Building a Performance Model
				Section 6.5.  Using the Model
				Section 6.6.  Secure Downloads
				Section 6.7.  Experimental Comparison of Two Servers
				Section 6.8.  Concluding Remarks
				Section 6.9.  Exercises
				Bibliography
			Chapter 7.  Case Study III: A Data Center
				Section 7.1.  Introduction
				Section 7.2.  The Data Center
				Section 7.3.  Building a Model
				Section 7.4.  Using the Model
				Section 7.5.  Another Modeling Approach
				Section 7.6.  A Cost Analysis
				Section 7.7.  Concluding Remarks
				Section 7.8.  Exercises
				Bibliography
			Chapter 8.  Case Study IV: An E-Business Service
				Section 8.1.  Introduction
				Section 8.2.  The E-Business Service
				Section 8.3.  The E-Business Workload
				Section 8.4.  Building a Performance Model
				Section 8.5.  Using the Performance Model
				Section 8.6.  Adding More Servers
				Section 8.7.  Concluding Remarks
				Section 8.8.  Exercises
				Bibliography
			Chapter 9.  Case Study V: A Help-Desk Service
				Section 9.1.  Introduction
				Section 9.2.  The Help Desk Service
				Section 9.3.  A Performance Model
				Section 9.4.  Techniques for SPE
				Section 9.5.  Concluding Remarks
				Section 9.6.  Exercises
				Bibliography
		Part II:  The Theory of Performance Engineering
			Chapter 10.  Markov Models
				Section 10.1.  Introduction
				Section 10.2.  Modeling Context
				Section 10.3.  Motivating Examples
				Section 10.4.  Model Construction
				Section 10.5.  Model Solution
				Section 10.6.  Model Interpretation
				Section 10.7.  Model Assumptions and Limitations
				Section 10.8.  Generalized Birth-Death Models
				Section 10.9.  Beyond the Basics
				Section 10.10.  Chapter Summary
				Section 10.11.  Exercises
				Bibliography
			Chapter 11.  Single Queue Systems
				Section 11.1.  Introduction
				Section 11.2.  Single Queue Single Server Systems
				Section 11.3.  The M/M/1 Queue
				Section 11.4.  The M/G/1 Queue
				Section 11.5.  M/G/1 with Vacations
				Section 11.6.  M/G/1 with Priorities
				Section 11.7.  Approximation Results
				Section 11.8.  Concluding Remarks
				Section 11.9.  Exercises
				Bibliography
			Chapter 12.  Single Class MVA
				Section 12.1.  Introduction
				Section 12.2.  MVA Development
				Section 12.3.  The MVA Algorithm
				Section 12.4.  Balanced Systems
				Section 12.5.  MVA Extensions and Limitations
				Section 12.6.  Chapter Summary
				Section 12.7.  Exercises
				Bibliography
			Chapter 13.  Queuing Models with Multiple Classes
				Section 13.1.  Introduction
				Section 13.2.  The Need for Multiple-Class Models
				Section 13.3.  Simple Two-Class Model
				Section 13.4.  Notation and Assumptions
				Section 13.5.  Closed Models
				Section 13.6.  Open Models
				Section 13.7.  Mixed Models
				Section 13.8.  Concluding Remarks
				Section 13.9.  Exercises
				Bibliography
			Chapter 14.  Queuing Models with Load Dependent Devices
				Section 14.1.  Introduction
				Section 14.2.  Motivating Example
				Section 14.3.  Single Class Models with LD Devices
				Section 14.4.  Multiclass Closed Models with LD Devices
				Section 14.5.  Multiclass Open Models with LD Devices
				Section 14.6.  Flow-Equivalent Server Method
				Section 14.7.  Concluding Remarks
				Section 14.8.  Exercises
				Bibliography
			Chapter 15.  Non Product-Form Queuing Models
				Section 15.1.  Introduction
				Section 15.2.  Modeling High Service Time Variability
				Section 15.3.  Modeling Blocking Effects
				Section 15.4.  Modeling Priority Scheduling
				Section 15.5.  Modeling Software Contention
				Section 15.6.  Modeling Fork/Join Queuing Networks
				Section 15.7.  Concluding Remarks
				Section 15.8.  Exercises
				Bibliography