9780130906731

Practical systems modeling: planning performance, availability, security, and moreComputing systems must meet increasingly strict Quality of Service (QoS) requirements for performance, availability, security, and maintainability. To achieve these goals, designers, analysts, and capacity planners need a far more thorough understanding of QoS issues, and the implications of their decisions. Now, three leading experts present a complete, application-driven framework for understanding and estimating performance. You'll learn exactly how to map real-life systems to accurate performance models, and use those models to make better decisions--both up front and throughout the entire system lifecycle. Coverage includes: State-of-the-art quantitative analysis techniques, supported by extensive numerical examples and exercisesQoS issues in requirements analysis, specification, design, development, testing, deployment, operation, and system evolution Specific scenarios, including e-Business and database services, servers, clusters, and data centersTechniques for identifying potential congestion at both software and hardware levelsPerformance Engineering concepts and toolsDetailed solution techniques including exact and approximate MVA and Markov ChainsModeling of software contention, fork-and-join, service rate variability, and priorityAbout the Web SiteThe accompanying Web site provides companion Excel workbooks that implement many of the book's algorithms and numerical examples.

TERM	PRICE	DUE
SEMESTER	$47.51	Dec 13
QUARTER	$45.13	Aug 16
SHORT TERM	$42.76	Jul 01

Lawrence W. Dowdy is Professor and former Chair of Computer Science at Vanderbilt University.

Preface	p. 1
The Practice of Performance Engineering	p. 9
Computer System Lifecycle	p. 11
Introduction	p. 11
QoS in IT Systems	p. 12
Response Time	p. 13
Throughput	p. 13
Availability	p. 16
Reliability	p. 18
Security	p. 18
Scalability	p. 19
Extensibility	p. 19
System Life Cycle	p. 19
Requirements Analysis and Specification	p. 20
System Design	p. 22
System Development	p. 23
System Testing	p. 23
System Deployment	p. 24
System Operation	p. 24
System Evolution	p. 26
A Reference Model for IT Systems	p. 27
Concluding Remarks	p. 28
Exercises	p. 30
Bibliography	p. 31
From Systems to Descriptive Models	p. 35
Introduction	p. 35
Modeling	p. 36
A Simple Database Server Example	p. 38
The Database Server Example: Multiple Classes	p. 40
The Database Server Example: Open and Closed Classes	p. 42
The Database Server Example: a Mixed Model	p. 43
The Database Server Example: Types of Resources	p. 45
The Database Server Example: Blocking	p. 46
The Database Server Example: Software Contention	p. 48
Database Example: Simultaneous Resource Possession	p. 49
Database Example: Class Switching	p. 51
Database Example: Queuing Disciplines	p. 52
QN Models	p. 53
Concluding Remarks	p. 57
Exercises	p. 57
Bibliography	p. 59
Quantifying Performance Models	p. 61
Introduction	p. 61
Basic Performance Results	p. 61
Utilization Law	p. 64
Service Demand Law	p. 65
The Forced Flow Law	p. 68
Little's Law	p. 69
Interactive Response Time Law	p. 72
Bounds on Performance	p. 74
Using QN Models	p. 80
Concluding Remarks	p. 83
Exercises	p. 84
Bibliography	p. 87
Performance Engineering Methodology	p. 89
Introduction	p. 89
Performance Engineering	p. 90
Motivating Example	p. 92
A Model-based Methodology	p. 99
Workload Model	p. 103
Types of Workload Models	p. 103
Clustering Analysis	p. 106
Performance Models	p. 108
Specifying Performance Objectives	p. 110
Specifying a Service Level Agreement	p. 111
Specifying Response Time	p. 112
Specifying Cost	p. 113
Concluding Remarks	p. 116
Exercises	p. 117
Bibliography	p. 117
Case Study I: A Database Service	p. 121
Introduction	p. 121
Database Service Example	p. 121
Preliminary Analysis of the Workload	p. 122
Workload Clustering	p. 124
Building a Performance Model	p. 126
Apportioning Total Utilization to Individual Classes	p. 127
Computing Service Demands	p. 129
Using the Model	p. 130
Adding a Third Disk	p. 131
Using a Dual CPU System	p. 133
Using Faster Disks	p. 134
Moving to a 4-CPU System	p. 135
Monitoring Tools	p. 135
Hardware Monitors	p. 136
Software Monitors	p. 137
Hybrid Monitors	p. 139
Event-trace Monitoring	p. 139
Sampling Monitoring	p. 140
Measurements Techniques	p. 141
Obtaining Input Parameters	p. 142
Measuring CPU Utilization	p. 143
Overhead Representation	p. 150
Arrival Rate	p. 151
Concurrency Level	p. 152
Number of Active Terminals and Think Time	p. 153
CPU Service Demand	p. 154
I/O Service Demands	p. 156
Concluding Remarks	p. 158
Exercises	p. 159
Bibliography	p. 162
Case Study II: A Web Server	p. 165
Introduction	p. 165
The Web Server	p. 165
Preliminary Analysis of the Workload	p. 166
Building a Performance Model	p. 169
Computing Concurrency Levels	p. 170
Computing Service Demands	p. 170
Using the Model	p. 173
Secure Downloads	p. 177
Experimental Comparison of Two Servers	p. 179
Concluding Remarks	p. 183
Exercises	p. 183
Bibliography	p. 185
Case Study III: A Data Center	p. 187
Introduction	p. 187
The Data Center	p. 188
Building a Model	p. 190
Using the Model	p. 192
Another Modeling Approach	p. 198
A Cost Analysis	p. 200
Concluding Remarks	p. 201
Exercises	p. 202
Bibliography	p. 202
Case Study IV: An E-Business Service	p. 205
Introduction	p. 205
The E-Business Service	p. 205
The E-Business Workload	p. 206
Building a Performance Model	p. 209
Using the Performance Model	p. 212
Adding More Servers	p. 214
Concluding Remarks	p. 217
Exercises	p. 218
Bibliography	p. 219
Case Study V: A Help-Desk Service	p. 221
Introduction	p. 221
The Help Desk Service	p. 224
Workload Characterization	p. 225
Database Design	p. 227
Transaction Logic	p. 229
A Performance Model	p. 233
Estimating the Number of I/Os	p. 233
Estimating Service Demands	p. 239
Techniques for SPE	p. 241
Obtaining Data for SPE	p. 243
Concluding Remarks	p. 244
Exercises	p. 245
Bibliography	p. 248
The Theory of Performance Engineering	p. 251
Markov Models	p. 253
Introduction	p. 253
Modeling Context	p. 255
Motivating Examples	p. 258
Model Construction	p. 262
Model Solution	p. 267
Model Interpretation	p. 272
Model Assumptions and Limitations	p. 276
Generalized Birth-Death Models	p. 279
Beyond the Basics	p. 280
Chapter Summary	p. 283
Exercises	p. 284
Bibliography	p. 288
Single Queue Systems	p. 291
Introduction	p. 291
Single-Line Single-Server Systems	p. 292
The M/M/1 Queue	p. 294
The M/G/1 Queue	p. 296
M/G/1 with Vacations	p. 298
M/G/1 with Priorities	p. 301
Non-Preemptive Priorities	p. 303
Preemptive Resume Priorities	p. 304
Approximation Results	p. 305
Concluding Remarks	p. 308
Exercises	p. 308
Bibliography	p. 310
Single Class MVA	p. 311
Introduction	p. 311
MVA Development	p. 312
The MVA Algorithm	p. 323
Balanced Systems	p. 327
MVA Extensions and Limitations	p. 331
Chapter Summary	p. 332
Exercises	p. 332
Bibliography	p. 335
Queuing Models with Multiple Classes	p. 337
Introduction	p. 337
The Need for Multiple-Class Models	p. 338
Simple Two-Class Model	p. 341
Notation and Assumptions	p. 345
Closed Models	p. 349
Exact Solution Algorithm	p. 352
Closed Models: Case Study	p. 353
Approximate Solution Algorithms	p. 357
Open Models	p. 360
Analysis of Multiclass Open Models	p. 363
Open Models: Case Study	p. 365
Mixed Models	p. 370
Concluding Remarks	p. 374
Exercises	p. 374
Bibliography	p. 377
Queuing Models with Load Dependent Devices	p. 379
Introduction	p. 379
Motivating Example	p. 380
Client-Server Performance	p. 381
Design Questions for a CS Application	p. 383
System and Workload Specification	p. 385
Single Class Models with LD Devices	p. 386
Multiclass Closed Models with LD Devices	p. 392
Multiclass Open Models with LD Devices	p. 397
Flow-Equivalent Server Method	p. 403
Concluding Remarks	p. 406
Exercises	p. 407
Bibliography	p. 408
Non Product-Form Queuing Models	p. 411
Introduction	p. 411
Modeling High Service Time Variability	p. 412
The Decomposition Approach	p. 413
New MVA-based Decomposition Approach	p. 416
Modeling Blocking Effects	p. 417
Single Class	p. 419
Multiple Classes	p. 422
Modeling Priority Scheduling	p. 426
Two-Priority Example	p. 427
SWIC Priority Algorithm	p. 430
Modeling Software Contention	p. 432
Single Class Algorithm	p. 434
Open QN at the Software Level	p. 440
The Multiclass Algorithm	p. 442
Modeling Fork/Join Queuing Networks	p. 444
Concluding Remarks	p. 448
Exercises	p. 448
Bibliography	p. 449
Subject Index	p. 454
Table of Contents provided by Ingram. All Rights Reserved.

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.

Amazon no longer offers textbook rentals. We do!

Performance by Design Computer Capacity Planning By Example

Performance by Design Computer Capacity Planning By Example

0130906735

Summary

Author Biography

Table of Contents

Supplemental Materials

Excerpts

Write a Review