Reliable Computer Systems (eBook)

Design and Evaluatuion

Daniel Siewiorek, Robert Swarz (Autoren)

eBook Download: PDF

2014 | 2. Auflage
908 Seiten
Elsevier Science (Verlag)
978-1-4832-9743-9 (ISBN)

Infos

Enhance your hardware/software reliability Enhancement of system reliability has been a major concern of computer users and designers ¦ and this major revision of the 1982 classic meets users' continuing need for practical information on this pressing topic. Included are case studies of reliable systems from manufacturers such as Tandem, Stratus, IBM, and Digital, as well as coverage of special systems such as the Galileo Orbiter fault protection system and AT&T telephone switching processors.

Inhalt

Front Cover 1
Reliable Computer Systems: Design and Evaluation 4
Copyright Page 5
Table of Contents 8
Dedication 6
Preface 16
PART I: THE THEORY OF RELIABLE SYSTEM DESIGN 22
CHAPTER 1. FUNDAMENTAL CONCEPTS 24
Physical Levels in a Digital System 26
Temporal Stages of a Digital System 27
Cost of a Digital System 39
Summary 42
References 42
CHAPTER 2 . FAULTS AND THEIR MANIFESTATIONS 43
System Errors 45
Fault Manifestations 52
Fault Distributions 70
Distribution Models for Permanent Faults: The MIL-HDBK-217 Model 78
Distribution Models for Intermittent and Transient Faults 86
Software Fault Models 94
Summary 97
References 97
Problems 98
CHAPTER 
100 
System-Failure Response Stages 101
Hardware Fault-Avoidance Techniques 105
Hardware Fault-Detection Techniques 117
Hardware Masking Redundancy Techniques 159
Hardware Dynamic Redundancy Techniques 190
Software Reliability Techniques 222
Summary 240
References 240
Problems 242
CHAPTER 
249 
Specification-Based Diagnosis 250
Symptom-Based Diagnosis 281
Summary 289
References 289
Problems 290
CHAPTER 
292 
Introduction 292
Survey of Evaluation Criteria: Hardware 293
Survey of Evaluation Criteria: Software 300
Reliability Modeling Techniques: Combinatorial Models 306
Examples of Combinatorial Modeling 315
Reliability and Availability Modeling Techniques: Markov Models 326
Examples of Markov Modeling 355
Availability Modeling Techniques 363
Software Assistance for Modeling Techniques 370
Applications of Modeling Techniques to Systems Designs 377
Summary 412
References 412
Problems 413
CHAPTER 
423 
Fundamental Concepts 423
Cost Models 429
Summary 440
References 440
Problems 441
PART II: THE PRACTICE OF RELIABLE SYSTEM DESIGN 444
Fundamental Concep 445
General-Purpose Computing 445
High-Availability Systems 445
Long-Life Systems 446
Critical Computations 446
CHAPTER 
448 
Introduction 448
Generic Computer 448
DEC 451
IBM 452
The DEC Case: RAMP in the VAX Family 454
The VAX Architecture 454
First-Generation VAX Implementations 460
Second-Generation VAX Implementations 476
References 505
The IBM Case Part I: Reliability, Availability, and Serviceability in IBM 308X and IBM 3090 Processor Complexes 506
Technology 506
Manufacturing 507
Overview of the 3090 Processor Complex 514
References 528
The IBM Case Part II: Recovery Through Programming: MVS Recovery Management 529
Introduction 529
RAS Objectives 530
Overview of Recovery Management 530
MVS/XA Hardware Error Recovery 532
MVS/XA Serviceability Facilities 541
Availability 543
Summary 544
Bibliography 544
Reference 544
CHAPTER 
545 
Introduction 545
AT& T Switching Systems
Tandem Computers, Inc 549
Stratus Computers, Inc 552
References 554
The AT& T Case Part I: Fault-Tolerant Design of AT&
Introduction 554
Allocation and Causes of System Downtime 555
Duplex Architecture 556
Fault Simulation Techniques 559
First-Generation ESS Processors 561
Second-Generation Processors 565
Third-Generation 3B20D Processor 572
Summary 593
References 594
The AT& T Case Part II: Large-Scale Real-Time Program Retrofit Methodology in AT&
5ESS Switch Architecture Overview 595
Software Replacement 597
Summary 606
References 607
The Tandem Case: Fault Tolerance in Tandem Computer Systems 607
Hardware 609
Processor Module Implementation Details 618
Integrity S2 639
Maintenance Facilities and Practices 643
Software 646
Operations 668
Summary and Conclusions 668
References 669
The Stratus Case: The Stratus Architecture 669
Stratus Solutions to Downtime 671
Issues of Fault Tolerance 673
System Architecture Overview 674
Recovery Scenarios 685
Architecture Tradeoffs 686
Stratus Software 687
Service Strategies 690
Summary 691
CHAPTER 
692 
Introduction 692
Generic Spacecraft 692
Deep-Space Planetary Probes 697
Other Noteworthy Spacecraft Designs 700
References 700
The Galileo Case: Galileo Orbiter Fault Protection System 700
The Galileo Spacecraft 701
Attitude and Articulation Control Subsystem 701
Command and Data Subsystem 704
AACS/CDS Interactions 708
Sequences and Fault Protection 709
Fault-Protection Design Problems and Their Resolution 710
Summary 711
References 711
CHAPTER 
712 
Introduction 712
C.vmp 712
SIFT 714
The C.vmp Case: A Voted Multiprocessor 715
System Architecture 715
Issues of Processor Synchronization 720
Performance Measurements 723
Operational Experiences 728
References 730
The SIFT Case: Design and Analysis of a Fault-Tolerant Computer for Aircraft Control 731
Motivation and Background 731
SIFT Concept of Fault Tolerance 732
The SIFT Hardware 740
The Software System 744
The Proof of Correctness 749
Summary 754
Appendix: Sample Special Specification 754
References 756
PART III: A DESIGN METHODOLOGY AND EXAMPLE OF DEPENDABLE SYSTEM DESIGN 758
CHAPTER 
760 
Introduction 760
A Design Methodology for Dependable System Design 760
The VAXft 310 Case: A Fault-Tolerant System by Digital Equipment Corporation 766
Defining Design Goals and Requirements for the VAXft 310 767
VAXft 310 Overview 768
Details of VAXft 310 Operation 777
Summary 787
APPENDIXES 790
APPENDIX A 792
Error-Correcting Codes for Semiconductor Memory Applications: A State-of-the-Art Review 792
Introduction 792
Binary Linear Block Codes 794
SEC-DEC Codes 796
SEC-DED-SBD Codes 799
SBC-DBD Codes 800
DEC-TED Codes 802
Extended Error Correction 805
Conclusions 807
References 807
APPENDIX B 808
Arithmetic Error Codes: Cost and Effectiveness Studies for Application in Digital System Design 808
Methodology of Code Evaluation 808
Fault Effects in Binary Arithmetic Processors 811
Low-Cost Radix-2 Arithmetic Codes 815
Multiple Arithmetic Error Codes 820
References 823
APPENDIX C 824
Design for Testability—A Survey 824
Introduction 824
Design for Testability 828
Ad-Hoc Design for Testability 829
Structured Design for Testability 834
Self-Testing and Built-in Tests 842
Conclusion 849
References 850
APPENDIX D 852
Summary of MIL-HDBK-217E Reliability Model 852
Failure Rate Model and Factors 852
Reference 854
APPENDIX E 856
Algebraic Solutions to Markov Models 856
Solution of MTTF Models 858
Complete Solution for Three- and Four-State Models 859
Solutions to Commonly Encountered Markov Models 860
References 860
GLOSSARY 862
REFERENCES 866
CREDITS 906
TRADEMARKS 911
INDEX 912

Produkt-Details

• Erscheint lt. Verlag: 28.6.2014
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Betriebssysteme / Server
• Themenwelt: Informatik ► Netzwerke ► Mail Server
• Themenwelt: Mathematik / Informatik ► Informatik ► Theorie / Studium
• Themenwelt: Informatik ► Weitere Themen ► Hardware
• Themenwelt: Technik ► Maschinenbau
• ISBN-10: 1-4832-9743-8 / 1483297438
• ISBN-13: 978-1-4832-9743-9 / 9781483297439