Hardware And Software Fault Tolerance In Parallel Computing Systems

Fault tolerance has been an active research area for many years. This volume presents papers from a workshop held in 1993 where a small number of key researchers and practitioners in the area met to discuss the experiences of industrial practitioners, to provide a perspective on the state of the art of fault tolerance research, to determine whether the subject is becoming mature, and to learn from the experiences so far in order to identify what might be important research topics for the coming years. The workshop provided a more intimate environment for discussions and presentations than usual at conferences. The papers in the volume were presented at the workshop, then updated and revised to reflect what was learned at the workshop.

The most important use of computing in the future will be in the context of the global "digital convergence" where everything becomes digital and every thing is inter-networked. The application will be dominated by storage, search, retrieval, analysis, exchange and updating of information in a wide variety of forms. Heavy demands will be placed on systems by many simultaneous re quests. And, fundamentally, all this shall be delivered at much higher levels of dependability, integrity and security. Increasingly, large parallel computing systems and networks are providing unique challenges to industry and academia in dependable computing, espe cially because of the higher failure rates intrinsic to these systems. The chal lenge in the last part of this decade is to build a systems that is both inexpensive and highly available. A machine cluster built of commodity hardware parts, with each node run ning an OS instance and a set of applications extended to be fault resilient can satisfy the new stringent high-availability requirements. The focus of this book is to present recent techniques and methods for im plementing fault-tolerant parallel and distributed computing systems. Section I, Fault-Tolerant Protocols, considers basic techniques for achieving fault-tolerance in communication protocols for distributed systems, including synchronous and asynchronous group communication, static total causal order ing protocols, and fail-aware datagram service that supports communications by time.

The production of a new version of any book is a daunting task, as many authors will recognise. In the field of computer science, the task is made even more daunting by the speed with which the subject and its supporting technology move forward. Since the publication of the first edition of this book in 1981 much research has been conducted, and many papers have been written, on the subject of fault tolerance. Our aim then was to present for the first time the principles of fault tolerance together with current practice to illustrate those principles. We believe that the principles have (so far) stood the test of time and are as appropriate today as they were in 1981. Much work on the practical applications of fault tolerance has been undertaken, and techniques have been developed for ever more complex situations, such as those required for distributed systems. Nevertheless, the basic principles remain the same.

This book addresses the question of how system software should be designed to account for faults, and which fault tolerance features it should provide for highest reliability. With this second edition of Software Design for Resilient Computer Systems the book is thoroughly updated to contain the newest advice regarding software resilience. With additional chapters on computer system performance and system resilience, as well as online resources, the new edition is ideal for researchers and industry professionals. The authors first show how the system software interacts with the hardware to tolerate faults. They analyze and further develop the theory of fault tolerance to understand the different ways to increase the reliability of a system, with special attention on the role of system software in this process. They further develop the general algorithm of fault tolerance (GAFT) with its three main processes: hardware checking, preparation for recovery, and the recovery procedure. For each of the three processes, they analyze the requirements and properties theoretically and give possible implementation scenarios and system software support required. Based on the theoretical results, the authors derive an Oberon-based programming language with direct support of the three processes of GAFT. In the last part of this book, they introduce a simulator, using it as a proof of concept implementation of a novel fault tolerant processor architecture (ERRIC) and its newly developed runtime system feature-wise and performance-wise. Due to the wide reaching nature of the content, this book applies to a host of industries and research areas, including military, aviation, intensive health care, industrial control, and space exploration.

This timely text presents a comprehensive overview of fault tolerance techniques for high-performance computing (HPC). The text opens with a detailed introduction to the concepts of checkpoint protocols and scheduling algorithms, prediction, replication, silent error detection and correction, together with some application-specific techniques such as ABFT. Emphasis is placed on analytical performance models. This is then followed by a review of general-purpose techniques, including several checkpoint and rollback recovery protocols. Relevant execution scenarios are also evaluated and compared through quantitative models. Features: provides a survey of resilience methods and performance models; examines the various sources for errors and faults in large-scale systems; reviews the spectrum of techniques that can be applied to design a fault-tolerant MPI; investigates different approaches to replication; discusses the challenge of energy consumption of fault-tolerance methods in extreme-scale systems.

This book presents the theory behind software-implemented hardware fault tolerance, as well as the practical aspects needed to put it to work on real examples. By evaluating accurately the advantages and disadvantages of the already available approaches, the book provides a guide to developers willing to adopt software-implemented hardware fault tolerance in their applications. Moreover, the book identifies open issues for researchers willing to improve the already available techniques.

Software fault tolerance techniques involve error detection, exception handling, monitoring mechanisms, and error recovery. This issue of Trends in Software focuses on identification, formulation, application, and evaluation of current software fault tolerance techniques.