Overview
89970-8
The #1 guide to clustering for every IT professional!
From Microsoft to IBM, Compaq to Sun to DEC, virtually every large computer company now uses clustering as a key strategy for high-availability, high-performance computing. This book tells you why-and how. It cuts through the marketing hype and techno-religious wars surrounding parallel processing, delivering the practical information you need to purchase, market, plan or design servers and other high-performance computing systems.
- Microsoft Cluster Services ("Wolfpack")
- IBM Parallel Sysplex and SP systems
- DEC OpenVMS Cluster and Memory Channel
- Tandem ServerNet and Himalaya
- Intel Virtual Interface Architecture
- Symmetric Multiprocessors (SMPs) and NUMA systems
With unequalled simplicity, directness, and humor, expert Gregory Pfister delivers all the information you need to make critical strategic decisions. He introduces the primary technologies involved in clustering, and shows why they are becoming so important. He compares clustering with symmetric multiprocessing, demonstrating major differences that are often "papered over." The legendary first edition of this book predicted the cluster revolution now underway. Its refreshing style, candid opinions, and simple explanations made it an underground classic. This new edition adds more than 150 pages of new material, including detailed new coverage of high availability, and Non-Uniform Memory Access (NUMA).
The classic exposition of "The ongoing battle in lowly parallel computing" has been revised and updated. The prognostications and predictions of the first lucid and eminently readable edition have come to pass and become history. This humorous narrative guides you through the leading edge concepts and technologies that will define tomorrow's computers, their capabilities, and ultimately their use. It asks such fundamental questions as "What are clusters, and why use them?" Then goes on to define clusters, discuss hardware concepts, and more importantly examine the state of software.
Synopsis
As Microsoft's much-touted "Wolfpack" Cluster Server shows, clustering technology has arrived in the marketplace. Clustering is now a strategic direction for Microsoft, Compaq, IBM, Sun, DEC, Novell, and every other large computer company – and their products are rolling out now. This comprehensive, highly-readable guide helps you make sense of clustering in all its forms, not just a single company's offering. Gregory Pfister – one of the world's most respected experts on clustering technology – delivers all the information you need to make critical strategic decisions. He introduces the primary hardware and software technologies involved in clusters, and shows why they have become popular – and will become increasingly important. He presents the background that system planners, purchasers, designers and architects need to make effective use of clustering. He compares different types of clusters and the workloads they are best used for. He presents a detailed comparison of clusters with symmetric multiprocessing — demonstrating major differences that are often "papered over." The book contains extensive new coverage of availability issues, as well as detailed coverage of Non-Uniform Memory Access (NUMA), the technology at the heart of new offerings from Sequent, HP, Pyramid, NCR and others. "Pfister is a prophet with an attitude..." – Norris Parker Smith, HPCWire.
Booknews
For people planning to purchase, sell, design, or administer a server or multi-user computer system, explains the key strategy of clustering used by most of the big computer companies for high-availability, high-performance parallel computing. Includes a substantially annotated bibliography. Updated and corrected from the 1995 edition. Annotation c. by Book News, Inc., Portland, Or.
Editorials
From Barnes & Noble
Fatbrain Review
The classic exposition of "The ongoing battle in lowly parallel computing" has been revised and updated. The prognostications and predictions of the first lucid and eminently readable edition have come to pass and become history. This humorous narrative guides you through the leading edge concepts and technologies that will define tomorrow's computers, their capabilities, and ultimately their use. It asks such fundamental questions as "What are clusters, and why use them?" Then goes on to define clusters, discuss hardware concepts, and more importantly examine the state of software.The book explains symmetric multiprocessing concepts, NUMA variants (Non-Uniform Memory Access), then objectively dissects programming models and issues such as small N vs. large N, shared disk or not? (But first asks the question, What is a programming model?) It discusses the concept of 'high availability', then puts symmetric multiprocessors, NUMA and clusters into perspective with respect to performance, cost and other business issues. The author explains benchmarks and standards, indeed examines the whole concept of clustering and the directions this technology is taking.
This objective, semi-technical and well-organized treatise explains and clarifies much. No doubt it will also irritate many techno-fanatics. This is a recommended publication for computer professionals, IT and technical managers. The author is an IBM Senior Technical Staff Member at Austin.