The GRID, according to the editors, is an emerging infrastructure that will fundamentally change the way we think about—and use—computing. The grid will connect multiple regional and national computational grids to create a universal source of computing power
. The goal of this book is to provide simultaneously a manifesto, design blueprint, user guide, and research agenda for future grid systems.
As a manifesto, the book seeks to make the case for computational grids, explaining why they are important and why we should be concerned with making them reality. As a design blueprint, the book is intended to describe what grids will look like, how they will be constructed, and how they will operate. As a user guide, the book is intended to the scientists, engineers, and others who will develop applications for computational grids. As a research agenda, the book describes the state of the art in relevant disciplines and the areas in which gaps in our knowledge demand further research.
The book contains two introductory chapters and 20 technical chapters written by distinguished experts in high-performance computing and networking. The technical chapters are grouped into four sections, concerned with applications, programming tools, services, and infrastructure. The authors of each chapter summarize the state of the art in their particular technology area, indicating where further developments will likely take place and the achievements expected within the next five to ten years. Chapter 1 analyzes the emergence of the new infrastructure from several points of view. Computational grids are briefly compared with other significant infrastructures, such as the electric power grid, which provides pervasive access to power and has had a dramatic impact on human capabilities and society. Chapter 2 provides answers to six questions: Why do we need computational grids? What types of applications will grids be used for? How will grids be programmed? What is involved in building a grid? What problems must be solved to enable grid development? Chapters 3 through 6 discuss applications in four major areas: distributed supercomputing, real-time instrumentation systems, data-intensive applications, and teleimmersion. Chapters 7 through 10 are concerned with application development tools. The four chapters cover high-level application-specific tools, compilers and languages, object technologies, and commodity technologies. Chapters 11 through 16 are concerned with the services required to support grid applications and tools. The first of these chapters describes a grid toolkit; the other five discuss issues relating to high-performance schedulers, high-throughput resource management, instrumentation, performance analysis, and security. Chapters 17 through 22 cover various aspects of the low-level infrastructure on which grids will be constructed. The first five chapters cover computing platforms, protocols, network resource management, operating system and interface issues, and network technologies; the sixth reviews lessons learned from building networking and meta-computing test-beds.
The book is an important reference book for anyone interested in high-speed computing and networking and curious to know and understand how the scientists see the future of the network computing behind Internet2 and Next Generation Internet. The authors succeeded in their complex mission to create a clear vision of how grids are used, what they look like, and the nature of any obstacles to progress. It also could be used as a textbook for a graduate course in advanced networking and distributed computing.
Ami Marowka,
Hebrew University of Jerusalem, Israel