Grid Computing

• While clusters are collections of computers tied together as a single system, grids consist of multiple systems that work together while maintaining their distinct identities.
• In their article ``The grid grows up'', Fred Douglis and Ian Foster (2003) defined the term Grid to denote middleware infrastructure, tools, and applications concerned with integrating geographically distributed computational resources.
• Owing to the decentralized and heterogeneous nature of the grid, the middleware that glues the different components is more complicated compared with that of clusters.
• Resembling an electric power grid, the computing grid is expected to become a pervasive computing infrastructure that supports large-scale and resource-intensive applications.
• The significant increase in application complexity and the need for collaboration have made grids an attractive computing infrastructure. Applications will continue to be complex, multidisciplinary, and multidimensional, and collaboration will become the default mode of operation. Thus, the need for the distributed grid infrastructure will continue to be an important resource.
• A user signing on at one location would view computers at other remote locations as if they were part of the local system. Grid computing works by polling the resources available, and then allocating them to individual tasks as the need arise. Resources are returned to the pool upon completion of the task. Grid gives an illusion of a big virtual computer capable of carrying out enormous tasks.
• Support of grids requires innovative solutions to a number of challenging issues including: resource management, resource monitoring, interoperability, security, billing and accounting, communication, and performance.
• There are several examples of grid platforms and tools such as Globus and TeraGrid.
  • The Globus Toolkit is an enabling technology for the grid. The toolkit includes software services and libraries for resource monitoring, discovery, and management, plus security and file management. It also includes software for communication, fault detection, and portability. The Globus Toolkit has grown through an open-source strategy. Version 1.0 was introduced in 1998 followed by the 2.0 release in 2002. The latest 3.0 version is based on new open-standard Grid services.
  • TeraGrid is a large high-performance computing project headed by the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign. The TeraGrid uses thousands of Intel Itanium 2 processors located at four sites in the United States. The TeraGrid is an effort to build and deploy the world's largest, fastest distributed infrastructure for open scientific research. The TeraGrid is expected to include 20 teraflops of computing power, facilities capable of managing and storing nearly 1 petabyte of data, high-resolution visualization environments, and toolkits for grid computing. These components will be tightly integrated and connected through a network that will operate at 40 gigabits per second.