Information Technology Reference
In-Depth Information
3 Grid Basics
Katarina Stanoevska-Slabeva, Thomas Wozniak
3.1 Introduction
The term Grid or Grid Computing implies different technologies, markets and solu-
tions to different people. The meanings associated with the terms range from cluster
computing, High Performance Computing (HPC), utility computing, peer-to-peer
computing to specific new types of infrastructure. In order to clarify the position, the
aim of this chapter is to define and explain Grid Computing. Thereby, the following
aspects will be considered:
• Definition of Grid Computing
• Explanation of Grid Computing Architectures
• Overview of basic functionalities and components of Grid Computing
• Overview of advantages and risks associated with Grid Computing
• Classification of Grids
• Overview of trends related to Grid Computing such as Service-oriented
Computing (SOC), Software-as-a-Service (SaaS), and Cloud Computing.
3.2 What is Grid Computing?
Grid Computing is a complex phenomenon that has its roots in eScience and has
evolved from earlier developments in parallel, distributed and HPC (see for example
Weishäupl et al. 2005 and Harms et al. 2006). It emerged in the early 1990s, when
high performance computers were connected by fast data communication with the
aim to support calculation- and data-intensive scientific applications. At that time,
this was denoted hyper computing or meta computing and the emphasis was on
coordinated usage of available computing resources for high performance applica-
tions (Reinefeld and Schintke 2004).
The first most cited definition of Grid Computing reflected these origins and was
suggested by Foster and Kesselman (1998):
“A computational grid is a hardware and software infrastructure that provides dependable,
consistent, pervasive, and inexpensive access to high-end computational capabilities.”
Based on the hyper computing examples and the example of cluster computing, it
became evident that resource sharing might be relevant for other application areas
as well. Consequently, it became clear that resource sharing should be provided in
a generic manner and not targeted only for specific high performance applications
(Reinefeld and Schintke 2004). Given this, development of support for generic IT
resource sharing started to be considered as the real “Grid problem”. According to
Foster et al. (2001):
