Contents 1. Introduction
What is Cluster Computing?
Cluster computing can be defined as distributed computing where the underlying hardware consists of a collection of similar workstations or PCs, closely connected by means of a high-speed local-area network or private system network (Tanenbaum et al, 2007).
A cluster can in turn be defined as a collection of computers that are connected and used as a single computing resource (Pfister, 1998).
The above definitions fall within the range of supercomputer and scales further by allowing a cluster of supercomputers to be used for metacomputing.
Essentially, cluster computing can be described as the fusion of parallel, high-performance, distributed and high-availability computing.
Cluster computing,…show more content… High performance micro-processors
2. High-speed networks
3. Standard tools for high performance distributed computing The increasing need of computing power for computational science and commercial applications presented itself as a possible fourth trend, coupled with the high cost and low accessibility of traditional supercomputers.
The current trend in parallel computing is to move away from traditional specialized supercomputing platforms, e.g. Cray/SGI, to cheaper and general purpose systems consisting of loosely coupled components built up from single or multiprocessor workstations or PCs.
This approach has a number of advantages, including low cost, high performance, and a wide variety of applications. 2. Why use cluster computing?
The emergence of cluster platforms was driven by a number of academic projects, such as Beowulf1, HPVM2, and Berkeley NOW3 (Network of Workstations) that have proven the advantage of clusters over traditional…show more content… 2.1 Cluster Architecture
A cluster is a type of parallel or distributed computer system which consists of inter-connected stand-alone computers working together as a single integrated computing resource (R. Buyya, 1999). The key components in a cluster consists of multiple stand-alone computers (Workstations, PCs or SMPs), operating systems (each node having the same), high-performance interconnections, middleware, parallel programming environments, and applications.
2.2 Single System Image (SSI)
The Single System Image, or SSI, represents the view of a distributed system as a single unified computing resource. This provides better usability for users as it hides the complexities of the underlying distributed and heterogeneous natures of clusters.
SSI can be established through one of several mechanisms implemented at various levels of abstraction in the cluster architecture: i.e. hardware, operating system, middleware and applications.
SSI cluster-based system design focuses on complete transparency of resource management, scalable performance and system availability in supporting user