Taurus Hard Soft Solutions Ltd.-Beowulf Clusters

» Sankhya Clusters

Beowulf Clusters

Beowulf Clusters can be described as - Multiple commodity computer systems connected over a network to "work either as a Load Balanced Server, or as a Parallel Computer system" and running software that allows each of them to work on individual pieces of one greater task.

The concept of Beowulf Clusters originated at the Center of Excellence in Space Data and Information Sciences (CESDIS), located at the NASA Goddard Space Flight Center in Maryland. Don Becker and his colleagues first deployed Beowulf Clusters since budgetary restrictions denied them access to commercial supercomputer that they needed to perform complex analysis of the very large space data sets that NASA missions generate.

The goal of building a Beowulf cluster was to create a cost-effective parallel computing system from mass-market commodity, off-the-shelf components to satisfy specific computational requirements in the earth and space sciences community. With the rapid advancement and increasing availability of microprocessor technologies, high-speed network interconnects, and other related components, Beowulf clusters have become the fastest growing choice for building clusters for HPC. Since Beowulf clusters only use mass-market components and are not subject to delays and costs from custom parts and proprietary design.

ARCHITECTURE & DESIGN

Beowulf Clusters feature a parallel computing system that usually consists of one master node and one or more compute nodes, interconnected via widely available network interconnects. All of the nodes in a typical Beowulf cluster are commodity systems-PCs/workstations/servers running commodity software from Open Source. The master node acts as a server for Network File System (NFS) and as a gateway to the outside world. As an NFS server, the master node provides user file space and other common system software to the compute nodes via NFS. As a gateway, the master node allows users to gain access through it to the compute nodes.

Usually, the master node is the only machine that is also connected to the outside world using a second network interface card (NIC). The main task of the compute nodes is to execute parallel jobs. In most cases, therefore, the compute nodes do not have keyboards, pointing device, video cards, or monitors. All access to the client nodes is provided via remote connections from the master node. Because compute nodes do not need to access machines outside the cluster, nor do machines outside the cluster need to access compute nodes directly, compute nodes commonly use private IP addresses. Compute nodes use standard message-passing middleware, such as Message Passing Interface (MPI) and OpenMP, to exchange information.

BENEFITS OF BEOWULF CLUSTERS

Built out of relatively inexpensive commodity components - Commodity Of The Shelf (COTS)computer systems and hence COST EFFECTIVE.
Easy to employ the latest technologies.
State of the art systems can be used.
Performance and size are scalable by adding more compute nodes.
Very good performance

OPERATING SYSTEM AND LIBRARIES

Majority of Beowulf Clusters mostly use Open Source Stable, Reliable, Secured, Popular Linux OS, Compilers, Parallel Math Kernel Libraries, hence, NO COSTS ON OS, COMPILERS & LIBRARIES. Also Cluster Monitoring and Management Tools from Open Source.

All Copyrights Reserved 2007, Taurus Hard Soft Solutions Ltd.