Search:
Computing and Library Services - delivering an inspiring information environment

High Flexibility Multi-Platform Hybrid Computer Cluster

Liang, Shuo (2012) High Flexibility Multi-Platform Hybrid Computer Cluster. Masters thesis, University of Huddersfield.

[img]
Preview
PDF - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (1991kB) | Preview

    Abstract

    Along with the development of computer hardware and open source software, the Beowulf Clusters have become an economic and practical choice of small-and-medium-sized institutions to shorten their research cycle. In many growing Universities, departmental clusters are being set up on the departmental demand for running simulations, rendering and other calculations. Hence, in the University, individual departments may have their own HPC resources.

    However, the staff and students of these Higher or Further Education Institutes are familiar with various software, which run on different operating systems, e.g. Windows and Linux. Furthermore, the platform-crossing software generally gives Windows users easier and friendlier interface. To support these software, their small-scale computer clusters have to be divided in two or more computer clusters. Although the virtualisation technology could be an effective choice, many of the Beowulf Clusters, which are built by legacy hardware, do not support the virtualisation.

    As a result of our research work, a cluster middleware based on OSCAR 5.2 beta 2 is being developed to achieve the function of implementing a Linux-Windows Hybrid HPC Cluster, which holds the characters of each operating system and accepts and schedules jobs in both batch job schedulers. By using Linux CentOS 5.5 with the improved OSCAR middleware with Windows Server 2008 and Windows HPC 2008 R2, a bi-stable hybrid system has been deployed at the University of Huddersfield. This hybrid cluster is known as the Queensgate Cluster.

    Item Type: Thesis (Masters)
    Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
    Schools: School of Computing and Engineering
    Depositing User: Carol Doyle
    Date Deposited: 17 Jul 2012 16:15
    Last Modified: 17 Jul 2012 16:15
    URI: http://eprints.hud.ac.uk/id/eprint/14065

    Document Downloads

    Downloader Countries

    More statistics for this item...

    Item control for Repository Staff only:

    View Item

    University of Huddersfield, Queensgate, Huddersfield, HD1 3DH Copyright and Disclaimer All rights reserved ©