CluMSy: Cluster management system

Today, supercomputers are generally being replaced by network of standalone computing nodes that works together to perform specific tasks due to the large gap between their cost-benefit ratio. The capabilities of a cluster of workstations (COWs) over a single computing node make it possible to achie...

Full description

Saved in:
Bibliographic Details
Main Authors: Camarillo, Reynaldo Jose C., Pe-Aguirre, Frances Ellen O., So, Jessamine Y., Sy, Mara Ailiez C.
Format: text
Language:English
Published: Animo Repository 2004
Subjects:
Online Access:https://animorepository.dlsu.edu.ph/etd_bachelors/14250
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: De La Salle University
Language: English
Description
Summary:Today, supercomputers are generally being replaced by network of standalone computing nodes that works together to perform specific tasks due to the large gap between their cost-benefit ratio. The capabilities of a cluster of workstations (COWs) over a single computing node make it possible to achieve high-performance parallel computing. Cluster Management Systems (CMS) aid users in monitoring and managing cluster of workstations. These systems keep track of the resources, manage the processes and monitor the utilization of each node in the cluster. Though, these cluster management systems requires users to adapt to an unfamiliar environment and majority of the cluster management systems at present deal solely with monitoring and limited process management. To address this issue, the proponents implemented a system called Cluster Management System (CluMSy) that provides both monitoring and management of files, processes, accounts and packages but are cluster-enabled utilities based on the classical UNIX commands that survived amidst the GUI revolution. The Cluster Connection Manager (CCM) provides a simple parallel programming environment that handles the parallel execution of these classical commands. Aside from monitoring and management functions, these cluster-enabled utilities also assist users in preparation and termination of parallel program executions.