Towards an Autonomic Cluster Management System (ACMS) with Reflex Autonomicity

Authors:
Walt Truszkowski;Mike Hinchey;Roy Sterritt
Affiliations:
NASA Goddard Space Flight Center Information Systems Division Greenbelt, MD, USA;NASA Goddard Space Flight Center Information Systems Division Greenbelt, MD, USA;University of Ulster School of Computing and Mathematics, Jordanstown Campus Northern Ireland
Venue:
ICPADS '05 Proceedings of the 11th International Conference on Parallel and Distributed Systems - Workshops - Volume 02
Year:
2005

Citing 0
Cited 1

Autonomic agents for survivable security systems

EUC'05 Proceedings of the 2005 international conference on Embedded and Ubiquitous Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Cluster computing, whereby a large number of simple processors or nodes are combined together to apparently function as a single powerful computer, has emerged as a research area in its own right. The approach offers a relatively inexpensive means of providing a fault-tolerant environment and achieving significant computational capabilities for highperformance computing applications. However, the task of manually managing and configuring a cluster quickly becomes daunting as the cluster grows in size. Autonomic computing, with its vision to provide selfmanagement, can potentially solve many of the problems inherent in cluster management. We describe the development of a prototype Autonomic Cluster Management System (ACMS) that exploits autonomic properties in automating cluster management and its evolution to include reflex reactions via pulse monitoring.