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

WF Truszkowski, MG Hinchey, R Sterritt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

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 high-performance 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 self-management, 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.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages478-482
Number of pages5
DOIs
Publication statusPublished - 22 Jul 2005
EventWorkshop on Reliability and Autonomic Management in Parallel and Distributed Systems (RAMPDS-05) at ICPADS-2005 - Fukuoka, Japan
Duration: 22 Jul 2005 → …

Workshop

WorkshopWorkshop on Reliability and Autonomic Management in Parallel and Distributed Systems (RAMPDS-05) at ICPADS-2005
Period22/07/05 → …

Fingerprint

Cluster computing
Monitoring

Keywords

  • High performance computing
  • NASA
  • Power system management
  • Prototypes
  • Space technology
  • Concurrent computing
  • Scalability
  • Availability
  • Computer networks
  • Energy management

Cite this

Truszkowski, WF ; Hinchey, MG ; Sterritt, R. / Towards an Autonomic Cluster Management System (ACMS) with Reflex Autonomicity. Unknown Host Publication. 2005. pp. 478-482
@inproceedings{1cf66525f0be45e5a9ee5e00d46e56d5,
title = "Towards an Autonomic Cluster Management System (ACMS) with Reflex Autonomicity",
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 high-performance 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 self-management, 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.",
keywords = "High performance computing, NASA, Power system management, Prototypes, Space technology, Concurrent computing, Scalability, Availability, Computer networks, Energy management",
author = "WF Truszkowski and MG Hinchey and R Sterritt",
year = "2005",
month = "7",
day = "22",
doi = "10.1109/ICPADS.2005.281",
language = "English",
pages = "478--482",
booktitle = "Unknown Host Publication",

}

Truszkowski, WF, Hinchey, MG & Sterritt, R 2005, Towards an Autonomic Cluster Management System (ACMS) with Reflex Autonomicity. in Unknown Host Publication. pp. 478-482, Workshop on Reliability and Autonomic Management in Parallel and Distributed Systems (RAMPDS-05) at ICPADS-2005, 22/07/05. https://doi.org/10.1109/ICPADS.2005.281

Towards an Autonomic Cluster Management System (ACMS) with Reflex Autonomicity. / Truszkowski, WF; Hinchey, MG; Sterritt, R.

Unknown Host Publication. 2005. p. 478-482.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Towards an Autonomic Cluster Management System (ACMS) with Reflex Autonomicity

AU - Truszkowski, WF

AU - Hinchey, MG

AU - Sterritt, R

PY - 2005/7/22

Y1 - 2005/7/22

N2 - 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 high-performance 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 self-management, 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.

AB - 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 high-performance 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 self-management, 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.

KW - High performance computing

KW - NASA

KW - Power system management

KW - Prototypes

KW - Space technology

KW - Concurrent computing

KW - Scalability

KW - Availability

KW - Computer networks

KW - Energy management

U2 - 10.1109/ICPADS.2005.281

DO - 10.1109/ICPADS.2005.281

M3 - Conference contribution

SP - 478

EP - 482

BT - Unknown Host Publication

ER -