Fault Tolerant Cluster Computing through Replication
Long-lived parallel applications running on work station clusters are vulnerable to single-node or multiple-node failures. Fault recovery is therefore required to prevent immature program termination. However, much of the runtime overhead imposed by fault tolerance schemes is generally due to the co...
Saved in:
Main Author: | |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
1997
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/1053 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-2052 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-20522010-12-22T08:24:06Z Fault Tolerant Cluster Computing through Replication SHUM, Kam Hong Long-lived parallel applications running on work station clusters are vulnerable to single-node or multiple-node failures. Fault recovery is therefore required to prevent immature program termination. However, much of the runtime overhead imposed by fault tolerance schemes is generally due to the cost of transferring the checkpoint states of applications by disk I/O operations. In this paper, we propose a fault tolerant model in which checkpoint states are transferred between replicated parallel applications. We also describe how the resource consumption of the replicated applications can be minimized. The fault tolerant model has been implemented and tested on a workstation cluster and a Fujitsu AP3000 multi-processor machine. The measurements of our experiments have showed that efficient fault tolerance can be achieved by replicating parallel applications on clusters of computers. 1997-12-01T08:00:00Z text https://ink.library.smu.edu.sg/sis_research/1053 info:doi/10.1109/ICPADS.1997.652627 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems Numerical Analysis and Scientific Computing |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Databases and Information Systems Numerical Analysis and Scientific Computing |
spellingShingle |
Databases and Information Systems Numerical Analysis and Scientific Computing SHUM, Kam Hong Fault Tolerant Cluster Computing through Replication |
description |
Long-lived parallel applications running on work station clusters are vulnerable to single-node or multiple-node failures. Fault recovery is therefore required to prevent immature program termination. However, much of the runtime overhead imposed by fault tolerance schemes is generally due to the cost of transferring the checkpoint states of applications by disk I/O operations. In this paper, we propose a fault tolerant model in which checkpoint states are transferred between replicated parallel applications. We also describe how the resource consumption of the replicated applications can be minimized. The fault tolerant model has been implemented and tested on a workstation cluster and a Fujitsu AP3000 multi-processor machine. The measurements of our experiments have showed that efficient fault tolerance can be achieved by replicating parallel applications on clusters of computers. |
format |
text |
author |
SHUM, Kam Hong |
author_facet |
SHUM, Kam Hong |
author_sort |
SHUM, Kam Hong |
title |
Fault Tolerant Cluster Computing through Replication |
title_short |
Fault Tolerant Cluster Computing through Replication |
title_full |
Fault Tolerant Cluster Computing through Replication |
title_fullStr |
Fault Tolerant Cluster Computing through Replication |
title_full_unstemmed |
Fault Tolerant Cluster Computing through Replication |
title_sort |
fault tolerant cluster computing through replication |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
1997 |
url |
https://ink.library.smu.edu.sg/sis_research/1053 |
_version_ |
1770570834361974784 |