Toward understanding soft faults in high performance cluster networks

Jeffrey J. Evans; Seongbok Baik; Cynthia S. Hood; William Gropp

doi:10.1007/978-0-387-35674-7

Toward understanding soft faults in high performance cluster networks

Jeffrey J. Evans, Seongbok Baik, Cynthia S. Hood, William Gropp

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Fault management in high performance cluster networks has been focused on the notion of hard faults (Le., link or node failures). Network degradations that negatively impact performance but do not result in failures often go unnoticed. In this paper, we classify such degradations as 80ft faults. In addition, we identify consistent performance as an important requirement in cluster networks. Using this service requirement, we describe a comprehensive strategy for cluster fault management.

Original language	English (US)
Title of host publication	Integrated Network Management VIII
Subtitle of host publication	Managing It All - IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003
Publisher	Springer New York LLC
Pages	117-120
Number of pages	4
ISBN (Print)	9781475755213
DOIs	https://doi.org/10.1007/978-0-387-35674-7
State	Published - 2003
Externally published	Yes
Event	IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003 - Colorado Springs, CO, United States Duration: Mar 24 2003 → Mar 28 2003

Publication series

Name	IFIP Advances in Information and Communication Technology
Volume	118
ISSN (Print)	1868-4238

Other

Other	IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003
Country	United States
City	Colorado Springs, CO
Period	3/24/03 → 3/28/03

Keywords

Cluster
Fault management
Interconnection networks
Soft faults

ASJC Scopus subject areas

Information Systems
Computer Networks and Communications
Information Systems and Management

Access to Document

10.1007/978-0-387-35674-7

Fingerprint Dive into the research topics of 'Toward understanding soft faults in high performance cluster networks'. Together they form a unique fingerprint.

Cite this

Evans, J. J., Baik, S., Hood, C. S., & Gropp, W. (2003). Toward understanding soft faults in high performance cluster networks. In Integrated Network Management VIII: Managing It All - IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003 (pp. 117-120). (IFIP Advances in Information and Communication Technology; Vol. 118). Springer New York LLC. https://doi.org/10.1007/978-0-387-35674-7

Toward understanding soft faults in high performance cluster networks. / Evans, Jeffrey J.; Baik, Seongbok; Hood, Cynthia S.; Gropp, William.

Integrated Network Management VIII: Managing It All - IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003. Springer New York LLC, 2003. p. 117-120 (IFIP Advances in Information and Communication Technology; Vol. 118).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Evans, JJ, Baik, S, Hood, CS & Gropp, W 2003, Toward understanding soft faults in high performance cluster networks. in Integrated Network Management VIII: Managing It All - IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003. IFIP Advances in Information and Communication Technology, vol. 118, Springer New York LLC, pp. 117-120, IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003, Colorado Springs, CO, United States, 3/24/03. https://doi.org/10.1007/978-0-387-35674-7

Evans JJ, Baik S, Hood CS, Gropp W. Toward understanding soft faults in high performance cluster networks. In Integrated Network Management VIII: Managing It All - IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003. Springer New York LLC. 2003. p. 117-120. (IFIP Advances in Information and Communication Technology). https://doi.org/10.1007/978-0-387-35674-7

Evans, Jeffrey J. ; Baik, Seongbok ; Hood, Cynthia S. ; Gropp, William. / Toward understanding soft faults in high performance cluster networks. Integrated Network Management VIII: Managing It All - IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003. Springer New York LLC, 2003. pp. 117-120 (IFIP Advances in Information and Communication Technology).

@inproceedings{69e0a9eb41db4a6ead4a2f219ad2dc3a,

title = "Toward understanding soft faults in high performance cluster networks",

abstract = "Fault management in high performance cluster networks has been focused on the notion of hard faults (Le., link or node failures). Network degradations that negatively impact performance but do not result in failures often go unnoticed. In this paper, we classify such degradations as 80ft faults. In addition, we identify consistent performance as an important requirement in cluster networks. Using this service requirement, we describe a comprehensive strategy for cluster fault management.",

keywords = "Cluster, Fault management, Interconnection networks, Soft faults",

author = "Evans, {Jeffrey J.} and Seongbok Baik and Hood, {Cynthia S.} and William Gropp",

year = "2003",

doi = "10.1007/978-0-387-35674-7",

language = "English (US)",

isbn = "9781475755213",

series = "IFIP Advances in Information and Communication Technology",

publisher = "Springer New York LLC",

pages = "117--120",

booktitle = "Integrated Network Management VIII",

note = "IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003 ; Conference date: 24-03-2003 Through 28-03-2003",

}

TY - GEN

T1 - Toward understanding soft faults in high performance cluster networks

AU - Evans, Jeffrey J.

AU - Baik, Seongbok

AU - Hood, Cynthia S.

AU - Gropp, William

PY - 2003

Y1 - 2003

N2 - Fault management in high performance cluster networks has been focused on the notion of hard faults (Le., link or node failures). Network degradations that negatively impact performance but do not result in failures often go unnoticed. In this paper, we classify such degradations as 80ft faults. In addition, we identify consistent performance as an important requirement in cluster networks. Using this service requirement, we describe a comprehensive strategy for cluster fault management.

AB - Fault management in high performance cluster networks has been focused on the notion of hard faults (Le., link or node failures). Network degradations that negatively impact performance but do not result in failures often go unnoticed. In this paper, we classify such degradations as 80ft faults. In addition, we identify consistent performance as an important requirement in cluster networks. Using this service requirement, we describe a comprehensive strategy for cluster fault management.

KW - Cluster

KW - Fault management

KW - Interconnection networks

KW - Soft faults

UR - http://www.scopus.com/inward/record.url?scp=33845346572&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845346572&partnerID=8YFLogxK

U2 - 10.1007/978-0-387-35674-7

DO - 10.1007/978-0-387-35674-7

M3 - Conference contribution

AN - SCOPUS:33845346572

SN - 9781475755213

T3 - IFIP Advances in Information and Communication Technology

SP - 117

EP - 120

BT - Integrated Network Management VIII

PB - Springer New York LLC

T2 - IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003

Y2 - 24 March 2003 through 28 March 2003

ER -