MODELING AND MEASUREMENT OF FAULT-TOLERANT MULTIPROCESSORS.

Kang G. Shin, Michael H. Woodbury, Yann-Hang Lee

Research output: Contribution to journalArticle

Abstract

The workload effects on computer performance are addressed first for a highly reliable unibus multiprocessor used in real-time control. As an approach to studying these effects, a modified Stochastic Petri Net (SPN) is used to describe the synchronous operation of the multiprocessor system. From this model the vital components affecting performance can be determined. However, because of the complexity in solving the modified SPN, a simpler model, i. e. , a closed priority queueing network, is constructed that represents the same critical aspects. The use of this model in evaluating an existing system, the Fault Tolerant Multiprocessor (FTMP) at the NASA AIRLAB, is outlined with some experimental results. Also addressed in the technique of measuring fault latency, an important microscopic system parameter. The authors present a new methodology for indirectly measuring fault latency, and derive the distribution of fault latency from this methodology.

Original languageEnglish (US)
JournalNASA Contractor Reports
StatePublished - Aug 1985
Externally publishedYes

Fingerprint

Petri nets
Queueing networks
Real time control
NASA

ASJC Scopus subject areas

  • Aerospace Engineering

Cite this

MODELING AND MEASUREMENT OF FAULT-TOLERANT MULTIPROCESSORS. / Shin, Kang G.; Woodbury, Michael H.; Lee, Yann-Hang.

In: NASA Contractor Reports, 08.1985.

Research output: Contribution to journalArticle

@article{5755e256227b4aa3a3bcbbdfcc002679,
title = "MODELING AND MEASUREMENT OF FAULT-TOLERANT MULTIPROCESSORS.",
abstract = "The workload effects on computer performance are addressed first for a highly reliable unibus multiprocessor used in real-time control. As an approach to studying these effects, a modified Stochastic Petri Net (SPN) is used to describe the synchronous operation of the multiprocessor system. From this model the vital components affecting performance can be determined. However, because of the complexity in solving the modified SPN, a simpler model, i. e. , a closed priority queueing network, is constructed that represents the same critical aspects. The use of this model in evaluating an existing system, the Fault Tolerant Multiprocessor (FTMP) at the NASA AIRLAB, is outlined with some experimental results. Also addressed in the technique of measuring fault latency, an important microscopic system parameter. The authors present a new methodology for indirectly measuring fault latency, and derive the distribution of fault latency from this methodology.",
author = "Shin, {Kang G.} and Woodbury, {Michael H.} and Yann-Hang Lee",
year = "1985",
month = "8",
language = "English (US)",
journal = "NASA Contractor Reports",
issn = "0565-7059",

}

TY - JOUR

T1 - MODELING AND MEASUREMENT OF FAULT-TOLERANT MULTIPROCESSORS.

AU - Shin, Kang G.

AU - Woodbury, Michael H.

AU - Lee, Yann-Hang

PY - 1985/8

Y1 - 1985/8

N2 - The workload effects on computer performance are addressed first for a highly reliable unibus multiprocessor used in real-time control. As an approach to studying these effects, a modified Stochastic Petri Net (SPN) is used to describe the synchronous operation of the multiprocessor system. From this model the vital components affecting performance can be determined. However, because of the complexity in solving the modified SPN, a simpler model, i. e. , a closed priority queueing network, is constructed that represents the same critical aspects. The use of this model in evaluating an existing system, the Fault Tolerant Multiprocessor (FTMP) at the NASA AIRLAB, is outlined with some experimental results. Also addressed in the technique of measuring fault latency, an important microscopic system parameter. The authors present a new methodology for indirectly measuring fault latency, and derive the distribution of fault latency from this methodology.

AB - The workload effects on computer performance are addressed first for a highly reliable unibus multiprocessor used in real-time control. As an approach to studying these effects, a modified Stochastic Petri Net (SPN) is used to describe the synchronous operation of the multiprocessor system. From this model the vital components affecting performance can be determined. However, because of the complexity in solving the modified SPN, a simpler model, i. e. , a closed priority queueing network, is constructed that represents the same critical aspects. The use of this model in evaluating an existing system, the Fault Tolerant Multiprocessor (FTMP) at the NASA AIRLAB, is outlined with some experimental results. Also addressed in the technique of measuring fault latency, an important microscopic system parameter. The authors present a new methodology for indirectly measuring fault latency, and derive the distribution of fault latency from this methodology.

UR - http://www.scopus.com/inward/record.url?scp=0022106297&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022106297&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0022106297

JO - NASA Contractor Reports

JF - NASA Contractor Reports

SN - 0565-7059

ER -