TY - JOUR
T1 - Approach towards benchmarking of fault-tolerant commercial systems
AU - Tsai, Timothy K.
AU - Iyer, Ravishankar K.
AU - Jewitt, Doug
N1 - Copyright:
Copyright 2004 Elsevier Science B.V., Amsterdam. All rights reserved.
PY - 1996
Y1 - 1996
N2 - This paper presents a benchmark for dependable systems. The benchmark consists of two metrics, number of catastrophic incidents and performance degradation, which are obtained by a tool that (1) generates synthetic workloads that produce a high level of CPU, memory, and I/O activity and (2) injects CPU, memory, and I/O faults according to an injection strategy. The benchmark has been installed on two TMR-based prototype machines: TMR Prototype A and TMR Prototype B. An implementation for a third prototype, is based on a duplex architecture, is in progress. The results demonstrate the utility of the benchmark in comparing the system-level fault tolerance of these machines and in providing insight into their design. In particular, the benchmark shows that Prototype B suffers fewer catastrophic incidents than Prototype A under the same workload conditions and fault injection method. However, Prototype B also suffers more performance degradation in the presence of faults, which might be an important concern for time-critical applications.
AB - This paper presents a benchmark for dependable systems. The benchmark consists of two metrics, number of catastrophic incidents and performance degradation, which are obtained by a tool that (1) generates synthetic workloads that produce a high level of CPU, memory, and I/O activity and (2) injects CPU, memory, and I/O faults according to an injection strategy. The benchmark has been installed on two TMR-based prototype machines: TMR Prototype A and TMR Prototype B. An implementation for a third prototype, is based on a duplex architecture, is in progress. The results demonstrate the utility of the benchmark in comparing the system-level fault tolerance of these machines and in providing insight into their design. In particular, the benchmark shows that Prototype B suffers fewer catastrophic incidents than Prototype A under the same workload conditions and fault injection method. However, Prototype B also suffers more performance degradation in the presence of faults, which might be an important concern for time-critical applications.
UR - http://www.scopus.com/inward/record.url?scp=0029715010&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0029715010&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:0029715010
SN - 0731-3071
SP - 314
EP - 323
JO - Proceedings - Annual International Conference on Fault-Tolerant Computing
JF - Proceedings - Annual International Conference on Fault-Tolerant Computing
T2 - Proceedings of the 1996 26th International Symposium on Fault-Tolerant Computing
Y2 - 25 June 1996 through 27 June 1996
ER -