A network performance sensitivity metric for parallel applications
Jeffrey J. Evans, Cynthia S. Hood · International Journal of High Performance Computing and Networking · 2011
Excessive run time variability of parallel application codes on commodity clusters is a significant challenge. To gain insight into this problem, our earlier work developed tools to emulate parallel applications (PACE) by simulating computation and using the cluster’s interconnection network for communication, and further study parallel application run time sensitivity effects to controlled network performance degradation (PARSE). This work expands our previous efforts by presenting a metric derived from PARSE test results conducted on several widely used parallel benchmarks and application code fragments. The metric suggests that a parallel application’s sensitivity to network performance variation can be quantified relative to its behaviour in optimal network performance conditions. Ideas on how this metric can be useful to parallel application development, cluster system performance management and system administration are also presented.
Cited by 6 works. doi:10.1504/ijhpcn.2011.038706
Authors
References
- A case for NOW (Networks of Workstations)
- A case for networks of workstations (now)
- Reproducible Measurements of MPI Performance Characteristics
- The portable batch scheduler and the maui scheduler on linux clusters
- Supermon: a high-speed cluster monitoring system
- SKaMPI: A Detailed, Accurate MPI Benchmark
- SKaMPI: A detailed, accurate MPI benchmark
- Toward a realistic task scheduling model
- Using multirail networks in high-performance clusters
- Parallel Spectral Transform Shallow Water Model: a runtime-tunable parallel benchmark code