StressBench: A Configurable Full System Network and I/O Benchmark Framework

2021 IEEE High Performance Extreme Computing Conference (HPEC)(2021)

引用 1|浏览22
暂无评分
摘要
We present StressBench, a network benchmarking framework written for testing MPI operations and file I/O concurrently. It is designed specifically to execute MPI communication and file access patterns that are representative of real-world scientific applications. Existing tools consider either the worst case congestion with small abstract patterns or peak performance with simplistic patterns. StressBench allows for a richer study of congestion by allowing orchestration of network load scenarios that are representative of those typically seen at HPC centres, something that is difficult to achieve with existing tools. We demonstrate the versatility of the framework from micro benchmarks through to finely controlled congested runs across a cluster. Validation of the results using four proxy application communication schemes within StressBench against parent applications shows a maximum difference of 15%. Using the I/O modeling capabilities of StressBench, we are able to quantify the impact of file I/O on application traffic showing how it can be used in procurement and performance studies.
更多
查看译文
关键词
file access patterns,MPI communication,testing MPI operations,network benchmarking framework,benchmark framework,configurable full system network,parent applications,proxy application communication schemes,microbenchmarks,network load scenarios,StressBench,worst case congestion,real-world scientific applications
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要