BibTeX

@inproceedings{USFIUIBLPL21,
	author	 = {Radita Liem and Dmytro Povaliaiev and Jay Lofstead and Julian Kunkel and Christian Terboven},
	title	 = {{User-Centric System Fault Identification Using IO500 Benchmark}},
	year	 = {2021},
	month	 = {12},
	booktitle	 = {{In 2021 IEEE/ACM Sixth International Parallel Data Systems Workshop (PDSW)}},
	editor	 = {},
	publisher	 = {IEEE},
	pages	 = {35-40},
	conference	 = {International Parallel Data Systems Workshop (PDSW)},
	location	 = {St. Louis},
	doi	 = {https://doi.org/10.1109/PDSW54622.2021.00011},
	abstract	 = {I/O performance in a multi-user environment is difficult to predict. Users do not know what I/O performance to expect when running and tuning applications. We propose to use the IO500 benchmark as a way to guide user expectations on their application’s performance and to aid identifying root causes of their I/O problems that might come from the system. Our experiments describe how we manage user expectation with IO500 and provide a mechanism for system fault identification. This work also provides us with information of the tail latency problem that needs to be addressed and granular information about the impact of I/O technique choices (POSIX and MPI-IO).},
	url	 = {http://www.pdsw.org/pdsw21/index.shtml},
}