@inproceedings{57e119f2dd49405386259c90d40f13a1,
title = "Discovering job preemptions in the open science grid",
abstract = "The Open Science Grid(OSG)[9] is a world-wide computing system which facilitates distributed computing for scientific research. It can distribute a computationally intensive job to geo-distributed clusters and process job's tasks in parallel. For compute clusters on the OSG, physical resources may be shared between OSG and cluster's local user-submitted jobs, with local jobs preempting OSG-based ones. As a result, job preemptions occur frequently in OSG, sometimes significantly delaying job completion time. We have collected job data from OSG over a period of more than 80 days. We present an analysis of the data, characterizing the preemption patterns and different types of jobs. Based on observations, we have grouped OSG jobs into 5 categories and analyze the runtime statistics for each category. we further choose different statistical distributions to estimate probability density function of job runtime for different classes.",
keywords = "Distribution, Estimation, Failure pattern, Job failure, Job runtime, OSG, Pilot job, Preemption, Probability Density Function, Spatial locality, Temporal locality",
author = "Zhe Zhang and Derek Weitzel and Brian Bockelman and David Swanson",
note = "Funding Information: This work was supported by NSF award PHY-1148698, via subaward from University of Wisconsin-Madison. This research was done using resources provided by the Open Science Grid, which is supported by the National Science Foundation and the U.S. Department of Energy's Office of Science. This work was completed utilizing the Holland Computing Center of the University of Nebraska. Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 2018 Practice and Experience in Advanced Research Computing Conference: Seamless Creativity, PEARC 2018 ; Conference date: 22-07-2017 Through 26-07-2017",
year = "2018",
month = jul,
day = "22",
doi = "10.1145/3219104.3229282",
language = "English (US)",
isbn = "9781450364461",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
booktitle = "Practice and Experience in Advanced Research Computing 2018",
}