@inproceedings{93205758950d4be3be1988ef26f0275c,
title = "Two sides of a coin: Optimizing the schedule of mapreduce jobs to minimize their makespan and improve cluster performance",
abstract = "Large-scale MapReduce clusters that routinely process petabytes of unstructured and semi-structured data represent a new entity in the changing landscape of clouds. A key challenge is to increase the utilization of these MapReduce clusters. In this work, we consider a subset of the production workload that consists of MapReduce jobs with no dependencies. We observe that the order in which these jobs are executed can have a significant impact on their overall completion time and the cluster resource utilization. Our goal is to automate the design of a job schedule that minimizes the completion time (makespan) of such a set of MapReduce jobs. We offer a novel abstraction framework and a heuristic, called BalancedPools, that efficiently utilizes performance properties of MapReduce jobs in a given workload for constructing an optimized job schedule. Simulations performed over a realistic workload demonstrate that 15%-38% makespan improvements are achievable by simply processing the jobs in the right order.",
keywords = "Hadoop, MapReduce, batch workloads, minimized makespan, optimized schedule",
author = "Abhishek Verma and Ludmila Cherkasova and Campbell, {Roy H.}",
year = "2012",
doi = "10.1109/MASCOTS.2012.12",
language = "English (US)",
isbn = "9780769547930",
series = "Proceedings of the 2012 IEEE 20th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2012",
pages = "11--18",
booktitle = "Proceedings of the 2012 IEEE 20th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2012",
note = "2012 IEEE 20th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2012 ; Conference date: 07-08-2012 Through 09-08-2012",
}