Paper Info
Title
Job Coscheduling on Coupled High-End Computing Systems
Abstract
Supercomputer centers often deploy large-scale computing systems together with an associated data analysis or visualization system. In this paper, we propose a co scheduling mechanism, providing the ability to coordinate execution between jobs on different systems. The mechanism is built on top of a lightweight protocol for coordination between policy domains without manual intervention. We have evaluated this system using real job traces from Intrepid and Eureka, the production Blue Gene/P and data analysis systems, respectively, deployed at Argonne National Laboratory. Our experimental results quantify the costs of co scheduling and demonstrate that co scheduling can be achieved with limited impact on system performance under varying workloads.
Year
DOI
Venue
2011
10.1109/ICPPW.2011.59
ICPP Workshops
Keywords
Field
DocType
processor scheduling,coupled high-end computing system,argonne national laboratory,blue gene/p,supercomputer,visualization system,data analysis,eureka,system performance,data analysis system,deploy large-scale computing system,different system,job coscheduling,associated data analysis,intrepid,data visualisation,large-scale systems,co scheduling,lightweight protocol,coscheduling,data visualization,heterogeneous computing,parallel machines,high-end computing systems,co scheduling mechanism,job scheduling,large scale computing system,visual system
Data visualization,Lightweight protocol,Supercomputer,Visualization,Computer science,Coscheduling,Parallel computing,Symmetric multiprocessor system,Job scheduler,Operating system,Distributed computing,High end computing
Conference
ISSN
ISBN
Citations 
1530-2016 E-ISBN : 978-0-7695-4511-0
978-0-7695-4511-0
1
PageRank 
References 
Authors
0.35
23
5
Name
Order
Citations
PageRank
Wei Tang115210.65
Narayan Desai231929.73
Venkatram Vishwanath350747.27
Daniel Buettner41156.33
Zhiling Lan581854.25