Title :
Job Coscheduling on Coupled High-End Computing Systems
Author :
Tang, Wei ; Desai, Narayan ; Vishwanath, Venkatram ; Buettner, Daniel ; Lan, Zhiling
Author_Institution :
Dept. of Comput. Sci., Illinois Inst. of Technol. Chicago, Chicago, IL, USA
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.
Keywords :
data analysis; data visualisation; large-scale systems; parallel machines; processor scheduling; Argonne National Laboratory; Blue Gene/P; Eureka; Intrepid; coupled high-end computing system; data analysis; data visualization; job coscheduling; large scale computing system; lightweight protocol; supercomputer; Analytical models; Computational modeling; Data analysis; Data visualization; Laboratories; Scheduling; System recovery; coscheduling; heterogeneous computing; job scheduling; supercomputer;
Conference_Titel :
Parallel Processing Workshops (ICPPW), 2011 40th International Conference on
Conference_Location :
Taipei City
Print_ISBN :
978-1-4577-1337-8
Electronic_ISBN :
1530-2016
DOI :
10.1109/ICPPW.2011.59