Queueing performance analysis of co-scheduling in a pool of processors environment

Authors:
Margaret A. Schaar;Kemal Efe;Weijia Shang
Affiliations:
Center for Advanced Computer Studies, University of Southwestern Louisiana, Lafayette, LA;Center for Advanced Computer Studies, University of Southwestern Louisiana, Lafayette, LA;Department of Computer Engineering, Santa Clara University, Santa Clara, CA
Venue:
ICS '94 Proceedings of the 8th international conference on Supercomputing
Year:
1994

Citing 6
Cited 1

Data networks

Data networks
Using idle workstations in a shared computing environment

SOSP '87 Proceedings of the eleventh ACM Symposium on Operating systems principles
The Sprite Network Operating System

Computer
DAWGS—a distributed compute server utilizing idle workstations

Journal of Parallel and Distributed Computing
Collecting Unused Processing Capacity: An Analysis of Transient Distributed Systems

IEEE Transactions on Parallel and Distributed Systems
An overview of the Amoeba distributed operating system

ACM SIGOPS Operating Systems Review

Research: Effective queueing strategies for co-scheduling in a pool of processors

Computer Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We consider a connected set of workstations as a “pool of processors” and develop a queueing model to analyze the performance of optimal co-scheduling algorithms. The pool of processors model was originally developed for the Amoeba operating system. It was also used in the design of the recent IBM supercomputer model 9076 SP1. Recently, co-scheduling has been suggested as an approach for scheduling computationally intensive tasks in the pool of processors model. Co-scheduling algorithms select the best possible subset of workstations for a task to minimize its completion time.We develop a queueing model which allows us to investigate the dynamic performance of co-scheduling algorithms from the system point of view under several queueing strategies. We use six different queueing strategies in combination with co-scheduling and compare the results to the M/M/m system where arriving tasks would be assigned to workstations as whole computations, and no co-scheduling would take place. The results show that the co-scheduling approach is viable under a wide range of system parameters. Moreover, performance differences of queueing strategies tend to diminish as the number of workstations grows. This suggests that co-scheduling is universally applicable across the queueing disciplines considered here when there are a large number of workstations.