Optimal processor allocation to differentiated job flows

Authors:
Kimberly M. Wasserman;George Michailidis;Nicholas Bambos
Affiliations:
Mobile Wireless Group, Cisco Systems, Raleigh, NC;Department of Statistics, The University of Michigan, Ann Arbor, MI;Department of Electrical Engineering and Management Science and Engineering, Stanford University Stanford, CA
Venue:
Performance Evaluation
Year:
2006

Citing 3
Cited 1

Coordinating parallel processes on networks of workstations

Journal of Parallel and Distributed Computing
A Survey of Wormhole Routing Techniques in Direct Networks

Computer
Queueing Dynamics and Maximal Throughput Scheduling in Switched Processing Systems

Queueing Systems: Theory and Applications

The Future of Software Performance Engineering

FOSE '07 2007 Future of Software Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we study the problem of dynamic allocation of the resources of a general parallel processing system, comprised of M heterogeneous processors and M heterogeneous traffic flows. Each traffic flow is modeled as a Bernoulli sequence of binary random variables, with the arrival rate depending on the job class. The service times of the jobs are independent random variables with distributions that depend on both the job class and the processor class. We characterize the stability region for this system and introduce a processor allocation policy that stabilizes the system under the maximum possible traffic loadings. We also investigate some special cases of this model and finally characterize its performance in the presence of finite buffers.