Managing irregular workloads of cooperatively shared computing clusters

Authors:
Percival Xavier;Wentong Cai;Bu-Sung Lee
Affiliations:
School of Computer Engineering, Nanyang Technological University, Singapore;School of Computer Engineering, Nanyang Technological University, Singapore;School of Computer Engineering, Nanyang Technological University, Singapore
Venue:
ISPA'04 Proceedings of the Second international conference on Parallel and Distributed Processing and Applications
Year:
2004

Citing 9
Cited 0

A worldwide flock of Condors: load sharing among workstation clusters

Future Generation Computer Systems - Special issue: resource management in distributed systems
The Slack Method: A New Method for Static Allocation ofHard Real-Time Tasks

Real-Time Systems
Efficient Scheduling Algorithms for Real-Time Multiprocessor Systems

IEEE Transactions on Parallel and Distributed Systems
Supporting Priorities and Improving Utilization of the IBM SP Scheduler Using Slack-Based Backfilling

IPPS '99/SPDP '99 Proceedings of the 13th International Symposium on Parallel Processing and the 10th Symposium on Parallel and Distributed Processing
The EASY - LoadLeveler API Project

IPPS '96 Proceedings of the Workshop on Job Scheduling Strategies for Parallel Processing
Quelling Queue Storms

HPDC '03 Proceedings of the 12th IEEE International Symposium on High Performance Distributed Computing
Probabilistic performance guarantee for real-time tasks with varying computation times

RTAS '95 Proceedings of the Real-Time Technology and Applications Symposium
A Decentralized Hierarchical Scheduler for a Grid-Based Clearinghouse

IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
Slack Stealing Job Admission Control Scheduling

Slack Stealing Job Admission Control Scheduling

Quantified Score

Hi-index	0.00

Visualization

Abstract

Cooperative resource sharing enables distinct organizations to form a federation of computing resources. A functional broker is deployed to facilitate remote resource access within the community grid. A major issue is the problem of correlations in job arrivals caused by seasonal usage and/or coincident resource usage demand patterns where high levels of burstiness in job arrivals can cause the job queue of the broker to grow to an extent such that its performance becomes severely impaired. Since job arrivals cannot be controlled, management strategies must be employed to admit jobs to sustain the resource allocation performance of the broker. In this paper, we present a theoretical analysis of the problem of job traffic burstiness on resource allocation performance in order to elicit the general job management strategies to be employed. Based on the analysis, we define and justify a job management framework for the resource broker to cope with overload conditions caused by job arrival correlations.