Xue, J., Chester, A. P., He, L. and Jarvis, S. A. (2009) Model-driven server allocation in distributed enterprise systems. Communications of SIWN. 6, pp. 42-50. 1757-4439.
- Information
Information
Abstract:
Internet service providers (ISPs) usually use several server pools to host different web applications, to ensure smooth system management and minimum interference between applications. The workload demand in each of the pools can vary dramatically due to a number of factors, including timing and the types of the hosted applications. Therefore, it is desirable that servers should be able to switch between pools to optimise resource usage and maximise company revenue. Internet applications can be modelled as multi-tier queueing networks, with each network station corresponding to each application tier. The advantage of using an analytical model is that performance metrics can be easily computed, and potential system bottlenecks can be identified without running the actual system. In this paper, an analytical model is used to assist dynamic resource allocation in server pools. In addition, an admission control scheme is also used to deal with system overloading. Performance evaluation is conducted via simulation and the experimental results show the benefits of our approach for various workload scenarios
Uncontrolled Keywords:
Multi-tier, queueing network, bottleneck, server switching, revenue
Subjects:
Creators:
Xue, J., Chester, A. P., He, L. and Jarvis, S. A.
Publisher:
Foresight Academy of Technology Press
Faculties, Divisions and Institutes:
Date:
April 2009
Date Type:
Publication
Page Range:
pp. 42-50
Journal or Publication Title:
Communications of SIWN
Volume:
6
Language:
English
ISSN:
1757-4439
Status:
Published / Disseminated
Refereed:
Yes
 |