Efficient scheduling of heterogeneous continuous queries

Sharaf, Mohamed A., Chrysanthis, Panos K., Labrinidis, Alexandros and Pruhs, Kirk (2006). Efficient scheduling of heterogeneous continuous queries. In: VLDB 2006 : proceedings of the 32nd International Conference on Very Large Data Bases. 32nd International Conference on Very Large Data Bases, Seoul, Korea, (511-522). 12-15 September 2006.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
MIC12UQ259075.pdf Full text - not publicly available application/pdf 458.49KB 4
p511sharaf.pdf ERA evidence - not publicly available application/pdf 644.25KB 0
Author Sharaf, Mohamed A.
Chrysanthis, Panos K.
Labrinidis, Alexandros
Pruhs, Kirk
Title of paper Efficient scheduling of heterogeneous continuous queries
Conference name 32nd International Conference on Very Large Data Bases
Conference location Seoul, Korea
Conference dates 12-15 September 2006
Proceedings title VLDB 2006 : proceedings of the 32nd International Conference on Very Large Data Bases
Place of Publication New York, United States
Publisher ACM Digital Library
Publication Year 2006
Sub-type Fully published paper
ISBN 1595933859
9781595933850
Start page 511
End page 522
Total pages 12
Language eng
Abstract/Summary Data Stream Management Systems (DSMS) typically host multiple Continuous Queries (CQ) that process streams of data. In this paper, we examine the problem of how to schedule CQs in a DSMS to optimize for average QoS. We show that unlike standard on-line systems, scheduling policies in DSMSs that optimize for average response time will be different than policies that optimize for average slowdown which is more appropriate metric to use in the presence of a heterogeneous workload. We also propose a hybrid scheduling policy based on slowdown that strikes a fine balance between performance and fairness. We further discuss how our policies can be efficiently implemented and extended to exploit sharing in optimized multi-query plans and multi- stream CQs. Finally, we experimentally show using real data that our policies outperform currently used ones.
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status Non-UQ

 
Versions
Version Filter Type
Citation counts: Google Scholar Search Google Scholar
Created: Sun, 23 Oct 2011, 03:31:01 EST by Dr Mohamed Sharaf on behalf of School of Information Technol and Elec Engineering