Welcome to the ADMT Publication Server

Tuning QoD in Stream Processing Engines

DocUID: 2010-005 Full Text: PDF

Author: Mohamed A. Sharaf, Panos K. Chrysanthis, Alexandros Labrinidis

Abstract: Quality of Service (QoS) and Quality of Data (QoD) are the two major dimensions for evaluating any query processing system. In the context of data stream management systems (DSMSs), multi-query scheduling has been exploited to improve QoS. In this paper, we are proposing to exploit query scheduling to improve QoD in DSMSs. Specifically, we are presenting a new policy for scheduling multiple continuous queries with the objective of maximizing the freshness of the output data streams and hence the QoD of such outputs. The proposed Freshness-Aware Scheduling of Multiple Continuous Queries (FAS-MCQ) policy decides the execution order of continuous queries based on each query's properties (i.e., cost and selectivity) as well the properties of the input update streams (i.e., variability of updates). Our experimental results have shown that FAS-MCQ can improve QoD by up to 50\% compared to existing scheduling policies used in DSMSs. Finally, we propose and evaluate a parameterized version of our FAS-MCQ scheduler that is able to balance the trade-off between freshness and response time according to the application's requirements.

Published In: Twenty-First Australasian Database Conference

ISBN: 978-1-920682-85-9

Pages: pp. 103-112

Place Published: Brisbane, Australia

Year Published: 2010

Project: AQSIOS Subject Area: Data Streams

Publication Type: Conference Paper

Sponsor: NSF CAREER IIS-0746696, NSF IIS-0534531

Citation:Text Latex BibTex XML Mohamed A. Sharaf, Panos K. Chrysanthis, and Alexandros Labrinidis. Tuning QoD in Stream Processing Engines, Twenty-First Australasian Database Conference (ADC'10), pp. 103-112, 978-1-920682-85-9 , Brisbane, Australia, January 2010.