Adaptive Class-Based Scheduling of Continuous Queries
DocUID: 2012-002 Full Text:
PDF Author: Lory Al Moakar, Alexandros Labrinidis, Panos K. Chrysanthis
Abstract: The emergence of Data Stream Management Systems (DSMS) facilitates implementing many types of monitoring applications via continuous queries (CQs). However, these applications usually have different quality-of-service requirements for different CQs. In this work, we are proposing the Adaptive Broadcast-Disks-Style (BDS) scheduler, a new scheduling policy which employs two-level scheduling that can handle different ranks of CQ classes. The BDS scheduler optimizes the weighted average response time of the CQ classes while still preserving the relative importance of each class. We demonstrate that BDS outperforms state-of-the-art schedulers and adapts to changes in the workload without manual intervention.
Published In: Proc. of the Seventh International Workshop on Self-Managing Database Systems
Pages: pp. 1-6
Year Published: 2012
Project: AQSIOS Subject Area: Data Streams
Publication Type: Workshop Paper
Sponsor: NSF OIA-1028162, NSF CAREER IIS-0746696, NSF IIS-0534531