QoS-Aware Scheduling for Mixed Real-Time Queries over Data Streams

Data stream management systems (DSMSs) usually need to satisfy multiple QoS requirements of applications, including timing and precision constraints. This paper focuses on the problem of real-time query model and scheduling in a DSMS to meet multiple performance objectives. At first, a mixed real-time query model is introduced which is composed of periodic, continuous and one-time queries with deadlines. Moreover, an adaptive QoS-aware scheduling strategy, termed FC-TBS, is proposed to schedule these queries using feedback control mechanism. The objective of the FC-TBS strategy is to guarantee the deadlines of periodic queries and minimize the number of deadline violations for aperiodic queries. Besides the system tries to improve the overall query quality by adaptively adjusting CPU utilization factor for aperiodic queries according to work-load characteristics and application-defined relationship between sample ratio and QoS. Experimental results show that the FC-TBS strategy is more effective than other mixed scheduling algorithms and can deal with workload fluctuations gracefully.