Achieving High Freshness and Optimal Throughput in CPU-Limited Execution of Multi-join Continuous Queries

Due to high data volumes and unpredictable arrival rates, continuous query systems processing expensive queries in real-time may fail to keep up with the input data streams - resulting in buffer overflow and uncontrolled data loss. We explore join direction adaptation (JDA) to tackle CPU-limited processing of multijoin stream queries. The existing JDA solutions allocate the scarce CPU resources to the most productive half-way join within a single operator. We instead leverage the operator interdependencies to optimize the overall query throughput. We identify result staleness, typically ignored by most state-of-the-art techniques, as a critical issue in CPU-limited processing. It gets further aggravated if throughput optimizing techniques are employed. We establish the novel path-productivity model and the Freshness predicate. Our proposed JAQPOT approach is the first integrated solution to achieve near optimal query throughput while also guaranteeing freshness satisfiability. JAQP...

• Type: Journal
• Year: 2011
• Where: BNCOD
• Authors: Abhishek Mukherji, Elke A. Rundensteiner, Matthew O. Ward
• Keywords: BNCOD 2011, Data Streams, Database, Plan Shape, Productivity Model