StreaMon: An Adaptive Engine for Stream Query Processing

Abstract

<i>StreaMon</i> is the adaptive query processing engine of the <i> STREAM</i> prototype Data Stream Management System (DSMS). A fundamental challenge in many DSMS applications (e.g., network monitoring, financial monitoring over stock tickers, sensor processing) is that conditions may vary significantly over time. Since queries in these systems are usually long-running, or <i>continuous</i>, it is important to consider <i> adaptive</i> approaches to query processing. Without adaptivity, performance may drop drastically as stream data and arrival characteristics, query loads, and system conditions change over time. StreaMon uses several techniques to support adaptive query processing. We demonstrate three of them: <ol> <li> Reducing run-time memory requirements for continuous queries by exploiting stream data and arrival patterns. </li> <li> Adaptive join ordering for pipelined multiway stream joins, with strong quality guarantees. </li> <li> Placing subresult caches adaptively in pipelined multiway stream joins to avoid recomputation of intermediate results. </li> </ol>