Scalable online first-order monitoring

Abstract Online monitoring is the task of identifying complex temporal patterns while incrementally processing streams data-carrying events. Existing state-of-the-art monitors for first-order patterns, which may refer to and quantify over data values, can process modest velocity in real-time. We show how scale up substantially higher velocities by slicing stream, based on events’ into substreams that be monitored independently. Because not embarrassingly parallel general, lead duplication. To reduce this overhead, we adapt hash-based partitioning techniques from databases setting. implement these an automatic slicer Apache Flink empirically evaluate its performance using two tools—MonPoly DejaVu—to monitor substreams. Our evaluation attests substantial scalability improvements both tools.