Demo: elastic mapreduce-style processing of fast data

MapReduce is a popular scalable processing framework for large-scale data. In this paper we demonstrate Enorm, which represents our efforts on rectifying the traditional batch-oriented MapReduce framework for low-latency data stream processing. Most existing work have focused on how to extend the MapReduce framework for low-latency data stream processing, but overlooked the problem of obtaining runtime elasticity. The demonstration focuses on two important features in Enorm. (1) sharing aggregate computations among overlapping windows and (2) runtime elasticity.