On-the-fly sharing for streamed aggregation
Proceedings of the 2006 ACM SIGMOD international conference on Management of data
NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation
Muppet: MapReduce-style processing of fast data
Proceedings of the VLDB Endowment
Hi-index | 0.00 |
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.