@inproceedings{cacd4aa67ffa460491acce31c8d3cf59,
title = "Stela: Enabling stream processing systems to scale-in and scale-out on-demand",
abstract = "The era of big data has led to the emergence of new real-time distributed stream processing engines like Apache Storm. We present Stela (STream processing ELAsticity), a stream processing system that supports scale-out and scale-in operations in an on-demand manner, i.e., when the user requests such a scaling operation. Stela meets two goals: 1) it optimizes post-scaling throughput, and 2) it minimizes interruption to the ongoing computation while the scaling operation is being carried out. We have integrated Stela into Apache Storm. We present experimental results using micro-benchmark Storm applications, as well as production applications from industry (Yahoo! Inc. and IBM). Our experiments show that compared to Apache Storm's default scheduler, Stela's scale-out operation achieves throughput that is 21-120% higher, and interruption time that is significantly smaller. Stela's scale-in operation chooses the right set of servers to remove and achieves 2X-5X higher throughput than Storm's default strategy.",
keywords = "Distributed Systems, Elasticity, Scalability, Stream Processing",
author = "Le Xu and Boyang Peng and Indranil Gupta",
year = "2016",
month = jun,
day = "1",
doi = "10.1109/IC2E.2016.38",
language = "English (US)",
series = "Proceedings - 2016 IEEE International Conference on Cloud Engineering, IC2E 2016: Co-located with the 1st IEEE International Conference on Internet-of-Things Design and Implementation, IoTDI 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "22--31",
booktitle = "Proceedings - 2016 IEEE International Conference on Cloud Engineering, IC2E 2016",
address = "United States",
note = "4th IEEE Annual International Conference on Cloud Engineering, IC2E 2016 ; Conference date: 04-04-2016 Through 08-04-2016",
}