alefais / packet-streaming-bench-sigcomm22poster

Source code of a heavy hitter packet streaming application implemented with four stream processing systems: Flink, Spark Streaming, Storm and WindFlow.

Heavy hitter detection - Stream Benchmark

This repository includes the implementation of a heavy hitter detection network traffic query. Four different Stream Processing Systems (SPSs) have been used in this benchmark.

Framework	Version used	Source code
Apache Flink	1.14.4 (for Scala 2.12)	Link
Apache Spark Streaming	3.2.1	Link
Apache Storm	2.4.0	Link
WindFlow	3.0.0	Link

The code released as open source is part of our research aiming to shed some lights on the best streaming engine for network traffic analysis.

Conference Poster at SIGCOMM '22 Posters and Demos

If you are interested, have a look at our poster "Mind the Cost of Telemetry Data Analysis".

How to cite

If our work reveals to be useful for your research, we kindly ask you to give credit to our effort by citing the following paper:

@inproceedings{TelemetryStreamBench,
    author = {Fais, Alessandra and Antichi, Gianni and Giordano, Stefano and Lettieri, Giuseppe and Procissi, Gregorio},
    title = {{Mind the Cost of Telemetry Data Analysis}},
    year = {2022},
    booktitle = {Special Interest Group on Data Communication (SIGCOMM)},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    abstract = {Data Stream Processing engines are emerging as a promising solution to efficiently process a continuous amount of telemetry information. In this poster, we compare four of them: Storm, Flink, Spark and WindFlow. The aim is to shed some lights on the best streaming engine for network traffic analysis.},
    keywords = {streaming analysis, measurement, data center, programmability},
    location = {Amsterdam, Netherlands},
    series = {SIGCOMM '22}
}

Contributors

The main developer and maintainer of this repository is Alessandra Fais.