Scaling Out the Performance of Service Monitoring Applications with BlockMon

  • Davide Simoncelli
  • Maurizio Dusi
  • Francesco Gringoli
  • Saverio Niccolini
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7799)

Abstract

To cope with real-time data analysis as the amount of data being exchanged over the network increases, an idea is to re-design algorithms originally implemented on the monitoring probe to work in a distributed manner over a stream-processing platform. In this paper we show preliminary performance analysis of a Twitter trending algorithm when running over BlockMon, an open-source monitoring platform which we extended to run distributed data-analytics algorithms: we show that it performs up to 23.5x and 34.2x faster on BlockMon than on Storm and Apache S4 respectively, two emerging stream-processing platforms.

References

  1. 1.
    Apache Hadoop, http://hadoop.apache.org (accessed September 01, 2012)
  2. 2.
    Dean, J., Ghemawat, S.: Mapreduce: simplified data processing on large clusters. Commun. ACM 51(1), 107–113 (2008)CrossRefGoogle Scholar
  3. 3.
    di Pietro, A., Huici, F., Bonelli, N., Trammell, B., Kastovsky, P., Groleat, T., Vaton, S., Dusi, M.: Blockmon: Toward high-speed composable network traffic measurement. In: Proceedings of the IEEE Infocom Conference, Mini-conference (2013)Google Scholar
  4. 4.
    BlockMon, http://blockmon.github.com/blockmon (accessed August 30, 2012)
  5. 5.
    Storm, http://storm-project.net (accessed August 30, 2012)
  6. 6.
    Apache S4, http://incubator.apache.org/s4 (accessed August 30, 2012)

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Davide Simoncelli
    • 1
  • Maurizio Dusi
    • 2
  • Francesco Gringoli
    • 1
  • Saverio Niccolini
    • 2
  1. 1.University of Brescia – CNITBresciaItaly
  2. 2.NEC Laboratories EuropeHeidelbergGermany

Personalised recommendations