Select Your Language

Infrastructure and Management

Cloud Computing

Storage

Runtimes

Integration and Automation

  • Comments
  • Cluster performance degradation

    Posted on

    Hi,

    We are trying to validate the cluster performance based on number of read and write operation.
    RadarGun tool used for performance measurement.

    RadarGun is configured as below,

    • Number of Thread accessing the Cache : 40
    • Number of Entry per thread : 100000
    • Read/Write Ratio : 60-40
    • Cluster size : 5

    There is a big dip in the performance while size of the entry is increased.
    Approximately 17K tps ( for 1K size entry) is decreased to 3K tps (for 4K size entry) and also cluster becoming very unstable.

    Attached the infinispan and jgroups configured with this post.

    Will these configuration are OK or does it requires any tuning.

    Regards,
    Vadivel G

    Attachments

    by

    points

    Responses

    Red Hat LinkedIn YouTube Facebook X, formerly Twitter

    Quick Links

    Help

    Site Info

    Related Sites

    © 2026 Red Hat