Scalability tests of the ActiveMQ broker

  • 300 topics.
  • 300 consumers (1 per topic).
  • 15 producers (each one sending to 20 different topics).
  • 3000 messages sent all at once! (around 10 messages per topic).
  • Message size > 2 KB

UPDATE: I've just realized that the first 200 consumers are allocated in vnode machines. Taking into account that I/O and networking are the bottlenecks (by far) in virtualized environments, the results should be even better if we allocate all the consumers in machines with dedicated hardware. That would also explain why the section x=[200,300] in the first chart is significantly better than the rest.

The results:

Seconds/Message Memory usage

Interesting comparison of messaging systems:

-- JoseDana - 01 Apr 2009

Topic attachments
I Attachment History Action Size Date Who Comment
PNGpng messages_durable.png r1 manage 5.0 K 2009-04-01 - 17:56 JoseDana  
PNGpng system_durable.png r1 manage 3.1 K 2009-04-01 - 17:56 JoseDana  
Edit | Attach | Watch | Print version | History: r2 < r1 | Backlinks | Raw View | WYSIWYG | More topic actions
Topic revision: r2 - 2020-08-19 - TWikiAdminUser
    • Cern Search Icon Cern Search
    • TWiki Search Icon TWiki Search
    • Google Search Icon Google Search

    Sandbox/SandboxArchive All webs login

This site is powered by the TWiki collaboration platform Powered by PerlCopyright & 2008-2023 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
or Ideas, requests, problems regarding TWiki? use Discourse or Send feedback