Below are a summary of the results and some notes about the testing.


Cluster size Call Rate Event Rate TCAP message Rate Results

One node


36,000 events/s

64,000 messages/s

Two nodes


67,500 events/s

120,000 messages/s


Below are notes about the test procedure, types of graphs in the results, and how to calculate the number of dialogs per second.

Test procedure

Test calls:

  • were evenly distributed between all available cluster nodes

  • had originating and terminating treatment

  • were monitored for the entire duration on the originating leg

  • lasted 60s.

10% of calls involved a map query.

Types of graphs

The individual test results include the following types of graphs:

Response Times

Distribution of response-time changes during the course of the test run.

Response Time Distribution

Overall distribution of response times from the entire test run.

CPU Utilization

Percentage of CPU used by Rhino nodes, as reported by the kernel.


Heap usage.

Calculating number of dialogs

To calculate the number of dialogs (for example, using 8,000 calls per second):

  • All calls involve originating and terminating treatment (in our example, this means 16,000 dialogs).

  • 10% of calls involve a query to the HLR (800 dialogs).

…​for a total of 16,800 dialogs per second.

Previous page Next page