This page summarises the results for the MMTEL scenario group executed with three hosts, each running a single node. Replication to support failover using the Cassandra Key-Value store is enabled. Detailed metrics follow the summary tables.

Benchmarks

Call rate

300 calls per second across the four scenarios

Node Across 8 vCPUs

1

500

2

480

3

500

Note Maximum theoretical CPU usage is 800.
Node Average heap

1

5200MB

2

5000MB

3

5000MB

Scenario latencies

Scenario 50th 75th 90th 95th 99th

CDIV Busy-response

48.3ms

93.4ms

148ms

188ms

318ms

CDIV Success-response

48.1ms

92.8ms

148ms

189ms

320ms

CDIV Success-response with OIP

47.7ms

92.7ms

148ms

188ms

317ms

VoLTE full preconditions and 1 session refresh scenario latencies

58.3ms

106ms

169ms

212ms

369ms

VoLTE full preconditions

52.4ms

97.2ms

155ms

197ms

332ms

Note Callflows for each of the scenarios are available in Benchmark Scenarios.

Detailed metrics

CPU usage

rhino cluster 101 cpu
rhino cluster 102 cpu
rhino cluster 103 cpu

Heap usage

rhino cluster 101 heap
rhino cluster 102 heap
rhino cluster 103 heap

CDIV Busy-response scenario latencies

cdiv busy response basic latency

CDIV Success-response scenario latencies

cdiv success latency

CDIV Success-response with OIP scenario latencies

oip cdiv success latency

VoLTE full preconditions scenario latencies

volte full latency

VoLTE full preconditions and 1 session refresh scenario latencies

preconditions with 1 session refresh latency
Previous page Next page