Below are the hardware, software-ha, and Rhino configuration used for the Rhino benchmarks.
Hardware
The SIP HA and FT benchmark tests were run using configurations ranging from one node to four node clusters. Benchmarks are provided for both Java 7 and 8.
Two Java versions were used as there was significant modifications to garbage collection between Java 7 and 8.
The following hardware layout was used for the four node cluster tests.
![sip benchmarks hardware 4 nodes](../../images/sip-benchmarks/sip-benchmark-environment-and-configuration/sip-benchmarks-hardware-4-nodes.png)
Machine | CPUs | RAM | OS |
---|---|---|---|
1 |
2 x 6-core Xeon X5650 2.67GHz |
24G |
RHEL 7 |
2 |
2 x 6-core Xeon X5650 2.67GHz |
24G |
RHEL 7 |
3 |
2X Intel Xeon X5660 2.8GHz 12 core |
12G |
Centos 7 |
4 |
2X Intel Xeon X5660 2.8GHz 12 core |
12G |
Centos 7 |
Software (HA)
The SIP benchmark tests used the following software.
Software | Version |
---|---|
Java |
JDK 1.7.0_71 and JDK 1.8.0_60 |
Rhino |
Rhino 2.5.0.1 |
2.4.0.2 |
Rhino configuration
For the SIP benchmark tests, we made the following changes to the Rhino 2.4.0 default configuration.
Parameter | Value | Note |
---|---|---|
JVM Architecture |
64bit |
Enables larger heaps |
Heap size |
8192M |
|
New Gen size |
512M |
Increased from default of 128M to achieve higher throughput without increasing latency |
Staging queue size |
5000 |
Increased from default of 3000 to allow burst traffic |
Worker Pool size |
120 |
|
Worker Queue size |
1000 |
|
Transport |
TCP |
|
Staging threads |
400 |
Increased from default of 30 for reduced latency at high throughput |
Local Memory DB size |
200M |
Increased from default of 100M to allow more in-flight calls |