IT-SDK-Testing-Performance

Ref.

• https://jmeter.apache.org/usermanual/best-practices.html#bsh_scripting
• https://jmeter.apache.org/usermanual/component_reference.html#BeanShell_PostProcessor
• https://jmeter.apache.org/usermanual/functions.html
• https://www.blazemeter.com/blog/what-every-performance-tester-should-know-about-extracting-data-files-jmeter
• https://octoperf.com/blog/2018/04/23/jmeter-rest-api-testing/#rest-api-login

Ref-Used

• ctx : https://jmeter.apache.org/api/org/apache/jmeter/threads/JMeterContext.html
• vars: https://jmeter.apache.org/api/org/apache/jmeter/threads/JMeterVariables.html
• prev: https://jmeter.apache.org/api/org/apache/jmeter/samplers/SampleResult.html

Begriffe

• Throughput: is the number of requestes that a server can serve in a given time.
• Latency: is the time a request takes to travel from client to server and server to client. In other words, Delay.
• Response Time: Latency + Processing time (at application server level) = Response Time.

---

• Threads:
• Ramp up: how much time a chosen number of threads will be run on the server.

Infrastructure

• TOP: Cluster, Engine, Threads (Users)
• Clsuter: has 1 console (only one) and 0-14 engines.

Configuration

Cluster: 1 Console & 0-14 Engines.
Engines: 
Threads: 500 users.
Ramp-up: 40 minutes.
Iteration: forever.
Duration: 50 minutes.

K6

Settings

sysctl net.ipv4.ip_local_port_range
sysctl net.ipv4.tcp_tw_reuse
sysctl net.ipv4.tcp_timestamps
ulimit -n
#####################################################
sysctl -w net.ipv4.ip_local_port_range="32768 60999"
sysctl -w net.ipv4.tcp_tw_reuse=2
sysctl -w net.ipv4.tcp_timestamps=1
ulimit -n 1024
#####################################################
sysctl -w net.ipv4.ip_local_port_range="1024 65535"
sysctl -w net.ipv4.tcp_tw_reuse=1
sysctl -w net.ipv4.tcp_timestamps=1
ulimit -n 250000