Sysbench - Scriptable database and system performance benchmark¶
sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. It is most frequently used for database benchmarks, but can also be used to create arbitrarily complex workloads that do not involve a database server.
With the sysbench benchmark you can measure the CPU, Memory, Database and Filesystem characteritics of your Kubernetes cluster.
Mode of operation¶
Kubestone generates a Kubernetes Job from each Sysbench CR that will run a single pod with the defined job. Sysbench's input parameters can be specified in the CR with their respective names:
sysbench [options]... [testname] [command]
You can find configuration example in the GitHub repository.
kubectl create --namespace kubestone -f https://raw.githubusercontent.com/xridge/kubestone/master/config/samples/perf_v1alpha1_sysbench.yaml
Please refer to the quickstart guide for details on generic principles and setup of Kubestone.
The complete documentation of sysbench CR can be found in the API Docs.
Docker Image for sysbench is provided via xridge's sysbench repository.
sysbench is licensed as GPLv2.