benchmark-runner 1.0.2

Benchmark Runner Tool


[](media/run.png)

Benchmark-Runner

This tool provides a lightweight and flexible framework for running benchmark workloads on Kubernetes/OpenShift-CNV Pod or VM.

This tool support the following workloads:

• hammerdb: running hammerdb workload on the following databases: MSSQL, Mariadb, Postgresql on Pod and VM hammerdb
• stressng: running stressng workload on Pod or VM stressng
• uperf: running uperf workload on Pod or VM uperf

** First Phase: support benchmark-operator workload

Reference:

• The benchmark-runner package is placed in PyPi
• The benchmark-runner container image is placed in Quay.io

Table of Contents

• Installation
• Run workload using Docker/Podman
• Run workload in Pod using Kubernetes/OpenShift
• Post Installation

Installation

Download benchmark-runner image from quay.io

podman pull quay.io/ebattat/benchmark-runner:latest

Environment variables description:

(mandatory)KUBECONFIG=$KUBECONFIG

(mandatory)KUBEADMIN_PASSWORD=$KUBEADMIN_PASSWORD

(mandatory)workload=$workload

Choose one from the following list:

['stressng_pod', 'stressng_vm','uperf_pod', 'uperf_vm', 'hammerdb_pod_mariadb', 'hammerdb_pod_mssql', 'hammerdb_pod_postgres', 'hammerdb_vm_mariadb', 'hammerdb_vm_mssql', 'hammerdb_vm_postgres']

(mandatory)elasticsearch=elasticsearch

(optional)pin_node1=pin_node1

(optional)pin_node2=pin_node2

Run workload using Podman/Docker

# workload=stressng_pod
sudo podman run --rm --name benchmark-runner -e KUBECONFIG=$KUBECONFIG -e KUBEADMIN_PASSWORD=$KUBEADMIN_PASSWORD -e workload=stressng_pod -e elasticsearch=elasticsearch -e pin_node1=pin_node1 -e log_level=INFO quay.io/ebattat/benchmark-runner:latest

# custom workload data configuration (path for custom workload data: -v /home/user/workload/workload_data.yaml:/benchmark_runner/benchmark_operator/template/workload/workload_data.yaml)
sudo podman run --rm --name benchmark-runner -e KUBECONFIG=$KUBECONFIG -e KUBEADMIN_PASSWORD=$KUBEADMIN_PASSWORD -e workload=stressng_pod -e elasticsearch=elasticsearch -e pin_node1=pin_node1 -e log_level=INFO -v /home/user/stressng/stressng_data.yaml:/benchmark_runner/benchmark_operator/template/stressng/stressng_data.yaml --privileged quay.io/ebattat/benchmark-runner:latest

Run workload in Pod using Kubernetes/OpenShift]

[TBD]

Post Installation

Delete benchmark-runner image

sudo podman rmi quay.io/ebattat/benchmark-runner:latest