benchmark-runner 1.0.56

Benchmark Runner Tool

Benchmark-Runner

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

This tool support the following workloads:

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

** First Phase: supports benchmark-operator workloads

Hammerdb Kibana dashboard:

Reference:

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

Table of Contents

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

Installation

optional:

Download benchmark-runner image from quay.io

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

Run workload using Podman/Docker

Environment variables description:

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: PIN_NODE_BENCHMARK_OPERATOR=$pin_node_benchmark_operator [node selector for benchmark operator pod]

mandatory: PIN_NODE1=$pin_node1 [node1 selector for running the workload]

mandatory: PIN_NODE2=$pin_node2 [node2 selector for running the workload, i.e. uperf there are server and client]

optional: ELASTICSEARCH=$elasticsearch [ elasticsearch service name]

optional: ELASTICSEARCH_PORT=$elasticsearch_port

sudo podman run --rm -e WORKLOAD=stressng_pod -e KUBEADMIN_PASSWORD=$kubeadmin_password -e ELASTICSEARCH=$elasticsearch -e ELASTICSEARCH_PORT=$elasticsearch_port -e PIN_NODE1=$pin_node1 -v /root/.kube/config:/root/.kube/config -e log_level=INFO --privileged quay.io/ebattat/benchmark-runner:latest

# For custom workload data configuration add:
-v /home/user/stressng/stressng_data.yaml:/benchmark_runner/benchmark_operator/template/stressng/stressng_data.yaml

Run workload in Pod using Kubernetes/OpenShift

[TBD]

Post Installation

optional:

Delete benchmark-runner image

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