stress-ng — System Stress Testing
NOTE
Status: implemented and unit-tested, not proven on hardware. See the implementation status table. Command examples on this page show the intended workflow; the param block of each script is the authority for parameter names. Not proven on a live cluster.
stress-ng performs CPU, memory, cache, and I/O stress testing for capacity planning and burn-in validation. It includes 370+ stressors and runs on Linux VMs via Ansible deployment.
Run This Test
Prerequisites
- Linux VMs deployed on your Azure Local cluster
- Ansible 2.14+ installed on your management workstation
- SSH key-based access to Linux VMs
- Framework prerequisites completed
Step 1 — Install stress-ng on target VMs
There is no PowerShell install script. The Ansible playbook installs stress-ng on Linux VMs:
bash
ansible-playbook -i common/ansible/inventory/hosts.yml tools/stress-ng/playbooks/deploy-stress-ng.ymlStep 2 — Run a stress test
powershell
.\tools\stress-ng\scripts\Start-StressNgTest.ps1 `
-ClusterName "hci01.corp.infiniteimprobability.com" `
-Nodes @("hci01-node1", "hci01-node2") `
-Profile "cpu-stress" `
-DurationSeconds 600Step 3 — Collect results
powershell
.\tools\stress-ng\scripts\Collect-StressNgResults.ps1 `
-ClusterName "hci01.corp.infiniteimprobability.com" `
-Nodes @("hci01-node1", "hci01-node2") `
-RunId "<run-id-from-previous-step>"When to Use stress-ng
| Scenario | stress-ng |
|---|---|
| CPU thermal and power validation | ✅ |
| Memory stability under pressure | ✅ |
| Burn-in testing of new cluster nodes | ✅ |
| Determine maximum safe CPU utilization | ✅ |
| Cache and TLB stress testing | ✅ |
Key Capabilities
- 370+ stressors across CPU, memory, filesystem, network, and OS categories
- YAML job files for reproducible configurations
- Metrics — bogo ops/s, thermal zone readings, power measurement
- Stressor classes for targeted testing (cpu, memory, io, network, etc.)
- Verification mode for checking compute accuracy under load
What You Get
After a test completes, you will have:
- Bogo ops/s (bogus operations per second) per stressor per node
- Thermal readings if available on hardware
- Aggregated metrics across all nodes
- Reports in PDF, DOCX, and/or XLSX format
File Locations
| Component | Path |
|---|---|
| Scripts | tools/stress-ng/scripts/ |
| Workload Profiles | tools/stress-ng/config/profiles/ |
| Ansible Playbooks | tools/stress-ng/playbooks/ |
| Alert Rules | tools/stress-ng/monitoring/alert-rules.yml |
| Report Templates | tools/stress-ng/reports/templates/ |
| Tests | tools/stress-ng/tests/ |
| Logs | tools/stress-ng/logs/ |
Deep Dive
| Topic | Page |
|---|---|
| Ansible deployment details | Installation |
| CPU, memory, and I/O profiles | Workload Profiles |
| Alert rules during test runs | Monitoring |
| Report formats and templates | Reporting |
| Common errors and fixes | Troubleshooting |
Automate This Test
To run stress-ng on a schedule or as part of a CI/CD workflow, see CI/CD Pipelines. The pipeline calls the same scripts listed above.