CIQ

Warewulf

Modern, Scalable, HPC Cluster Management & Provisioning

Warewulf simplifies management and scale of HPC clusters.

Download solution brief

Warewulf Management Web Interface now available from CIQ

Warewulf: The Open Source Choice for HPC Cluster Management

Warewulf streamlines the deployment and management of large Linux clusters. It presents a modern approach to managing complex clustered infrastructure and pioneered the concept of stateless computing

Stateless Provisioning

Warewulf has pioneered the practice of stateless computing in HPC. Compute nodes typically boot from the network and run entirely in memory using an image provided by the Warewulf server. This approach to imaging makes management, updates, and reimaging efficient and fast.

While primarily stateless, Warewulf can also handle stateful nodes with local disks, whether you want local storage for virtual memory, local scratch, log retention, or clustered file systems.

Centralized Management

A central Warewulf server manages the operating system images, configurations, and provisioning of all the compute nodes in the cluster. This provides a single point of control for administration, and a single source of truth for configuration.

Hardware and OS Agnostic

Warewulf can run cluster nodes independent of the architecture and configuration of the server node, supporting both x86 and ARM CPUs among others. It can provision most Linux distributions, including Rocky Linux, Red Hat Enterprise Linux (RHEL), CentOS, SUSE, Debian, and Ubuntu.

Container Integration

Warewulf (optionally) leverages container images and tooling (whether you use Docker, Podman, or Apptainer) to define and manage node images. This greatly simplifies image creation and management, and supports integration with modern DevOps practices.

CLI and API

Warewulf is typically managed via a powerful command-line interface; but it also delivers a REST API that opens up the platform for automation and tighter integration into local infrastructure.

Developed in the Open

With over 500 GitHub stars, the Warewulf GitHub project is a testament to the value of open source development in action. It includes contributions from CIQ, Intel, OpenHPC, and SUSE, along with academic and research partners.

Tech Preview

Warewulf Web Interface

CIQ recently opened up a tech preview program of a new Web Interface for Warewulf. Built on Cockpit, the new UI simplifies cluster administration for new and existing administrators while maintaining Warewulf’s flexibility for research, commercial and fully-integrated environments.

Warewulf In Use

While primarily used in High-Performance Computing (HPC) clusters, Warewulf's flexible architecture makes it suitable for other clustered Linux environments, including:

  • HPC Clusters
  • Clustered Web Servers
  • Kubernetes
  • Large-scale test & development environment
  • Visualization and Render Farms
  • Distributed Storage Clusters
  • Parallel File Systems

Need Warewulf Support?

Let us help you get the most out of your Warewulf deployment! We can assist with configuration and deployment advice, custom node images, custom overlays, and development of new features. Reach out to our team to learn more.

Download the Warewulf Guide

Download the Warewulf Solution Guide and learn more about Warewulf and CIQ support!

Download solution brief

Key Warewulf Resources

Documentation

Our docs are online so you can explore deeper concepts and get a sense of how it works.

Tech Session

In this video, session we walk through the basics of Warewulf and introduce many of its concepts

Watch now

GitHub Repo

You can access the Warewulf open source project on Github.

Download Warewulf

Related content

Warewulf: Using Warewulf to Manage GPU clusters

Warewulf: Using Warewulf to Manage GPU clusters

Jan 9, 2025

Warewulf

Research Computing Roundtable: AI in 2024

Research Computing Roundtable: AI in 2024

Mar 14, 2024

Warewulf

Code to Conquer: Best Practices for Achieving Peak Performance in HPC Systems

Code to Conquer: Best Practices for Achieving Peak Performance in HPC Systems

Jan 25, 2024

Rocky Linux

123
6
>>>

Get a demo

Fill out this form, and we will be in touch to schedule the demo.