Cluster Platform Knowledgebase

This site documents the considerations and guidelines for designing and developing a HPC platform for cluster computing. The documentation describes general practices and considerations when designing a HPC platform as well as recommendations and guides used by Alces Software to configure HPC platforms.

License

This documentation is released under the Creative-Commons: Attribution-ShareAlike 4.0 International license.

Introduction

• Introduction
• Overviews

Network and Hardware

• Considerations for Network and Hardware Design
• Recommendations for Network and Hardware Design

Infrastructure

• Considerations for Infrastructure Design
• Recommendations for Infrastructure Design

01. Base System Deployment

• Base System Overview
• Considerations for Software and Application Deployment
• Master Node Setup
• Controller VM Setup
• Deployment Example

02. Repository Management

• Repository Overview
• Repository Mirror Server

03. User Management

• User Management Overview
• Considerations for User Management
• Recommendations for User Management

04. Storage

• Storage Overview
• Considerations for Storage Solution
• Recommendations for Storage Solution

05. Monitoring

• Monitoring Overview
• Considerations for Monitoring the HPC Platform
• Recommendations for Monitoring the HPC Platform

06. Hardware Drivers

• Hardware Drivers Overview
• First Boot Script Environment
• Compute Node Setup

07. HPC Environment

• HPC Environment Overview
• Considerations for HPC Environment Design
• Recommendations for HPC Environment Design

Verification

• Considerations for HPC Platform Verification
• Recommendations for HPC Platform Verification

Deployment on AWS

• Setting Up AWS Environment for HPC Platform