Windows HPC Server 2008 Design and Deployment Guide

Applies To: Windows HPC Server 2008

This guide provides conceptual information for planning the deployment of a high performance computing cluster using Windows® HPC Server 2008. It also provides step-by-step procedures for deploying the head node in your cluster, adding compute nodes, and for verifying that your deployment was successful.

The following information may also be useful when you are planning and deploying an HPC cluster:

• You can configure your HPC cluster for high availability by installing the head node in the context of a failover cluster. If the server that is acting as the head node fails, the other server in the failover cluster automatically begins acting as the head node (through a process known as failover). For more information about running an HPC cluster with failover clustering, see the Configuring Failover Clustering in Windows HPC Server 2008 Step-by-Step Guide (https://go.microsoft.com/fwlink/?LinkId=123894).

• Some design and deployment decisions have specific security implications in an HPC cluster. For more information, see Security in Windows HPC Server 2008 (https://go.microsoft.com/fwlink/?LinkId=157794).

Sections in this guide

This guide contains the following sections:

Checklist: Deploy an HPC Cluster (Overview)

Step 1: Prepare for Your Deployment

Step 2: Deploy the Head Node

Step 3: Configure the Head Node

Step 4: Add Compute Nodes to the Cluster

Step 5: Run Diagnostic Tests on the Cluster

Step 6: Run a Test Job on the Cluster

Additional Resources

Appendices