® ®
The Altix ICE Cluster Administration course provides knowledge and practice in basic cluster administration areas as IPMI configuration, SGI Tempo cluster software installation and configuration, Torque configuration and job submittal, Infiniband configuration and cluster monitoring and troubleshooting using Ganglia tools and Performance Co-Pilot tools.
Topics Covered
- ICE hardware overview
- IPMI configuration and use
- Troubleshoot startup problems
- Software installation
- Cluster configuration
- Cluster imaging
- Infiniband software overview
- Customize the Cluster
- Install Intel Cluster toolkit and Intel MPI
- Cluster monitoring
- Cluster maintenance
- Torque overview
- Troubleshoot problems
Objectives
Upon completion of this course, the student should be able to:
- Use the ipmi tools to setup for cluster imaging
- Setup Serial Over Lan for console access and power control
- Troubleshoot startup problems
- Install SGI Tempo Cluster Manager software
- Configure a cluster using the SGI Tempo
- Image compute nodes with SGI Tempo
- Use OFED Infiniband software
- Setup user accounts
- Install and Configure Intel Cluster Toolkit and MPI
- Run MPI applications across the cluster
- Monitor a running cluster with ganglia and PCP
- Add and remove compute nodes
- Setup Torque
- Submit batch jobs with Torque
- View diagnostic logs
Target Audience
- Experienced Linux system administrators
- Experienced Linux users who must maintain their own systems
Prerequisites
- Linux system administration experience that includes installing the operating system, adding and removing users, editing files, configuring software services, configuring network devices.
- DNS,NIS,NFS,ssh,NAT
Class Hours
Class starts at 9:00 AM. The course dates and times will be included in the confirmation notice you receive from SGI after you register.
