SGI® Management Center for Altix® ICE

Document Number: 007-5718-002

Front Matter

| List of Figures | List of Examples | List of Tables | List of Procedures |


Table of Contents

New Features in This Manual
Major Documentation Changes

About This Guide
Related Publications
Obtaining Publications
Conventions
Reader Comments

1. SGI Altix ICE System Overview
Hardware Overview
Networks
Network Interface Naming Conventions

2. System Discovery, Installation, and Configuration
Configuring Factory-installed SGI Altix ICE System
Accessing SGI Management Center
Overview of Installing Software and Configuring Your SGI Altix ICE System
Installing SMC for Altix ICE Admin Node Software
discover Command
Installing Software on the Rack Leader Controllers and Service Nodes
blademond Command For Automatic Blade Discovery
Discovering Compute Nodes
Service Node Discovery, Installation, and Configuration
Configure the Backup DNS Server
InfiniBand Configuration
Redundant Management Network
MySQL Database Server Replication
Configuring the Service Node
Setting Up an NFS Home Server on a Service Node for Your Altix ICE System
RHEL Service Node House Network Configuration
Setting Up a NIS Server for Your Altix ICE System
Installing SMC for Altix ICE Patches and Updating SGI Altix ICE Systems
Cascading Dual-Boot
Installing MPI on a Running Altix ICE System
System Admin Controller High Availability Solution
Rack Leader Controller High Availability Solution

3. System Operation
Software Image Management
Power Management Commands
C3 Commands
cadmin: SMC for Altix ICE Administrative Interface
Console Management
Keeping System Time Synchronized
Changing the Size of /tmp on Compute Nodes
Enabling or Disabling the Compute Node iSCSI Swap Device
Changing the Size of Per-node Swap Space
Switching Compute Nodes to a tmpfs Root
Setting up Local Storage Space for Swap and Scratch Disk Space
Viewing the Compute Node Read-Write Quotas
RAID Utility
Restoring the grub Boot-loader on a Node
Backing up and Restoring the System Database
Enabling EDNS
Firmware Management

4. System Fabric Management
InfiniBand Fabric Management

5. System Maintenance, Monitoring, and Debugging
Maintenance Procedures
Node Replacement Procedure for a Cold Spare Admin, Leader, and Service Nodes
How To Avoid Out of Memory Occurrences on SLES11 and PBS Pro
Inventory Verification Tool
System Monitoring Overview
System Monitoring Operation
Monitoring System Metrics with Performance Co-Pilot
Setting up the Embedded Support Partner
Troubleshooting
kdump Utility
System Firmware

A. Out of Memory Adjustment

Index