Administrator’s Guide

• Preface
• Scyld ClusterWare Design Overview
  • System Architecture
    • System Hardware Context
    • Network Topologies
    • System Data Flow
    • System Software Context
    • System Level Files
  • Technical Description
    • Compute Node Boot Procedure
    • BProc Distributed Process Space
    • Compute Node Categories
    • Compute Node States
    • Miscellaneous Components
  • Software Components
    • BeoBoot Tools
    • BProc Daemons
    • BProc Clients
    • ClusterWare Utilities
• Monitoring the Status of the Cluster
  • Monitoring Utilities
    • Cluster Monitoring Interfaces
    • Monitoring Daemons
  • Using the Data
  • beostatus
    • beostatus File Menu
    • beostatus Modes
  • beostat
  • bpstat
  • Ganglia
  • beoweb
• Configuring the Cluster
  • Configuring the Cluster Manually
    • Configuration Files
    • Command Line Tools
    • Configuring CPU speed/power for Compute Nodes
    • Adding New Kernel Modules
    • Accessing External License Servers
    • Configuring SSH for Remote Job Execution
    • Interconnects
• Remote Administration and Monitoring
  • Command Line Tools
  • X Forwarding
• Managing Users on the Cluster
  • Managing User Accounts
    • Adding New Users
    • Removing Users
  • Managing User Groups
    • Creating a Group
    • Adding a User to a Group
    • Removing a Group
  • Controlling Access to Cluster Resources
    • What Node Ownership Means
    • Checking Node Ownership
    • Setting Node Ownership
• Job Batching
  • Enabling TORQUE or Slurm
• Managing Non-Scyld Nodes
  • DHCP IP address assignment to devices
  • Simple provisioning using PXE
  • Simple provisioning using the class directive
  • Booting a node from the local harddrive
  • Provisioning a non-Scyld node
  • Integrating a non-Scyld node into the cluster
• Managing Multiple Master Nodes
  • Active-Passive Masters
  • Active-Active Masters
• Managing Node Failures
  • Protecting an Application from Node Failure
  • Compute Node Failure
    • When Compute Nodes Fail
    • Compute Node Data
  • Master Node Failure
    • When Master Nodes Fail - Without Run-to-Completion
    • When Master Nodes Fail - With Run-to-Completion
• Compute Node Boot Options
  • Compute Node Boot Media
    • PXE
    • Local Disk
    • Linux BIOS
    • Flash Disk
  • Changing Boot Settings
    • Adding Steps to the node_up Script
    • Per-Node Parameters
    • Other Per-Node Config Options
  • Error Logs
• Disk Partitioning
  • Disk Partitioning Concepts
  • Disk Partitioning with ClusterWare
    • Master Node
    • Compute Nodes
  • Default Partitioning
    • Master Node
    • Compute Nodes
  • Partitioning Scenarios
    • Applying the Default Partitioning
    • Specifying Manual Partitioning
• File Systems
  • File Systems on a Cluster
    • Local File Systems
    • Network/Cluster File Systems
  • NFS
    • NFS on Clusters
    • Configuration of NFS
  • ROMIO
    • Reasons to Use ROMIO
    • Installation and Configuration of ROMIO
  • Other Cluster File Systems
• Load Balancing
  • Load Balancing in a Scyld Cluster
    • Mapping Policy
    • Queuing Policy
  • Implementing a Scheduling Policy
• IPMI
  • IPMITool
• Updating Software On Your Cluster
  • What Can’t Be Updated
• Special Directories, Configuration Files, and Scripts
  • What Resides on the Master Node
    • /etc/beowulf/ directory
    • /usr/lib/beoboot directory
    • /var/beowulf directory
    • /var/log/beowulf directory
  • What Gets Put on the Compute Nodes at Boot Time
  • /usr/lib/locale/locale-archive Internationalization
  • Site-Local Startup Scripts
  • Sample Kickstart Script