Jump to content United States-English
HP.com Home Products and Services Support and Drivers Solutions How to Buy
» Contact HP
More options
HP.com home

HP XC System Software: Installation Guide
Version 3.1

» 

Technical documentation

Complete book in PDF
» Feedback
Content starts here

 » Table of Contents

 » Glossary

 » Index

HP Part Number: 5991-7401

Published: November 2006

Abstract

This document describes how to install and configure HP XC System Software Version 3.1 on HP Cluster Platforms 3000, 4000, and 6000.


Table of Contents

About This Document
Intended Audience
How to Use This Document
Naming Conventions Used in This Document
New and Changed Information in This Edition
Typographic Conventions
HP XC and Related HP Products Information
Related information
Manpages
HP Encourages Your Comments
1 Preparing for a New Installation
Task 1: Read Related Documentation
Task 2: Plan for Future HP XC Releases
Task 3: Prepare Existing HP XC Systems
Task 4: Prepare the Hardware
Task 5: Verify Firmware Versions
Task 6: Arrange for IP Address Assignments and Host Names
Task 7: Have the License Key File Ready
Task 8: Purchase Additional Software from HP and Third-Party Vendors
Task 9: Plan a Service Availability Strategy
What Is Improved Availability?
How to Configure Improved Availability
Choose an Availability Tool
Write Translator and Other Supporting Scripts
Choose Nodes as Members of Availability Sets
Role Assignments for Improved Availability
Use the Improved Availability Planning Worksheet
You Are Done
2 Installing Software on the Head Node
Software Installation Overview
Kickstart Installation Process
HP XC Software Stack
Kickstart Installation File
Default File System Layout and Disk Partition Sizes
Task 1: Gather Information Required for the Installation
Task 2: Start the Installation Process
Task 3: Install Additional RPMs from the HP XC DVD
Install the HP XC Serviceguard RPM
Install Optional Linux RPMs
Task 4: Install Additional Software from Local Distribution Media
Install Additional HP Software Products
Install Third-Party Software Products
Install Compilers
You Are Done
3 Configuring and Imaging the System
System Configuration and Imaging Overview
System Configuration Process
System Imaging Process
System Configuration and Imaging Log Files
Task 1: Prepare for the System Configuration
Task 2: Change the Default IP Address Base (Optional)
Task 3: Run the cluster_prep Command to Prepare the System
Task 4: Install Patches or RPM Updates
Download and Install Patches
Rebuild Kernel Dependent Modules
Task 5: Run the discover Command to Discover System Components
Modify the Default Password for HP ProLiant DL140 and DL145 Hardware Models
Task 6: Set Up the System Environment
Put the License Key File in the Correct Location (Required)
Configure Interconnect Switch Monitoring Line Cards (Required)
Configure sendmail (Required)
Customize the Nagios Environment (Required)
Set the BMC/IPMI Password on HP Integrity Systems (Required)
Install Additional Software over the Network
Create the /hptc_cluster File System
Modify Workstation Model Names in the Database
Enable Software RAID-0 or RAID-1 on Client Nodes
Create Local User Accounts
Override Default User and Group Account IDs
Customize Client Node Disk Partitioning
Create the HP Modular Cooling System Configuration File
Task 7: Run the cluster_config Utility to Configure the System
Task 8: Configure Availability Sets
Task 9: Assign Node Roles
Task 10: Respond to Configuration Questions
Task 11: Run the startsys Utility to Start the System and Propagate the Golden Image
Task 12: Perform Postconfiguration Tasks for the InfiniBand Interconnect
Task 13: Create a Lock LUN Device File
Task 14: Start Availability Tools
Task 15: Configure SNMP Trap Destination for Enclosures
Task 16: Configure SNMP Trap Destination for Modular Cooling System Devices
Task 17: Finalize the Configuration of Compute Resources
Perform SLURM Postconfiguration Tasks
Perform LSF Postconfiguration Tasks
You Are Done
4 Verifying the System and Creating a Baseline Record of the Configuration
Task 1: Verify the LSF Configuration
Verify LSF-HPC with SLURM
Verify Standard LSF
Task 2: Verify Availability Tools
Task 3: Run the OVP to Verify Software and Hardware Components
Task 4: Use Nagios to View System Health
Task 5: Take a Snapshot of the Database
Task 6: Create a Baseline Report of the System Configuration
You Are Done
5 Upgrading an HP XC System
Software Upgrade Overview
Upgrade Types
Differences Between Major and Minor Upgrades
Upgrade Characteristics
Supported Upgrade Paths
Upgrade Commands
Is Upgrading Right for Your System?
Task 1: Prepare for the Upgrade
Task 2: Prepare the System State
Task 3: Install the Upgrade RPM and Prepare the System
Task 4: Upgrade Linux and HP XC RPMs
Major Upgrade: Upgrade RPMs
Minor Upgrade: Upgrade RPMs
Task 5: View the Results of the RPM Upgrade
Task 6: Install Patches and Re-Install Additional Software
Task 7: Manually Merge File Customizations
Task 8: Configure the System and Propagate the Golden Image
Task 9: Image and Boot the System and Start Compute Resources
Task 10: Start Availability Tools After the Upgrade
Task 11: Verify the Upgrade
6 Reinstalling Version 3.1
Reinstall Systems with HP ProLiant Hardware Models
Reinstall the Entire System
Reinstall One or More Nodes
Reinstall Systems with HP Integrity Hardware Models
Reinstall the Entire System
Reinstall One or More Nodes
A Installation and Configuration Checklist
B Host Name and Password Guidelines
Host Name Guidelines
Password Guidelines
C Enabling telnet on iLO and iLO2 Devices
iLO Devices
iLO2 Devices
D Configuring Interconnect Switch Monitoring Cards
Configure Quadrics Switch Controller Cards
Configure Myrinet Switch Monitoring Line Cards
Configure InfiniBand Switch Controller Cards
E Customizing Client Node Disks
Overview of Client Node Disk Imaging
Configure Disks Dynamically
Example 1: Changing Default Partition Sizes and Swap Space for All Client Nodes
Example 2: Customizing Partition Sizes on a Group of Client Nodes
Configure Disks Statically
Enable Static Disk Configuration
Customize Client Disk Configuration
F Node Roles, Services, and the Default Configuration
Default Node Role Assignments
Special Considerations for Modifying Default Node Role Assignments
General Considerations
Special Considerations for Systems with 63 or Fewer Nodes
Special Considerations for Systems with 64 or More Nodes
Special Considerations for Improved Availability
Role Definitions
Availability Role
Avail_node_management Role
Common Role
Compute Role
Console_network Role
Disk_io Role
External Role
Login Role
Management Hub Role
Management Server Role
NIS Server Role
Node Management Role
Resource Management Role
G Using the cluster_config Command-Line Menu
cluster_config Command-Line Menu Overview
List Node Configuration Information
Modify Node Configuration
Modify an Ethernet Connection
Modify Node Role Assignments
Analyze Current Role Assignments Against HP Recommendations
Customize Service and Client Configurations
Services Configuration Commands
H Determining the Network Type
I LSF Installation Values
J OVP Command Output
K upgraderpms Command Output
L Installing and Using PBS Professional
PBS Professional Overview
Before You Begin
Plan the Installation
Perform Installation Actions Specific to HP XC
Configure PBS Professional under HP XC
Configure the OpenSSH scp Utility
Remove Nodes from the SLURM or LSF Configuration
Add Nodes to the PBS Professional Configuration
Replicate Execution Nodes
Enter License Information
Start the Service Daemons
Set Up PBS Professional at the User Level
Run HP MPI Tasks
M Installing the Maui Scheduler
Maui Scheduler Overview
Readiness Criteria
Before You Begin
Installation Procedure
Task 1: Download the Maui Scheduler Kit
Task 2: Compile the Maui Scheduler from Its Source Distribution
Task 3: Update the Maui Scheduler Configuration File
Task 4: Edit the SLURM Configuration File
Task 5: Configure the Maui Scheduler
Verify Successful Installation of the Maui Scheduler
N Troubleshooting
Troubleshoot the Discovery Process
Discovery Process Hangs While Discovering Console Ports
ProCurve Switches Do Not Obtain Their IP Addresses
ProCurve Switches May Take Time to Get IP Addresses
Not All Console Ports Are Discovered
Some Console Ports Have Not Obtained Their IP Addresses
Not All Nodes Are Discovered
Troubleshoot the Cluster Configuration Process
Troubleshoot the Imaging Process
Monitor an Imaging Session
Troubleshoot Licenses
Troubleshoot OVP Results
Troubleshoot the Software Upgrade Procedure
Glossary
Index

List of Figures

N-1 Discovery Flowchart

List of Tables

Installation Types
Naming Conventions
1-1 Improved Availability Summary
1-2  Role and Service Placement for Improved Availability
1-3 Availability Sets Worksheet
2-1  HP XC Software Stack
2-2 Default Values in the ks.cfg File
2-3 Default Disk Partition Layout on the Head Node
2-4 Chip Architecture by Cluster Platform
2-5 Information Required for the Kickstart Installation Session
2-6 Kickstart Boot Command Line
3-1 Information Required by the cluster_prep Command
3-2 Information Required by the discover Command
3-3 Information Required by the cluster_config Utility
3-4 System Environment Setup Tasks
3-5 HP XC Default User and Group Account IDs
3-6 Default Client Node Partition Layout
3-7 Number of NFS Daemons Based on System Size
3-8 Characteristics of LSF-HPC with SLURM and Standard LSF
3-9 The startsys Command-Line Options for Initial System Image and Boot
5-1 Upgrade Types
5-2 Upgrade Characteristics
5-3 Supported Upgrade Paths
5-4 Commands Used During the Upgrade Process
5-5 Upgrade Readiness Criteria
5-6 Upgrade Boot Command Line Based on Cluster Platform Chip Architecture
5-7 Files Containing User Customizations
5-8 Upgrade Options for the cluster_config Utility
5-9 Responding to cluster_config Prompts During an Upgrade
A-1 Installation and Configuration Checklist
D-1 Quadrics Switch Controller Card Naming Conventions and IP Addresses for Reduced Bandwidth
D-2 Quadrics Switch Controller Card Naming Conventions and IP Addresses for Full Bandwidth
D-3 Myrinet Switch Controller Card Naming Conventions and IP Addresses
D-4 InfiniBand Switch Controller Card Naming Conventions and IP Addresses
F-1 Default Role Assignments Based on System Size
G-1 Description of cluster_config Command-Line Menu Options
G-2 General Command Output of the Analyze Option
G-3 Specific Node-By-Node Output of the Analyze Option
G-4 Service Configuration Command Descriptions
H-1 Network Type Based on System Topology
I-1 Default Installation Values for LSF
M-1 Maui Scheduler Readiness Criteria
M-2 Maui Scheduler Diagnostic Commands
N-1 Diagnosing System Imaging Problems
N-2 Software Upgrade Log Files
Printable version
Privacy statement Using this site means you accept its terms Feedback to webmaster
© 2003 Hewlett-Packard Development Company, L.P.