Sun HPC ClusterTools 8.2.1c Software
User’s Guide
821-1319-10
Contents |
1. Introduction to Sun HPC ClusterTools Software
Open Runtime Environment (ORTE)
Executing Programs With mpirun
Integration With Distributed Resource Management Systems
Performance Analysis With Sun Studio Analyzer
Communications Failover Feature In Multi-Rail Infiniband Configurations
How the Open MPI Environment Is Integrated With Distributed Resource Management Systems
Using Sun Grid Engine With ORTE
Submitting Jobs Under Sun Grid Engine Integration
How ORTE Works With Zones in the Solaris 10 Operating System
3. Setting Up Your Environment
Using Non-Default Error Handlers
5. Running Programs With the mpirun Command
Using Environment Variables With the mpirun Command
Using MCA Parameters With the mpirun Command
To Run a Program With Default Settings
To Direct mpirun By Using an Appfile
Mapping MPI Processes to Nodes
Specifying Hosts By Using a Hostfile
Specifying Hosts By Using the --host Option
To Specify Multiple Slots Using the --host Option
Excluding Hosts From Scheduling By Using the --host Option
Comparing By-Slot to By-Node Scheduling
Controlling Other Job Attributes
To Change the Working Directory
Submitting Jobs Under Sun Grid Engine Integration
Defining Parallel Environment (PE) and Queue
Submitting Jobs in Interactive Mode
To Set the Interactive Display
To Verify That Sun Grid Engine Is Running
To Start an Interactive Session Using qrsh
Using MPI Client/Server Applications
To Launch the Client/Server Job
Troubleshooting Client/Server Jobs
Handling Network Failures In Multi-Rail Infiniband Configurations
Forcing Failovers for Port Event Errors
6. Running Programs With mpirun in Distributed Resource Management Systems
mpirun Options for Third-Party Resource Manager Integration
Checking Your Open MPI Configuration
Running Parallel Jobs in the PBS Environment
To Run an Interactive Job in PBS
Running Parallel Jobs in the Sun Grid Engine Environment
Defining Parallel Environment (PE) and Queue
Submitting Jobs Under Sun Grid Engine Integration
To Set the Interactive Display
Using Sun Grid Engine as the Job Launcher
7. Using MCA Parameters With mpirun
About the Modular Component Architecture
Using the ompi_info Command With MCA Parameters
To List All MCA Parameters For a Framework
To Display All MCA Parameters For a Selected Component
To Set MCA Parameters From the Command Line
Using MCA Parameters As Environment Variables
To Set MCA Parameters in the sh Shell
To Set MCA Parameters in the C Shell
To Specify MCA Parameters Using a Text File
Including and Excluding Components
To Include and Exclude Components Using the Command Line
Using MCA Parameters With Sun Grid Engine
Changing the Default Values in MCA Parameters
8. Using the DTrace Utility With Open MPI
Checking the mpirun Privileges
To Determine the Correct Privileges on the Cluster
Running DTrace with MPI Programs
Running an MPI Program Under DTrace
To Trace a Program Using the mpitrace.d Script
To Trace a Parallel Program and Get Separate Trace Files
Attaching DTrace to a Running MPI Program
To Attach DTrace to a Running MPI Program
Using the DTrace mpiperuse Provider
DTrace Support in the ClusterTools Software
Specifying an mpiperuse Probe in a D Script
How To Use mpiperuse Probes to See Message Queues
To Count the Number of Messages To or From a Host
To Count the Number of Messages To or From Specific BTLs
To Obtain Distribution Plots of Message Sizes Sent or Received From a Host
To Create Distribution Plots of Message Sizes By Communicator, Rank, and Send/Receive
Exceeding the File Descriptor Limit
Increasing the Number of Available File Descriptors
To View the Hard Limit from the C Shell
To View the Hard Limit from the Bourne Shell
To Increase the Number of File Descriptors
Setting File Descriptor Limits When Using Sun Grid Engine
Copyright © 2010, Oracle and/or its affiliates. All rights reserved.