Contents

Sun HPC ClusterTools trademark 5 Software User's Guide

817-0084-10

Contents

1. Introduction to Sun HPC ClusterTools Software

Supported Configurations

Sun HPC ClusterTools Runtime Environment (CRE)

Executing Programs With mprun

Killing Programs

Displaying Job Information

Displaying Node Information

Integration With Distributed Resource Management Systems

Sun MPI and MPI I/O

Support for TotalView

2. Fundamental Concepts

Clusters and Nodes

How Partitions Are Enabled and Selected

How the CRE Environment Is Integrated With Distributed Resource Management Systems

How Programs Are Launched

How Distributed Resource Managers Work

3. Before You Begin

Command and Man Page Paths

Authentication Methods

4. Running Programs With mprun

Controlling Where the Program Runs

Precedence for Program Execution

small space How to Run a Program With Default Settings

small space How to Run on a Different Cluster (-c)

small space How to Run on a Different Partition (-p)

small space How to Run as Multiple Processes (-np)

small space How to Share Nodes (-j)

small space How to Enable Process Spawning (-Ys)

small space How to Disable Process Spawning (-Ns)

small space How to Wrap Multiple Processes (-W)

small space How to Settle for Available Processes (-S)

small space How to Include Independent Nodes (-u)

small space How to Combine Process Placement Options

Mapping MPI Processes to Nodes

small space How to Distribute Processes Among Nodes (-l)

small space How to Distribute Processes by Block (-Z and -Zt)

small space How to Distribute Processes by Rank Map (-m)

small space How to Reserve Resources For Spawning or Multithreading (-nr)

small space How to Select Nodes by Resource Requirement (-R)

Controlling Input/Output

small space How to Redirect Output to mprun (-D)

small space How to Redirect Output to Individual Files (-B)

small space How to Shut Off All Standard I/O (-N)

small space How to Redirect With an Argument Vector (-A)

small space How to Read Standard Input From /dev/null (-n)

small space How to Redirect With a Custom Configuration (-I)

Controlling Other Job Attributes

small space How to Include Shell-Specific Actions

small space How to Move a Process to the Background

small space How to Change the Working Directory (-C)

small space How to Use a Different User Name (-U)

small space How to Use a Different Group Name (-G)

small space How to Run a Job on a Different Project (-P)

small space How to Specify Verbose Output (-v)

small space How to Display Command Help (-h)

small space How to Display the Command's Version (-V)

small space How to Display Job Status Information (-J)

small space How to Store Job Name in a File (-d)

small space How to Tag Output With Its Rank Number (-o)

Command Reference (mprun)

5. Running Programs With mprun in Distributed Resource Management Systems

mprun Options for DRM Integration

Improper Flag Combinations for Batch Jobs

Running Parallel Jobs in the PBS Environment

small space How to Run an Interactive Job in PBS

small space How to Run a Script Job in PBS

Running Parallel Jobs in the LSF Environment

small space How to Run an Interactive Job in LSF

small space How to Run a Script Job in LSF

small space How to Run an LSF Job in Compatibility Mode

Running Parallel Jobs in the SGE Environment

small space How to Run an Interactive Job in SGE

small space How to Run a Script Job in SGE

6. Killing or Sending Signals to Programs With mpkill

What You Can Do

small space How to Kill a Running Program

small space How to Remove All Traces of a Job

small space How to Display a List of Supported Signals (-l -d)

small space How to Send a Signal to a Job

7. Displaying Program Information With mpps

What You Can Do

small space How to Display Job Status

small space How to Display Information About Individual Jobs (-J)

small space How to Display Job Name, PID, and Host of Current Job (-b)

small space How to Display Information About All Jobs (-e)

small space How to Display a Job's Start Time (-f)

small space How to Display Job Information by Partition (-A -a)

small space How to Display Job Information by Process (-p -P)

Command Reference (mpps)

8. Profiling Programs With MPPROF

Enabling MPI Profiling

Controlling Data Collection

MPI_PROFDATADIR

MPI_PROFINDEXFDIR

MPI_PROFINTERVAL

MPI_PROFMAXFILESIZE

Using mpprof to Generate Reports

mpprof Command Syntax

Generating a Message Passing Report

Reporting on Specific Processes

Reporting Processes That Occur After a Specified Time Interval

To Save Report Output for Later Use

A Sample Report

Using mpdump to Convert Intermediate Binary Files to ASCII Files

The mpdump Command Syntax

A Sample mpdump File

9. Displaying Information With mpinfo

What You Can Do

small space How to Display Information About Published Names (-T)

small space How to Display Information About Any Cluster (-c)

small space How to Display Information About the Current Cluster (-C)

small space How to Display Information About Individual Partitions (-p)

small space How to Display Information About All Partitions (-P)

small space How to Display Information About Individual Nodes (-n)

small space How to Display Information About All Nodes (-N)

small space How to Display an Online List of Valid Attributes (-lc, -lp, -ln)

small space How to Restrict Output to Individual Attributes (-A)

small space How to Display Information in Verbose Mode (-v)

Command Reference (mpinfo)

Copyright © 2003, Sun Microsystems, Inc. All rights reserved.