openmpi/orte/tools/orterun/help-orterun.txt

# -*- text -*-
#
# Copyright (c) 2004-2006 The Trustees of Indiana University and Indiana
#                         University Research and Technology
#                         Corporation.  All rights reserved.
# Copyright (c) 2004-2005 The University of Tennessee and The University
#                         of Tennessee Research Foundation.  All rights
#                         reserved.
# Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
#                         University of Stuttgart.  All rights reserved.
# Copyright (c) 2004-2005 The Regents of the University of California.
#                         All rights reserved.
# Copyright (c) 2007-2016 Cisco Systems, Inc.  All rights reserved.
# Copyright (c) 2012      Oak Ridge National Labs.  All rights reserved.
# Copyright (c) 2017      Intel, Inc. All rights reserved.
# $COPYRIGHT$
#
# Additional copyrights may follow
#
# $HEADER$
#
# This is the US/English general help file for Open RTE's orterun.
#
[orterun:init-failure]
Open RTE was unable to initialize properly.  The error occured while
attempting to %s.  Returned value %d instead of ORTE_SUCCESS.
[orterun:usage]
%s (%s) %s

Usage: %s [OPTION]...  [PROGRAM]...
Start the given program using Open RTE

%s

Report bugs to %s
[orterun:version]
%s (%s) %s

Report bugs to %s
[orterun:allocate-resources]
%s was unable to allocate enough resources to start your application.
This might be a transient error (too many nodes in the cluster were
unavailable at the time of the request) or a permenant error (you
requsted more nodes than exist in your cluster).

While probably only useful to Open RTE developers, the error returned
was %d.
[orterun:error-spawning]
%s was unable to start the specified application.  An attempt has been
made to clean up all processes that did start.  The error returned was
%d.
[orterun:appfile-not-found]
Unable to open the appfile:

    %s

Double check that this file exists and is readable.
[orterun:executable-not-specified]
No executable was specified on the %s command line.

Aborting.
[orterun:multi-apps-and-zero-np]
%s found multiple applications specified on the command line, with
at least one that failed to specify the number of processes to execute.
When specifying multiple applications, you must specify how many processes
of each to launch via the -np argument.
[orterun:nothing-to-do]
%s could not find anything to do.

It is possible that you forgot to specify how many processes to run
via the "-np" argument.
[orterun:call-failed]
%s encountered a %s call failure.  This should not happen, and
usually indicates an error within the operating system itself.
Specifically, the following error occurred:

    %s

The only other available information that may be helpful is the errno
that was returned: %d.
[orterun:environ]
%s was unable to set
 %s = %s
in the environment. Returned value %d instead of ORTE_SUCCESS.
[orterun:precondition]
%s was unable to precondition transports
Returned value %d instead of ORTE_SUCCESS.
[orterun:attr-failed]
%s was unable to define an attribute
Returned value %d instead of ORTE_SUCCESS.
#
[orterun:proc-ordered-abort]
%s has exited due to process rank %lu with PID %lu on
node %s calling "abort". This may have caused other processes
in the application to be terminated by signals sent by %s
(as reported here).
#
[orterun:proc-exit-no-sync]
%s has exited due to process rank %lu with PID %lu on
node %s exiting improperly. There are three reasons this could occur:

1. this process did not call "init" before exiting, but others in
the job did. This can cause a job to hang indefinitely while it waits
for all processes to call "init". By rule, if one process calls "init",
then ALL processes must call "init" prior to termination.

2. this process called "init", but exited without calling "finalize".
By rule, all processes that call "init" MUST call "finalize" prior to
exiting or it will be considered an "abnormal termination"

3. this process called "MPI_Abort" or "orte_abort" and the mca parameter
orte_create_session_dirs is set to false. In this case, the run-time cannot
detect that the abort call was an abnormal termination. Hence, the only
error message you will receive is this one.

This may have caused other processes in the application to be
terminated by signals sent by %s (as reported here).

You can avoid this message by specifying -quiet on the %s command line.
#
[orterun:proc-exit-no-sync-unknown]
%s has exited due to a process exiting without calling "finalize",
but has no info as to the process that caused that situation. This
may have caused other processes in the application to be
terminated by signals sent by %s (as reported here).
#
[orterun:proc-aborted]
%s noticed that process rank %lu with PID %lu on node %s exited on signal %d.
#
[orterun:proc-aborted-unknown]
%s noticed that the job aborted, but has no info as to the process
that caused that situation.
#
[orterun:proc-aborted-signal-unknown]
%s noticed that the job aborted by signal, but has no info as
to the process that caused that situation.
#
[orterun:proc-aborted-strsignal]
%s noticed that process rank %lu with PID %lu on node %s exited on signal %d (%s).
#
[orterun:abnormal-exit]
WARNING: %s has exited before it received notification that all
started processes had terminated.  You should double check and ensure
that there are no runaway processes still executing.
#
[orterun:sigint-while-processing]
WARNING: %s is in the process of killing a job, but has detected an
interruption (probably control-C).

It is dangerous to interrupt %s while it is killing a job (proper
termination may not be guaranteed).  Hit control-C again within 1
second if you really want to kill %s immediately.
#
[orterun:double-prefix]
Both a prefix was supplied to %s and the absolute path to %s was
given:

  Prefix: %s
  Path:   %s

Only one should be specified to avoid potential version
confusion. Operation will continue, but the -prefix option will be
used. This is done to allow you to select a different prefix for
the backend computation nodes than used on the frontend for %s.
#
[orterun:app-prefix-conflict]
Both a prefix or absolute path was given for %s, and a different
prefix provided for the first app_context:

  Mpirun prefix: %s
  App prefix:    %s

Only one should be specified to avoid potential version
confusion. Operation will continue, but the application's prefix
option will be ignored.
#
[orterun:empty-prefix]
A prefix was supplied to %s that only contained slashes.

This is a fatal error; %s will now abort.  No processes were launched.
#
[debugger-mca-param-not-found]
Internal error -- the orte_base_user_debugger MCA parameter was not able to
be found.  Please contact the Open RTE developers; this should not
happen.
#
[debugger-orte_base_user_debugger-empty]
The MCA parameter "orte_base_user_debugger" was empty, indicating that
no user-level debuggers have been defined.  Please set this MCA
parameter to a value and try again.
#
[debugger-not-found]
A suitable debugger could not be found in your PATH.  Check the values
specified in the orte_base_user_debugger MCA parameter for the list of
debuggers that was searched.
#
[debugger-exec-failed]
%s was unable to launch the specified debugger.  This is what was
launched:

    %s

Things to check:

    - Ensure that the debugger is installed properly
    - Ensure that the "%s" executable is in your path
    - Ensure that any required licenses are available to run the debugger
#
[orterun:sys-limit-pipe]
%s was unable to launch the specified application as it encountered an error:

Error: system limit exceeded on number of pipes that can be open
Node: %s

when attempting to start process rank %lu.

This can be resolved by setting the mca parameter opal_set_max_sys_limits to 1,
increasing your limit descriptor setting (using limit or ulimit commands),
asking the system administrator for that node to increase the system limit, or
by rearranging your processes to place fewer of them on that node.
#
[orterun:sys-limit-sockets]
Error: system limit exceeded on number of network connections that can be open

This can be resolved by setting the mca parameter opal_set_max_sys_limits to 1,
increasing your limit descriptor setting (using limit or ulimit commands),
or asking the system administrator to increase the system limit.
#
[orterun:pipe-setup-failure]
%s was unable to launch the specified application as it encountered an error:

Error: pipe function call failed when setting up I/O forwarding subsystem
Node: %s

while attempting to start process rank %lu.
#
[orterun:sys-limit-children]
%s was unable to launch the specified application as it encountered an error:

Error: system limit exceeded on number of processes that can be started
Node: %s

when attempting to start process rank %lu.

This can be resolved by either asking the system administrator for that node to
increase the system limit, or by rearranging your processes to place fewer of them
on that node.
#
[orterun:failed-term-attrs]
%s was unable to launch the specified application as it encountered an error:

Error: reading tty attributes function call failed while setting up
I/O forwarding system
Node: %s

while attempting to start process rank %lu.
#
[orterun:wdir-not-found]
%s was unable to launch the specified application as it could not
change to the specified working directory:

Working directory: %s
Node: %s

while attempting to start process rank %lu.
#
[orterun:exe-not-found]
%s was unable to find the specified executable file, and therefore
did not launch the job.  This error was first reported for process
rank %lu; it may have occurred for other processes as well.

NOTE: A common cause for this error is misspelling a %s command
      line parameter option (remember that %s interprets the first
      unrecognized command line token as the executable).

Node:       %s
Executable: %s
#
[orterun:exe-not-accessible]
%s was unable to launch the specified application as it could not access
or execute an executable:

Executable: %s
Node: %s

while attempting to start process rank %lu.
#
[orterun:pipe-read-failure]
%s was unable to launch the specified application as it encountered an error:

Error: reading from a pipe function call failed while spawning a local process
Node: %s

while attempting to start process rank %lu.
#
[orterun:proc-failed-to-start]
%s was unable to start the specified application as it encountered an
error:

Error code: %d
Error name: %s
Node: %s

when attempting to start process rank %lu.
#
[orterun:proc-socket-not-avail]
%s was unable to start the specified application as it encountered an
error:

Error name: %s
Node: %s

when attempting to start process rank %lu.
#
[orterun:proc-failed-to-start-no-status]
%s was unable to start the specified application as it encountered an
error on node %s. More information may be available above.
#
[orterun:proc-failed-to-start-no-status-no-node]
%s was unable to start the specified application as it encountered an
error.  More information may be available above.
#
[debugger requires -np]
The number of MPI processes to launch was not specified on the command
line.

The %s debugger requires that you specify a number of MPI processes to
launch on the command line via the "-np" command line parameter.  For
example:

    %s -np 4 %s

Skipping the %s debugger for now.
#
[debugger requires executable]
The %s debugger requires that you specify an executable on the %s
command line; you cannot specify application context files when
launching this job in the %s debugger.  For example:

    %s -np 4 my_mpi_executable

Skipping the %s debugger for now.
#
[debugger only accepts single app]
The %s debugger only accepts SPMD-style launching; specifying an
MPMD-style launch (with multiple applications separated via ':') is
not permitted.

Skipping the %s debugger for now.
#
[orterun:daemon-died-during-execution]
%s has detected that a required daemon terminated during execution
of the application with a non-zero status. This is a fatal error.
A best-effort attempt has been made to cleanup. However, it is
-strongly- recommended that you execute the orte-clean utility
to ensure full cleanup is accomplished.
#
[orterun:no-orted-object-exit]
%s was unable to determine the status of the daemons used to
launch this application. Additional manual cleanup may be required.
Please refer to the "orte-clean" tool for assistance.
#
[orterun:unclean-exit]
%s was unable to cleanly terminate the daemons on the nodes shown
below. Additional manual cleanup may be required - please refer to
the "orte-clean" tool for assistance.
#
[orterun:event-def-failed]
%s was unable to define an event required for proper operation of
the system. The reason for this error was:

Error: %s

Please report this to the Open MPI mailing list users@open-mpi.org.
#
[orterun:ompi-server-filename-bad]
%s was unable to parse the filename where contact info for the
ompi-server was to be found. The option we were given was:

--ompi-server %s

This appears to be missing the required ':' following the
keyword "file". Please remember that the correct format for this
command line option is:

--ompi-server file:path-to-file

where path-to-file can be either relative to the cwd or absolute.
#
[orterun:ompi-server-filename-missing]
%s was unable to parse the filename where contact info for the
ompi-server was to be found. The option we were given was:

--ompi-server %s

This appears to be missing a filename following the ':'. Please
remember that the correct format for this command line option is:

--ompi-server file:path-to-file

where path-to-file can be either relative to the cwd or absolute.
#
[orterun:ompi-server-filename-access]
%s was unable to access the filename where contact info for the
ompi-server was to be found. The option we were given was:

--ompi-server %s

Please remember that the correct format for this command line option is:

--ompi-server file:path-to-file

where path-to-file can be either relative to the cwd or absolute, and that
you must have read access permissions to that file.
#
[orterun:ompi-server-file-bad]
%s was unable to read the ompi-server's contact info from the
given filename. The filename we were given was:

FILE: %s

Please remember that the correct format for this command line option is:

--ompi-server file:path-to-file

where path-to-file can be either relative to the cwd or absolute, and that
the file must have a single line in it that contains the Open MPI
uri for the ompi-server. Note that this is *not* a standard uri, but
a special format used internally by Open MPI for communications. It can
best be generated by simply directing the ompi-server to put its
uri in a file, and then giving %s that filename.
[orterun:multiple-hostfiles]
Error: More than one hostfile was passed for a single application
context, which is not supported at this time.
#
[orterun:conflicting-params]
%s has detected multiple instances of an MCA param being specified on
the command line, with conflicting values:

MCA param: %s
Value 1: %s
Value 2: %s

This MCA param does not support multiple values, and the system is unable
to identify which value was intended. If this was done in error, please
re-issue the command with only one value. You may wish to review the
output from ompi_info for guidance on accepted values for this param.

[orterun:server-not-found]
%s was instructed to wait for the requested ompi-server, but was unable to
establish contact with the server during the specified wait time:

Server uri:  %s
Timeout time: %ld

Error received: %s

Please check to ensure that the requested server matches the actual server
information, and that the server is in operation.
#
[orterun:server-unavailable]
The user has called an operation involving MPI_Connect and/or MPI_Accept
that spans multiple invocations of mpirun. This requires the support of
the ompi-server tool, which must be executing somewhere that can be
accessed by all participants.

Please ensure the tool is running, and provide each mpirun with the MCA
parameter "pmix_server_uri" pointing to it.
#
[orterun:malformedport]
An operation involving MPI_Connect and/or MPI_Accept was called with
an unrecognized port string. This typically happens when passing the
string on a cmd line and failing to properly quote it to protect
against the special characters it includes
#
[orterun:ompi-server-pid-bad]
%s was unable to parse the PID of the %s to be used as the ompi-server.
The option we were given was:

--ompi-server %s

Please remember that the correct format for this command line option is:

--ompi-server PID:pid-of-%s

where PID can be either "PID" or "pid".
#
[orterun:ompi-server-could-not-get-hnp-list]
%s was unable to search the list of local %s contact files to find the
specified pid.  You might check to see if your local session directory
is available and that you have read permissions on the top of that
directory tree.
#
[orterun:ompi-server-pid-not-found]
%s was unable to find an %s with the specified pid of %d that was to
be used as the ompi-server.  The option we were given was:

--ompi-server %s

Please remember that the correct format for this command line option is:

--ompi-server PID:pid-of-%s

where PID can be either "PID" or "pid".
#
[orterun:write_file]
%s was unable to open a file to printout %s as requested. The file
name given was:

File: %s
#
[orterun:multiple-paffinity-schemes]
Multiple processor affinity schemes were specified (can only specify
one):

Slot list: %s
opal_paffinity_alone:  true

Please specify only the one desired method.
#
[orterun:slot-list-failed]
We were unable to successfully process/set the requested processor
affinity settings:

Specified slot list: %s
Error: %s

This could mean that a non-existent processor was specified, or
that the specification had improper syntax.
#
[orterun:invalid-node-rank]
An invalid node rank was obtained - this is probably something
that should be reported to the OMPI developers.
#
[orterun:invalid-local-rank]
An invalid local rank was obtained - this is probably something
that should be reported to the OMPI developers.
#
[orterun:invalid-phys-cpu]
An invalid physical processor id was returned when attempting to
set processor affinity - please check to ensure that your system
supports such functionality. If so, then this is probably something
that should be reported to the OMPI developers.
#
[orterun:failed-set-paff]
An attempt to set processor affinity has failed - please check to
ensure that your system supports such functionality. If so, then
this is probably something that should be reported to the OMPI
developers.
#
[orterun:topo-not-supported]
An attempt was made to bind a process to a specific hardware topology
mapping (e.g., binding to a socket) but the operating system does not
support such topology-aware actions.  Talk to your local system
administrator to find out if your system can support topology-aware
functionality (e.g., Linux Kernels newer than v2.6.18).

Systems that do not support processor topology-aware functionality
cannot use "bind to socket" and other related functionality.

  Local host:        %s
  Action attempted:  %s %s
  Application name:  %s
#
[orterun:binding-not-avail]
A request to bind the processes if the operating system supports such
an operation was made, but the OS does not support this operation:

  Local host:        %s
  Action requested:  %s
  Application name:  %s

Because the request was made on an "if-available" basis, the job was
launched without taking the requested action. If this is not the
desired behavior, talk to your local system administrator to find out
if your system can support the requested action.
#
[orterun:not-enough-resources]
Not enough %s were found on the local host to meet the requested
binding action:

  Local host:        %s
  Action requested:  %s
  Application name:  %s

Please revise the request and try again.
#
[orterun:paffinity-missing-module]
A request to bind processes was made, but no paffinity module
was found:

  Local host:        %s

This is potentially a configuration. You can rerun your job without
requesting binding, or check the configuration.
#
[orterun:invalid-slot-list-range]
A slot list was provided that exceeds the boundaries on available
resources:

  Local host: %s
  Slot list:  %s

Please check your boundaries and try again.
#
[orterun:proc-comm-failed]
A critical communication path was lost to:

  My name:      %s
  Process name: %s
  Node:         %s
#
[orterun:proc-mem-exceeded]
A process exceeded memory limits:

  Process name: %s
  Node:         %s
#
[orterun:proc-stalled]
One or more processes appear to have stalled - a monitored file
failed to show the required activity.
#
[orterun:proc-sensor-exceeded]
One or more processes have exceeded a specified sensor limit, but
no further info is available.
#
[orterun:proc-heartbeat-failed]
%s failed to receive scheduled heartbeat communications from a remote
process:

  Process name: %s
  Node:         %s
#
[orterun:non-zero-exit]
%s detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

  Process name: %s
  Exit code:    %d
#
[orterun:unrecognized-mr-type]
%s does not recognize the type of job. This should not happen and
indicates an ORTE internal problem.
#
[multiple-combiners]
More than one combiner was specified. The combiner takes the output
from the final reducer in each chain to produce a single, combined
result. Thus, there can only be one combiner for a job. Please
review your command line and try again.
#
[orterun:negative-nprocs]
%s has detected that one or more applications was given a negative
number of processes to run:

  Application:  %s
  Num procs:    %d

Please correct this value and try again.
#
[orterun:timeout]
The user-provided time limit for job execution has been reached:

  Timeout: %d seconds

The job will now be aborted.  Please check your code and/or
adjust/remove the job execution time limit (as specified by --timeout
command line option or MPIEXEC_TIMEOUT environment variable).
#
[orterun:conflict-env-set]
ERROR: You have attempted to pass environment variables to Open MPI
with both the "-x" method and by setting the MCA parameter "mca_base_env_list".

Open MPI does not support mixing these two methods.  Please choose one
method and try launching your job again.

Your job will now abort.
#
[orterun:pmix-failed]
The call to pmix_init_server() failed. This may be due to your
system's restriction for Unix's socket's path-length.

   orte_proc_session_dir: %s

Please try to set TMPDIR to something short (like /tmp) or change
Your computer's name (see uname -n).
#
[orterun:timeoutconflict]
Conflicting requests for timeout were given:

  --timeout command line option: %d
  MPIEXEC_TIMEOUT envar:         %s

Only one method should be provided, or else they must agree. Please
correct and retry.