ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
caac0e0182
openmpi/orte/mca/plm/tm/help-plm-tm.txt

53 строки
1.7 KiB
Plaintext
Исходник Обычный вид История

Add --prefix processing for the tm pls This commit was SVN r7580.
2005-10-02 15:58:18 +04:00
# -*- text -*-
#
Update the copyright notices for IU and UTK. This commit was SVN r7999.
2005-11-05 22:57:48 +03:00
# Copyright (c) 2004-2005 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.
Add --prefix processing for the tm pls This commit was SVN r7580.
2005-10-02 15:58:18 +04:00
# 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.
# $COPYRIGHT$
#
# Additional copyrights may follow
#
# $HEADER$
#
Update the TM launcher so it provides an appropriate error message when encountering an invalid launch_id. This is a first step towards fixing ticket #1016, but needs to be followed by a more complete solution. This commit was SVN r14578.
2007-05-04 00:14:24 +04:00
[tm-bad-launchid]
The TM (PBS / Torque) process starter cannot spawn the specified
application on a remote node due to an invalid launch_id.
This is most likely due to use of the "--hostfile" option to the
Merge the ORTE devel branch into the main trunk. Details of what this means will be circulated separately. Remains to be tested to ensure everything came over cleanly, so please continue to withhold commits a little longer This commit was SVN r17632.
2008-02-28 04:57:57 +03:00
command line with one or more hosts in that file not having
been allocated to this job.
Update the TM launcher so it provides an appropriate error message when encountering an invalid launch_id. This is a first step towards fixing ticket #1016, but needs to be followed by a more complete solution. This commit was SVN r14578.
2007-05-04 00:14:24 +04:00
Removing "--hostfile" from the command line will likely allow the
Merge the ORTE devel branch into the main trunk. Details of what this means will be circulated separately. Remains to be tested to ensure everything came over cleanly, so please continue to withhold commits a little longer This commit was SVN r17632.
2008-02-28 04:57:57 +03:00
application to be launched.
Update the TM launcher so it provides an appropriate error message when encountering an invalid launch_id. This is a first step towards fixing ticket #1016, but needs to be followed by a more complete solution. This commit was SVN r14578.
2007-05-04 00:14:24 +04:00
#
Add --prefix processing for the tm pls This commit was SVN r7580.
2005-10-02 15:58:18 +04:00
[multiple-prefixes]
Multiple different --prefix options were specified to mpirun for the
same node. This is a fatal error for the TM (PBS / Torque) process
starter in Open MPI.
The first two prefix values supplied for node %s were:
%s
and %s
- Don't overwrite rc with the return value from pls_tm_disconnect -- it's always ORTE_SUCCESS and sometimes masks real !=ORTE_SUCCESS rc values. - Add MCA param pls_tm_want_path_check. If nonzero (the default), check for the orted in the PATH before each tm_spawn()'ing (doing a little caching so that we don't hammer on the filesystem -- remember all the PATH's where we successfully found the orted so that we don't have to query the filesystem multiple times for a PATH where we previously found the orted) - Be sure to opal_argv_split() the pls_tm_orted MCA param This commit was SVN r7625.
2005-10-04 23:38:51 +04:00
#
Complete modifications for failed-to-start of applications. Modifications for failed-to-start of orteds coming next. This completes the minor changes required to the PLS components. Basically, there is a small change required to the parameter list of the orted cmd functions. I caught and did it for xcpu and poe, in addition to the components listed in my email - so I think that only leaves xgrid unconverted. The orted fail-to-start mods will also make changes in the PLS components, but those can be localized so they come in one at a time. This commit was SVN r14499.
2007-04-25 00:53:54 +04:00
[tm-spawn-failed]
The TM (PBS / Torque) process starter failed to spawn a daemon (orted)
on a remote node.
- Don't overwrite rc with the return value from pls_tm_disconnect -- it's always ORTE_SUCCESS and sometimes masks real !=ORTE_SUCCESS rc values. - Add MCA param pls_tm_want_path_check. If nonzero (the default), check for the orted in the PATH before each tm_spawn()'ing (doing a little caching so that we don't hammer on the filesystem -- remember all the PATH's where we successfully found the orted so that we don't have to query the filesystem multiple times for a PATH where we previously found the orted) - Be sure to opal_argv_split() the pls_tm_orted MCA param This commit was SVN r7625.
2005-10-04 23:38:51 +04:00
Complete modifications for failed-to-start of applications. Modifications for failed-to-start of orteds coming next. This completes the minor changes required to the PLS components. Basically, there is a small change required to the parameter list of the orted cmd functions. I caught and did it for xcpu and poe, in addition to the components listed in my email - so I think that only leaves xgrid unconverted. The orted fail-to-start mods will also make changes in the PLS components, but those can be localized so they come in one at a time. This commit was SVN r14499.
2007-04-25 00:53:54 +04:00
Command line: %s
Node name: %s
Launch id: %d
- Don't overwrite rc with the return value from pls_tm_disconnect -- it's always ORTE_SUCCESS and sometimes masks real !=ORTE_SUCCESS rc values. - Add MCA param pls_tm_want_path_check. If nonzero (the default), check for the orted in the PATH before each tm_spawn()'ing (doing a little caching so that we don't hammer on the filesystem -- remember all the PATH's where we successfully found the orted so that we don't have to query the filesystem multiple times for a PATH where we previously found the orted) - Be sure to opal_argv_split() the pls_tm_orted MCA param This commit was SVN r7625.
2005-10-04 23:38:51 +04:00
If you do not understand this error mesage, please try the following:
Complete modifications for failed-to-start of applications. Modifications for failed-to-start of orteds coming next. This completes the minor changes required to the PLS components. Basically, there is a small change required to the parameter list of the orted cmd functions. I caught and did it for xcpu and poe, in addition to the components listed in my email - so I think that only leaves xgrid unconverted. The orted fail-to-start mods will also make changes in the PLS components, but those can be localized so they come in one at a time. This commit was SVN r14499.
2007-04-25 00:53:54 +04:00
1. Ensure that the executable "orted" is in your PATH
2. Use the --prefix option to indicate where we can
find that executable
3. Talk to your local system administrator
Копировать постоянную ссылку