1
1

Improve the error message for when ompi-checkpoint cannot find a HNP to connect to.

This commit fixes trac:2189.

cmr:v1.4 (needs custom patch)
cmr:v1.5

This commit was SVN r22477.

The following Trac tickets were found above:
  Ticket 2189 --> https://svn.open-mpi.org/trac/ompi/ticket/2189
Этот коммит содержится в:
Josh Hursey 2010-01-25 19:17:43 +00:00
родитель 34281f0fa2
Коммит 36ab4a60b3
2 изменённых файлов: 34 добавлений и 12 удалений

Просмотреть файл

@ -52,16 +52,31 @@ Error: The process with PID %d is not checkpointable.
We were looking for the named file:
%s
[no_hnps]
Error: Unable to find a list of active MPIRUN processes on this machine.
This could be due to one of the following:
- The PID specified (%d) is not that of an active MPIRUN.
- The session directory location could not be found/parsed.
ompi-checkpoint attempted to find the session directory:
%s/%s
Check to make sure that this directory exists while the MPIRUN
process is running.
Return Code: %d (%s)
[no_universe]
Error: Unable to find the contact information for PID %d.
Error: Unable to find the requested, active MPIRUN process on this machine.
This could be due to one of the following:
- The jobid specified by the '--hnp-jobid' option is not
correct.
- The PID is not that of an active MPIRUN.
- The application with this PID isn't checkpointable
- The application with this PID isn't an Open MPI application.
ompi-checkpoint attempted to find the session directory:
%s
- The PID specified (%d) is not that of an active MPIRUN.
- The application with this PID is not checkpointable
- The application with this PID is not an Open MPI application.
- The session directory location could not be parsed.
ompi-checkpoint attempted to use the session directory:
%s/%s
[unable_to_connect]
Error: Unable to connect to the Head Node Process to initiate the

Просмотреть файл

@ -235,10 +235,7 @@ main(int argc, char *argv[])
* Find the HNP that we want to connect to, if it exists
***************************/
if (ORTE_SUCCESS != (ret = find_hnp())) {
opal_output(0,
"HNP with PID %d Not found!",
orte_checkpoint_globals.pid);
ORTE_ERROR_LOG(ret);
/* Error printed by called function */
exit_status = ret;
goto cleanup;
}
@ -473,7 +470,11 @@ static int find_hnp(void) {
*/
OBJ_CONSTRUCT(&hnp_list, opal_list_t);
if (ORTE_SUCCESS != (ret = orte_list_local_hnps(&hnp_list, true) ) ) {
ORTE_ERROR_LOG(ret);
opal_show_help("help-orte-checkpoint.txt", "no_hnps", true,
orte_checkpoint_globals.pid,
orte_process_info.tmpdir_base,
orte_process_info.top_session_dir,
ret, ORTE_ERROR_NAME(ret));
exit_status = ret;
goto cleanup;
}
@ -489,7 +490,13 @@ static int find_hnp(void) {
goto cleanup;
}
}
/* If no match was found, error out */
opal_show_help("help-orte-checkpoint.txt", "no_universe", true,
orte_checkpoint_globals.pid,
orte_process_info.tmpdir_base,
orte_process_info.top_session_dir);
cleanup:
while (NULL != (item = opal_list_remove_first(&hnp_list))) {
OBJ_RELEASE(item);