1
1
openmpi/orte/mca/errmgr/hnp/help-orte-errmgr-hnp.txt
Ralph Castain f3d90dfb8d Fully restore fault recovery, both at the individual process and daemon level.
NOTE: MPI fault recovery remains unavailable pending merge from Josh. This only covers ORTE-level processes.

This commit was SVN r23335.
2010-07-01 19:45:43 +00:00

43 строки
1.1 KiB
Plaintext

-*- text -*-
#
# Copyright (c) 2010 Cisco Systems, Inc. All rights reserved.
#
# $COPYRIGHT$
#
# Additional copyrights may follow
#
# $HEADER$
#
# This is the US/English general help file for ORTE Errmgr HNP module.
#
[errmgr-hnp:unknown-job-error]
An error has occurred in an unknown job. This generally should not happen
except due to an internal ORTE error.
Job state: %s
This information should probably be reported to the OMPI developers.
#
[errmgr-hnp:daemon-died]
The system has lost communication with the following daemon:
Daemon: %s
Node: %s
The reason for the lost communication channel is unknown. Possible
reasons include failure of the daemon itself, failure of the
connecting fabric/switch, and loss of the host node. Please
check with your system administrator to try and determine the
source of the problem.
Your job is being terminated as a result.
#
[errmgr-hnp:cannot-relocate]
The system is unable to relocate the specified process:
Process: %s
because the application for that process could not be found. This
appears to be a system error. Please report it to the ORTE
developers.