ompi-restart1
Restart a previously checkpointed parallel job using the open pal checkpoint/restart service (crs) note: ompi-restart, and orte-restart are all exact synonyms for each other. using any of the names will result in exactly identical behavior.
Usage
ompi-restart [options]
<GLOBAL
SNAPSHOT
HANDLE>
Options
ompi-restart will attempt to restart a previously checkpointed parallel job from the global snapshot handle reference returned by ompi_checkpoint.
- <GLOBAL SNAPSHOT HANDLE>
-
The global snapshot handle reference returned by ompi_checkpoint, used to restart the job. This is required to be the last argument to this command.
-
-h | --help -
Display help for this command
-
-p | --preload -
Preload the checkpoint files on the remote systems before restarting the application. Disabled by default.
-
--fork -
Fork off a new process, which is the restarted process. By default, the restarted process will replace ompi-restart.
-
-s | --seq -
The sequence number of the checkpoint to restart from. By default, the most recent sequence number is used (specified by -1).
-
-hostfile | --hostfile -
The hostfile from which to restart the application. Useful in unscheduled environments. (Same behavior as --machinefile option)
-
-machinefile | --machinefile -
The machinefile from which to restart the application. Useful in unscheduled environments. (Same behavior as --hostfile option)
-
-v | --verbose -
Enable verbose output for debugging.
- -gmca | --gmca <key> <value>
-
Pass global MCA parameters that are applicable to all contexts. <key> is the parameter name; <value> is the parameter value.
- -mca | --mca <key> <value>
-
Send arguments to various MCA modules.
Overview
ompi-restart can be invoked multiple, non-overlapping times. This allows the user to restart a previously running parallel job.
Releases
3 releases since Debian 6.0 (Squeeze); the text changed 2 times.