drestart
Restarts a checkpoint (IBM RS6000 machines only)
Format
Restarts a checkpoint on IBM AIX
drestart [ -halt ] [-g gid ] [ -r host ] [ -no_same_hosts ]
Arguments
-halt
TotalView stops checkpointed processes after it restarts them.
-g gid
Names the control group into which TotalView places all created processes.
-r host
Names the remote host upon which the restart occurs.
-no_same_hosts
Restart can use any available hosts. If you do not use this option, the restart occurs on the same hosts upon which the program was executing when the checkpoint file was made. If these hosts are not available, the restart operation fails.
Description
The drestart command restores and restarts all of the checkpointed processes. The CLI attaches to the base process, and if there are parallel processes related to this base process, TotalView then attaches to them.
Restarting using LoadLeveler
If you checkpointed a LoadLeveler POE job, you cannot restart it with this command. You must resubmit the program as a LoadLeveler job to restart the checkpoint. You also need to set the MP_POE_RESTART_SLEEP environment variable to an appropriate number of seconds. After you restart POE, start TotalView and attach to POE. POE tells TotalView when it is time to attach to the parallel task so that it can complete the restart operation.
NOTE: When attaching to POE, parallel tasks will not have been created yet, so you should avoid trying to attach to them. Therefore, use the-no_attach_paralleloption when using the dattach command to attach to POE.
Examples
drestart
Restarts the checkpointed processes. The CLI automatically attaches to parallel processes.
drestart -halt -no_same_hosts
Restarts the checkpointed processes using available hosts. Stops checkpointed processes after restoring them.
Related Topics
