To restart a job on another host, both hosts must be binary compatible, run the same OS version, have access to the executable, have access to all open files (LSF must locate them with an absolute path name), and have access to the checkpoint directory.

The environment variable LSB_RESTART is set to Y when a job is restarted.

LSF invokes the erestart(8) executable found in LSF_SERVERDIR to perform the restart.

Only the bsub options listed here can be used with brestart.

Like bsub, brestart calls the master esub (mesub), which invokes any mandatory esub executables configured by an LSF administrator, and any executable named esub (without .application) if it exists in LSF_SERVERDIR. Only esub executables invoked by bsub can change the job environment on the submission host. An esub invoked by brestart cannot change the job environment.

Options

The following option applies only to brestart.

-fForces the job to be restarted even if non-restartable conditions exist (these conditions are operating system specific).

See bsub(1) for a description of all other options.

Limitations

In kernel-level checkpointing, you cannot change the value of core limit, CPU limit, stack limit or memory limit with brestart.

See also

bsub(1), bjobs(1), bmod(1), bqueues(1), bhosts(1), bchkpnt(1), lsbqueues(5), echkpnt(8), erestart(8), mbatchd(8)

Platform LSF Command Reference 147