LSB_MC_CHKPNT_RERUN

Description

For checkpointable multicluster jobs, if a restart attempt fails, the job is rerun from the beginning (instead of from the last checkpoint) without administrator or user intervention.

The submission cluster does not need to forward the job again. The execution cluster reports the job’s new pending status back to the submission cluster, and the job is dispatched to the same host to restart from the beginning

Default

n