Methods, systems, and products for dynamically reassigning a connected node to a block of compute nodes for re-launching a failed job that include: identifying that a job failed to execute on the block of compute nodes because connectivity failed between a compute node assigned as at least one of the connected nodes for the block of compute nodes and its supporting I/O node; and re-launching the job, including selecting an alternative connected node that is actively coupled for data communications with an active I/O node; and assigning the alternative connected node as the connected node for the block of compute nodes running the re-launched job.
STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT
This invention was made with Government support under Contract No. B554331 awarded by the Department of Energy. The Government has certain rights in this invention.