a job's completion before allocating already released resources to pending
    jobs. This can be used to reduce fragmentation of resources.

  documentation, read config, show config, and run PrologSlurmctld when a job
  is allocated resources (startup synchronization still needed).

    https://computing.llnl.gov/linux/slurm/power_save.html or 
    "man slurm.conf" (SuspendProgram and related parameters) for more 
    information.
This is the final installment of the work: update some documenation, 
    increase default ResumeRate, and reduce frequency of retrying 
    batch launch state check.

    "man slurm.conf" (SuspendProgram and related parameters) for more 
    information.
NOTE: the step create logic needs to be modify to return EAGAIN or the 
    like until the node's state NOT_RESPONDING flag gets cleared.

    longer needed.

See NEWS for identification of all changes

    ping the node immediately to clear the NOT_RESPONDING flag.

    expression rather than one line per node. Frequency of log messages is 
    dependent upon SlurmctldDebug value from 300 seconds at SlurmctldDebug<=3
    to 1 second at SlurmctldDebug>=5.

    the node to be returned to use when it starts responding rather than 
    remaining in a non-usable state.

    info reported to Maui.

    of a non-root user to change a job's comment field (used by Maui/Moab for
    storing scheduler state information).

    configuration must be specified in slurm.conf for gang scheduling now.

    The current limit is 4GB.

    in slurm v1.2).

    a job step is cancelled, another is started immediately (before the 
    first one completely terminates) and ports are reused. 
    NOTE: This change requires that SLURM be updated on all nodes of the
    cluster at the same time. There will be no impact upon currently running
    jobs (they will ignore the jobid/stepid at the end of the message).