Avoiding a slurmctld crash when scheduling problems due to resources. Setting an ADMIN hold instead.

Cray - Improve support for zero compute note resource allocations.
Partition used can now be configured with no nodes nodes.

Conflicts:
	NEWS

Conflicts:
	META

The symptom is that SLURM schedules lower priority jobs to run when higher priority, dependent jobs have their dependencies satisfied.  This happens because dependent jobs still have a priority of 1 when the job queue is sorted in the schedule() function.  The proposed fix forces jobs to have their priority updated when their dependencies are satisfied.

and task count that isn't an even cut.

Original code by Damien François. <damien.francois@uclouvain.Be>

plugin fails to load.

place)

plugin

possible.  Otherwise if it fails it wouldn't happen to the slurmstepd
and might be missed by failing silently.

It will also mess up the packing/unpacking since it should be obvious if
it fails on the slurmctld.

slurmctld when starting up the jobacct_gather plugin.  It isn't needed
and makes errors in the slurmctld if not running as root.

Original patch from Martin Perry (Bull)