If a job's CPUs/task ratio is increased due to configured MaxMemPerCPU,
then increase it's allocated CPU count in order to enforce CPU limits.
Previous logic would increase/set the cpus_per_task as needed if a
job's --mem-per-cpu was above the configured MaxMemPerCPU, but NOT
increase the min_cpus or max_cpus varilable. This resulted in allocating
the wrong CPU count.

values.

This required a fairly major re-write of the select plugin logic
bug 1975

Correct some cgroup paths ("step_batch" vs. "step_4294967294", "step_exter"
    vs. "step_extern", and "step_extern" vs. "step_4294967295").

Document that if a job's memory per CPU limit exceeds the system
limit, that the job's memory limit is decreased and it's CPU count
increased automatically.

Conflicts:
	NEWS
	src/slurmctld/job_mgr.c
	src/srun/libsrun/launch.c

Continuation of 1252d1a1
Bug 1938

Requeue/hold batch job launch request if job already running. This is
  possible if node went to DOWN state, but jobs remained active.
In addition, if a prolog/epilog failed DRAIN the node rather than
  setting it down, which could kill jobs that could continue to
  run.
bug 1985

This makes srun more consistent with salloc and sbatch

Previous logic would not report termiation siganl, only exit code,
  which could be meaningless.

Bug 1938

Bug 1984

When nodes have been allocated to a job and then released by the
  job while resizing, this patch prevents the nodes from continuing
  to appear allocated and unavailable to other jobs. Requires
  exclusive node allocation to trigger. This prevents the previously
  reported failure, but a proper fix will be quite complex and
  delayed to the next major release of Slurm (v 16.05).
bug 1851

When nodes have been allocated to a job and then released by the
  job while resizing, this patch prevents the nodes from continuing
  to appear allocated and unavailable to other jobs. Requires
  exclusive node allocation to trigger. This prevents the previously
  reported failure, but a proper fix will be quite complex and
  delayed to the next major release of Slurm (v 16.05).
bug 1851

Optimizing topology takes place first, then picking lowest weight
nodes within the switches offering the best fit.
bug 1979

Add ability to change a job array's maximum running task count:
    "scontrol update jobid=# arraytaskthrottle=#"
bug 1863

Added as part of requeue/hold update

Was printing "Name=#" rather than "JobID=#"

Validate that sbatch, srun, salloc return partition error message
on invalid partition name.
bug 1223

option.

we are root or slurmuser.  This was hiding a bug that will be fixed in the
next commit.

Previous logic would stop at "/".

bug 1228

Modify scontrol requeue and requeue_hold commands to accept comma
  delimited list of job IDs.
bug 1929

Previously, scontrol would generate an error if passed a comma
  delimited list of job IDs. A space delimited list would be
  accepted. This increases compatability with some other Slurm
  commands.
bug 1929