Added sbatch '--parsable' option to output only the job id number and the
cluster name separated by a semicolon rather than "Submitted batch job....".
Errors will still be displayed.

needed to forward a message the slurmd would core dump.

describing that jobs must be drained from cluster before deploying
any checkpoint plugin.

Properly enforce a job's cpus-per-task option when a job's allocation is
constrained on some nodes by the mem-per-cpu option.
bug 590

limit scheduling logic depth by partition.

bug 586

Partial response to bug 521

No change in logic, just change name of recently added env var

Set the environment variable SLURM_PARTITION to the partition in
which a job is running. Set for salloc, sbatch and srun.

Set GPU_DEVICE_ORDINAL environment variable.

Previous logic would try to pick a specific node count and on a
heterogeneous system, this would cause a problem. This change
largely reverts commit a270417b

beside the numerical values.

Added whole_node field to job_resources structure
Enable gang scheduling for jobs with core specialization and other
jobs allocated whole nodes.

i.e. salloc -n32 doesn't request the number of nodes and with the previous
code if this request used 4 nodes and only 1 was left in GrpNodes it
would just run with no issue since we were checking things before we
selected how many nodes it ran on.

Now we check this afterwards so we always check the limits on how many
nodes, cpus and how much memory is to be used.

Fix step allocation when some CPUs are not available due to memory limits.
This happens when one step is active and using memory that blocks the
scheduling of another step on a portion of the CPUs needed. The new step
is now delayed rather than aborting with "Requested node configuration is
not available".
bug 577

incorrectly when using the hostlist_push_host function and
input surrounded by [].

based on ionode count correctly on slurmctld restart.

Split a slurmctld's job record "shared" field into "share_res"
(share resource) and "whole_node" fields. Needed to better manage
allocation of whole nodes for core specialization without disabling
gang scheduling of such jobs.

to suspend/resume array elements.