If a batch job is submitted that can not be started due to its
core specialization count being equal to or larger than the
node's core count, then reject it at submit time rather than
queuing the job.

linking)

If the Cray MPMD commands have different arguments then they should
appear in separate lines in the MPMD data structure.

starts and then a minor typo fix

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.

Conflicts:
	src/plugins/select/bluegene/select_bluegene.c
	src/slurmctld/step_mgr.c

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

For Kelly ;)

No change in logic, just rename a variable for better clarity.

ports.

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

based on ionode count correctly on slurmctld restart.

With select/cons_res plugin and a job using the --exclusive option
if the partition supports gang scheduling or mutliple jobs per node,
then allocate CPUs to multiple jobs, but allocate the job every
CPU on each node.

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.

would be set, but this is safer.

continue the operation for other elements.

Signed-off-by: Danny Auble <da@schedmd.com>

to suspend/resume array elements.

This reverts commit 34fd501c.