On Bluegene/Q systems, the job step allocation needs to be larger
than requested in some cases due to the job allocation geometry
(e.g. a 5 cnode allocation needs to be scaled up to at least
6 cnodes). This enhancement fixes that logic if multiple size
increases are needed.

next parallel step is ran on a sub block, SLURM won't over
subscribe cnodes.

This reverts commit c5d63854 from 8/11/2011. The memory
copy is not a leak, but is required to avoid memory corruption.

make sure that a job has a step_list before creating an interator for it

Improve logging messages and readability of some code

This prevents bad node index values in a job step completion record
from crashing slurmctld, as is possible if srun has bad configuration
information about a job step or other failure.

Add a basic test of Bluegene/Q job step allocations within an existing
job allocation.

on a Bluegene/Q system when srun's --test-only option is used within
an existing allocation then launch the job directly with the slurmd
daemon and do not use IBM's "runjob" command. Useful for testing.

BLUEGENE - Modify "scontrol show step" to show  I/O nodes (BGL and BGP) or
c-nodes (BGQ) allocated to each step. Change field name from "Nodes=" to
"BP_List=".

The test is now more generic to support all Bluegene system types

cannot fit into the available shape.

Modify existing tests so they all run as desired on an emulated Bluegene/Q system

Previous code would fail when trying to launch more than 4096 tasks,
which is a problem on BGQ systems where SLURM actually launches job
steps.

The SLURM_JOB_CPUS_PER_NODE and SLURM_TASKS_PER_NODE environment
variables were being improperly set for IBM Bluegene systems

or not.

This change applies only to Cray systems and only when the srun
wrapper for aprun. Map --exclusive to -F exclusive and --share to
-F share. Note this does not consider the partition's Shared
configuration, so it is an imperfect mapping of options.

On Cray systems only, the value of avail_node_bitmap was not being
properly set for non-responsive nodes.

A node DOWN to ALPS will be marked DOWN to SLURM only after reaching
SlurmdTimeout. In the interim, the node state will be NO_RESPOND. This
change makes behavior makes SLURM handling of the node DOWN state more
consistent with ALPS. This change effects only Cray systems.

Fix the node state accounting to be consistent with the node state
set by ALPS.

Split set_node_down() into two functions: set_node_down() will continue
to accept a node name as an argument and set_node_down_ptr() which is new
and accepts a node pointer as an argument and will be faster.