Fix bug in select/cons_res task distribution logic when tasks-per-node=0.
Eliminates misleading slurmctld message
"error:  cons_res: _compute_c_b_task_dist oversubscribe."
This problem was introduced in SLURM version 2.2.5 in order to fix
a task distribution problem when cpus_per_task=0. Patch from Rod Schultz, Bull.

This fixes a possible race condition when running test15.5 depending
which message arrives first at shutdown.

In the srun/aprun wrapper man page, clarify how conflicing command
line options for --alps and native srun options are handled.

Improve documentation with respect to preemption rules, namely
PreemptMode=suspend is incompatible with PreemptType=preempt/qos.
Patch from Bill Brophy, Bull.

using gang scheduling to finish.  Before the pending jobs would fail
waiting for all other time slicing jobs to finish.

common .la for the block allocator

in the block allocator

common location

block allocator in the bluegene plugin

srun wrapper for srun not getting all arguments when job allocation did not
exist at execution time.

If the srun wrapper is executed when there is no job allocation, then
create an allocation using salloc and call the srun wrapper again so
that we can configure memory limits in aprun's execute line. Without
this change, aprun would lack the memory allocation information and
the task launch would fail if the job were allocated less than the
full node.

Prevent duplicate arguments to aprun from the srun.pl wrapper.
This could happen if the command line included "--alps" arguments
plus other arguments generated by the normal srun options. For example:
srun -t 5 --alps="-t300" a.out
specifies the job time limit in two places.

Set SLURM_MEM_PER_CPU or SLURM_MEM_PER_NODE environment variables for both
interactive (salloc) and batch jobs if the job has a memory limit. For Cray
systems also set CRAY_AUTO_APRUN_OPTIONS environment variable with the
memory limit.

Clarify in the srun (aprun wrapper) which options apply to an existing
job allocation or new allocation and which are not applicable to Cray
computers.

asking for less than 1 mb per PE.

Correction to srun man page. Get SIGINT working when srun spawns salloc.

For front-end configurations (Cray and IBM BlueGene), bind each batch job to
a unique CPU to limit the damage which a single job can cause. Previously any
single job could use all CPUs causing problems for other jobs or system
daemons. This addresses a problem reported by Steve Trofinoff, CSCS.

There was a table added, but it all ran together without being put
into a table or list. I changed it to an unordered list.

enforce memory limits.

man pages. Patch by Nancy Kritkausky, Bull.

Bill Brophy, Bull.

Note the job and partition state file formats have changed and RPCs
with information for jobs and partitions have changed.