Change some sched/backfill messages to be more clear
Change some sched/builtin messages and variable names to
no longer reference "backfill".

Prevent a possible buffer overflow if the task prolog output
exceeds 4096 bytes.

Expand StdIn/Out/Err string length output by "scontrol show job" from 128
to 1024 bytes.
bug 712

See bug 701

salloc/srun, instead wait in the slurmd when a step hits a node and the
prolog is still running.

Wait for a job to begin execution prior to testing its allocated
resources to confirm proper core specialization support.

Failed to find individual jobs to resume.

priority/basic - Insure job priorities continue to decrease when jobs are
submitted with the --nice option.
bug 707

If one task of a job array can not be scheduled in the main
scheduling loop, skip the subsequent tasks of that same
job array.

This reverts commit 6cd208e0.

has ran yet or not.

Cray/ALPS system, otherwise use the slurmd to wait on the prolog to gate
the start of the step.

Fix some sinfo and squeue sorting anomalies due to differences in data
types.
See bug 706

bluegene.conf

restarted.

allocation instead of just the first.

There were several recently added node states missing from the
scontrol and sinfo man pages.

Update scontrol update jobID logic to operate on entire job arrays.

Add squeue job format option of "%y" to print a job's nice value.
bug 696

Expand the description of the SchedulingParameters max_sched_time
configuration parameter for greater clarity

Move start time of main scheduling loop timeout after locks are aquired.
bug 698

Quite a few recent reasons were missing from the squeue man page.

controls how frequently the main scheduling loop will execute.

limits how long the main scheduling loop can execute for