the job starts update the cpus_per_task appropriately.

This also moves update num_tasks to after the setting of node counts on
an update.  It didn't appear to matter, but the cpus_per_task and
pn_min_cpus had to be figured out after the cpus and nodes were set but
before tasks.

Bug 2302

burst_buffer/cray - Improve tracking of allocated resources to handle race
    condition when reading state while buffer allocation is in progress.
Also initialize a mutex

DBD for the first time.  The corruption is only noticed at shutdown.

Bug 2293

Conflicts:
	META
	NEWS
	src/slurmctld/job_scheduler.c

Set job's reason to "Priority" when higher priority job in that partition
    (or reservation) can not start rather than leaving the reason set to
    "Resources".
bug 2285

error message.

If a reservation's nodes value is "all" then track the current nodes in the
    system, even if those nodes change. Nodes will automatically be added to
    or removed from a reservation when slurm.conf changes.
bug 2204

Bug 2281

Rename the variable to match rest of codebase while here. This is related to
bug 2295, although snprintf() protects against buffer overflow in 15.08 and up.

Later releases have switched over to snprintf to avoid this issue, but 14.11
did not get that patch. Bug 2295.

time.

nojobs.

static/overlap systems when some hardware issue happens when restarting
the slurmctld.

a dynamic system and mark the block in error on a static/overlap system.

Bug 2273

Don't use lower weight nodes for job allocation when topology/tree used.
bug 2284

Preemption/gang scheduling: If a job is suspended at slurmctld restart or
    reconfiguration time, then leave it suspended rather than resume+suspend.
bug 2274

bug 2276

Add cray-specific port configuration information which considers
  Realm-Specific IP Addressing (RSIP).
bug 2277

Filter out some message commonly generated in high-throughput
  computing environments.
bug 2282

task/affinity: Disable core-level task binding if more CPUs required than
    available cores.
bug 2267

Improve the logging of job submit RPC contents; add descriptor/name
  to some of the fields printed rather than just raw numbers.

Log as error if more than 3 aeld connects per second that cause is
  likely duplicate slurmctld daemon
bug 2278

This is needed to properly enforce limits and account for usage.

Remove the 1024-character limit on lines in batch scripts, which was
causing long lines to be silently truncated. I noticed it when jobs were
getting created with fewer dependencies than specified.

Also increase the line length when showing job info.