Previously under some conditions that boot completion was ignored
and the job kept pending.

silence clang warning about unsupported flag. if we want
performance we have other ways to chase after it, the reason
for this specific flag has long since passed. if you're still
using gcc 3.4 there are plenty of other issues in modern slurm.

run autogen.sh to account for removal of auxdir/x_ac_cflags.m4

Superfluous xstrdup call to passed argument causes
a small memory leak in sreport, caught by Coverity.

Update some node feature logic to support KNL nodes.

If a user submits a job with duplcate partition names (e.g.
  "sbatch --partition=debug,debug,debug", slurm was creating
  multiple (duplicate) records in the job's partition list.
  This change prevents duplicate entries in that list.

Bug 2364

Commit fa331e30 fixes this.  The logic was bad to begin with...

uint32_t new_cpus = detail_ptr->num_tasks
	/ detail_ptr->cpus_per_task;

The / should had been * this whole time.  This was the reason we found
this in the first place.

bug 2369

# Conflicts:
#	src/slurmctld/reservation.c

If scancel is operating on large number of jobs and RPC responses from
    slurmctld daemon are slow then introduce a delay in sending the cancel job
    requests from scancel in order to reduce load on slurmctld.
bug 2256

If a job launch is delayed, the test was failing due to bad parsing.
These lines were being interpretted as a counter folloed by node
names of "queued" and "has":
  srun: job 1332712 queued and waiting for resources
  srun: job 1332712 has been allocated resources

Expand documentation for advanced reservation Purge_Comp flag in
  scontrol man page, add to advanced reservation web page, increase
  minimum start time from 1 to 5 minutes

bug 2366

Conflicts:
	META
	NEWS

Backfill scheduling properly synchronized with Cray Node Health Check.
    Prior logic could result in highest priority job getting improperly
    postponed.
bug 2350

This corrects logic from commit e5a61746
that could result in use of NULL pointer

It was previously triggered by executing "scontrol reconfig" on a
  front-end system while there was a job in completing state.

Properly account for memory, CPUs and GRES when slurmctld is reconfigured
    while there is a suspended job. Previous logic would add the CPUs, but not
    memory or GPUs. This would result in underflow/overflow errors in select
    cons_res plugin.
bug 2353