Added CpuFreqDef configuration parameter in slurm.conf to specify the
default CPU frequency and governor to be set at job end.

failure as well as interactive user.

epilog complete message comes from that node do not process the batch step
information since the job has already been requeued because the epilog
script running isn't guaranteed in this situation.

start of requeued jobs.

Expand from 8 to 16 bits for more than 256 sizes

sched/backfill - Fix anomaly that could result in jobs being scheduled out
of order.
bug 911

Without this a batch script could be bound to a single CPU rather
than the full job allocation. This is a revision to commit
399cb897
without which batch scripts has no binding to CPUs via hwloc

squeue and scontrol to report a job's "shared" value based upon partition
options rather than reporting "unknown" if job submission does not use
--exclusive or --shared option.
bug 939

exit code.

a fix to handle sacct under this new method.

signal to the batch script only.

process terminated by a signal.

error message and avoid to loop forever, give up after 120 seconds.

This reverts commit 53706b41.

Conflicts:

	NEWS

Report correct partition associated with a step if the job is submitted to
multiple partitions. Previously all of the partitions that the job could
run in would be reported for the step.

Added squeue -O/--Format option that makes all job and step fields available
for printing.

Without this, the record of gres allocated to steps will remain
allocated and not be available to job steps after being requeued.

sched/backfill - If job started with infinite time limit, set its end_time
one year in the future. Previous logic would based it upon INFINITE and
produce an overflow of the uint32_t time.

Report correct CPU count allocated to job when allocated whole node even if
not using all CPUs.
bug 909

Fix bug which could report to squeue the wrong partition for a running job
that is submitted to multiple partitions.