The task_dist_states variable has been split into "flags" and "base"
components. Added SLURM_DIST_PACK_NODES and SLURM_DIST_NO_PACK_NODES values
to give user greater control over task distribution. The srun --dist options
has been modified to accept a "Pack" and "NoPack" option. These options can
be used to override the CR_PACK_NODE configuration option.

to have all the limits a QOS has.  If a limit is set in both QOS
the partition QOS will override the job's QOS unless the job's QOS has the
'PartitionQOS' flag set.

Make the standard smap job information display fit in an 80 character
wide window. Recently expanded size for job array ID was 81 characters.
Expand minimum window size for smap to run from 72 to 80 characters.

Convert "#BB" options in script into simpler combined buffer request specification

Sufficiently large jobids (greater than INT_MAX) are displayed
incorrectly by smap. Change output of jobid to support uint32_t
values and shift remaining colums appropriately to the right.

Update un/pack and scontrol output
Add some back-end logic

Conflicts:
	doc/man/man5/slurm.conf.5

when running from cache.

Bug 1305

Fix bug with GRES having multiple types that can cause slurmctld abort.
This can be reproduced with select/cons_res and one Gres like this:
Name=gpu Type=kepler File=/dev/tty0
A bad index was being used that caused an assert.

Logic introdiced in version 14.03.10 to support requeueing of jobs
with GRES allocated to currently running steps broke select/linear
due to differernces in the plugin logic. The commit with the bad
logic is 1209a664

This will be required to parse the commands used by burst_buffer/cray

Bug 1298

Flesh out burst_buffer/cray more
More refactoring of the logic for use of common functions
Add PrivateData configuration parameter
Support reading different configuration file for each plugin
Improve job clean up, event logging

Bug 1301

Plus more refactoring of the logic for use of common functions

have no weight.  This allows for association and QOS decay limits to work.

Before without this option accounting would not be correct unless the
job was allocating enough resources to fill up the socket.  Making this
the default makes it so the entire socket is allocated to job similar to
the way CR_CORE works with allocating the entire core to the job even if
they don't allocate the whole core.

Conflicts:
	src/plugins/priority/multifactor/fair_tree.c

option.

Move a lot of logic from generic plugin to common and add calls from cray plugin
Add logic for burst_buffer/cray to read and report burst_buffer.conf
Move hash management functions into common