of it's dimensions of length 3.  There is a limitation in the IBM I/O
subsystem that is problematic with multiple sub-blocks with a dimension
of length 3, so we will disallow them to be able to be created.  This
mean you if you ask the system for an allocation of 12 c-nodes you will
be given 16.  If this is ever fix in BGQ you can remove this patch.

Validate MPI rank values returned in test of MPI

Fix for srun allocating running within existing allocation with --exclude
option and --nnodes count small enough to remove more nodes.

    > salloc -N 8
    salloc: Granted job allocation 1000008
    > srun -N 2 -n 2 --exclude=tux3 hostname
    srun: error: Unable to create job step: Requested node configuration is not available

Patch from Phil Eckert, LLNL.

Add call to mpi_hook_slurmstepd_prefork() from slurmstep
immediately prior to fork/exec of user tasks.
Patch from Hongjia Cao, NUDT.

Add a generic data forwarding protocol to slurmd which uses its
existing hierarchical communications protocol.
Patch from Hongjia Cao, NUDT.

Patch from Hongjia Cao, NUDT.

Patch from Hongjia Cao, NUDT.

Make step launch API more robust if there are NULL pointers.
Patch from Hongjia Cao, NUDT.

Avoid failure when common I/O function is passed a NULL pointer.
Patch from Hongjia Cao, NUDT.

Modify some I/O handler functions to return when passed a NULL I/O
pointer rather than aborting.
Patch from Hongjia Cao, NUDT.

In srun --multi-prog mode, treat file name that begins with "."
as an absolute pathname with no need to use PATH.
Patch by Hongjia Cao, NUDT.

Fix for srun allocating running within existing allocation with --exclude
option and --nnodes count small enough to remove more nodes.

    > salloc -N 8
    salloc: Granted job allocation 1000008
    > srun -N 2 -n 2 --exclude=tux3 hostname
    srun: error: Unable to create job step: Requested node configuration is not available

Patch from Phil Eckert, LLNL.

Add simplified version of configurator too.
Work by Nathan Yee, SchedMD

Fix bug in step task distribution when nodes are not configured in numeric
order. Patch from Hongjia Cao, NUDT.

Fix bug in step task distribution when nodes are not configured in numeric
order. Patch from Hongjia Cao, NUDT.

Add logic to cache GPU file information (bitmap index mapping to device
file number) in the slurmd daemon and transfer that information to the
slurmstepd whenever a job step is initiated. This is needed to set the
appropriate CUDA_VISIBLE_DEVICES environment variable value when the
devices are not in strict numeric order (e.g. some GPUs are skipped).
Based upon work by Nicolas Bigaouette.

Based upon work by Nicolas Bigaouette

Based upon work by Nicolas Bigaouette

Conflicts:
	src/slurmctld/node_scheduler.c

Fix bug when requeued batch job is scheduled to run on a different node
zero, but attemts job launch on old node zero causing fatal error
"Invalid host_index -1 for job #"

Avoid slurmctld abort due to bad pointer when setting an advanced
reservation MAINT flag if it contains no nodes (only licenses).

blocks are in an error state.