NEWS: Add 1.10.3 bullet about zero-length datatypes

[jsquyres]

Signed-off-by: Jeff Squyres [email protected]

Merge this if open-mpi/ompi-release#1121 is merged.

[jsquyres]

@rhc54 Getting some Mellanox Jenkins failures, which I think are about binding (this failure has nothing to do with this PR -- this PR is about adding a bullet to NEW regarding datatypes):

07:59:50 + for hca_dev in '$(ibstat -l)'
07:59:50 ++ cat /sys/class/infiniband/mlx4_0/device/numa_node
07:59:50 + var=0
07:59:50 + export TEST_CLOSEST_NUMA=0
07:59:50 + TEST_CLOSEST_NUMA=0
07:59:50 + /var/lib/jenkins/jobs/gh-ompi-master-pr/workspace-2/ompi_install1/bin/mpirun -np 8 --map-by dist -mca rmaps_dist_device mlx4_0 -x TEST_CLOSEST_NUMA -x TEST_PHYS_ID_COUNT -x TEST_CORE_ID_COUNT /scrap/jenkins/jenkins/jobs/gh-ompi-master-pr/workspace-2/jenkins_scripts/jenkins/ompi/mindist_test
07:59:52 
07:59:52 Success rank - 6: only one NUMA is scheduled.
07:59:52 
07:59:52 Success rank - 2: only one NUMA is scheduled.
07:59:52 
07:59:52 Success rank - 0: only one NUMA is scheduled.
07:59:52 
07:59:52 Success rank - 4: only one NUMA is scheduled.
07:59:52 
07:59:52 Error rank - 5: scheduled on wrong NUMA node - 1, should be 0
07:59:52 
07:59:52 Error rank - 7: scheduled on wrong NUMA node - 1, should be 0
07:59:52 
07:59:52 Error rank - 3: scheduled on wrong NUMA node - 1, should be 0
07:59:52 
07:59:52 Error rank - 1: scheduled on wrong NUMA node - 1, should be 0
07:59:53 -------------------------------------------------------
07:59:53 Primary job  terminated normally, but 1 process returned
07:59:53 a non-zero exit code. Per user-direction, the job has been aborted.
07:59:53 -------------------------------------------------------
07:59:53 --------------------------------------------------------------------------
07:59:53 mpirun detected that one or more processes exited with non-zero status, thus causing
07:59:53 the job to be terminated. The first process to do so was:
07:59:53 
07:59:53   Process name: [[35509,1],1]
07:59:53   Exit code:    1
07:59:53 --------------------------------------------------------------------------

[jsquyres]

@rhc54 The same Mellanox Jenkins issues are showing up on #1612 -- I can't tell if this is a bad test in Mellanox Jenkins, or if this is a real issue on master (but unrelated to these PRs).

[ibm-ompi]

Test passed.

[jsquyres]

This was pulled into v1.10 and will come to master when the v1.10.2 bullets are manually brought back over. Closing this PR.