Conflicts:
	src/plugins/select/cray/select_cray.c

Otherwise blade_cnt is potentially greater than
bit_size(jobinfo->blade_map) which leads to an assertion failure.

Bug 3033.

instead of 2+. Continuation of previous commit.

with hwloc.

This patch has two parts:
1. When a job is intially submitted, the Slurm was failing to set
   an initial reason for the job not starting.
2. After a job was submitted, it was sometimes failing to reset
   the job's reason. It was also failing to reset the "last_job_update"
   time, so something like "squeue -i1" would not get the new reason.
bug 3025

Fix multipart srun submission with EnforcePartLimits=NO and job violating
    the partition limits.
bug 3025

bug 3011

both)  Continuation of commit 95fa8e8e.

# Conflicts:
#	Makefile.in
#	auxdir/Makefile.in
#	contribs/Makefile.in
#	contribs/cray/Makefile.in
#	contribs/cray/csm/Makefile.in
#	contribs/lua/Makefile.in
#	contribs/mic/Makefile.in
#	contribs/openlava/Makefile.in
#	contribs/pam/Makefile.in
#	contribs/pam_slurm_adopt/Makefile.in
#	contribs/perlapi/Makefile.in
#	contribs/perlapi/libslurm/Makefile.in
#	contribs/perlapi/libslurmdb/Makefile.in
#	contribs/phpext/Makefile.in
#	contribs/pmi2/Makefile.in
#	contribs/seff/Makefile.in
#	contribs/sgather/Makefile.in
#	contribs/sgi/Makefile.in
#	contribs/sjobexit/Makefile.in
#	contribs/slurmdb-direct/Makefile.in
#	contribs/torque/Makefile.in
#	doc/Makefile.in
#	doc/html/Makefile.in
#	doc/man/Makefile.in
#	doc/man/man1/Makefile.in
#	doc/man/man3/Makefile.in
#	doc/man/man5/Makefile.in
#	doc/man/man8/Makefile.in
#	etc/Makefile.in
#	src/Makefile.in
#	src/api/Makefile.in
#	src/bcast/Makefile.in
#	src/common/Makefile.in
#	src/database/Makefile.in
#	src/db_api/Makefile.in
...

If all GRES were not defined on all nodes OR if a regular expression was used
   for a GRES file configuration (e.g. in gres.conf
   "Type=gpu Files=/dev/nvidia[0-4]"), then memory corruption was likely.
   The logic has been bad since its inception several years ago.

was put in as 4294967294 instead of -2.

POLLRDHUP does not exist on BSD, define to POLLHUP as done elsewhere.

Linux manages to work around it, but FreeBSD definitely requires it.

Dependency from use of pthread_kill(), introduced in dd4990a2.

Revert commit 933d4fba
bug 2704

Problem reported by Coverity

The original logic in c69650a9
  was flawed. This commit removes that logic. New logic is still
  required for proper enforcement.

The attached patch switches to a more reliable method of detecting
service nodes, using xtcli status. In addition, it switches to the print
function to be better compatible with python 3.

Remove DelayBoot configuration parameter from knl.conf and move to
  SchedulerParameters.
Set job default delay_boot value from configuration parameter
Enforce delay-boot scheduling logic.

multiple versions.

on the most recent pmix_vX.so file.
One is free to directly use new "pmix_vX" plugin names as well.

NOTE: there is one small artifact introduced by this fix - there will be
no "pmix" name in the output of "srun --mpi=list" but the most recent plugin
will be duplicated:

$ ./srun --mpi=list
srun: MPI types are...
srun: mpi/none
srun: mpi/mvapich
srun: mpi/mpich1_shmem
srun: mpi/mpichgm
srun: mpi/pmix_v1      <----
srun: mpi/mpichmx
srun: mpi/lam
srun: mpi/pmi2
srun: mpi/openmpi
srun: mpi/mpich1_p4
srun: mpi/pmix_v1      <----

conflicting pmix versions.

linking against.

commit 20a73c508e1.

of what is in the header file of pmix.