This commit changes the logic of selecting a type of collective. The
Tree-based algorithm will be selected when fence with an empty data
contribution, which allows for improved fence performance.

Bug 6637.

Bug 6411.

Continuation of 36c30487

Bug 6782

Otherwise, we could send communication packets bigger than max_allowed_packet.

Bug 6832.

Co-authored-by: Tim Wickberg <tim@schedmd.com>

Regression introduced in 8d643e79.

Bug 6832.

The problem was freeing an interior pointer to buffer contents before
the call to FREE_NULL_BUFFER. The issue was only triggered when loading
an archived data with protocol version < 17.11.

Regression introduced in 8d643e79.

Bug 6832.

Bug 6440

Link to build, add site_factor/none as the default (null) plugin.

Connect in to priority_multifactor plugin.

Note that the job_write_lock acquisition in _decay_thread() is promoted
one level to protect both the fair tree use of it alongside the new
site_factor plugin. As fair_tree has been made the default, I felt it was
better to handle it this way, rather than have site_factor reacquire the
locks right after fair_tree dropped them. For sites running without
fair_tree, this does represent a minor drop in potential concurrency.

Bug 5202.

when not the head job.

Bug 6837

For more in depth explanation see comment 24

When specifying -j and not -s then non-eligible jobs will be shown
by sacct.
Time windows can also be used with -S and -E.
If --state is also used then non-eligible jobs won't be shown,
because non-eligible are not actually PD.

Bug 6873

# Conflicts:
#	NEWS

Bug 6805

Bug 6898

Cancelled jobs before start have time_start=0 in the DB, but their
time_end!=0 (the cancel time).
Query fixed to handle properly these cases for -s PD.

Bug 6894

Now that the pid is no longer an argument, the name doesn't make sense.
Change to container_g_join() to reflect the underlying functionality.

Bug 6567.

Brought the option in line with the "numtasks" option you use when
not specifying --step. Preserved backwards compatbility for "numtask"
for steps. Also upated docs and expect test.

Bug 6861

Bug 6236

Properly initialize structures throughout Slurm.

Bug 6613

Bug 6613

Bug 6613

Bug 6711.

Regression from aca37654

.

Bug 6826.

Co-authored-by: Chad Vizino <chad@schedmd.com>

Overrides any setting for SLURM_EXPORT_ENV, which can make nesting jobs
simpler.

If SBATCH_EXPORT_ENV=NONE (which will cause SLURM_EXPORT_ENV=NONE to be set
in the batch step) is used alongside SRUN_EXPORT_ENV=ALL, this allows for
the batch environment to be reset, but then for changes made in the batch
script (e.g., loading modules with 'module load') to propagate out as part
of the step launch.

The same can be accomplished by the user in their scripts by explicitly
setting 'srun --export=ALL ...' for every step launch, but this should
provide an easier mechanism for sites to make this behavior the default
for their users by pushing this pair of environment variables into their
users default profiles.

Bug 5537.

Matches PrologSlurmctld/EpilogSlurmctld behavior to Prolog.

Bug 6615.

Bug 6737.

Bug 6252

to run RebootProgram from ctld.

Bug 6115

Bug 6010

Bug 6869

to guarantee a minimum runtime before preemption.

Bug 5519

to send user signal at preemption time.

Bug 5867

These are conditions that need to remain constant until something
changes on the job to reevaluate.

Bug 6625

What was happening here is you had to not be >= operator to have the old
limits removed.  This makes it so it always happens.

Bug 6625

Bug 6625

Before we went up the tree to the next assoc_ptr.  As we validate an
association on the id as well as the uid the assoc_ptr was eventually
going to become invalid.  Setting it to NULL here solves a bunch of
issues with things later on.

Bug 6625

Bug 6625

Bug 6625.

Don't abort when the job doesn't have an association that was removed before the job was able to make it to the database.

Bug 6625

Bug 6625