Increase the maximum array len large to be packed/unpacked with one order of
magnitude, since the current value demonstrated it is not enough when an MPI
program spawns a considerable amount of tasks over a big set of nodes.

This limit was introduced in 627928f4.

Bug 7495

There was never any security to allow for this,
so we are just removing it.

Bug 7765

Admin/Operator users were not able to skip MaxQueryTimeRange when trying
to show/fix runaway jobs.
This commit uses _validate_operator() instead of
_validate_slurm_user() in _get_jobs_cond() as well as check for operators
in _fix_runaway_jobs().

Bug 7765

Bug 7708

Don't remove jobs from preemptee_candidates List.

Bug 7708

Since this happens inside a the user process, this can inadvertently
cause the user's job to die by running out of file descriptors.

Bug 7814.

Co-authored-by: William Arndt <warndt@lbl.gov>

Bug 7499

Regression introduced in fb26b706.

Bug 7675

Now the signaling of the batch step and the handeling of the flags is totally
handled in _kill_all_active_steps() in slurmd, and _handle_signal_container()
in stepd to ensure that:
- if KILL_JOB_BATCH then only batch container is signaled
- if KILL_FULL_JOB then batch script and its children are also signaled
- if both of the above then only the batch script and its children are signaled

We do not relay anymore on proctrack_g_signal() to handle the batch step
signaling anymore, therefore it works the same for all proctrack plugins.

This commit also includes minor related fixes in other code handling such
signaling flags, and documentation improvement.

Bug 7282

Signed-off-by: Tim Wickberg <tim@schedmd.com>

Bug 7697

1cd43fce

Bug 7630

Bug 7727

This was missed in commit 6ac4ce84.

An incorrect logic with the variables holding available cores in the
gres_plugin_job_core_filter3() function lead to a potential infinite
"while (avail_cores_tot > req_cores)" loop, leaving slurmctld unresponsive.

Bug 7685.

Bug 7719

Signed-off-by: Danny Auble <da@schedmd.com>

Regression caused by 72736af2.

Bug 7708.

FastSchedule will be removed in 20.02.
FastSchedule=2 functionality has been moved to
SlurmdParameters=config_overrides.

Bug 7496.


Signed-off-by: Tim Wickberg <tim@schedmd.com>

Bug 7699

Continuation of 64876087

Bug 7698

Bug 4781

Otherwise, there could be time frames where printed schednodes
information could be obsolete.

Bug 7676.

exclusively to that job.

Bug 7510

use correct start_time for TIME_FLOAT resevation
in _job_overlap()

Bug 7458

Bug 7458

Bug 7458

Move _validate_node_choice() before prolog/epilog check

Bug 7458

Free the gres_devices list to avoid a valgrind warning on exit.

Bug 7644.

Continuation of 30bbc11d



Bug 7445

Signed-off-by: Dominik Bartkiewicz <bart@schedmd.com>

When --batch=<feature> is used, the batch_host isn't chosen until the
job is being launched -- because the features could be different on boot
(e.g. KNL nodes). Thus if the job is allocated nodes that need to be
booted, it needs to wait till they are all booted so it can make a
decision at launch time.

Bug 7445

Signed-off-by: Dominik Bartkiewicz <bart@schedmd.com>

This is a continuation to 7da439b4

Bug 7445

Only do so once the task actually finishes. Otherwise, a requeued task
could set an incorrect max_exit_code even if completed with exit code 0
after re-running again, leading to problems with i.e. other jobs with an
afterok type of dependency on such array relying on the incorrectly set
max_exit_code.

Bug 7552.

In case of features like cpu&fastio&[knl|westmere] additional bit_or
resulted in returning something like (cpu&fastio)|knl|westmere, which
is obviously wrong. XOR/XAND features are handled properly in
_get_req_features.

Bug 7378

Handle situation where a slurmctld tries to communicate with slurmdbd more than once at the same time.

What can happen here is the slurmdbd/slurmctld connection gets hung up
somehow.  If the slurmctld is restarted a new connection is made along
side the old connection.  When the old connection gets unwedged the old
connection will clear out the registration of the slurmctld making it so
no updates are sent to that slurmctld.

What this does is checks for old connections when a registration message
comes in.  If we find one we print error set the rem_port = 0 and
remove it from the list.  This makes it so when it gets unwedged we just
close the socket instead of remove the registration.

Bug 5213

Bug 7360.

in track scripts code.

Bug 7360


Signed-off-by: Alejandro Sanchez <alex@schedmd.com>

The implementation of priority_p_job_end in priority/multifactor
expects the job state to be set to complete or completing in order to
properly remove some job usage from the assoc and qos. This must be
simulated by the pack job run check code, or the check-time usage is not
removed.

Bug 7284

It wasn't properly set under certain conditions.

Bug 7276

Bug 7410.

Consider jobs in COMPLETING state as being available immediatley for
a job will-run evaluation. This assumes the completion will happen
very soon after the test is run.

bug 6769

All of the select plugins were performing a duplicate resource free
for jobs in completing state when performing a will-run test for
new jobs. This would frequently result in underflow messages.

Bug 6769