This mostly reverts commit 8325e9f8.

Bug 4478

We decided to not do this by default for the slurmd.  See bug 4478 for
more info/reasoning.

We also didn't want to rely on #include <linux/oom.h> since that might
not exist everywhere.

Format for inserted X11 cookies is now hostname/unix:display, rather
than localhost:display. This seems to resolve some issues for different
setups while not causing any issues in my test environments. This also
helps avoid a conflict between multiple nodes in a larger job if the
same display number is allocated on multiple nodes simultaneously.

Bug 4420.

Bug 4483

Bug 4541

The slurm and pmix RPMs both attempt to install a libpmi. While Slurm's
version should be preferred, the best way to handle this is to have both
pmix and slurm packages split this off into a separate RPM that can
conflict with each other, giving the admin a way to resolve the conflict
manually.

Bug 4511.

The cluster name could have been free'd before it would be strdup'ed.
Happens when a federated persisent connection is established and the
cluster needs to sync up with the remote cluster.

Bug 4503

Remove the origin job when a remote sibling job was cancelled while the
origin was down.

e.g.
job originated on cluster1
job runs on cluster2
cluster1 goes down
job is cancelled on cluster2
cluster1 comes backup. The origin job should be removed if the sibling
job was cancelled.

The user_name is only populated if LaunchParameters=send_gids is set.
Without this field set, the pam_setup call will get NULL instead of the
user_name, leading to batch job launch failures. (The step launch code
already handles this same issue separately.)

Bug 4412.

On a job [pack]allocation RPC request, if the allocation succeed but the
send response message back to the client failed (i.e. srun was killed before
it could receive the response), then modify the job_record pointer so that
the job_state is set to FAILED, the exit_code as if the job got a SIGTERM
signal and the state_reason to FAIL_LAUNCH. Then users when querying
the job with sacct can discern that something bad happend for this scenario,
instead of STATE being showed as COMPLETED and the ExitCode as 0:0.

Bug 4513.

Use FREE_NULL_BUFFER instead, otherwise we could attempt to
free_buffer this a second time if we jump to the rwfail label.

Bug 4484.

When printing fields in sacct with user specified units (--units), the
nnodes field showed an incorrect string. This commit reverts a65fa572
and avoids the unit conversion, which does not make sense outside the
context of a Blue Gene systems (deprecated) anyways.

Bug 4490.

Slurm may generate empty manifest files depending on configuration
and library availability. Disable the new empty manifest check to
allow builds to proceed with rpm 4.13+ / Fedora 25+.

Bug 4453.

before printing anything for a connection.

field.

Bug 4529

fails. The description of the failure will be in the job's "Reason" field.

Bug 4529

buffer error.

Bug 4529

Bug 4222.

on startup. Just use the checkpointed job_id_sequence. get_next_job_id()
will not use a jobid if it's in use in the system.

Bug 4538

node_features/knl_generic - If plugin can not fully load then do not spawn
    a background pthread (which will fail with invalid memory reference).

completely instead of right after the parent job finishes.

Bug 4516

bug 3582

when a job requests no tasks and more memory than MaxMemPer{CPU|NODE}.

e.g.
sbatch --wrap="sleep 10"

Bug 4515

This will give expected results. Found while working on Bug 4515.

And print an appropriate fatal error message rather than relying
upon random errno value.

Bug 4523

Bug 4478.

In the federation case, the origin job is completed in the database when
a sibling job starts the job. The complete message is then sent again to
the database when the job is completed on the sibling cluster but
it is updated with the sibling job's exit code.

The jobcomp plugin didn't handle the multiple updates to the record.
This change allows the existing record to be updated.

Bug 4493

Bug 4500

The pid files in slurm.conf and the systemd service files must match,
or systemd will time out looking for the wrong pid file. Currently,
the Cray slurm.conf template has different pid files for slurmctld and
slurmd than the service files.

There's no reason for us to use these nonstandard pid files, and it
will save us some headaches to switch over.

bug 4496

In 1.10+ they changed the hid_t from an int to a long int which
messes things up as they use the top 32 bits for stuff right off
the bat.  This fixes the scenario by handing the number with a int32_t
instead of an int.

Bug 3795

Fix potential node reboot timeout problem for "scontrol reboot" command.
bug 4203

The - character is treated as a range if not first or last in the
[] brackets. Moving it in between . and / broke the regex subtly.

Inadvertently broken by a268b644.

Bug 4417.

Bug 4169

Found using test38.17

Otherwise poll() cannot monitor these ports properly,
leading to potential network traffic problems.

Bug 4467.

until the prolog and extern step are fully ran/launched.

Only matters if running with PrologFlags=[contain|alloc].

patch 2 of 2

Bug 4458

Patch 1 of 2

Bug 4458

Due to the way Cray builds Slurm, the prefix and bindir paths include the
Slurm version (/opt/slurm/<version>). This means every time we update to a
new Slurm version we must update the Slurm ansible playbook. It also means
that the slurm_playbook.yaml file must be built with Slurm to be used
(it can't simply be copied directly).

The attached patch updates the playbook to determine the version of Slurm
to use from the module file, and hardcodes the sysconfdir setting we give
in our Slurm installation guide. If a customer uses different paths, they
can update the playbook to meet their needs.

Bug 4360.

when trying to signal a step that is still running a prolog.

Bug 4446