The slurmctld would segfault if we didn't check this.

Bug 6449.

already booted when slurmctld daemon is reconfigured.

Bug 6457

Bug 6468.

Bug 5513.

Bug 6458

Bug 6458

Lustre client stats moved to /sys/kernel/debug/lustre/llite with 2.12.

Bug 6385.

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

The correct printf format for size_t is %zu not %lu.

Bug 6430

The code to handle it was already there, this just made it so we
actually parsed it.

Bug 6430

Commit 750cc23e changed the signature for slurm_xmalloc, which
needs to be mirrored here in slurm-perl.h.

Bug 6436.

Force intermediate values to uint64_t to catch the potential overflow.

CVE-2019-6438.

On a heterogeneous system the gres.conf coming from various nodes
might not be complete.  The slurm.conf has a complete list of possible
gres on the other hand.

If the GRES doesn't exist we will print an error and use the id instead
of the name, but this should never happen.

Bug 6366

When trying to update the partition list of a job it didn't
get updated.

Bug 6329

Bug 6320

Bug 6004

specific tasks.

Bug 6357

Bug 6004

Update seff to reflect API change from rss_max to tres_usage_in_max. Use
Slurmdb::find_tres_count_in_string to parse out the TRES_MEM value.

Bug 6004

Bug 5736

This check really is there to test if we have dynamic(inactive) features.

Obviously this doesn't work on heterogeneous systems, but there is no
good way to check for this as this check is used long before nodes are
considered.

Bug 6242

Docs updated with details. 'node' is simply removed from the tres list;
the report will continue if other valid tres are specified.

Bug 5954

Bug 6356.

Fixed srun from double printing invalid option
msg twice. Also removed the unused -b flag from sbatch.

Bug 6356.

This patch fixes the regression caused by 07483564 where only the
linux plugin was handling this scenario correctly.

Bug 6332

Bug 6331

Add a debug statement.

Bug 5823

When the backup slurmdbd is active, there is no need to print
connection errors every 10 minutes when the backup checks in on the
primary, at least at the 'error' level.

Prevent dbd clients, like sacctmgr, from printing a connection error
when running commands against the backup slurmdbd unless debug2.
Before, the clients would always print errors when trying to access
the primary dbd first.

Bug 5823

Fix issue introduced in commit 164d4878 that avoided a job to be modified
setting the current reservation to none.

Bug 6309

which caused negative values and values starting with a decimal
to be invalid for PriorityWeightTRES and TRESBillingWeight.

Bug 6217

Bug 6321

As pthread_rwlock_t is a struct, we cannot use this syntax
to initialize all elements of the array to the same value
as we would if these were any basic type.

Instead, move the initialization to a dedicated loop to ensure
all locks are initialized correctly.

This does not seem to have caused any issues on Linux platforms,
but macOS at least does notice this mistake.

Bug 6319.

Enabling this alters the scheduling sorting algorithm so that hetjob
components belonging to the same hetjob are attempted to be scheduled
consecutively (not interleaved with other jobs or hetjob components).

Bug 5579.

AccrueTime limits.

Bug 6002


Co-authored-by: Felip Moll <felip.moll@schedmd.com>

Regression introduced in ccafaf7b.

Replace the (was always set to true) check_current_dir argument to
search_path() with check_cwd_last boolean to indicate if cwd should be
evaluated first (needed by sbatch) or last (salloc/srun).

Bug 6271.

Bug 6169

Bug 6289