The problem was that MPS and GPU plugins each have separate device
file records that point to the same file (duplicate device files are
normally rejected in gres.conf, so this is a special case). So when a
comprehensive GRES device list was assembled from each plugin in
gres_plugin_get_allocated_devices(), these files were being
double-counted, causing the issue.

The solution is to make this comprehensive GRES list unique by
omitting records with duplicate file paths.

Bug 7630

archive dump and archive load are two complementary options with
different arguments for each.

Bug 7279

Bug 7556

Bug 7727

This was missed in commit 6ac4ce84.

Bug 7754

Using numbers is still supported, however, may be very misleading.
We shouldn't use it in examples.

Bug 7751

Bug 7723

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 7664

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

Test DAILY reservation conflict

Bug 7458

use _resv_time_overlap() in _resv_overlap()

Bug 7458

Bug 7458

Bug 7458

Move _validate_node_choice() before prolog/epilog check

Bug 7458

Bug 6513.

Bug 6513.

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

Bug 7644.

Bug 7149.

Continuations of a2f2894f



Bug 7445

Signed-off-by: Marshall Garey <marshall@schedmd.com>