- 02 Aug, 2018 9 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
to dictate what state of node is after reboot.
-
Brian Christiansen authored
update_node_msg_t->node_state is uint32_t but we were putting a uint16_t into it. NO_VAL16 wouldn't have gone up to the controller.
-
Brian Christiansen authored
-
Brian Christiansen authored
-
Brian Christiansen authored
-
- 01 Aug, 2018 4 commits
-
-
Marshall Garey authored
Bug 5196.
-
Marshall Garey authored
Needed for node_record_count. Bug 5196.
-
Tim Wickberg authored
This reverts commit a10454f7.
-
Marshall Garey authored
Bug 5196
-
- 31 Jul, 2018 2 commits
-
-
Danny Auble authored
-
Morris Jette authored
Bug 5070
-
- 30 Jul, 2018 2 commits
-
-
Tim Wickberg authored
-
Tim Wickberg authored
-
- 28 Jul, 2018 6 commits
-
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Tim Wickberg authored
-
- 27 Jul, 2018 12 commits
-
-
Danny Auble authored
Bug 5468 This is a backport of commit cefc9ec1.
-
Danny Auble authored
-
Felip Moll authored
Bug 4918
-
Tim Wickberg authored
Collapse error message on to one line when they weren't previously, and fixup argument indentation as well while here. find . -name '*\.[ch]' -exec sed -i s/error\(\[\ \]*\"sched:\ /sched_error\(\"/ {} \;
-
Tim Wickberg authored
These calls will replace all these: error("sched: message...") with: sched_error("message...") This allows the _log_msg function to stop calling xstrncmp() on every log message while holding log_lock when SchedLogLevel > 0. This behavior has effectively removed all concurrency from slurmctld when SchedLogLevel is enabled, and prevented larger scale systems from being able to start up - see bug 3746 for an example of this.
-
Tim Wickberg authored
Update all calling locations, and as this is a static function change the name to _log_msg from log_msg while here.
-
Tim Wickberg authored
-
Tim Wickberg authored
-
Dominik Bartkiewicz authored
scheduling cycle. Primarily caused by EnforcePartLimits=ALL. Bug 5452
-
Tim Wickberg authored
-
Tim Wickberg authored
This requires all calls to slurm_addto_char_list() to change to slurm_addto_char_list_with_case().
-
Tim Wickberg authored
Rather than replace all existing references, keep the existing function name and signature, and break off the body into slurm_addto_char_list_with_case() with the lower_case_normalization option set to true. Locations that need to disable this case normalization will thus have access to this same function, just by the longer name with the extra boolean.
-
- 25 Jul, 2018 5 commits
-
-
Tim Wickberg authored
fdopen returns NULL on failure. It is impossible for (FILE *) to be less than zero, so this check would have always succeeded even in the event of a failure. CID 187087.
-
Tim Wickberg authored
-
Tim Wickberg authored
CID 187179.
-
Tim Wickberg authored
CID 187085.
-
Marshall Garey authored
not find any jobs. The actual syntax for that sacctmgr command is sacctmgr show runawayjobs [clustername] but sometimes people mistakenly do sacctmgr show runaway jobs in which case it would look for runaway jobs on a cluster named "jobs" and print the message "Runaway Jobs: No runaway jobs found" because the clustername was wrong. This patch changes that message to say "Runaway Jobs: No runaway jobs found on cluster jobs" so that people know they made a mistake in syntax.
-