- 30 Jun, 2014 5 commits
-
-
David Bigagli authored
-
Danny Auble authored
-
Danny Auble authored
-
jette authored
If MinJobAge is configured too low, then job records can be purged before these tests issue the job requeue test, resulting in their failure
-
jette authored
Without this, the record of gres allocated to steps will remain allocated and not be available to job steps after being requeued.
-
- 29 Jun, 2014 1 commit
-
-
jette authored
sched/backfill - If job started with infinite time limit, set its end_time one year in the future. Previous logic would based it upon INFINITE and produce an overflow of the uint32_t time.
-
- 27 Jun, 2014 7 commits
-
-
David Bigagli authored
-
Morris Jette authored
Report correct CPU count allocated to job when allocated whole node even if not using all CPUs. bug 909
-
David Bigagli authored
-
Morris Jette authored
Rather than relying upon the default shared value being (uint16_t)NO_VAL;
-
Morris Jette authored
Don't log the job's incoming nice value is NO_VAL - NICE_OFFSET
-
Morris Jette authored
A function was added in commit 7cae0abb that was essentially identical to a previously existant function. The redundant function has been removed.
-
Morris Jette authored
Fix bug which could report to squeue the wrong partition for a running job that is submitted to multiple partitions.
-
- 26 Jun, 2014 11 commits
-
-
Danny Auble authored
-
Danny Auble authored
you could get multiple '*' wckeys.
-
Danny Auble authored
deleting users.
-
Danny Auble authored
able to be destroyed for debug.
-
Morris Jette authored
For each job the backfill scheduling is testing, print not only the job ID, but also its priority and partition.
-
Morris Jette authored
Correction to commit aeecd03c for some configuration
-
Morris Jette authored
Change the log format to match that of slurm.conf
-
Morris Jette authored
Clarify the meaning of the AllowGroups configuration parameter a bit more.
-
Morris Jette authored
Original version did not end an indent properly
-
Morris Jette authored
Remove some debugging logic accidentally included in commit 7a187f10
-
Morris Jette authored
sched/backfill: Correct job start time estimate with advanced reservations. Under some conditions, the job start time would be set to the end time of an advanced reservation that may have nothing to do with that job's resource requirements. bug 911
-
- 25 Jun, 2014 15 commits
-
-
Morris Jette authored
-
Morris Jette authored
Log more backfill scheduling actions including where/when jobs will run even if they can not start until long in the future
-
Morris Jette authored
-
Danny Auble authored
-
Remi Palancher authored
file.
-
Bill Brophy authored
If we don't it could get messed up on a reconfig.
-
Danny Auble authored
-
Danny Auble authored
-
David Bigagli authored
-
Danny Auble authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Logic used to identify cores which are usable with each GRES weas incorrect. bug 905
-
Danny Auble authored
QOS had a GrpNodes set.
-
Danny Auble authored
-
- 24 Jun, 2014 1 commit
-
-
Morris Jette authored
Fix for core-based advanced reservations where the distribution of cores across nodes is not even. Failing test case: system has 10 nodes, 1 of which is fully occupied create reservation with 9 nodes and 10 cores always would fail with "busy nodes" error
-