- 01 Apr, 2019 2 commits
-
-
Morris Jette authored
This eliminates a slurmctld error message when a job shrinks to size zero. There is no need to re-compute the CPU count and the job_resources node_bitmap is empty. Logic works fine without this change if job size shrinks, but not to size zero. bug 6472
-
Morris Jette authored
When a job size was reset to zero, this error message was printed: slurm_allocation_lookup: Job/step already completing or completed which may lead the user to believe the operation failed when it worked as planned. Now it prints this: To reset Slurm environment variables, execute For bash or sh shells: . ./slurm_job_43565_resize.sh For csh shells: source ./slurm_job_43565_resize.csh Where the reset scripts contain zero node count information: export SLURM_NODELIST="" export SLURM_JOB_NODELIST="" export SLURM_NNODES=0 export SLURM_JOB_NUM_NODES=0 export SLURM_JOB_CPUS_PER_NODE="" unset SLURM_NPROCS unset SLURM_NTASKS unset SLURM_TASKS_PER_NODE
-
- 31 Mar, 2019 4 commits
-
-
Brian Christiansen authored
-
Brian Christiansen authored
Continuation of 2764f3fd Bug 6589
-
Brian Christiansen authored
Continuation of 9a243a1a Bug 6592
-
Brian Christiansen authored
-
- 30 Mar, 2019 1 commit
-
-
Morris Jette authored
Many comments were modified to follow Linux kernel standard Many log messages were using the old function name and now print __func__ instead A few log messages lacked the function name and those were added
-
- 29 Mar, 2019 2 commits
-
-
Morris Jette authored
No change in any logic
-
Morris Jette authored
This adds logic to validate the count of GRES by device Type and not just Name and modifies the data structures as needed for consistency within slurmctld.
-
- 28 Mar, 2019 3 commits
-
-
Morris Jette authored
-
Broderick Gardner authored
Removed linear search, replaced with direct record references and a hashmap. This is faster and avoids potential collisions between assoc id's and user id's. Bug 4811
-
Broderick Gardner authored
Fixed existing usages as well. Bug 4811
-
- 27 Mar, 2019 11 commits
-
-
Morris Jette authored
Coverity CID 197448 bug 6303
-
Morris Jette authored
Remove reference to REQUEST_SIGNAL_PROCESS_GROUP in slurmstepd. It has been defunct since July 2013
-
Morris Jette authored
sort the expected and actual output for GRES APIs irrelevant. Depending upon the GRES plugins loaded (specifically gres/gpu plus gres/mps), the GRES records can be sorted by File name to insure the GRES records line up (the same position in both lists should refer to the same device file).
-
Alejandro Sanchez authored
-
Dominik Bartkiewicz authored
Bug 6750.
-
Danny Auble authored
-
Morris Jette authored
This logic could allocate to a job a GRES device with an availability count of zero.
-
Morris Jette authored
-
Morris Jette authored
This should only happen if there is flawed logic somewhere, but avoiding an abort is better than not.
-
Morris Jette authored
If the count of GPUs configured in slurm.conf and gres.conf differ and FastSchedule>=1 then the bitmap identifying the GPU allocation sent from slurmctld to slurmd will differ. Previously this resulted in CUDA_VISIBLE_DEVICES being set to NULL. Now it will be set correctly. bug 6725
-
Morris Jette authored
If slurmd finds GRES with files and slurmctld can't use them (i.e. slurm.conf has a GRES count of 0), then avoid trying to create zero length bitmaps in the GRES data structure. bug 6725
-
- 26 Mar, 2019 15 commits
-
-
Morris Jette authored
This makes the gres bitmap size equal to the number of records for shared gres (i.e. gres/mps), otherwise it is the gres count (i.e. gres/gpu). bug 6733
-
Morris Jette authored
if the device files for gres/gpu are out of order or grouped in an unordered fashion (e.g. "Name=gpu Files=/dev/nvidia[2,8,10]") then split the gres/gpu records to one record per file and make sure the gres/mps records are in an identical order. Required for matching gres/gpu and gres/mps records (one GPU can be allocated either as gres/gpu or as gres/mps, but not both, so we need to be able to match records in slurmctld).
-
Morris Jette authored
Coverity CID 197447
-
Alejandro Sanchez authored
Bug 6710.
-
Marshall Garey authored
Bug 6590.
-
Morris Jette authored
Make some tests better able to work with CR_ONE_TASK_PER_CORE
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
More testing required. This configuration is still disabled in select_cons_tres.c
-
Morris Jette authored
Add --ntasks-per-core option to execute line as needed
-
Morris Jette authored
Without this change, test7.17 was failing
-
Morris Jette authored
Cosmetic change No change in logic
-
Morris Jette authored
cosmetic change only
-
Morris Jette authored
This can happen on node failure
-
Morris Jette authored
Use stored pointer rather than pointer to pointer for cleaner code. No change in logic.
-
- 25 Mar, 2019 2 commits
-
-
Broderick Gardner authored
Workaround involves specifying the index name when modifying an existing index. Bug 6303
-
Broderick Gardner authored
The correct use of correct_query and query is clarified here. Also adds saving the index name to parsing so correct_query can be set to the correct "drop <index name>" for future query. Bug 6303
-