- 24 Jun, 2017 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
- 21 Jun, 2017 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
- 20 Jun, 2017 4 commits
-
-
Morris Jette authored
The launch for pack-job 1+ fails in api/step_launch.c slurm_step_launch_add() right now, but the logic in srun seems OK.
-
Morris Jette authored
-
Morris Jette authored
The job allocation response does not include the time limit and it would not be used later in the srun logic anyway.
-
Morris Jette authored
Rather than the launch plugins directly access srun's "opt" options data structure, pass a pointer to the options specifications for that particular portion of a heterogeneous job.
-
- 19 Jun, 2017 2 commits
-
-
Morris Jette authored
Fix some parsing issues with respect to memory management, avoid memory over-writing and double free Create one step per pack job (no work on launch yet)
-
Morris Jette authored
Needed to copy some strings to avoid memory corruption
-
- 15 Jun, 2017 5 commits
-
-
Morris Jette authored
Fix problem reported by Clang
-
Morris Jette authored
Validate allocation against request for pack jobs Set some pack job environment variables
-
Morris Jette authored
Without this, terminating srun with ctrl-c will leave job allocation around
-
Morris Jette authored
-
Morris Jette authored
-
- 14 Jun, 2017 4 commits
-
-
Morris Jette authored
srun --test-only option functional for pack jobs
-
Morris Jette authored
-
Morris Jette authored
Document which srun-specific options will be propagated between job steps rather than reset. Also propagate checkpoint options for consistency with sbatch.
-
Morris Jette authored
It is needed by the perl APIs
-
- 13 Jun, 2017 4 commits
-
-
Morris Jette authored
This is just phase 1 of the parsing changes required for srun to support pack jobs
-
Morris Jette authored
This will route a heterogeneous job submitted to multiple clusters to the one cluster able to start all compoments fastest.
-
Morris Jette authored
-
Morris Jette authored
-
- 08 Jun, 2017 5 commits
-
-
Morris Jette authored
-
Morris Jette authored
salloc was failing to report the "Granted job allocation #" message and on termination was only deleting the last pack job component.
-
Morris Jette authored
-
Morris Jette authored
Fix problems reported by valgrind, several memory leaks and one memory reference after free.
-
Morris Jette authored
This is needed to support requeue and other operations on the pack job as a whole
-
- 07 Jun, 2017 10 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Make sure the pack_job_id values match, just in case something bad happended with the job records. If they don't match, log an error and skip the records.
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Always start the script in the correct component's allocation and get the script from the corrrect location (could work before but dependent upon race condition).
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
If num_tasks == NO_VAL but min_cpus != NO_VAL, then num_cpus gets reset to NO_VAL, which results in select/cons_res getting stuck in a very slow loop (counting up to NO_VAL).
-
Morris Jette authored
-
- 06 Jun, 2017 2 commits
-
-
Morris Jette authored
There are a couple more left to handle
-
Morris Jette authored
Copy the strings into job request descriptor rather than just copying the variable pointers to avoid over-writing contents
-