- 24 Jul, 2014 3 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
David Bigagli authored
the jobid string. Reuse the existing job_step_kill_msg_t structure.
-
- 23 Jul, 2014 1 commit
-
-
Morris Jette authored
-
- 22 Jul, 2014 4 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
David Bigagli authored
if no other command line options are specified.
-
David Bigagli authored
-
- 21 Jul, 2014 5 commits
-
-
Morris Jette authored
This is the infrastructure needed to modify a job array with the new job array data structures. There will need to be additional work once the RPC is fleshed out.
-
Morris Jette authored
Previously would not work properly if a job array to be canceled was partly running and partly pending
-
Morris Jette authored
-
Morris Jette authored
This is important for job array modifications. Log the job ID in the job record rather than in the modify request.
-
Morris Jette authored
-
- 16 Jul, 2014 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
For improved support of job arrays
-
- 15 Jul, 2014 6 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
-
David Bigagli authored
-
David Bigagli authored
which then kill the job or the job array.
-
Morris Jette authored
Added SchedulerParameters options of bf_max_job_array_resv to control how many tasks of a job array should have resources reserved for them.
-
- 14 Jul, 2014 3 commits
-
-
Morris Jette authored
Modify to work if the bitmap sizes of the job and user specification vary.
-
Morris Jette authored
-
Morris Jette authored
-
- 12 Jul, 2014 1 commit
-
-
Morris Jette authored
This adds a new function job_str_signal() which can be used to cancel/signal a job array using a single RPC rather than a series if RPCs, one per job record, which does not work with the new job array data structure. This new logic is untested.
-
- 11 Jul, 2014 1 commit
-
-
Morris Jette authored
-
- 07 Jul, 2014 7 commits
-
-
Morris Jette authored
Partitial fix for new job array data structure
-
Morris Jette authored
Fix squeue --array/-r option to print individual job array task records even if then are all in a single job record from slurmctld.
-
Morris Jette authored
-
Morris Jette authored
Change un/pack_bit_str() to pack_bit_str_hex(), which has much better scalability and performance.
-
Morris Jette authored
-
Morris Jette authored
set exit code on a failure mode previously ignored
-
Morris Jette authored
-
- 04 Jul, 2014 2 commits
-
-
Morris Jette authored
Move the formatting of a job array's task ID string from slurmctld to the client to reduce system overhead. There is logic in place to translate the full bitmap into a string, but in the worst case this can take roughly one minute (e.g. 1-1000000:2,2) so by default only the first 1024 bytes in the string are set. There is logic in the code to translate the full string, but commented out.
-
Morris Jette authored
-
- 03 Jul, 2014 5 commits
-
-
Morris Jette authored
Fix some anomalies in the main scheduling loop for job arrays Improve logging in the main scheduling loop for job arrays
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Now able to run job arrays based upon the new job array data structure.
-
Morris Jette authored
This adds logic to copy a job record for a job array when we actually schedule one of them. More work is still needed.
-