- 18 Dec, 2013 2 commits
-
-
Andrew Elwell authored
Removed references to scripts that are no longer distributed with the sources.
-
Nathan Yee authored
-
- 17 Dec, 2013 4 commits
-
-
Danny Auble authored
Conflicts: src/slurmctld/proc_req.c
-
Danny Auble authored
It was found the realloc logic could result in Valgrind complaining of uninitialized data when doing a bit_fmt on the realloced bit structure. using xrealloc instead fixes the issue and makes things good, perhaps speeds things up as well.
-
Danny Auble authored
-
Danny Auble authored
will return ENOTCONN and not initialize the addr_str causing valgrind errors.
-
- 16 Dec, 2013 6 commits
-
-
Morris Jette authored
Conflicts: doc/html/team.shtml doc/man/man1/scontrol.1
-
Morris Jette authored
-
Morris Jette authored
-
Hughes, Doug authored
This allows multiple job ids to hold, uhold, resume, suspend, release, etc.
-
Morris Jette authored
Conflicts: testsuite/expect/test14.4
-
Morris Jette authored
-
- 14 Dec, 2013 8 commits
-
-
Danny Auble authored
-
Danny Auble authored
226b49a3
-
Danny Auble authored
-
Morris Jette authored
Test would periodically fail due to expect timing. This seems to fix the problem
-
David Bigagli authored
job.
-
Danny Auble authored
-
David Bigagli authored
-
David Bigagli authored
channel with the slurmstepd on that node.
-
- 13 Dec, 2013 13 commits
-
-
Morris Jette authored
Bug introduced earlier today in commit 8df024c1
-
Danny Auble authored
-
Morris Jette authored
Correction to bad merge of slurm-2.6 in commit 88220a2b
-
Morris Jette authored
Conflicts: src/slurmd/slurmstepd/task.c
-
Morris Jette authored
-
Morris Jette authored
Fix slurmstepd race condition when separate threads are reading and modifying the job's environment, which can result in the slurmstepd failing with an invalid memory reference. Observed at shutdown when trying to run the task epilog and trying to read the env var: SLURM_STEP_KILLED_MSG_NODE_ID
-
Morris Jette authored
Previously was allocating sizeof(char *) rather than sizeof(char), so we save some space here.
-
Morris Jette authored
We do not want to look at the core file, so avoid generating it and then having to manually clear it later.
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
- 12 Dec, 2013 7 commits
-
-
Morris Jette authored
-
Morris Jette authored
Without this flag, if the configuration changes or is inconsistent between nodes then the pack and unpack can be out of sync in terms of what data is expected. This will let server tell the client what data is packed.
-
Morris Jette authored
-
Morris Jette authored
Without this change, sstat would try to unpack accounting data that was never packed, resulting in message unpack errors.
-
Morris Jette authored
There were some parsing issues and the test was not as general as it should have been
-
Danny Auble authored
-
Danny Auble authored
-