- 24 Dec, 2003 2 commits
- 23 Dec, 2003 6 commits
-
-
Moe Jette authored
see memory leaks.
-
Moe Jette authored
(it grows anyway). Fix state read logic to better handle error conditions.
-
Moe Jette authored
Fix update node RPC to handle reason field change without state change. State was being handled as type int instead of uint16_t so NO_VAL check was not working properly.
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
"Scontrol abort" works. It was leaving a hung pthread due to a recent change. Fix a couple of potential memory leaks "switch_type" has been added to config data structure, un/pack, etc, but not yet reported to the user or documented yet. The plugins now use function calls to get a their type and plugin directory from a common data structure rather than individually reading and parsing the configuration file.
-
- 22 Dec, 2003 3 commits
- 20 Dec, 2003 4 commits
-
-
Mark Grondona authored
-
Mark Grondona authored
-
Mark Grondona authored
-
Mark Grondona authored
-
- 19 Dec, 2003 3 commits
-
-
Mark Grondona authored
-
Mark Grondona authored
(as well as the reverse) in all qsw code. - move elanhosts.[ch] to common - initialize elanhost_config on demand in qsw.c - remove calls to elanhosts in slurmd/elan_interconnect.c - merge libhostlist into libcommon since elanhosts needs it.
-
Moe Jette authored
-
- 18 Dec, 2003 3 commits
- 17 Dec, 2003 1 commit
-
-
jwindley authored
-
- 15 Dec, 2003 4 commits
- 12 Dec, 2003 8 commits
-
-
Mark Grondona authored
o set exit code to 1 if any tasks failed
-
Mark Grondona authored
-
Mark Grondona authored
to srun or slurmctld. o new errno ESLURMD_UID_NOT_FOUND
-
jwindley authored
-
Moe Jette authored
functions, but only for a single task. Multi-task support will need to wait for modifications to srun and its communications protocol.
-
Mark Grondona authored
-
Mark Grondona authored
-
Mark Grondona authored
-
- 11 Dec, 2003 6 commits
-
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
sharing via node record of job count (0 | 1) and bitmap of nodes which permit sharing. Previous logic could permit a job accepting shared nodes to be scheduled on a node that already had a running job not accepting shared nodes.
-
Moe Jette authored
Just log open failure and continue.
-