- 27 Sep, 2003 3 commits
-
-
Mark Grondona authored
-
Moe Jette authored
-
Moe Jette authored
-
- 26 Sep, 2003 1 commit
-
-
Moe Jette authored
Was overwritting data off of buffer passed as argument.
-
- 25 Sep, 2003 10 commits
-
-
Mark Grondona authored
o Use hostname instead of ip addr string in MPIR_proctable to allow TotalView bulk launch capability. o Add --jobid option to srun
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
ranged string rather than one message per node (too verbose).
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
node begins to respond again.
-
Moe Jette authored
lowest active job priority (for working down as new jobs are initiated). This bug only applies when slurmctld restarts and there are jobs in system hold state (priority 1).
-
Moe Jette authored
-
Moe Jette authored
This is a problem on PVC, where nodes are regularly DRAINED.
-
- 24 Sep, 2003 3 commits
-
-
jwindley authored
-
jwindley authored
-
Mark Grondona authored
srun erroneously expected replies from these hosts (gnats:291)
-
- 23 Sep, 2003 5 commits
-
-
Mark Grondona authored
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
scalability. An arbitrary number of requests may be queued and they are processed one per second until the queue is empty or pending requests were last attempted recently (configuration parameters set to 60 seconds as a minimum retry interval).
-
Moe Jette authored
These jobs are reported by slurmd on node registration. They are logged but otherwise ignored by slurmctld. Several changes to slurmd logging messaged to report job id and step id using %u format rather than %d format (which shows no-allocate job id values as negative numbers).
-
- 22 Sep, 2003 2 commits
- 21 Sep, 2003 11 commits
-
-
Moe Jette authored
--relative option is lower than the node count specified. The --relative option takes precedence.
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
that reach the slurm inactivity time limit.
-
Moe Jette authored
control (it needs to complete all pending RPCs and save state before the primary reads state and takes over).
-
Moe Jette authored
responsibilities (backup was routinely reading at startup).
-
Moe Jette authored
server to shutdown request.
-
Moe Jette authored
SIGPWR, and SIGLOST.
-
Moe Jette authored
and when returned to service went improperly back into state DRAINING (job counter was inconsistent).
-
Moe Jette authored
transition to DRAINED state.
-
- 20 Sep, 2003 5 commits
-
-
Moe Jette authored
data will not be used and the process is too slow anyway.
-
Moe Jette authored
EPILOG_COMPLETE_MESSAGE. At this time the job is COMPLETED and all associated nodes available.
-
Mark Grondona authored
-
Moe Jette authored
-
Mark Grondona authored
on nodes relative to the current allocation. o srun no longer sends SIGKILL to job if one task is killed except if --no-allocate is used. (the job will otherwise be killed by the controller anyway)
-