- 04 Jul, 2003 4 commits
-
-
Moe Jette authored
nodes which are also in completing or down state.
-
Moe Jette authored
Create the job hash table at slurmctld initialization.
-
Moe Jette authored
WaitTime sets srun's default value for --wait. MaxJobCount sets the maximum job count for slurmctld (replacing #define MAX_JOB_CNT). MinJobAge sets the minimum job purrge age for slurmctld (replacing #define MIN_JOB_AGE).
-
Moe Jette authored
-
- 03 Jul, 2003 5 commits
- 02 Jul, 2003 4 commits
-
-
Mark Grondona authored
-
Mark Grondona authored
-
Moe Jette authored
-
Moe Jette authored
with sinfo.
-
- 01 Jul, 2003 10 commits
-
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
the node is DOWN. This gets cleaned up when the KILL_JOB RPC gets issued.
-
Moe Jette authored
-
Moe Jette authored
-
Moe Jette authored
job, step, node, and partition info. Add new function to free slurm_credential from RPC response.
-
Moe Jette authored
job, step, node, and partition info.
-
Mark Grondona authored
-
Mark Grondona authored
-
Moe Jette authored
-
- 30 Jun, 2003 4 commits
- 28 Jun, 2003 3 commits
-
-
Moe Jette authored
-
Moe Jette authored
-
Mark Grondona authored
-
- 27 Jun, 2003 5 commits
-
-
Mark Grondona authored
o session manager waits for processes in its session, not just children. This fixes a problem when tasks are being attached to by a debugger. o Add elanhosts.[ch] for Elan host config file parsing. Used in slurm to install ElanID/hostname pairs into the kernel. Note that the format of the elanhosts config file has changed.
-
Moe Jette authored
-
Mark Grondona authored
-
Moe Jette authored
but don't wait for any reply. We remove the DOWN node from the job's bitmap. As soon as the other nodes complete the KILL_JOB RPC, the job transistions to some COMPLETED state.
-
Moe Jette authored
-
- 26 Jun, 2003 1 commit
-
-
Moe Jette authored
-
- 25 Jun, 2003 2 commits
-
-
Moe Jette authored
If a node is down and not responding, don't bother to send a KILL_JOB RPC to it. If that is the only node associated with a job, don't have that job go through a COMPLETING state. It goes directly to a COMPLETED state. Also preserve the NO_RESPOND flag associated with a node if its state is changed via user request (e.g. scontrol).
-
Moe Jette authored
-
- 24 Jun, 2003 2 commits