Skip to content

Latest commit

 

History

History
37 lines (27 loc) · 1.03 KB

troubleshooting.md

File metadata and controls

37 lines (27 loc) · 1.03 KB
Raw

Notebook, Running

Exception: slurmdbd is running

Exception: slurmdbd is running. Previous simulation might still be up. Kill the process if you sure that it shouldn't be up.

Solution: kill slurmdbd

>ps -Af 
UID        PID  PPID  C STIME TTY          TIME CMD
slurm      539     1  4 21:24 ?        00:00:12 /opt/slurm_sim/sbin/slurmdbd -Dvv
slurm     1245  1021  0 21:28 pts/2    00:00:00 ps -Af
> kill -9 539

slurmctld

Fatal Errors

slurmctld: fatal: Unable to determine this slurmd's NodeName

FrontEndName can not be resolved

FrontEndName=bumblebee

slurmdbd: fatal: slurmdbd.conf file /home/slurm/work/micro_cluster/etc/slurmdbd.conf should be 600 is 644 accessible for group or others

slurmdbd: fatal: slurmdbd.conf file /home/slurm/work/micro_cluster/etc/slurmdbd.conf should be 600 is 644 accessible for group or others

chmod 600 /home/slurm/work/micro_cluster/etc/slurmdbd.conf

@TODO: add permission checking to slurmsim -v run_sim @TODO: add checking that slurmdbd started