[slurm-users] No error/output/run

Mark Hahn hahn at mcmaster.ca
Wed Jul 24 16:21:27 UTC 2019


>> why not use sacct?  squeue is only for queued and running jobs.
>
> $ sacct -j 1277
>       JobID    JobName  Partition    Account  AllocCPUS      State ExitCode
> ------------ ---------- ---------- ---------- ---------- ---------- --------
> 1277          my_lammps    EMERALD        z55         12     FAILED      1:0
> 1277.batch        batch                   z55          3     FAILED      1:0
>
> While it says "failed", I don't see any error in the output log.

which implies that the job failed before creating the output file.
could you have a problem accessing the working directory on the compute
nodes?  over-quota even?  I would certainly examine the slurm logs on 
the compute nodes.

regards, mark hahn.



More information about the slurm-users mailing list