Mahuika Slurm controllers are unreachable

Incident Report for NeSI Status

Resolved

This networking issue has also been resolved

Posted May 06, 2024 - 12:53 NZST

Monitoring

Slurm commands are now running in a more timely fashion, whilst we continue to run diagnostics

Posted Apr 29, 2024 - 17:02 NZST

Investigating

We are currently investigating an issue with Slurm on Mahuika which started at approx 11.10am. Slurm commands that need to connect to the relevant Slurm controllers (squeue, sinfo, sbatch are failing with timeouts.).

Posted Apr 29, 2024 - 12:00 NZST

This incident affected: Submit new HPC Jobs and Jupyter on NeSI (beta).