Leonardo: update on slurm controller issues and FAST storage resolution

Dear Users,

we would like to provide an update regarding the issues currently affecting Leonardo.

The problem on the $FAST filesystem has now been resolved, and the area is operating normally again.

However, we are still experiencing intermittent issues with the Slurm controller, which may temporarily become unresponsive. As a consequence, job submission and monitoring commands may occasionally fail or hang. In some cases, running jobs may also terminate unexpectedly without producing any output.

Our team is actively investigating the issue and working to restore full stability as soon as possible.

We apologise for the inconvenience and thank you for your patience and understanding.

Best regards,

HPC User Support – CINECA