Dear users,

The checks at the RAID and storage target level of the /work partition have now been successfully completed. We are currently running consistency checks at the distributed file system level to ensure the full resilience of the storage.

As part of this recovery process, we are also planning a full stop of the cluster either later today or tomorrow in order to improve the electrical protection of the storage servers. We will communicate the exact time of this intervention as soon as it is defined.

During this downtime, all services - including storage, login nodes, production nodes, and virtualization services - will be unavailable. The interruption is expected to last around one hour. After this maintenance, our plan is to release the cluster back in full production.

Thank you for your understanding and collaboration.

Best regards,
Lorenzo and Federico