Incident on CINECA services on June 13th

Dear Users,
Due to a sudden infrastucture malfunction happened on Friday, June 13th at around 8:40 am, several services, including UserDB, SSO authentication, CINECA HPC website and the ticketing system, have been offline for several hours. The services started resuming during the afternoon, and are now almost completely in production.

The HPC clusters have been functioning properly during the incident. It was not possible to download the certificate to access the clusters, but your previously submitted jobs were still running. Unfortunately, the mail service linked to our ticketing system is still recovering, so at the moment we are not able to see the tickets opened yesterday or any reply to previously opened tickets. We are investigating to understand if the ticket traffic can be recovered or was lost because of the incident; we kindly ask you to wait for further updates before submitting new tickets or replying to existent ones.

We keep working to a full restore of the services and we expect to return fully operational during the weekend.

We apologize for the inconvenience.

Best regards,
HPC User Support – CINECA