Skip to main content

[Resolved] Problems with GPFS; logins and jobs may be affected

Posted by on Wednesday, November 7, 2018 in Cluster Status Notice.

Update, 3pm:

/home is back online. Please check your jobs’ output very carefully as it is likely that many will need to be re-run, especially if they were performing I/O to or from /home. Jobs performing I/O to /scratch, /data, or /dors may have survived.

Please open a helpdesk ticket with us if you have any questions or concerns.

Shortly after the maintenance completed this morning we began to experience problems on our /home GPFS filesystem. This will impact logins and many jobs, but /scratch, /data, and /dors remain available if needed. We have a severity level 1 ticket open with IBM and are working to troubleshoot as quickly as possible. We will send an update once we have more information to share.