GPFS filesystem Problem on Oct 24 2019
We are having issues with GPFS filesystem (both project and scratch) on all clusters. OnDemand is also down.
We are having issues with GPFS filesystem (both project and scratch) on all clusters. OnDemand is also down.
The scratch filesystem has been returned to service.
Data on /fs/scratch is accessible now.
We fixed the problem with both project and scratch filesystem and the service has been restored.
We fixed the problem with both project and scratch filesystem.
Updated on 2:30pm Feb 1st:
Scratch filesystem is back. OnDemand is also available now.
Original Post:
Scratch filesystem is down now. Users can not access OSC OnDemand as well. Please use other methods to connect to OSC systems. We are working to fix this issue now and apologize for any inconvenience. Please contact OSC Help if you have any questions.
NFS outage on Thursday, Jan 17 from 7 am to 8 am
OSC is experiencing some problems with the Project and Scratch filesystems that are resulting in some jobs seeing "stale file handles". We are investigating the problem and will provide updates as we have them. Job scheduling is currently paused on all filesystems.
We are working with vendor engineers to resolve the issue, but you can currently still log in via SSH and access your files in your home directories. OnDemand logins will likely hang, and attempts to access files on Project or Scratch will likely fail.
All the services are back.
ACEs of a file in the user's home directory will be lost using vim
or cp