[Chtc-users] HPC Cluster issues resolved; users can resume normal cluster activity

[chtc-users@xxxxxxxxxxx]

Hello Again,

We have resolved the issues reported earlier (below) for the HPC Cluster, and there will be no need for cluster downtime tomorrow.

It is possible that access to some user files may have been temporarily interrupted. Our systems administrators will work tomorrow to fix the remaining file access issues, but please feel free to email chtc@xxxxxxxxxxx if you notice file access issues on the HPC Cluster that you would like addressed right away.

Best Wishes,

Your CHTC Team

(care of Lauren Michael, Research Computing Facilitator)

On Thu, Mar 5, 2015 at 2:36 PM, <chtc-users@xxxxxxxxxxx> wrote:

Greetings,

We have noticed a network issue on the HPC Cluster that may cause login failures for some users. While we are working to diagnose and address this issue, PLEASE minimize login attempts to the cluster until further notice.Â

If you absolutely need to log in to the cluster today, but experience a failure, please wait at least 30 minutes before attempting to log in again, as repeat login attempts will likely contribute further to the network issue. As far as we can tell, running and queued jobs should not be affected by the network issue we're seeing.

Depending on the outcome of our diagnostic work, we may need to take the cluster down at some point tomorrow and will provide more detail before that time. We will otherwise let users know when the login issue has been resolved, if we have solved it without the need for downtime tomorrow.

As always, please write to chtc@xxxxxxxxxxx if you have any questions or issues when using CHTC's HPC Cluster or any other CHTC compute system (like our HTCondor Pool).

Thank you,

Your CHTC Team

(care of Lauren Michael, Research Computing Facilitator)

_______________________________________________
Chtc-users mailing list
Chtc-users@xxxxxxxxxxx
To unsubscribe send an email to:
chtc@xxxxxxxxxxx
https://lists.cs.wisc.edu/mailman/listinfo/chtc-users