HPC Cluster outage postponed

[chtc-users@xxxxxxxxxxx]

Greetings CHTC users, 

 

The planned maintenance and HPC cluster outage anticipated for this Thursday (2/17) (see our original announcement below) has been postponed.

We do not yet know the new maintenance date, but will notify CHTC users via this list once we have that information. 

 

Best,

Your CHTC team

 

 

From: CHTC-users <chtc-users-bounces@xxxxxxxxxxx> on behalf of chtc-users--- via CHTC-users <chtc-users@xxxxxxxxxxx>
Reply-To: "chtc@xxxxxxxxxxx" <chtc@xxxxxxxxxxx>
Date: Monday, February 14, 2022 at 5:05 PM
To: chtc-users--- via CHTC-users <chtc-users@xxxxxxxxxxx>
Cc: "chtc-users@xxxxxxxxxxx" <chtc-users@xxxxxxxxxxx>
Subject: HPC Cluster Outage this Thursday (2/17)

 

Greetings CHTC Users,

 

Due to maintenance for the cooling infrastructure in one of CHTCâs server rooms, we will have a scheduled HPC cluster outage this Thursday (2/17). 

 

The HPC cluster, including execute nodes, head nodes, and filesystem, will be down starting at 6:00am on Thursday (2/17) with services expected to be restored by the end of the day. Only the HPC cluster should be impacted due to this outage; we do not expect it to impact our HTC system.

 

The HPC cluster is configured to not start new jobs that will not complete before the start of the scheduled downtime. Already-running jobs that do not complete by Thursday morning will be interrupted and re-queued once systems are operational. Users may want to remove any jobs that will be negatively impacted by this process. 

 

As always, email us at chtc@xxxxxxxxxxx with any questions. 

 

Regards,

Your CHTC Team