Jobs Remaining Idle, Maintenance to HTC System Underway


Date: Mon, 22 Aug 2022 19:10:20 +0000
From: chtc-users@xxxxxxxxxxx
Subject: Jobs Remaining Idle, Maintenance to HTC System Underway

Dear CHTC users, 

 

In a previous email (copied below), we notified users of scheduled maintenance to our HTC and HPC systems tomorrow, August 23rd. We have the following updates regarding impacts to jobs:  

 

HTC System (submit1, submit2): 

  • In preparation for this maintenance on the HTC system, we prevented new jobs from starting as of Friday afternoon, resulting in most jobs remaining “idle” over the weekend. 
  • Due to this preparation, the HTC system is now ready for maintenance and so we have started working on the HTC system today, August 22nd. We expect for maintenance on this system to be mostly completed by this evening, and jobs to resume matching shortly after. 

 

HPC Cluster (hpclogin1, hpclogin2): 

  • As of last week, a “maintenance reservation” on the HPC cluster prevented jobs from starting if they would not finish before August 23. 
  • Maintenance for our HPC system is still scheduled for tomorrow, August 23rd. 

 

Contact chtc@xxxxxxxxxxx with any questions. 

 

Best, 

Your CHTC Team

 

From: CHTC-users <chtc-users-bounces@xxxxxxxxxxx> on behalf of chtc-users--- via CHTC-users <chtc-users@xxxxxxxxxxx>
Date: Thursday, August 11, 2022 at 8:35 AM
To: chtc-users <chtc-users@xxxxxxxxxxx>
Cc: chtc-users@xxxxxxxxxxx <chtc-users@xxxxxxxxxxx>
Subject: Disruptions to CHTC systems on Tues, Aug 23

Greetings CHTC users, 

 

On Tuesday, August 23, many different components of CHTC systems will be updated with a needed operating system patch. We anticipate disruptions across all CHTC services, including (but not limited to) the submit servers and /staging file space on the HTC system as well as the login nodes and home directories on the HPC cluster. 

 

Potential issues that may occur include: 

  • Not being able to log in
  • Job failures due to not being able to read or write files
  • Job interruptions due to login node maintenance

 

This is also an opportune time to remind all CHTC users that our file systems are not backed up and it is your responsibility to make backups of important files and to move files that you are no longer using off CHTC systems. 

 

Please contact us at chtc@xxxxxxxxxxx with any questions or concerns in advance of this planned maintenance.

 

Best, 

Your CHTC team

[← Prev in Thread] Current Thread [Next in Thread→]