old news

/pfs/nobackup full - PLEASE remove old files!

  • Posted on: 28 April 2016
  • By: admin

As some of you may have noticed the /pfs/nobackup filesystem is chock full. As a side effect of that the batch systems are holding off on starting new jobs.

This is due to a lot of users keeping old files in the filesystem.

Please note that even if you are using a smaller amount than your quota limit you are obliged to remove old files and strive to keep your filesystem usage as small as possible.

Reduced HPC2N support during Holiday Break

  • Posted on: 28 April 2016
  • By: admin

Due to the oncoming winter holidays, HPC2N will be providing reduced support from Saturday the 21st of December, until Wednesday the 1st of January. HPC2N resources will be fully available, but response to support tickets, emails and such may be delayed.

We thank you for your patience and on behalf of the HPC2N team wish you a happy winter holiday season!  

Thu, 2013-12-19 10:29 | Daniel Petersen

Abisko batch system server to be upgraded

  • Posted on: 28 April 2016
  • By: admin

The final system to be upgraded is the batch system server.

To do this we need to have the system completely stopped so as to not risk any jobs failing.
We have therefor created a reservation on the whole batch system starting on Monday 2013-12-16 08:00, which means that no jobs are allowed to be running past that point.

I.e. no jobs will be allowed to start unless they have a runtime which guarantees that thay have finished before that time.

Mon, 2013-12-09 13:52 | Åke Sandgren

Upgrade of Abisko's operating system has now started

  • Posted on: 28 April 2016
  • By: admin

We have now started migrating the first 2 racks of nodes to Ubuntu Precise.

The old login node will be stopped after lunch today (2013-11-22) and upgraded.
During the upgrade of the login node we recommend that you use the
abisko-precise.hpc2n.umu.se login node for accessing your files and rebuilding of any programs using new modules and compilers.

As mentioned previously all information is available at /resources/hardware/abisko/os-upgrade

Power failure at HPC2N

  • Posted on: 28 April 2016
  • By: admin

We have suffered an extended power failure early in the morning (2013-11-20) and HPC2N resources may have limited or no availability until everything is up and running again.

Update 09:30
Power is now restored.

Update 11:00
Unfortunately the network in the building is still not working properly so everything should still be considered down.

Update 13:55
Power and network are now classified stable again, and login access and clusters are back online.

Wed, 2013-11-20 10:25 | Lars Viklund

Pages

Updated: 2024-04-17, 14:47