system news

Due to problems with the /pfs/nobackup filesystem both Akka and Abisko batch systems have been suspended.

One of the file servers has a broken moderboard and needs to be replaced.
ETA of a new moderboard is 2012-04-19.

We will investigate the other file servers for potential HW problems before taking the filesystem online again.

If everything else is ok we will run the filesystem with reduced capacity in the meantime.

Sat, 2012-04-14 16:26 | Åke Sandgren

The login node on Akka crashed on Saturday(2012-03-30), which affected access to the GPFS file system on the login node.

The licensing rules for SIESTA has changed and it is now possible for us to make it available for all academic users.

Please read the licens information for SIESTA at  www. icmab.es/dmmis/leem/siesta/CodeAccess/academic-licence.html https://departments.icmab.es/leem/siesta/News/siesta-GPL.txt

Fri, 2012-03-23 16:26 | Åke Sandgren

Matlab 2011b is now available on both Abisko and Akka. 

See our MATLAB page for more information.

The problem with MATLAB and java on abisko has now be solved!

Wed, 2012-02-29 13:06 | Björn Torkelsson

Gaussian 09 revision C.01 is now available on Abisko too. It has been available on Akka for some time.

Please see the Release Notes for more information about the new release. Information about using Gaussian at HPC2N is available at our Gaussian support page.

The time to transition Abisko from the interim to the final system is here. During the
transition, Abisko will be unavailable starting from Wednesday February 15th 08:00. Assuming the transition goes smoothly, we expect to have the final system functional early next week.

During the migration from the interim system, we need to make a few changes that are disruptive to the cluster interconnect. The batch nodes will therefore not process any jobs from the above point in time until the transition is complete.

The final system of Abisko is now available and the queues have been restored. 

We still have some things to fix and tune so there may be some interruption the next couple of weeks.

Not all 318 nodes will be available at the moment. The interim system has not been upgraded to the new CPU:s and some other nodes are used for running some tests.

Some software may still be missing, but we are working on building them.

More information about Abisko can be found here:

Today, between 08:00 and 16:00, Abisko will be unavailable because we have to move around some hardware related to the installation of the final system of Abisko.

Update 15:00:

Abisko is now back online.

Mon, 2011-12-12 11:58 | Björn Torkelsson

We are currently having  some problems with GPFS, the parallel filesystem, which we are investigating.

The queues on all clusters have been stopped.

Update 12:46
The problematic disk has been suspended and new data will not be written to it any longer.
Old, not broken, data can still be read.
Data is being migrated away from the problematic disk.
We currently do not have an estimate of how long this will take.

The problem with the GPFS parallel filesystem (/pfs/nobackup) has now been solved.
We did not see any indications of lost or damages files during the recovery process.
However you are advised to check your files to be on the safe side.

Batch queues have been reactivated.

Fri, 2011-12-02 14:58 | Åke Sandgren