Mesabi Retirement

After nearly a decade of service to researchers at the University of Minnesota, the Mesabi computing cluster will be retired on June 5, 2024 and MSI’s clusters will be reconfigured during Summer 2024. The Mangi nodes, which have been attached to Mesabi, will remain in service and be attached to Agate under the new arrangement. Agate will also be expanded with newly purchased nodes, including more nodes with GPUs, later in 2024.

Impacts for MSI users

SLURM Partitions:

SLURM Partitions retiring on June 5:

• large

• ram256g

• ram1t

• k40

• max

SLURM Partitions changing on June 5:

• small -> retargeting to Agate as amdsmall

Software:

• MSI has been rebuilding some software targeting Mesabi as needed, some modules have been rebuilt due to the change of operating system (see below).

• The Agate cluster had its operating system upgraded on May 1, 2024, from Centos7 to Rocky8 due to Centos7 reaching end-of-life. The nodes on the Mangi extension to Mesabi will be upgraded as part of their move over to the Agate cluster.

  • Two solutions for modules that can’t run on Rocky8: rebuild in the new Rocky 8 environment, or have a compatibility layer via an apptainer image

  • Details about using the apptainer workaround for old CentOS 7 applications which are not working on Rocky 8 can be found on this OS transition page: https://msi.umn.edu/news-and-events/msi-news/rocky8-transition