BwUniCluster2.0/Maintenance/2023-03
Jump to navigation
Jump to search
The following changes were introduced during the maintenance interval between on 20.03.2023 (Monday) 08:30 and 24.03.2023 (Friday) 15:00.
The host key of the system has not changed. You should not receive any warnings by your SSH client(s), but if there should be a warning or if you want to check that you are connecting to the correct system, you can verify the key hashes using the following list:
| Algorithm | Hash (SHA256) | Hash (MD5) |
|---|---|---|
| RSA | p6Ion2YKZr5cnzf6L6DS1xGnIwnC1BhLbOEmDdp7FA0 | 59:2a:67:44:4a:d7:89:6c:c0:0d:74:ba:3c:c4:63:6d |
| ECDSA | k8l1JnfLf1y1Qi55IQmo11+/NZx06Rbze7akT5R7tE8 | 85:d4:d9:97:e0:f0:43:30:6e:66:8e:d0:b6:9b:85:d1 |
| ED25519 | yEe5nJ5hZZ1YbgieWr+phqRZKYbrV7zRe8OR3X03cn0 | 42:d2:0d:ab:87:48:fc:1d:5d:b3:7c:bf:22:c3:5f:b7 |
Hardware
- All firmware versions on all components were upgraded.
Operating system
- The operating system was upgraded from RHEL 8.4 EUS to RHEL 8.6 EUS. We recommend to re-compile all applications after the upgrade.
- The Mellanox OFED InfiniBand Stack was updated.
Compilers, Libaries and Runtime Environments
Userspace tools
- pigz and pbzip are not supported anymore. Please use pzstd instead.
Software Modules
- The Lmod module system was upgraded.
- Old openmpi 4.0 modules were removed. Please use openmpi 4.1.
Batch system
- The Slurm version was upgraded to version 23.02.0.
- The Slurm partitions have changed:
- multiple and multiple_il maximum number of nodes is now 80
- the amount of available nodes in partition single has been increased
- the amount of available nodes in partition multiple has been decreased
Storage
- Lustre client, BeeGFS client and Spectrum Scale client were updated.
Graphics stack
- The NVIDIA driver was upgraded.
Containers
- Enroot was upgraded.
- Singularity was replaced with its successor Apptainer. (the command 'singularity' still works)
JupyterHub
- Jupyterhub was upgraded to version 3.1.1
- python3.9 is now used as the default
Resource Limits on Login Nodes
- After the maintenance the following per-user limits apply (via cgroups):
- 48 GB phyisical memory
- 400% CPU cycles (100% equals 1 thread)