45 Commits

Author SHA1 Message Date
33155fcb62 Enable netboot again for PXE 2025-10-01 16:40:16 +02:00
6e89b3f936 Specify the disk by path 2025-10-01 16:40:16 +02:00
f0f67f374e Prepare lake2 config after bootstrap
The disk ID is different under NixOS.
2025-10-01 16:40:16 +02:00
7443a192c6 Add lake2 bootstrap config 2025-10-01 16:40:16 +02:00
3c83996e26 Add agenix to PATH in hut 2025-10-01 16:40:16 +02:00
a4fc3d131a Store ceph secret key in age
This allows a node to mount the ceph FS without any extra ceph
configuration in /etc/ceph.
2025-10-01 16:40:16 +02:00
660a8ae163 Add rarias key for secrets 2025-10-01 16:40:16 +02:00
91270b26bb Add ceph metrics to prometheus 2025-10-01 16:40:16 +02:00
94ce6fedf9 Mount the ceph filesystem in hut 2025-10-01 16:40:16 +02:00
817c98d37b Add ceph config in bay 2025-10-01 16:40:16 +02:00
9cd013c4ed Add the bay host name 2025-10-01 16:40:16 +02:00
f707650724 Remove netboot and fixes 2025-10-01 16:40:15 +02:00
9c152ec9cc Add bay node 2025-10-01 16:40:15 +02:00
8fcb5a1079 Monitor power from other nodes via LAN 2025-10-01 16:40:15 +02:00
b80656228d Increase prometheus retention time to one year 2025-10-01 16:40:15 +02:00
cd6e6de2ad Don't set all_proxy 2025-10-01 16:40:15 +02:00
ae2007e2fe Allow access to devices for node_exporter 2025-10-01 16:40:15 +02:00
d8e366b444 GRUB version no longer needed 2025-10-01 16:40:15 +02:00
8c1bf6db42 Kill slurmd remaining processes on upgrade 2025-10-01 16:40:15 +02:00
a094093d95 koro: Add vlopez user 2025-10-01 16:40:15 +02:00
cbe53a6f0a Add koro node 2025-10-01 16:40:15 +02:00
1b8c3eb554 eudy: Add fcsv3 and intermediate versions for testing 2025-10-01 16:40:15 +02:00
c0335c1f95 eudy: Enable memory overcommit 2025-10-01 16:40:15 +02:00
d5857c0f7d eudy: disable all cpu mitigations 2025-10-01 16:40:15 +02:00
9097811cc0 Enable NTP using the BSC time server 2025-10-01 16:40:15 +02:00
83acd40880 Add the ssfhead node as gateway 2025-10-01 16:40:15 +02:00
ba75bf8249 Use our host names first by default 2025-10-01 16:40:15 +02:00
e9845cc76a Add DNS tools to resolve hosts 2025-10-01 16:40:15 +02:00
d5951483ee Lower perf_event_paranoid to -1 2025-10-01 16:40:15 +02:00
937d8a7637 Set perf paranoid to 0 by default 2025-10-01 16:40:15 +02:00
798e01f9e6 Add perf to packages 2025-10-01 16:40:15 +02:00
2ca7e7383e Allow srun to specify the cpu binding
The task/affinity plugin needs to be selected.
2025-10-01 16:40:15 +02:00
b610f12133 Move authorized keys to users.nix 2025-10-01 16:40:15 +02:00
b6aaeb8158 Add rpenacob user 2025-10-01 16:40:15 +02:00
3d0f86ac07 Add osumb to the system packages 2025-10-01 16:40:15 +02:00
45d7b31c0a Use explicit order in overlays 2025-10-01 16:40:15 +02:00
bae3c75222 Add mpich overlay 2025-10-01 16:40:15 +02:00
f51e910aff Add coments in slurm config 2025-10-01 16:40:15 +02:00
8b7ffc914a Add eudy host key to known hosts 2025-10-01 16:40:15 +02:00
afb2bea1c9 Rename xeon08 to eudy
From Eudyptula, a little penguin.
2025-10-01 16:40:15 +02:00
4afe3121e6 Add ssh host keys 2025-10-01 16:40:15 +02:00
39f15a1b4f Set the name of the slurm cluster to jungle 2025-10-01 16:40:15 +02:00
3fab341dc8 Change owl hostnames 2025-10-01 16:40:15 +02:00
6ec7353a27 Add owl and all partition 2025-10-01 16:40:15 +02:00
d679fd6314 Simplify flake and expose host pkgs
The configuration of the machines is now moved to m/
2025-10-01 16:40:15 +02:00