Commit Graph

379 Commits

Author SHA1 Message Date
e1b15035cc fix: fix dnsmasq for the obx domain 2025-10-01 09:04:44 +02:00
981eda082c Merge branch 'main' of gitlab.com:oceanbox/clusterfck 2025-10-01 09:02:31 +02:00
2bf922fb6d feat: set up the raid10 device on /work 2025-10-01 09:02:24 +02:00
Jonas Juselius
f6db232ca7 fix: move sudo settings from hpc module to actual nodes 2025-09-28 12:30:56 +02:00
Jonas Juselius
8c5ca68530 Merge branch 'main' of gitlab.com:oceanbox/nixos-clusters 2025-09-28 08:49:34 +02:00
Jonas Juselius
d481f6789c fix: disable tailscale dns 2025-09-28 08:49:26 +02:00
43547f45de fix: disable tailscale dns on login and manage 2025-09-28 08:48:35 +02:00
7be10b4457 fix: fix reuid-slurm.sh 2025-09-27 17:42:22 +02:00
Jonas Juselius
be13a10c8f fix: remove keys from git and share keys at toplevel 2025-09-27 16:13:16 +02:00
Jonas Juselius
799cb6cae1 fix: add 8.8.8.8 to ekman dnsmasq 2025-09-27 16:06:08 +02:00
eabb600641 Merge branch 'main' of gitlab.com:oceanbox/clusterfck 2025-09-27 16:01:07 +02:00
bc1ce00610 fix: add 8.8.8.8 to list of dnsmasq servers 2025-09-27 16:00:56 +02:00
Jonas Juselius
6d3d18bbe0 fix: remove extra msmtp stanza 2025-09-27 15:59:12 +02:00
Jonas Juselius
30d0180b59 feat: use central, off-site slurmdbd 2025-09-27 15:57:48 +02:00
Jonas Juselius
680330d569 fix: unify ekman c0 and c0x 2025-09-27 15:57:11 +02:00
e6cf1f6232 Merge branch 'main' of gitlab.com:oceanbox/clusterfck 2025-09-27 14:04:11 +02:00
caab89f642 feat: use central sulrmdbd, and misc fixes 2025-09-27 14:03:51 +02:00
a981f5e7ba fix: fix slurm and munge uid:s and gid:s 2025-09-27 13:42:38 +02:00
34c28e18bf fix: move bin to toplevel and add reuid-slurm.sh 2025-09-27 13:42:09 +02:00
Jonas Juselius
5dfc0743eb Merge branch 'main' of gitlab.com:oceanbox/nixos-clusters 2025-09-26 16:03:47 +02:00
398af17797 fix: slurm updates for rossby 2025-09-26 16:03:31 +02:00
998d551943 fix: use jwt, simplify slurmrestd, and make slurmdbd optional 2025-09-26 16:02:30 +02:00
Jonas Juselius
b2bf32dc73 fix: fix tailscale routing, etc. 2025-09-26 15:54:24 +02:00
Jonas Juselius
312b3906ab fix: disable raid on fs-backup (for now) 2025-09-26 15:53:46 +02:00
c9624213ed fix: fix slurmdbd setup 2025-09-25 15:52:30 +02:00
bcff2e6c2f Merge branch 'main' of gitlab.com:oceanbox/clusterfck 2025-09-25 12:38:44 +02:00
3c0a7f91f5 fix: slurm and stuff 2025-09-25 12:28:59 +02:00
46cf9da93f feat: allow tailnet access 2025-09-25 12:16:42 +02:00
2e919182d4 fix: remove /opt/singularity 2025-09-25 12:16:24 +02:00
ff3f897859 fix: rename features for better clarity 2025-09-25 12:15:51 +02:00
9b798444d1 feat: enable slurm jwt and remove slocket proxy 2025-09-25 12:15:24 +02:00
d2e27a7e87 feat: add slurm key generators and remove stale scripts 2025-09-25 12:08:05 +02:00
Jonas Juselius
d5cfcd2bf9 fix: reset systemd slurmrest socketConfig to true 2025-09-24 15:22:33 +02:00
Jonas Juselius
cf4ae97e1c feat: ekman on new cluster setup 2025-09-24 12:24:28 +02:00
Jonas Juselius
96f8215c52 feat: upgrade ekman to new cluster structure 2025-09-23 13:40:16 +02:00
Jonas Juselius
46473c88dd Merge branch 'main' of gitlab.com:oceanbox/nixos-clusters 2025-09-23 12:59:13 +02:00
fac7bdd62e fix: change feature manager to manage 2025-09-23 12:58:57 +02:00
Jonas Juselius
e38b0a2317 fix: change /frontend to /users 2025-09-23 12:30:18 +02:00
82a5328d7f feat: move /home and /opt to cephfs and tweak mounts 2025-09-23 12:11:53 +02:00
8894339216 fix: enable 100GbE and disable net mounts for now 2025-09-16 13:45:37 +02:00
f5679d39f9 fix: add missing nodes and disable net mounts for now 2025-09-16 13:43:00 +02:00
59db74b265 fix: misc fixes and tweaks 2025-09-16 13:42:25 +02:00
65aba0f69d fix: update Mellanox firmware tools 2025-09-16 13:41:01 +02:00
db794e6eea fix: fix extraSANs 2025-09-13 10:13:12 +02:00
4057a00143 fix: /work mount 2025-09-13 07:31:45 +02:00
14b5f07cc6 fix: move apiserver port to standard 6443 on (new) ekman 2025-09-13 07:11:04 +02:00
33a14d1509 fix: move IB network to 10.1.6.0/24 (get it? :) 2025-09-13 07:10:25 +02:00
3af5ba3fbd fix: add fs-work and etcd cluster 2025-09-13 07:03:17 +02:00
6767eb21e6 fix: move apiserver port to standard 6443 2025-09-13 07:00:49 +02:00
eb7b1f8130 fix: fix ekman part of botched merge 2025-09-12 14:38:36 +02:00