53 Commits

Author SHA1 Message Date
cd3284d1b2 Split xeon specific configuration from base
To accomodate the raccoon knights workstation, some of the configuration
pulled by m/common/main.nix has to be removed. To solve it, the xeon
specific parts are placed into m/common/xeon.nix and only the common
configuration is at m/common/base.nix.

Reviewed-by: Aleix Roca Nonell <aleix.rocanonell@bsc.es>
2024-06-03 09:20:11 +02:00
91a42375e3 Control user access to each machine
The users.jungleUsers configuration option behaves like the users.users
option, but defines the list attribute `hosts` for each user, which
filters users so that only the user can only access those hosts.

Reviewed-by: Aleix Roca Nonell <aleix.rocanonell@bsc.es>
2024-06-06 14:06:33 +02:00
df5a5e1668 Move slurm client in a separate module
Reviewed-by: Rodrigo Arias Mallo <rodrigo.arias@bsc.es>
2024-02-09 11:14:34 +01:00
f78f1a3ce6 Use tmpfs in /tmp
The /tmp directory was using the SSD disk which is not erased across
boots. Nix will use /tmp to perform the builds, so we want it to be as
fast as possible. In general, all the machines have enough space to
handle large builds like LLVM.

Reviewed-by: Aleix Roca Nonell <aleix.rocanonell@bsc.es>
2023-11-21 23:56:55 +01:00
2acfd589d4 BSC packages are no longer in bsc attribute
Reviewed-by: Aleix Roca Nonell <aleix.rocanonell@bsc.es>
2023-11-06 23:03:56 +01:00
18908c3019 Don't log SLURM connection attempts from ssfhead 2023-10-04 08:19:09 +02:00
94ead9b759 Enable direnv integration 2023-09-17 22:27:51 +02:00
e0b3dd961c Remove bscpkgs from the registry and nixPath
This is done to prevent accidental evaluations where the nixpkgs input
of bscpkgs is still pointing to a different version that the one
specified in the jungle flake. Instead use jungle#bscpkgs.X to get a
package from bscpkgs.
2023-09-15 11:58:47 +02:00
c73a337471 Don't fetch registry flakes from the net 2023-09-15 09:13:24 +02:00
a05d87d4b9 Enable fstrim service 2023-09-12 16:39:45 +02:00
b0b04e8fb1 Add encrypted munge key with agenix 2023-09-08 19:01:57 +02:00
a5e81fea95 Remove unused large port hole in firewall 2023-09-08 18:22:48 +02:00
e41404f619 Allow only some ports for srun 2023-09-08 17:51:37 +02:00
1c7ce3fc51 Block ssfhead from reaching our slurm daemon 2023-09-08 17:20:32 +02:00
bdd03dac60 Poweroff idle slurm nodes after 1 hour 2023-09-08 13:31:23 +02:00
21b38de26d Add IB and IPMI node host names 2023-09-08 13:21:37 +02:00
ae4ad95902 Add agenix to all nodes 2023-09-04 22:09:40 +02:00
875622ad0f Reorganize secrets and ssh keys
The agenix tools needs to read the secrets from a standalone file, but
we also need the same information for the SSH keys.
2023-09-04 21:36:31 +02:00
a7eddecf80 Add anavarro user 2023-09-04 16:00:01 +02:00
fcddbdb72b Set zsh inc_append_history option 2023-09-03 16:57:53 +02:00
bfb5363d94 Set zsh shell for rarias 2023-09-03 16:46:27 +02:00
44c1d958f4 Enable zsh and fix key bindings 2023-09-03 11:51:53 +02:00
e334891c41 Keep a log over time with the config commits 2023-09-02 23:49:41 +02:00
13b2379d97 Store nixos config in /etc/nixos/config.rev 2023-09-02 23:37:11 +02:00
b9598df864 Enable watchdog 2023-08-29 22:26:12 +02:00
042d85ba61 Also enable monitoring in lake2 2023-08-29 12:29:41 +02:00
7cd15b9732 Move pkgs overlay to overlay.nix 2023-08-25 18:12:00 +02:00
e8824bf72e Add the lake2 hostname to the hosts 2023-08-25 14:44:35 +02:00
bb8bf86051 Add ceph metrics to prometheus 2023-08-22 16:33:55 +02:00
1f270d070d Add the bay host name 2023-08-22 15:56:09 +02:00
b526531f20 Don't set all_proxy 2023-08-17 12:37:58 +02:00
b698b9da12 GRUB version no longer needed 2023-07-27 17:22:20 +02:00
c8ff31ec08 Kill slurmd remaining processes on upgrade 2023-07-27 14:24:21 +02:00
4878b6fd8b Add koro node 2023-07-21 10:34:19 +02:00
246226b3d3 Enable NTP using the BSC time server 2023-06-30 14:02:15 +02:00
aaa082390e Add the ssfhead node as gateway 2023-06-30 14:01:35 +02:00
cc2160f134 Use our host names first by default 2023-06-23 16:22:18 +02:00
01e7a9b8a4 Add DNS tools to resolve hosts 2023-06-23 16:12:25 +02:00
a66a4d9a43 Lower perf_event_paranoid to -1 2023-06-23 16:01:27 +02:00
31eace8400 Set perf paranoid to 0 by default 2023-06-21 16:23:16 +02:00
4997191f30 Add perf to packages 2023-06-21 15:41:06 +02:00
3ea8bdcdf1 Allow srun to specify the cpu binding
The task/affinity plugin needs to be selected.
2023-06-21 13:16:23 +02:00
7db6671ce5 Move authorized keys to users.nix 2023-06-20 14:08:34 +02:00
952541ff4a Add rpenacob user 2023-06-20 12:48:00 +02:00
d200e4b172 Add osumb to the system packages 2023-06-16 19:22:41 +02:00
60ee744a54 Use explicit order in overlays 2023-06-16 16:02:25 +02:00
3985e66fa4 Add mpich overlay 2023-06-16 14:16:51 +02:00
5010746e9c Add coments in slurm config 2023-06-16 14:16:14 +02:00
6df4924b00 Add eudy host key to known hosts 2023-06-16 17:29:48 +02:00
59a29e1af6 Rename xeon08 to eudy
From Eudyptula, a little penguin.
2023-06-16 17:16:05 +02:00