10 Commits

Author SHA1 Message Date
51977473cf Add acinca user
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-01 16:40:18 +02:00
dc4e2be9de Restart slurmd on failure
A failure to reach the control node can cause slurmd to fail and the
unit remains in the failed state until is manually restarted. Instead,
try to restart the service every 30 seconds, forever:

    owl1% systemctl show slurmd | grep -E 'Restart=|RestartUSec='
    Restart=on-failure
    RestartUSec=30s
    owl1% pgrep slurmd
    5903
    owl1% sudo kill -SEGV 5903
    owl1% pgrep slurmd
    6137

Fixes: #177
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-01 16:40:18 +02:00
7cdc5c0b5b Lower connect timeout when using hut substituter
Reviewed-by: Rodrigo Arias Mallo <rodrigo.arias@bsc.es>
2025-10-01 16:40:18 +02:00
3e0634a79e Use hut substituter in all nodes
Reviewed-by: Rodrigo Arias Mallo <rodrigo.arias@bsc.es>
2025-10-01 16:40:18 +02:00
d89e556ba9 Remove machine access for user csiringo
Reviewed-by: Rodrigo Arias Mallo <rodrigo.arias@bsc.es>
2025-10-01 16:40:18 +02:00
350e0ebecf Mount apex /home via NFS in raccoon
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-01 16:40:18 +02:00
b3c8e96f6a Remove extra SSH jump configuration
We now have direct visibility among nodes so we don't need any extra
SSH configuration to reach them.

Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-01 16:40:18 +02:00
c069f36013 Add raccoon peer to wireguard
It routes traffic from fox, apex and the compute nodes so that we can
reach the git servers and tent.

Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-01 16:40:18 +02:00
2c8b8354a3 Add raccoon host key
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-01 16:40:18 +02:00
f2c0dcd437 Restrict fox peer to a single IP
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-01 16:40:18 +02:00
22 changed files with 130 additions and 79 deletions

View File

@@ -2,21 +2,22 @@
# here all the public keys
rec {
hosts = {
hut = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICO7jIp6JRnRWTMDsTB/aiaICJCl4x8qmKMPSs4lCqP1 hut";
owl1 = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIMqMEXO0ApVsBA6yjmb0xP2kWyoPDIWxBB0Q3+QbHVhv owl1";
owl2 = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHurEYpQzNHqWYF6B9Pd7W8UPgF3BxEg0BvSbsA7BAdK owl2";
eudy = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIL+WYPRRvZupqLAG0USKmd/juEPmisyyJaP8hAgYwXsG eudy";
koro = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIImiTFDbxyUYPumvm8C4mEnHfuvtBY1H8undtd6oDd67 koro";
bay = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICvGBzpRQKuQYHdlUQeAk6jmdbkrhmdLwTBqf3el7IgU bay";
lake2 = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINo66//S1yatpQHE/BuYD/Gfq64TY7ZN5XOGXmNchiO0 lake2";
fox = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIDwItIk5uOJcQEVPoy/CVGRzfmE1ojrdDcI06FrU4NFT fox";
tent = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFAtTpHtdYoelbknD/IcfBlThwLKJv/dSmylOgpg3FRM tent";
apex = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIBvUFjSfoxXnKwXhEFXx5ckRKJ0oewJ82mRitSMNMKjh apex";
weasel = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFLJrQ8BF6KcweQV8pLkSbFT+tbDxSG9qxrdQE65zJZp weasel";
hut = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICO7jIp6JRnRWTMDsTB/aiaICJCl4x8qmKMPSs4lCqP1 hut";
owl1 = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIMqMEXO0ApVsBA6yjmb0xP2kWyoPDIWxBB0Q3+QbHVhv owl1";
owl2 = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHurEYpQzNHqWYF6B9Pd7W8UPgF3BxEg0BvSbsA7BAdK owl2";
eudy = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIL+WYPRRvZupqLAG0USKmd/juEPmisyyJaP8hAgYwXsG eudy";
koro = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIImiTFDbxyUYPumvm8C4mEnHfuvtBY1H8undtd6oDd67 koro";
bay = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICvGBzpRQKuQYHdlUQeAk6jmdbkrhmdLwTBqf3el7IgU bay";
lake2 = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINo66//S1yatpQHE/BuYD/Gfq64TY7ZN5XOGXmNchiO0 lake2";
fox = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIDwItIk5uOJcQEVPoy/CVGRzfmE1ojrdDcI06FrU4NFT fox";
tent = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFAtTpHtdYoelbknD/IcfBlThwLKJv/dSmylOgpg3FRM tent";
apex = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIBvUFjSfoxXnKwXhEFXx5ckRKJ0oewJ82mRitSMNMKjh apex";
weasel = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFLJrQ8BF6KcweQV8pLkSbFT+tbDxSG9qxrdQE65zJZp weasel";
raccoon = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGNQttFvL0dNEyy7klIhLoK4xXOeM2/K9R7lPMTG3qvK raccoon";
};
hostGroup = with hosts; rec {
compute = [ owl1 owl2 fox ];
compute = [ owl1 owl2 fox raccoon ];
playground = [ eudy koro weasel ];
storage = [ bay lake2 ];
monitor = [ hut ];

View File

@@ -5,6 +5,7 @@
../common/xeon.nix
../common/ssf/hosts.nix
../module/ceph.nix
../module/hut-substituter.nix
../module/slurm-server.nix
./nfs.nix
./wireguard.nix
@@ -56,17 +57,6 @@
};
};
# Use SSH tunnel to reach internal hosts
programs.ssh.extraConfig = ''
Host bscpm04.bsc.es gitlab-internal.bsc.es knights3.bsc.es
ProxyCommand nc -X connect -x localhost:23080 %h %p
Host raccoon
HostName knights3.bsc.es
ProxyCommand nc -X connect -x localhost:23080 %h %p
Host tent
ProxyJump raccoon
'';
networking.firewall = {
extraCommands = ''
# Blackhole BSC vulnerability scanner (OpenVAS) as it is spamming our
@@ -76,10 +66,4 @@
iptables -I nixos-fw 2 -p tcp -s 84.88.52.176 -j nixos-fw-refuse
'';
};
# Use tent for cache
nix.settings = {
extra-substituters = [ "https://jungle.bsc.es/cache" ];
extra-trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
};
}

View File

@@ -20,16 +20,23 @@
{
name = "fox";
publicKey = "VfMPBQLQTKeyXJSwv8wBhc6OV0j2qAxUpX3kLHunK2Y=";
allowedIPs = [ "10.106.0.0/24" ];
allowedIPs = [ "10.106.0.1/32" ];
endpoint = "fox.ac.upc.edu:666";
# Send keepalives every 25 seconds. Important to keep NAT tables alive.
persistentKeepalive = 25;
}
{
name = "raccoon";
publicKey = "QUfnGXSMEgu2bviglsaSdCjidB51oEDBFpnSFcKGfDI=";
allowedIPs = [ "10.106.0.236/32" "192.168.0.0/16" "10.0.44.0/24" ];
}
];
};
};
networking.hosts = {
"10.106.0.1" = [ "fox" ];
"10.106.0.236" = [ "raccoon" ];
"10.0.44.4" = [ "tent" ];
};
}

View File

@@ -3,6 +3,7 @@
{
imports = [
../common/ssf.nix
../module/hut-substituter.nix
../module/monitoring.nix
];

View File

@@ -15,8 +15,9 @@
hosts = {
"84.88.53.236" = [ "ssfhead.bsc.es" "ssfhead" ];
"84.88.51.152" = [ "raccoon" ];
"84.88.51.142" = [ "raccoon-ipmi" ];
"192.168.11.12" = [ "bscpm04.bsc.es" ];
"192.168.11.15" = [ "gitlab-internal.bsc.es" ];
};
};
}

View File

@@ -156,18 +156,30 @@
};
csiringo = {
# Arbitrary UID but large so it doesn't collide with other users on ssfhead.
uid = 9653;
isNormalUser = true;
home = "/home/Computational/csiringo";
description = "Cesare Siringo";
group = "Computational";
hosts = [ "apex" "weasel" ];
hosts = [ ];
hashedPassword = "$6$0IsZlju8jFukLlAw$VKm0FUXbS.mVmPm3rcJeizTNU4IM5Nmmy21BvzFL.cQwvlGwFI1YWRQm6gsbd4nbg47mPDvYkr/ar0SlgF6GO1";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHA65zvvG50iuFEMf+guRwZB65jlGXfGLF4HO+THFaed csiringo@bsc.es"
];
};
acinca = {
uid = 9654;
isNormalUser = true;
home = "/home/Computational/acinca";
description = "Arnau Cinca";
group = "Computational";
hosts = [ "apex" "hut" "fox" "owl1" "owl2" ];
hashedPassword = "$6$S6PUeRpdzYlidxzI$szyvWejQ4hEN76yBYhp1diVO5ew1FFg.cz4lKiXt2Idy4XdpifwrFTCIzLTs5dvYlR62m7ekA5MrhcVxR5F/q/";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFmMqKqPg4uocNOr3O41kLbZMOMJn3m2ZdN1JvTR96z3 bsccns@arnau-bsc"
];
};
};
groups = {

View File

@@ -4,7 +4,7 @@
./xeon.nix
./ssf/fs.nix
./ssf/hosts.nix
./ssf/hosts-remote.nix
./ssf/net.nix
./ssf/ssh.nix
];
}

View File

@@ -0,0 +1,9 @@
{ pkgs, ... }:
{
networking.hosts = {
# Remote hosts visible from compute nodes
"10.106.0.236" = [ "raccoon" ];
"10.0.44.4" = [ "tent" ];
};
}

View File

@@ -1,16 +0,0 @@
{
# Use SSH tunnel to apex to reach internal hosts
programs.ssh.extraConfig = ''
Host tent
ProxyJump raccoon
# Access raccoon via the HTTP proxy
Host raccoon knights3.bsc.es
HostName knights3.bsc.es
ProxyCommand=ssh apex 'nc -X connect -x localhost:23080 %h %p'
# Make sure we can reach gitlab even if we don't have SSH access to raccoon
Host bscpm04.bsc.es gitlab-internal.bsc.es
ProxyCommand=ssh apex 'nc -X connect -x localhost:23080 %h %p'
'';
}

View File

@@ -9,6 +9,7 @@
./cpufreq.nix
./fs.nix
./users.nix
../module/hut-substituter.nix
../module/debuginfod.nix
];

View File

@@ -8,6 +8,7 @@
../module/emulation.nix
../module/nvidia.nix
../module/slurm-client.nix
../module/hut-substituter.nix
./wireguard.nix
];
@@ -45,16 +46,6 @@
services.fail2ban.enable = true;
# Use SSH tunnel to reach internal hosts
programs.ssh.extraConfig = ''
Host bscpm04.bsc.es gitlab-internal.bsc.es tent
ProxyJump raccoon
Host raccoon
ProxyJump apex
HostName 127.0.0.1
Port 22022
'';
networking = {
timeServers = [ "ntp1.upc.edu" "ntp2.upc.edu" ];
hostName = "fox";
@@ -72,12 +63,6 @@
interfaces.enp1s0f0np0.useDHCP = true;
};
# Use hut for cache
nix.settings = {
extra-substituters = [ "https://jungle.bsc.es/cache" ];
extra-trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
};
# Recommended for new graphics cards
hardware.nvidia.open = true;

View File

@@ -29,12 +29,19 @@
# List of IPs assigned to this peer within the tunnel subnet. Used to configure routing.
allowedIPs = [ "10.106.0.30/32" ];
}
{
name = "raccoon";
publicKey = "QUfnGXSMEgu2bviglsaSdCjidB51oEDBFpnSFcKGfDI=";
allowedIPs = [ "10.106.0.236/32" "192.168.0.0/16" "10.0.44.0/24" ];
}
];
};
};
networking.hosts = {
"10.106.0.30" = [ "apex" ];
"10.106.0.236" = [ "raccoon" ];
"10.0.44.4" = [ "tent" ];
};
networking.firewall = {

View File

@@ -4,6 +4,7 @@
imports = [
../common/ssf.nix
../module/monitoring.nix
../module/hut-substituter.nix
];
boot.loader.grub.device = "/dev/disk/by-id/wwn-0x55cd2e414d53563a";

View File

@@ -6,5 +6,8 @@
{
extra-substituters = [ "http://hut/cache" ];
extra-trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
# Set a low timeout in case hut is down
connect-timeout = 3; # seconds
};
}

View File

@@ -12,6 +12,12 @@
# https://github.com/NixOS/nixpkgs/commit/ae93ed0f0d4e7be0a286d1fca86446318c0c6ffb
# https://bugs.schedmd.com/show_bug.cgi?id=2095#c24
KillMode = lib.mkForce "control-group";
# If slurmd fails to contact the control server it will fail, causing the
# node to remain out of service until manually restarted. Always try to
# restart it.
Restart = "always";
RestartSec = "30s";
};
services.slurm.client.enable = true;

View File

@@ -1,8 +0,0 @@
{
programs.ssh.extraConfig = ''
Host apex ssfhead
HostName ssflogin.bsc.es
Host hut
ProxyJump apex
'';
}

View File

@@ -3,11 +3,13 @@
{
imports = [
../common/base.nix
../common/ssf/hosts.nix
../module/emulation.nix
../module/debuginfod.nix
../module/ssh-hut-extern.nix
../module/nvidia.nix
../eudy/kernel/perf.nix
./wireguard.nix
../module/hut-substituter.nix
];
# Don't install Grub on the disk yet
@@ -43,9 +45,11 @@
};
};
nix.settings = {
extra-substituters = [ "https://jungle.bsc.es/cache" ];
extra-trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
# Mount the NFS home
fileSystems."/nfs/home" = {
device = "10.106.0.30:/home";
fsType = "nfs";
options = [ "nfsvers=3" "rsize=1024" "wsize=1024" "cto" "nofail" ];
};
# Enable performance governor

48
m/raccoon/wireguard.nix Normal file
View File

@@ -0,0 +1,48 @@
{ config, pkgs, ... }:
{
networking.nat = {
enable = true;
enableIPv6 = false;
externalInterface = "eno0";
internalInterfaces = [ "wg0" ];
};
networking.firewall = {
allowedUDPPorts = [ 666 ];
};
age.secrets.wgRaccoon.file = ../../secrets/wg-raccoon.age;
# Enable WireGuard
networking.wireguard.enable = true;
networking.wireguard.interfaces = {
wg0 = {
ips = [ "10.106.0.236/24" ];
listenPort = 666;
privateKeyFile = config.age.secrets.wgRaccoon.path;
# Public key: QUfnGXSMEgu2bviglsaSdCjidB51oEDBFpnSFcKGfDI=
peers = [
{
name = "fox";
publicKey = "VfMPBQLQTKeyXJSwv8wBhc6OV0j2qAxUpX3kLHunK2Y=";
allowedIPs = [ "10.106.0.1/32" ];
endpoint = "fox.ac.upc.edu:666";
persistentKeepalive = 25;
}
{
name = "apex";
publicKey = "VwhcN8vSOzdJEotQTpmPHBC52x3Hbv1lkFIyKubrnUA=";
allowedIPs = [ "10.106.0.30/32" "10.0.40.0/24" ];
endpoint = "ssfhead.bsc.es:666";
persistentKeepalive = 25;
}
];
};
};
networking.hosts = {
"10.106.0.1" = [ "fox.wg" ];
"10.106.0.30" = [ "apex.wg" ];
};
}

View File

@@ -3,9 +3,9 @@
{
imports = [
../common/xeon.nix
../common/ssf/hosts.nix
../module/emulation.nix
../module/debuginfod.nix
../module/ssh-hut-extern.nix
./monitoring.nix
./nginx.nix
./nix-serve.nix
@@ -15,6 +15,7 @@
../hut/msmtp.nix
../module/p.nix
../module/vpn-dac.nix
../module/hut-substituter.nix
];
# Select the this using the ID to avoid mismatches
@@ -35,6 +36,7 @@
defaultGateway = "10.0.44.1";
hosts = {
"84.88.53.236" = [ "apex" ];
"10.0.44.1" = [ "raccoon" ];
};
};

View File

@@ -3,6 +3,7 @@
{
imports = [
../common/ssf.nix
../module/hut-substituter.nix
];
# Select this using the ID to avoid mismatches

View File

@@ -4,6 +4,7 @@ let
hut = [ keys.hosts.hut ] ++ adminsKeys;
fox = [ keys.hosts.fox ] ++ adminsKeys;
apex = [ keys.hosts.apex ] ++ adminsKeys;
raccoon = [ keys.hosts.raccoon ] ++ adminsKeys;
mon = [ keys.hosts.hut keys.hosts.tent ] ++ adminsKeys;
tent = [ keys.hosts.tent ] ++ adminsKeys;
# Only expose ceph keys to safe nodes and admins
@@ -29,4 +30,5 @@ in
"wg-fox.age".publicKeys = fox;
"wg-apex.age".publicKeys = apex;
"wg-raccoon.age".publicKeys = raccoon;
}

BIN
secrets/wg-raccoon.age Normal file

Binary file not shown.