Compare commits

...

3 Commits

Author SHA1 Message Date
b39b258bff
Allow access to hut from fox 2025-10-01 17:20:52 +02:00
00fe0f46a1 Add acinca user
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-10-01 12:27:43 +02:00
79940876c3 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: rarias/jungle#177
Reviewed-by: Aleix Boné <abonerib@bsc.es>
2025-09-30 17:20:39 +02:00
4 changed files with 23 additions and 4 deletions

View File

@ -20,7 +20,7 @@
{
name = "fox";
publicKey = "VfMPBQLQTKeyXJSwv8wBhc6OV0j2qAxUpX3kLHunK2Y=";
allowedIPs = [ "10.106.0.1/32" ];
allowedIPs = [ "10.106.0.1/32" "10.0.40.0/24" ];
endpoint = "fox.ac.upc.edu:666";
# Send keepalives every 25 seconds. Important to keep NAT tables alive.
persistentKeepalive = 25;

View File

@ -156,7 +156,6 @@
};
csiringo = {
# Arbitrary UID but large so it doesn't collide with other users on ssfhead.
uid = 9653;
isNormalUser = true;
home = "/home/Computational/csiringo";
@ -168,6 +167,19 @@
"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

@ -23,11 +23,11 @@
peers = [
# List of allowed peers.
{
{
name = "apex";
publicKey = "VwhcN8vSOzdJEotQTpmPHBC52x3Hbv1lkFIyKubrnUA=";
# List of IPs assigned to this peer within the tunnel subnet. Used to configure routing.
allowedIPs = [ "10.106.0.30/32" ];
allowedIPs = [ "10.106.0.30/32" "10.0.40.7/32" ];
}
{
name = "raccoon";
@ -40,6 +40,7 @@
networking.hosts = {
"10.106.0.30" = [ "apex" ];
"10.0.40.7" = [ "hut" ];
"10.106.0.236" = [ "raccoon" ];
"10.0.44.4" = [ "tent" ];
};

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;