11 Commits

Author SHA1 Message Date
e065cde376 Use NixOS attributes for the install section 2023-09-18 19:27:14 +02:00
3bb0b550aa Add a RequiredBy dependency for remote-fs.target 2023-09-18 19:05:58 +02:00
e4cbcab81c Use a systemd mount directly for the nix store
Allows the LazyUnmount option and avoids the stage1 hack with
/nix//store.
2023-09-18 18:53:40 +02:00
77b41a90e2 Patch nix instead of using an override unit 2023-09-18 18:06:51 +02:00
1fc6891dc6 Remove nix-daemon.socket dependency of /nix/store
The dependency causes a cycle as the nix store will be mounted after the
network is ready, which itself depends on the socket.target which
requires the nix-daemon.socket to be ready too.
2023-09-18 17:28:47 +02:00
8c11c7460a Delay the mount until the network is ready 2023-09-18 16:07:46 +02:00
e6014511f5 Wait for the NFS hut store to be mounted 2023-09-18 15:50:37 +02:00
320c58ce48 Prevent the overlay to be mounted in stage1 2023-09-18 13:57:41 +02:00
d145ee9b2c Mount the overlay in /nix/store 2023-09-18 13:02:32 +02:00
140178d58e Begin the nix store overlay
We need to disable the read-only bind mount, so we can directly bind
mount the overlay.
2023-09-18 11:22:24 +02:00
d48f3b989a Enable direnv integration 2023-09-17 22:27:51 +02:00
136 changed files with 1041 additions and 4281 deletions

1
.gitignore vendored
View File

@@ -1,3 +1,2 @@
*.swp
/result
/misc

View File

@@ -150,27 +150,3 @@ And update grub.
```
# nix build .#nixosConfigurations.xeon02.config.system.build.kexecTree -v
```
## Chain NixOS in same disk with other systems
To install NixOS on a partition along another system which controls the GRUB,
first disable the grub device, so the GRUB is not installed in the disk by
NixOS (only the /boot files will be generated):
```
boot.loader.grub.device = "nodev";
```
Then add the following entry to the old GRUB configuration:
```
menuentry 'NixOS' {
insmod chain
search --no-floppy --label nixos --set root
configfile /boot/grub/grub.cfg
}
```
The partition with NixOS must have the label "nixos" for it to be found. New
system configuration entries will be stored in the GRUB configuration managed
by NixOS, so there is no need to change the old GRUB settings.

56
flake.lock generated
View File

@@ -6,15 +6,14 @@
"home-manager": "home-manager",
"nixpkgs": [
"nixpkgs"
],
"systems": "systems"
]
},
"locked": {
"lastModified": 1750173260,
"narHash": "sha256-9P1FziAwl5+3edkfFcr5HeGtQUtrSdk/MksX39GieoA=",
"lastModified": 1690228878,
"narHash": "sha256-9Xe7JV0krp4RJC9W9W9WutZVlw6BlHTFMiUP/k48LQY=",
"owner": "ryantm",
"repo": "agenix",
"rev": "531beac616433bac6f9e2a19feb8e99a22a66baf",
"rev": "d8c973fd228949736dedf61b7f8cc1ece3236792",
"type": "github"
},
"original": {
@@ -30,17 +29,17 @@
]
},
"locked": {
"lastModified": 1749650500,
"narHash": "sha256-2MHfVPV6RA7qPSCtXh4+KK0F0UjN+J4z8//+n6NK7Xs=",
"lastModified": 1694708510,
"narHash": "sha256-72bvRBhq8Q8V6ibsR9lyBE92V2EC6C6Ek3J5cOM79So=",
"ref": "refs/heads/master",
"rev": "9d1944c658929b6f98b3f3803fead4d1b91c4405",
"revCount": 961,
"rev": "3a4062ac04be6263c64a481420d8e768c2521b80",
"revCount": 862,
"type": "git",
"url": "https://git.sr.ht/~rodarima/bscpkgs"
"url": "https://pm.bsc.es/gitlab/rarias/bscpkgs.git"
},
"original": {
"type": "git",
"url": "https://git.sr.ht/~rodarima/bscpkgs"
"url": "https://pm.bsc.es/gitlab/rarias/bscpkgs.git"
}
},
"darwin": {
@@ -51,11 +50,11 @@
]
},
"locked": {
"lastModified": 1744478979,
"narHash": "sha256-dyN+teG9G82G+m+PX/aSAagkC+vUv0SgUw3XkPhQodQ=",
"lastModified": 1673295039,
"narHash": "sha256-AsdYgE8/GPwcelGgrntlijMg4t3hLFJFCRF3tL5WVjA=",
"owner": "lnl7",
"repo": "nix-darwin",
"rev": "43975d782b418ebf4969e9ccba82466728c2851b",
"rev": "87b9d090ad39b25b2400029c64825fc2a8868943",
"type": "github"
},
"original": {
@@ -73,11 +72,11 @@
]
},
"locked": {
"lastModified": 1745494811,
"narHash": "sha256-YZCh2o9Ua1n9uCvrvi5pRxtuVNml8X2a03qIFfRKpFs=",
"lastModified": 1682203081,
"narHash": "sha256-kRL4ejWDhi0zph/FpebFYhzqlOBrk0Pl3dzGEKSAlEw=",
"owner": "nix-community",
"repo": "home-manager",
"rev": "abfad3d2958c9e6300a883bd443512c55dfeb1be",
"rev": "32d3e39c491e2f91152c84f8ad8b003420eab0a1",
"type": "github"
},
"original": {
@@ -88,16 +87,16 @@
},
"nixpkgs": {
"locked": {
"lastModified": 1752436162,
"narHash": "sha256-Kt1UIPi7kZqkSc5HVj6UY5YLHHEzPBkgpNUByuyxtlw=",
"lastModified": 1693663421,
"narHash": "sha256-ImMIlWE/idjcZAfxKK8sQA7A1Gi/O58u5/CJA+mxvl8=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "dfcd5b901dbab46c9c6e80b265648481aafb01f8",
"rev": "e56990880811a451abd32515698c712788be5720",
"type": "github"
},
"original": {
"owner": "NixOS",
"ref": "nixos-25.05",
"ref": "nixos-unstable",
"repo": "nixpkgs",
"type": "github"
}
@@ -108,21 +107,6 @@
"bscpkgs": "bscpkgs",
"nixpkgs": "nixpkgs"
}
},
"systems": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
}
},
"root": "root",

View File

@@ -1,9 +1,9 @@
{
inputs = {
nixpkgs.url = "github:NixOS/nixpkgs/nixos-25.05";
nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
agenix.url = "github:ryantm/agenix";
agenix.inputs.nixpkgs.follows = "nixpkgs";
bscpkgs.url = "git+https://git.sr.ht/~rodarima/bscpkgs";
bscpkgs.url = "git+https://pm.bsc.es/gitlab/rarias/bscpkgs.git";
bscpkgs.inputs.nixpkgs.follows = "nixpkgs";
};
@@ -17,18 +17,13 @@ let
in
{
nixosConfigurations = {
hut = mkConf "hut";
tent = mkConf "tent";
owl1 = mkConf "owl1";
owl2 = mkConf "owl2";
eudy = mkConf "eudy";
koro = mkConf "koro";
bay = mkConf "bay";
lake2 = mkConf "lake2";
raccoon = mkConf "raccoon";
fox = mkConf "fox";
apex = mkConf "apex";
weasel = mkConf "weasel";
hut = mkConf "hut";
owl1 = mkConf "owl1";
owl2 = mkConf "owl2";
eudy = mkConf "eudy";
koro = mkConf "koro";
bay = mkConf "bay";
lake2 = mkConf "lake2";
};
packages.x86_64-linux = self.nixosConfigurations.hut.pkgs // {

View File

@@ -2,35 +2,28 @@
# 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";
};
hostGroup = with hosts; rec {
untrusted = [ fox ];
compute = [ owl1 owl2 ];
playground = [ eudy koro weasel ];
playground = [ eudy koro ];
storage = [ bay lake2 ];
monitor = [ hut ];
login = [ apex ];
system = storage ++ monitor ++ login;
system = storage ++ monitor;
safe = system ++ compute;
all = safe ++ playground;
};
admins = {
"rarias@hut" = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIE1oZTPtlEXdGt0Ak+upeCIiBdaDQtcmuWoTUCVuSVIR rarias@hut";
"rarias@tent" = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIwlWSBTZi74WTz5xn6gBvTmCoVltmtIAeM3RMmkh4QZ rarias@tent";
root = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIII/1TNArcwA6D47mgW4TArwlxQRpwmIGiZDysah40Gb root@hut";
rarias = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIE1oZTPtlEXdGt0Ak+upeCIiBdaDQtcmuWoTUCVuSVIR rarias@hut";
root = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIII/1TNArcwA6D47mgW4TArwlxQRpwmIGiZDysah40Gb root@hut";
};
}

View File

@@ -1,83 +0,0 @@
{ lib, config, pkgs, ... }:
{
imports = [
../common/xeon.nix
../common/ssf/hosts.nix
../module/ceph.nix
./nfs.nix
];
# Don't install grub MBR for now
boot.loader.grub.device = "nodev";
boot.initrd.kernelModules = [
"megaraid_sas" # For HW RAID
];
environment.systemPackages = with pkgs; [
storcli # To manage HW RAID
];
fileSystems."/home" = {
device = "/dev/disk/by-label/home";
fsType = "ext4";
};
# No swap, there is plenty of RAM
swapDevices = lib.mkForce [];
networking = {
hostName = "apex";
defaultGateway = "84.88.53.233";
nameservers = [ "8.8.8.8" ];
# Public facing interface
interfaces.eno1.ipv4.addresses = [ {
address = "84.88.53.236";
prefixLength = 29;
} ];
# Internal LAN to our Ethernet switch
interfaces.eno2.ipv4.addresses = [ {
address = "10.0.40.30";
prefixLength = 24;
} ];
# Infiniband over Omnipath switch (disconnected for now)
# interfaces.ibp5s0 = {};
nat = {
enable = true;
internalInterfaces = [ "eno2" ];
externalInterface = "eno1";
};
};
# 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
# logs. Insert as first position so we also protect SSH.
iptables -I nixos-fw 1 -p tcp -s 192.168.8.16 -j nixos-fw-refuse
# Same with opsmonweb01.bsc.es which seems to be trying to access via SSH
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

@@ -1,32 +0,0 @@
{ ... }:
{
services.nfs.server = {
enable = true;
lockdPort = 4001;
mountdPort = 4002;
statdPort = 4000;
exports = ''
/home 10.0.40.0/24(rw,async,no_subtree_check,no_root_squash)
'';
};
networking.firewall = {
# Check with `rpcinfo -p`
extraCommands = ''
# Accept NFS traffic from compute nodes but not from the outside
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 111 -j nixos-fw-accept
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 2049 -j nixos-fw-accept
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 4000 -j nixos-fw-accept
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 4001 -j nixos-fw-accept
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 4002 -j nixos-fw-accept
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 20048 -j nixos-fw-accept
# Same but UDP
iptables -A nixos-fw -p udp -s 10.0.40.0/24 --dport 111 -j nixos-fw-accept
iptables -A nixos-fw -p udp -s 10.0.40.0/24 --dport 2049 -j nixos-fw-accept
iptables -A nixos-fw -p udp -s 10.0.40.0/24 --dport 4000 -j nixos-fw-accept
iptables -A nixos-fw -p udp -s 10.0.40.0/24 --dport 4001 -j nixos-fw-accept
iptables -A nixos-fw -p udp -s 10.0.40.0/24 --dport 4002 -j nixos-fw-accept
iptables -A nixos-fw -p udp -s 10.0.40.0/24 --dport 20048 -j nixos-fw-accept
'';
};
}

View File

@@ -2,21 +2,21 @@
{
imports = [
../common/ssf.nix
../module/monitoring.nix
../common/main.nix
../common/monitoring.nix
];
# Select the this using the ID to avoid mismatches
boot.loader.grub.device = "/dev/disk/by-id/wwn-0x55cd2e414d53562d";
boot.kernel.sysctl = {
"kernel.yama.ptrace_scope" = lib.mkForce "1";
};
environment.systemPackages = with pkgs; [
ceph
];
services.slurm = {
client.enable = lib.mkForce false;
};
networking = {
hostName = "bay";
interfaces.eno1.ipv4.addresses = [ {
@@ -27,16 +27,6 @@
address = "10.0.42.40";
prefixLength = 24;
} ];
firewall = {
extraCommands = ''
# Accept all incoming TCP traffic from lake2
iptables -A nixos-fw -p tcp -s lake2 -j nixos-fw-accept
# Accept monitoring requests from hut
iptables -A nixos-fw -p tcp -s hut -m multiport --dport 9283,9002 -j nixos-fw-accept
# Accept all Ceph traffic from the local network
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 -m multiport --dport 3300,6789,6800:7568 -j nixos-fw-accept
'';
};
};
services.ceph = {

View File

@@ -1,20 +0,0 @@
{
# All machines should include this profile.
# Includes the basic configuration for an Intel server.
imports = [
./base/agenix.nix
./base/august-shutdown.nix
./base/boot.nix
./base/env.nix
./base/fs.nix
./base/hw.nix
./base/net.nix
./base/nix.nix
./base/ntp.nix
./base/rev.nix
./base/ssh.nix
./base/users.nix
./base/watchdog.nix
./base/zsh.nix
];
}

View File

@@ -1,14 +0,0 @@
{
# Shutdown all machines on August 2nd at 11:00 AM, so we can protect the
# hardware from spurious electrical peaks on the yearly electrical cut for
# manteinance that starts on August 4th.
systemd.timers.august-shutdown = {
description = "Shutdown on August 2nd for maintenance";
wantedBy = [ "timers.target" ];
timerConfig = {
OnCalendar = "*-08-02 11:00:00";
RandomizedDelaySec = "10min";
Unit = "systemd-poweroff.service";
};
};
}

View File

@@ -1,37 +0,0 @@
{ pkgs, config, ... }:
{
environment.systemPackages = with pkgs; [
vim wget git htop tmux pciutils tcpdump ripgrep nix-index nixos-option
nix-diff ipmitool freeipmi ethtool lm_sensors cmake gnumake file tree
ncdu config.boot.kernelPackages.perf ldns pv
# From bsckgs overlay
osumb
];
programs.direnv.enable = true;
# Increase limits
security.pam.loginLimits = [
{
domain = "*";
type = "-";
item = "memlock";
value = "1048576"; # 1 GiB of mem locked
}
];
environment.enableAllTerminfo = true;
environment.variables = {
EDITOR = "vim";
VISUAL = "vim";
};
programs.bash.promptInit = ''
PS1="\h\\$ "
'';
time.timeZone = "Europe/Madrid";
i18n.defaultLocale = "en_DK.UTF-8";
}

View File

@@ -1,22 +0,0 @@
{ pkgs, lib, ... }:
{
networking = {
enableIPv6 = false;
useDHCP = false;
firewall = {
enable = true;
allowedTCPPorts = [ 22 ];
};
# Make sure we use iptables
nftables.enable = lib.mkForce false;
hosts = {
"84.88.53.236" = [ "apex" "ssfhead.bsc.es" "ssfhead" ];
"84.88.51.152" = [ "raccoon" ];
"84.88.51.142" = [ "raccoon-ipmi" ];
};
};
}

View File

@@ -1,60 +0,0 @@
{ pkgs, nixpkgs, bscpkgs, theFlake, ... }:
{
nixpkgs.overlays = [
bscpkgs.bscOverlay
(import ../../../pkgs/overlay.nix)
];
nixpkgs.config.allowUnfree = true;
nix = {
nixPath = [
"nixpkgs=${nixpkgs}"
"jungle=${theFlake.outPath}"
];
registry = {
nixpkgs.flake = nixpkgs;
jungle.flake = theFlake;
};
settings = {
experimental-features = [ "nix-command" "flakes" ];
sandbox = "relaxed";
trusted-users = [ "@wheel" ];
flake-registry = pkgs.writeText "global-registry.json"
''{"flakes":[],"version":2}'';
keep-outputs = true;
};
gc = {
automatic = true;
dates = "weekly";
options = "--delete-older-than 30d";
};
};
# The nix-gc.service can begin its execution *before* /home is mounted,
# causing it to remove all gcroots considering them as stale, as it cannot
# access the symlink. To prevent this problem, we force the service to wait
# until /home is mounted as well as other remote FS like /ceph.
systemd.services.nix-gc = {
# Start remote-fs.target if not already being started and fail if it fails
# to start. It will also be stopped if the remote-fs.target fails after
# starting successfully.
bindsTo = [ "remote-fs.target" ];
# Wait until remote-fs.target fully starts before starting this one.
after = [ "remote-fs.target"];
# Ensure we can access a remote path inside /home
unitConfig.ConditionPathExists = "/home/Computational";
};
# This value determines the NixOS release from which the default
# settings for stateful data, like file locations and database versions
# on your system were taken. Its perfectly fine and recommended to leave
# this value at the release version of the first install of this system.
# Before changing this value read the documentation for this option
# (e.g. man configuration.nix or on https://nixos.org/nixos/options.html).
system.stateVersion = "22.11"; # Did you read the comment?
}

View File

@@ -1,164 +0,0 @@
{ pkgs, ... }:
{
imports = [
../../module/jungle-users.nix
];
users = {
mutableUsers = false;
users = {
# Generate hashedPassword with `mkpasswd -m sha-512`
root.openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKBOf4r4lzQfyO0bx5BaREePREw8Zw5+xYgZhXwOZoBO ram@hop"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINa0tvnNgwkc5xOwd6xTtaIdFi5jv0j2FrE7jl5MTLoE ram@mio"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIF3zeB5KSimMBAjvzsp1GCkepVaquVZGPYwRIzyzaCba aleix@bsc"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIII/1TNArcwA6D47mgW4TArwlxQRpwmIGiZDysah40Gb root@hut"
];
rarias = {
uid = 1880;
isNormalUser = true;
linger = true;
home = "/home/Computational/rarias";
description = "Rodrigo Arias";
group = "Computational";
extraGroups = [ "wheel" ];
hashedPassword = "$6$u06tkCy13enReBsb$xiI.twRvvTfH4jdS3s68NZ7U9PSbGKs5.LXU/UgoawSwNWhZo2hRAjNL5qG0/lAckzcho2LjD0r3NfVPvthY6/";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKBOf4r4lzQfyO0bx5BaREePREw8Zw5+xYgZhXwOZoBO ram@hop"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINa0tvnNgwkc5xOwd6xTtaIdFi5jv0j2FrE7jl5MTLoE ram@mio"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGYcXIxe0poOEGLpk8NjiRozls7fMRX0N3j3Ar94U+Gl rarias@hal"
];
shell = pkgs.zsh;
};
arocanon = {
uid = 1042;
isNormalUser = true;
home = "/home/Computational/arocanon";
description = "Aleix Roca";
group = "Computational";
extraGroups = [ "wheel" "tracing" ];
hashedPassword = "$6$hliZiW4tULC/tH7p$pqZarwJkNZ7vS0G5llWQKx08UFG9DxDYgad7jplMD8WkZh5k58i4dfPoWtnEShfjTO6JHiIin05ny5lmSXzGM/";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIF3zeB5KSimMBAjvzsp1GCkepVaquVZGPYwRIzyzaCba aleix@bsc"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGdphWxLAEekicZ/WBrvP7phMyxKSSuLAZBovNX+hZXQ aleix@kerneland"
];
};
};
jungleUsers = {
rpenacob = {
uid = 2761;
isNormalUser = true;
home = "/home/Computational/rpenacob";
description = "Raúl Peñacoba";
group = "Computational";
hosts = [ "apex" "owl1" "owl2" "hut" "tent" "fox" ];
hashedPassword = "$6$TZm3bDIFyPrMhj1E$uEDXoYYd1z2Wd5mMPfh3DZAjP7ztVjJ4ezIcn82C0ImqafPA.AnTmcVftHEzLB3tbe2O4SxDyPSDEQgJ4GOtj/";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFYfXg37mauGeurqsLpedgA2XQ9d4Nm0ZGo/hI1f7wwH rpenacob@bsc"
];
};
anavarro = {
uid = 1037;
isNormalUser = true;
home = "/home/Computational/anavarro";
description = "Antoni Navarro";
group = "Computational";
hosts = [ "apex" "hut" "tent" "raccoon" "fox" "weasel" ];
hashedPassword = "$6$EgturvVYXlKgP43g$gTN78LLHIhaF8hsrCXD.O6mKnZSASWSJmCyndTX8QBWT6wTlUhcWVAKz65lFJPXjlJA4u7G1ydYQ0GG6Wk07b1";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIMsbM21uepnJwPrRe6jYFz8zrZ6AYMtSEvvt4c9spmFP toni@delltoni"
];
};
abonerib = {
uid = 4541;
isNormalUser = true;
home = "/home/Computational/abonerib";
description = "Aleix Boné";
group = "Computational";
hosts = [ "apex" "owl1" "owl2" "hut" "tent" "raccoon" "fox" "weasel" ];
hashedPassword = "$6$V1EQWJr474whv7XJ$OfJ0wueM2l.dgiJiiah0Tip9ITcJ7S7qDvtSycsiQ43QBFyP4lU0e0HaXWps85nqB4TypttYR4hNLoz3bz662/";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIIFiqXqt88VuUfyANkZyLJNiuroIITaGlOOTMhVDKjf abonerib@bsc"
];
};
vlopez = {
uid = 4334;
isNormalUser = true;
home = "/home/Computational/vlopez";
description = "Victor López";
group = "Computational";
hosts = [ "apex" "koro" ];
hashedPassword = "$6$0ZBkgIYE/renVqtt$1uWlJsb0FEezRVNoETTzZMx4X2SvWiOsKvi0ppWCRqI66S6TqMBXBdP4fcQyvRRBt0e4Z7opZIvvITBsEtO0f0";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGMwlUZRf9jfG666Qa5Sb+KtEhXqkiMlBV2su3x/dXHq victor@arch"
];
};
dbautist = {
uid = 5649;
isNormalUser = true;
home = "/home/Computational/dbautist";
description = "Dylan Bautista Cases";
group = "Computational";
hosts = [ "apex" "hut" "tent" "raccoon" ];
hashedPassword = "$6$a2lpzMRVkG9nSgIm$12G6.ka0sFX1YimqJkBAjbvhRKZ.Hl090B27pdbnQOW0wzyxVWySWhyDDCILjQELky.HKYl9gqOeVXW49nW7q/";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIAb+EQBoS98zrCwnGKkHKwMLdYABMTqv7q9E0+T0QmkS dbautist@bsc-848818791"
];
};
dalvare1 = {
uid = 2758;
isNormalUser = true;
home = "/home/Computational/dalvare1";
description = "David Álvarez";
group = "Computational";
hosts = [ "apex" "hut" "tent" "fox" ];
hashedPassword = "$6$mpyIsV3mdq.rK8$FvfZdRH5OcEkUt5PnIUijWyUYZvB1SgeqxpJ2p91TTe.3eQIDTcLEQ5rxeg.e5IEXAZHHQ/aMsR5kPEujEghx0";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGEfy6F4rF80r4Cpo2H5xaWqhuUZzUsVsILSKGJzt5jF dalvare1@ssfhead"
];
};
varcila = {
uid = 5650;
isNormalUser = true;
home = "/home/Computational/varcila";
description = "Vincent Arcila";
group = "Computational";
hosts = [ "apex" "hut" "tent" "fox" ];
hashedPassword = "$6$oB0Tcn99DcM4Ch$Vn1A0ulLTn/8B2oFPi9wWl/NOsJzaFAWjqekwcuC9sMC7cgxEVb.Nk5XSzQ2xzYcNe5MLtmzkVYnRS1CqP39Y0";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKGt0ESYxekBiHJQowmKpfdouw0hVm3N7tUMtAaeLejK vincent@varch"
];
};
pmartin1 = {
# Arbitrary UID but large so it doesn't collide with other users on ssfhead.
uid = 9652;
isNormalUser = true;
home = "/home/Computational/pmartin1";
description = "Pedro J. Martinez-Ferrer";
group = "Computational";
hosts = [ "fox" ];
hashedPassword = "$6$nIgDMGnt4YIZl3G.$.JQ2jXLtDPRKsbsJfJAXdSvjDIzRrg7tNNjPkLPq3KJQhMjfDXRUvzagUHUU2TrE2hHM8/6uq8ex0UdxQ0ysl.";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIV5LEAII5rfe1hYqDYIIrhb1gOw7RcS1p2mhOTqG+zc pedro@pedro-ThinkPad-P14s-Gen-2a"
];
};
};
groups = {
Computational = { gid = 564; };
tracing = { };
};
};
}

View File

@@ -2,7 +2,7 @@
{
# Use the GRUB 2 boot loader.
boot.loader.grub.enable = true;
boot.loader.grub.enable = lib.mkForce true;
# Enable GRUB2 serial console
boot.loader.grub.extraConfig = ''
@@ -11,12 +11,14 @@
terminal_output --append serial
'';
# Enable serial console
boot.kernelParams = [
"console=tty1"
"console=ttyS0,115200"
];
boot.kernel.sysctl = {
"kernel.perf_event_paranoid" = lib.mkDefault "-1";
# Allow ptracing (i.e. attach with GDB) any process of the same user, see:
# https://www.kernel.org/doc/Documentation/security/Yama.txt
"kernel.yama.ptrace_scope" = "0";
};
boot.kernelPackages = pkgs.linuxPackages_latest;

View File

@@ -13,12 +13,16 @@
[ { device = "/dev/disk/by-label/swap"; }
];
# Mount the home via NFS
fileSystems."/home" = {
device = "10.0.40.30:/home";
fsType = "nfs";
options = [ "nfsvers=3" "rsize=1024" "wsize=1024" "cto" "nofail" ];
};
# Tracing
fileSystems."/sys/kernel/tracing" = {
device = "none";
fsType = "tracefs";
};
# Mount a tmpfs into /tmp
boot.tmp.useTmpfs = true;
}

97
m/common/main.nix Normal file
View File

@@ -0,0 +1,97 @@
{ config, pkgs, nixpkgs, bscpkgs, agenix, theFlake, ... }:
{
imports = [
./agenix.nix
./boot.nix
./fs.nix
./hw.nix
./net.nix
./ntp.nix
./slurm.nix
./ssh.nix
./users.nix
./watchdog.nix
./rev.nix
./zsh.nix
];
nixpkgs.overlays = [
bscpkgs.bscOverlay
(import ../../pkgs/overlay.nix)
];
system.configurationRevision =
if theFlake ? rev
then theFlake.rev
else throw ("Refusing to build from a dirty Git tree!");
nix.nixPath = [
"nixpkgs=${nixpkgs}"
"jungle=${theFlake.outPath}"
];
nix.settings.flake-registry =
pkgs.writeText "global-registry.json" ''{"flakes":[],"version":2}'';
nix.registry.nixpkgs.flake = nixpkgs;
nix.registry.jungle.flake = theFlake;
environment.systemPackages = with pkgs; [
vim wget git htop tmux pciutils tcpdump ripgrep nix-index nixos-option
nix-diff ipmitool freeipmi ethtool lm_sensors ix cmake gnumake file tree
ncdu config.boot.kernelPackages.perf ldns
# From bsckgs overlay
bsc.osumb
];
programs.direnv.enable = true;
systemd.services."serial-getty@ttyS0" = {
enable = true;
wantedBy = [ "getty.target" ];
serviceConfig.Restart = "always";
};
# Increase limits
security.pam.loginLimits = [
{
domain = "*";
type = "-";
item = "memlock";
value = "1048576"; # 1 GiB of mem locked
}
];
time.timeZone = "Europe/Madrid";
i18n.defaultLocale = "en_DK.UTF-8";
environment.variables = {
EDITOR = "vim";
VISUAL = "vim";
};
nix.settings.experimental-features = [ "nix-command" "flakes" ];
nix.settings.sandbox = "relaxed";
nix.settings.trusted-users = [ "@wheel" ];
nix.gc.automatic = true;
nix.gc.dates = "weekly";
nix.gc.options = "--delete-older-than 30d";
programs.bash.promptInit = ''
PS1="\h\\$ "
'';
# Copy the NixOS configuration file and link it from the resulting system
# (/run/current-system/configuration.nix). This is useful in case you
# accidentally delete configuration.nix.
#system.copySystemConfiguration = true;
# This value determines the NixOS release from which the default
# settings for stateful data, like file locations and database versions
# on your system were taken. Its perfectly fine and recommended to leave
# this value at the release version of the first install of this system.
# Before changing this value read the documentation for this option
# (e.g. man configuration.nix or on https://nixos.org/nixos/options.html).
system.stateVersion = "22.11"; # Did you read the comment?
}

94
m/common/net.nix Normal file
View File

@@ -0,0 +1,94 @@
{ pkgs, ... }:
{
# Infiniband (IPoIB)
environment.systemPackages = [ pkgs.rdma-core ];
boot.kernelModules = [ "ib_umad" "ib_ipoib" ];
networking = {
enableIPv6 = false;
useDHCP = false;
defaultGateway = "10.0.40.30";
nameservers = ["8.8.8.8"];
proxy = {
default = "http://localhost:23080/";
noProxy = "127.0.0.1,localhost,internal.domain,10.0.40.40";
# Don't set all_proxy as go complains and breaks the gitlab runner, see:
# https://github.com/golang/go/issues/16715
allProxy = null;
};
firewall = {
enable = true;
allowedTCPPorts = [ 22 ];
extraCommands = ''
# Prevent ssfhead from contacting our slurmd daemon
iptables -A nixos-fw -p tcp -s ssfhead --dport 6817:6819 -j nixos-fw-log-refuse
# But accept traffic to slurm ports from any other node in the subnet
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 6817:6819 -j nixos-fw-accept
# We also need to open the srun port range
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 60000:61000 -j nixos-fw-accept
'';
};
extraHosts = ''
10.0.40.30 ssfhead
84.88.53.236 ssfhead.bsc.es ssfhead
# Node Entry for node: mds01 (ID=72)
10.0.40.40 bay mds01 mds01-eth0
10.0.42.40 bay-ib mds01-ib0
10.0.40.141 bay-ipmi mds01-ipmi0
# Node Entry for node: oss01 (ID=73)
10.0.40.41 oss01 oss01-eth0
10.0.42.41 oss01-ib0
10.0.40.142 oss01-ipmi0
# Node Entry for node: oss02 (ID=74)
10.0.40.42 lake2 oss02 oss02-eth0
10.0.42.42 lake2-ib oss02-ib0
10.0.40.143 lake2-ipmi oss02-ipmi0
# Node Entry for node: xeon01 (ID=15)
10.0.40.1 owl1 xeon01 xeon01-eth0
10.0.42.1 owl1-ib xeon01-ib0
10.0.40.101 owl1-ipmi xeon01-ipmi0
# Node Entry for node: xeon02 (ID=16)
10.0.40.2 owl2 xeon02 xeon02-eth0
10.0.42.2 owl2-ib xeon02-ib0
10.0.40.102 owl2-ipmi xeon02-ipmi0
# Node Entry for node: xeon03 (ID=17)
10.0.40.3 xeon03 xeon03-eth0
10.0.42.3 xeon03-ib0
10.0.40.103 xeon03-ipmi0
# Node Entry for node: xeon04 (ID=18)
10.0.40.4 xeon04 xeon04-eth0
10.0.42.4 xeon04-ib0
10.0.40.104 xeon04-ipmi0
# Node Entry for node: xeon05 (ID=19)
10.0.40.5 koro xeon05 xeon05-eth0
10.0.42.5 koro-ib xeon05-ib0
10.0.40.105 koro-ipmi xeon05-ipmi0
# Node Entry for node: xeon06 (ID=20)
10.0.40.6 xeon06 xeon06-eth0
10.0.42.6 xeon06-ib0
10.0.40.106 xeon06-ipmi0
# Node Entry for node: xeon07 (ID=21)
10.0.40.7 hut xeon07 xeon07-eth0
10.0.42.7 hut-ib xeon07-ib0
10.0.40.107 hut-ipmi xeon07-ipmi0
# Node Entry for node: xeon08 (ID=22)
10.0.40.8 eudy xeon08 xeon08-eth0
10.0.42.8 eudy-ib xeon08-ib0
10.0.40.108 eudy-ipmi xeon08-ipmi0
'';
};
}

View File

@@ -1,7 +1,6 @@
{ theFlake, ... }:
let
# Prevent building a configuration without revision
rev = if theFlake ? rev then theFlake.rev
else throw ("Refusing to build from a dirty Git tree!");
in {
@@ -16,6 +15,4 @@ in {
DATENOW=$(date --iso-8601=seconds)
echo "$DATENOW booted=$BOOTED current=$CURRENT next=$NEXT" >> /var/configrev.log
'';
system.configurationRevision = rev;
}

View File

@@ -47,7 +47,8 @@ in {
];
partitionName = [
"owl Nodes=owl[1-2] Default=YES DefaultTime=01:00:00 MaxTime=INFINITE State=UP"
"owl Nodes=owl[1-2] Default=YES MaxTime=INFINITE State=UP"
"all Nodes=owl[1-2],hut Default=NO MaxTime=INFINITE State=UP"
];
# See slurm.conf(5) for more details about these options.
@@ -82,37 +83,9 @@ in {
# Reduce port range so we can allow only this range in the firewall
SrunPortRange=60000-61000
# Use cores as consumable resources. In SLURM terms, a core may have
# multiple hardware threads (or CPUs).
SelectType=select/cons_tres
# Ignore memory constraints and only use unused cores to share a node with
# other jobs.
SelectTypeParameters=CR_Core
# Required for pam_slurm_adopt, see https://slurm.schedmd.com/pam_slurm_adopt.html
# This sets up the "extern" step into which ssh-launched processes will be
# adopted. Alloc runs the prolog at job allocation (salloc) rather than
# when a task runs (srun) so we can ssh early.
PrologFlags=Alloc,Contain,X11
# LaunchParameters=ulimit_pam_adopt will set RLIMIT_RSS in processes
# adopted by the external step, similar to tasks running in regular steps
# LaunchParameters=ulimit_pam_adopt
SlurmdDebug=debug5
#DebugFlags=Protocol,Cgroup
'';
extraCgroupConfig = ''
CgroupPlugin=cgroup/v2
#ConstrainCores=yes
'';
};
# Place the slurm config in /etc as this will be required by PAM
environment.etc.slurm.source = config.services.slurm.etcSlurm;
age.secrets.mungeKey = {
file = ../../secrets/munge-key.age;
owner = "munge";

View File

@@ -1,10 +0,0 @@
{
# Provides the base system for a xeon node in the SSF rack.
imports = [
./xeon.nix
./ssf/fs.nix
./ssf/hosts.nix
./ssf/net.nix
./ssf/ssh.nix
];
}

View File

@@ -1,8 +0,0 @@
{
# Mount the home via NFS
fileSystems."/home" = {
device = "10.0.40.30:/home";
fsType = "nfs";
options = [ "nfsvers=3" "rsize=1024" "wsize=1024" "cto" "nofail" ];
};
}

View File

@@ -1,23 +0,0 @@
{ pkgs, ... }:
{
networking.hosts = {
# Login
"10.0.40.30" = [ "apex" ];
# Storage
"10.0.40.40" = [ "bay" ]; "10.0.42.40" = [ "bay-ib" ]; "10.0.40.141" = [ "bay-ipmi" ];
"10.0.40.41" = [ "oss01" ]; "10.0.42.41" = [ "oss01-ib0" ]; "10.0.40.142" = [ "oss01-ipmi" ];
"10.0.40.42" = [ "lake2" ]; "10.0.42.42" = [ "lake2-ib" ]; "10.0.40.143" = [ "lake2-ipmi" ];
# Xeon compute
"10.0.40.1" = [ "owl1" ]; "10.0.42.1" = [ "owl1-ib" ]; "10.0.40.101" = [ "owl1-ipmi" ];
"10.0.40.2" = [ "owl2" ]; "10.0.42.2" = [ "owl2-ib" ]; "10.0.40.102" = [ "owl2-ipmi" ];
"10.0.40.3" = [ "xeon03" ]; "10.0.42.3" = [ "xeon03-ib" ]; "10.0.40.103" = [ "xeon03-ipmi" ];
#"10.0.40.4" = [ "tent" ]; "10.0.42.4" = [ "tent-ib" ]; "10.0.40.104" = [ "tent-ipmi" ];
"10.0.40.5" = [ "koro" ]; "10.0.42.5" = [ "koro-ib" ]; "10.0.40.105" = [ "koro-ipmi" ];
"10.0.40.6" = [ "weasel" ]; "10.0.42.6" = [ "weasel-ib" ]; "10.0.40.106" = [ "weasel-ipmi" ];
"10.0.40.7" = [ "hut" ]; "10.0.42.7" = [ "hut-ib" ]; "10.0.40.107" = [ "hut-ipmi" ];
"10.0.40.8" = [ "eudy" ]; "10.0.42.8" = [ "eudy-ib" ]; "10.0.40.108" = [ "eudy-ipmi" ];
};
}

View File

@@ -1,23 +0,0 @@
{ pkgs, ... }:
{
# Infiniband (IPoIB)
environment.systemPackages = [ pkgs.rdma-core ];
boot.kernelModules = [ "ib_umad" "ib_ipoib" ];
networking = {
defaultGateway = "10.0.40.30";
nameservers = ["8.8.8.8"];
firewall = {
extraCommands = ''
# Prevent ssfhead from contacting our slurmd daemon
iptables -A nixos-fw -p tcp -s ssfhead --dport 6817:6819 -j nixos-fw-refuse
# But accept traffic to slurm ports from any other node in the subnet
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 6817:6819 -j nixos-fw-accept
# We also need to open the srun port range
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 60000:61000 -j nixos-fw-accept
'';
};
};
}

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

@@ -1,18 +1,22 @@
{ lib, ... }:
let
keys = import ../../../keys.nix;
keys = import ../../keys.nix;
hostsKeys = lib.mapAttrs (name: value: { publicKey = value; }) keys.hosts;
in
{
# Enable the OpenSSH daemon.
services.openssh.enable = true;
# Connect to intranet git hosts via proxy
programs.ssh.extraConfig = ''
Host bscpm02.bsc.es bscpm03.bsc.es gitlab-internal.bsc.es alya.gitlab.bsc.es
User git
ProxyCommand nc -X connect -x localhost:23080 %h %p
'';
programs.ssh.knownHosts = hostsKeys // {
"gitlab-internal.bsc.es".publicKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIF9arsAOSRB06hdy71oTvJHG2Mg8zfebADxpvc37lZo3";
"bscpm03.bsc.es".publicKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIM2NuSUPsEhqz1j5b4Gqd+MWFnRqyqY57+xMvBUqHYUS";
"bscpm04.bsc.es".publicKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPx4mC0etyyjYUT2Ztc/bs4ZXSbVMrogs1ZTP924PDgT";
"glogin1.bsc.es".publicKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFsHsZGCrzpd4QDVn5xoDOtrNBkb0ylxKGlyBt6l9qCz";
"glogin2.bsc.es".publicKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFsHsZGCrzpd4QDVn5xoDOtrNBkb0ylxKGlyBt6l9qCz";
};
}

75
m/common/users.nix Normal file
View File

@@ -0,0 +1,75 @@
{ pkgs, ... }:
{
users = {
mutableUsers = false;
users = {
# Generate hashedPassword with `mkpasswd -m sha-512`
root.openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKBOf4r4lzQfyO0bx5BaREePREw8Zw5+xYgZhXwOZoBO ram@hop"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINa0tvnNgwkc5xOwd6xTtaIdFi5jv0j2FrE7jl5MTLoE ram@mio"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIF3zeB5KSimMBAjvzsp1GCkepVaquVZGPYwRIzyzaCba aleix@bsc"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIII/1TNArcwA6D47mgW4TArwlxQRpwmIGiZDysah40Gb root@hut"
];
rarias = {
uid = 1880;
isNormalUser = true;
home = "/home/Computational/rarias";
description = "Rodrigo Arias";
group = "Computational";
extraGroups = [ "wheel" ];
hashedPassword = "$6$u06tkCy13enReBsb$xiI.twRvvTfH4jdS3s68NZ7U9PSbGKs5.LXU/UgoawSwNWhZo2hRAjNL5qG0/lAckzcho2LjD0r3NfVPvthY6/";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKBOf4r4lzQfyO0bx5BaREePREw8Zw5+xYgZhXwOZoBO ram@hop"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINa0tvnNgwkc5xOwd6xTtaIdFi5jv0j2FrE7jl5MTLoE ram@mio"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGYcXIxe0poOEGLpk8NjiRozls7fMRX0N3j3Ar94U+Gl rarias@hal"
];
shell = pkgs.zsh;
};
arocanon = {
uid = 1042;
isNormalUser = true;
home = "/home/Computational/arocanon";
description = "Aleix Roca";
group = "Computational";
extraGroups = [ "wheel" ];
hashedPassword = "$6$hliZiW4tULC/tH7p$pqZarwJkNZ7vS0G5llWQKx08UFG9DxDYgad7jplMD8WkZh5k58i4dfPoWtnEShfjTO6JHiIin05ny5lmSXzGM/";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIF3zeB5KSimMBAjvzsp1GCkepVaquVZGPYwRIzyzaCba aleix@bsc"
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGdphWxLAEekicZ/WBrvP7phMyxKSSuLAZBovNX+hZXQ aleix@kerneland"
];
};
rpenacob = {
uid = 2761;
isNormalUser = true;
home = "/home/Computational/rpenacob";
description = "Raúl Peñacoba";
group = "Computational";
hashedPassword = "$6$TZm3bDIFyPrMhj1E$uEDXoYYd1z2Wd5mMPfh3DZAjP7ztVjJ4ezIcn82C0ImqafPA.AnTmcVftHEzLB3tbe2O4SxDyPSDEQgJ4GOtj/";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFYfXg37mauGeurqsLpedgA2XQ9d4Nm0ZGo/hI1f7wwH rpenacob@bsc"
];
};
anavarro = {
uid = 1037;
isNormalUser = true;
home = "/home/Computational/anavarro";
description = "Antoni Navarro";
group = "Computational";
hashedPassword = "$6$QdNDsuLehoZTYZlb$CDhCouYDPrhoiB7/seu7RF.Gqg4zMQz0n5sA4U1KDgHaZOxy2as9pbIGeF8tOHJKRoZajk5GiaZv0rZMn7Oq31";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAILWjRSlKgzBPZQhIeEtk6Lvws2XNcYwHcwPv4osSgst5 anavarro@ssfhead"
];
};
};
groups = {
Computational = { gid = 564; };
};
};
}

View File

@@ -1,7 +0,0 @@
{
# Provides the base system for a xeon node, not necessarily in the SSF rack.
imports = [
./base.nix
./xeon/console.nix
];
}

View File

@@ -1,14 +0,0 @@
{
# Restart the serial console
systemd.services."serial-getty@ttyS0" = {
enable = true;
wantedBy = [ "getty.target" ];
serviceConfig.Restart = "always";
};
# Enable serial console
boot.kernelParams = [
"console=tty1"
"console=ttyS0,115200"
];
}

View File

@@ -2,14 +2,14 @@
{
imports = [
../common/ssf.nix
../common/main.nix
#(modulesPath + "/installer/netboot/netboot-minimal.nix")
./kernel/kernel.nix
./cpufreq.nix
./fs.nix
./users.nix
../module/debuginfod.nix
./slurm.nix
];
# Select this using the ID to avoid mismatches

View File

@@ -21,9 +21,9 @@ let
# configfile = if lockdep then ./configs/lockdep else ./configs/defconfig;
#};
kernel = nixos-fcs;
kernel = nixos-fcsv3;
nixos-fcs-kernel = lib.makeOverridable ({gitCommit, lockStat ? false, preempt ? false, branch ? "fcs"}: pkgs.linuxPackagesFor (pkgs.buildLinux rec {
nixos-fcs-kernel = {gitCommit, lockStat ? false, preempt ? false, branch ? "fcs"}: pkgs.linuxPackagesFor (pkgs.buildLinux rec {
version = "6.2.8";
src = builtins.fetchGit {
url = "git@bscpm03.bsc.es:ompss-kernel/linux.git";
@@ -40,13 +40,35 @@ let
};
kernelPatches = [];
extraMeta.branch = lib.versions.majorMinor version;
}));
});
nixos-fcs = nixos-fcs-kernel {gitCommit = "8a09822dfcc8f0626b209d6d2aec8b5da459dfee";};
nixos-fcs-lockstat = nixos-fcs.override {
nixos-fcsv1 = nixos-fcs-kernel {gitCommit = "bc11660676d3d68ce2459b9fb5d5e654e3f413be";};
nixos-fcsv2 = nixos-fcs-kernel {gitCommit = "db0f2eca0cd57a58bf456d7d2c7d5d8fdb25dfb1";};
nixos-fcsv3 = nixos-fcs-kernel {gitCommit = "6c17394890704c3345ac1a521bb547164b36b154";};
# always use fcs_sched_setaffinity
#nixos-debug = nixos-fcs-kernel {gitCommit = "7d0bf285fca92badc8df3c9907a9ab30db4418aa";};
# remove need_check_cgroup
#nixos-debug = nixos-fcs-kernel {gitCommit = "4cc4efaab5e4a0bfa3089e935215b981c1922919";};
# merge again fcs_wake and fcs_wait
#nixos-debug = nixos-fcs-kernel {gitCommit = "40c6f72f4ae54b0b636b193ac0648fb5730c810d";};
# start from scratch, this is the working version with split fcs_wake and fcs_wait
nixos-debug = nixos-fcs-kernel {gitCommit = "c9a39d6a4ca83845b4e71fcc268fb0a76aff1bdf"; branch = "fcs-test"; };
nixos-fcsv1-lockstat = nixos-fcs-kernel {
gitCommit = "bc11660676d3d68ce2459b9fb5d5e654e3f413be";
lockStat = true;
};
nixos-fcs-lockstat-preempt = nixos-fcs.override {
nixos-fcsv2-lockstat = nixos-fcs-kernel {
gitCommit = "db0f2eca0cd57a58bf456d7d2c7d5d8fdb25dfb1";
lockStat = true;
};
nixos-fcsv3-lockstat = nixos-fcs-kernel {
gitCommit = "6c17394890704c3345ac1a521bb547164b36b154";
lockStat = true;
};
nixos-fcsv3-lockstat-preempt = nixos-fcs-kernel {
gitCommit = "6c17394890704c3345ac1a521bb547164b36b154";
lockStat = true;
preempt = true;
};

7
m/eudy/slurm.nix Normal file
View File

@@ -0,0 +1,7 @@
{ lib, ... }:
{
services.slurm = {
client.enable = lib.mkForce false;
};
}

View File

@@ -1,80 +0,0 @@
{ lib, config, pkgs, ... }:
{
imports = [
../common/base.nix
../common/xeon/console.nix
../module/emulation.nix
../module/nvidia.nix
];
# Select the this using the ID to avoid mismatches
boot.loader.grub.device = "/dev/disk/by-id/wwn-0x500a07514b0c1103";
# No swap, there is plenty of RAM
swapDevices = lib.mkForce [];
boot.initrd.availableKernelModules = [ "xhci_pci" "ahci" "nvme" "usbhid" "usb_storage" "sd_mod" ];
boot.kernelModules = [ "kvm-amd" "amd_uncore" ];
hardware.cpu.amd.updateMicrocode = lib.mkDefault config.hardware.enableRedistributableFirmware;
hardware.cpu.intel.updateMicrocode = lib.mkForce false;
# Use performance for benchmarks
powerManagement.cpuFreqGovernor = "performance";
# Disable NUMA balancing
boot.kernel.sysctl."kernel.numa_balancing" = 0;
# Expose kernel addresses
boot.kernel.sysctl."kernel.kptr_restrict" = 0;
services.openssh.settings.X11Forwarding = true;
networking = {
timeServers = [ "ntp1.upc.edu" "ntp2.upc.edu" ];
hostName = "fox";
# UPC network (may change over time, use DHCP)
# Public IP configuration:
# - Hostname: fox.ac.upc.edu
# - IP: 147.83.30.141
# - Gateway: 147.83.30.130
# - NetMask: 255.255.255.192
# Private IP configuration for BMC:
# - Hostname: fox-ipmi.ac.upc.edu
# - IP: 147.83.35.27
# - Gateway: 147.83.35.2
# - NetMask: 255.255.255.0
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;
# Mount NVME disks
fileSystems."/nvme0" = { device = "/dev/disk/by-label/nvme0"; fsType = "ext4"; };
fileSystems."/nvme1" = { device = "/dev/disk/by-label/nvme1"; fsType = "ext4"; };
# Make a /nvme{0,1}/$USER directory for each user.
systemd.services.create-nvme-dirs = let
# Take only normal users in fox
users = lib.filterAttrs (_: v: v.isNormalUser) config.users.users;
commands = lib.concatLists (lib.mapAttrsToList
(_: user: [
"install -d -o ${user.name} -g ${user.group} -m 0755 /nvme{0,1}/${user.name}"
]) users);
script = pkgs.writeShellScript "create-nvme-dirs.sh" (lib.concatLines commands);
in {
enable = true;
wants = [ "local-fs.target" ];
after = [ "local-fs.target" ];
wantedBy = [ "multi-user.target" ];
serviceConfig.ExecStart = script;
};
}

View File

@@ -1,14 +0,0 @@
modules:
http_2xx:
prober: http
timeout: 5s
http:
follow_redirects: true
preferred_ip_protocol: "ip4"
valid_status_codes: [] # Defaults to 2xx
method: GET
icmp:
prober: icmp
timeout: 5s
icmp:
preferred_ip_protocol: "ip4"

View File

@@ -1,44 +1,22 @@
{ config, pkgs, lib, ... }:
{ config, pkgs, ... }:
{
imports = [
../common/ssf.nix
../common/main.nix
../module/ceph.nix
../module/debuginfod.nix
../module/emulation.nix
../module/slurm-client.nix
./gitlab-runner.nix
./monitoring.nix
./nfs.nix
./slurm-server.nix
./slurm-daemon.nix
./nix-serve.nix
./public-inbox.nix
./gitea.nix
./msmtp.nix
./postgresql.nix
./nginx.nix
./p.nix
#./pxe.nix
];
boot.binfmt.emulatedSystems = [ "aarch64-linux" "powerpc64le-linux" "riscv64-linux" ];
# Select the this using the ID to avoid mismatches
boot.loader.grub.device = "/dev/disk/by-id/wwn-0x55cd2e414d53567f";
fileSystems = {
"/" = lib.mkForce {
device = "/dev/disk/by-label/nvme";
fsType = "ext4";
neededForBoot = true;
options = [ "noatime" ];
};
"/boot" = lib.mkForce {
device = "/dev/disk/by-label/nixos-boot";
fsType = "ext4";
neededForBoot = true;
};
};
boot.loader.grub.device = "/dev/disk/by-id/ata-INTEL_SSDSC2BB240G7_PHDV6462004Y240AGN";
networking = {
hostName = "hut";
@@ -50,20 +28,5 @@
address = "10.0.42.7";
prefixLength = 24;
} ];
firewall = {
extraCommands = ''
# Accept all proxy traffic from compute nodes but not the login
iptables -A nixos-fw -p tcp -s 10.0.40.30 --dport 23080 -j nixos-fw-log-refuse
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 23080 -j nixos-fw-accept
'';
# Flush all rules and chains on stop so it won't break on start
extraStopCommands = ''
iptables -F
iptables -X
'';
};
};
# Allow proxy to bind to the ethernet interface
services.openssh.settings.GatewayPorts = "clientspecified";
}

View File

@@ -1,63 +0,0 @@
{ config, lib, ... }:
{
age.secrets.giteaRunnerToken.file = ../../secrets/gitea-runner-token.age;
services.gitea = {
enable = true;
appName = "Gitea in the jungle";
settings = {
server = {
ROOT_URL = "https://jungle.bsc.es/git/";
LOCAL_ROOT_URL = "https://jungle.bsc.es/git/";
LANDING_PAGE = "explore";
};
metrics.ENABLED = true;
service = {
REGISTER_MANUAL_CONFIRM = true;
ENABLE_NOTIFY_MAIL = true;
};
log.LEVEL = "Warn";
mailer = {
ENABLED = true;
FROM = "jungle-robot@bsc.es";
PROTOCOL = "sendmail";
SENDMAIL_PATH = "/run/wrappers/bin/sendmail";
SENDMAIL_ARGS = "--";
};
};
};
services.gitea-actions-runner.instances = {
runrun = {
enable = true;
name = "runrun";
url = "https://jungle.bsc.es/git/";
tokenFile = config.age.secrets.giteaRunnerToken.path;
labels = [ "native:host" ];
settings.runner.capacity = 8;
};
};
systemd.services.gitea-runner-runrun = {
path = [ "/run/current-system/sw" ];
serviceConfig = {
# DynamicUser doesn't work well with SSH
DynamicUser = lib.mkForce false;
User = "gitea-runner";
Group = "gitea-runner";
};
};
users.users.gitea-runner = {
isSystemUser = true;
home = "/var/lib/gitea-runner";
description = "Gitea Runner";
group = "gitea-runner";
extraGroups = [ "docker" ];
createHome = true;
};
users.groups.gitea-runner = {};
}

View File

@@ -1,111 +1,54 @@
{ pkgs, lib, config, ... }:
{
age.secrets.gitlab-pm-shell.file = ../../secrets/gitlab-runner-shell-token.age;
age.secrets.gitlab-pm-docker.file = ../../secrets/gitlab-runner-docker-token.age;
age.secrets.gitlab-bsc-docker.file = ../../secrets/gitlab-bsc-docker-token.age;
age.secrets.ovniToken.file = ../../secrets/ovni-token.age;
age.secrets.nosvToken.file = ../../secrets/nosv-token.age;
services.gitlab-runner = {
enable = true;
settings.concurrent = 5;
services = let
common-shell = {
services = {
ovni-shell = {
registrationConfigFile = config.age.secrets.ovniToken.path;
executor = "shell";
tagList = [ "nix" "xeon" ];
registrationFlags = [
# Using space doesn't work, and causes it to misread the next flag
"--locked='false'"
];
environmentVariables = {
SHELL = "${pkgs.bash}/bin/bash";
};
};
common-docker = {
executor = "docker";
ovni-docker = {
registrationConfigFile = config.age.secrets.ovniToken.path;
dockerImage = "debian:stable";
tagList = [ "docker" "xeon" ];
registrationFlags = [
"--locked='false'"
"--docker-network-mode host"
];
environmentVariables = {
https_proxy = "http://hut:23080";
http_proxy = "http://hut:23080";
https_proxy = "http://localhost:23080";
http_proxy = "http://localhost:23080";
};
};
in {
# For pm.bsc.es/gitlab
gitlab-pm-shell = common-shell // {
authenticationTokenConfigFile = config.age.secrets.gitlab-pm-shell.path;
};
gitlab-pm-docker = common-docker // {
authenticationTokenConfigFile = config.age.secrets.gitlab-pm-docker.path;
};
gitlab-bsc-docker = {
# gitlab.bsc.es still uses the old token mechanism
registrationConfigFile = config.age.secrets.gitlab-bsc-docker.path;
tagList = [ "docker" "hut" ];
environmentVariables = {
# We cannot access the hut local interface from docker, so we connect
# to hut directly via the ethernet one.
https_proxy = "http://hut:23080";
http_proxy = "http://hut:23080";
};
executor = "docker";
dockerImage = "alpine";
dockerVolumes = [
"/nix/store:/nix/store:ro"
"/nix/var/nix/db:/nix/var/nix/db:ro"
"/nix/var/nix/daemon-socket:/nix/var/nix/daemon-socket:ro"
];
dockerExtraHosts = [
# Required to pass the proxy via hut
"hut:10.0.40.7"
];
dockerDisableCache = true;
nosv-docker = {
registrationConfigFile = config.age.secrets.nosvToken.path;
dockerImage = "debian:stable";
tagList = [ "docker" "xeon" ];
registrationFlags = [
# Increase build log length to 64 MiB
"--output-limit 65536"
"--docker-network-mode host"
"--docker-cpus 56"
];
preBuildScript = pkgs.writeScript "setup-container" ''
mkdir -p -m 0755 /nix/var/log/nix/drvs
mkdir -p -m 0755 /nix/var/nix/gcroots
mkdir -p -m 0755 /nix/var/nix/profiles
mkdir -p -m 0755 /nix/var/nix/temproots
mkdir -p -m 0755 /nix/var/nix/userpool
mkdir -p -m 1777 /nix/var/nix/gcroots/per-user
mkdir -p -m 1777 /nix/var/nix/profiles/per-user
mkdir -p -m 0755 /nix/var/nix/profiles/per-user/root
mkdir -p -m 0700 "$HOME/.nix-defexpr"
mkdir -p -m 0700 "$HOME/.ssh"
cat > "$HOME/.ssh/config" << EOF
Host bscpm04.bsc.es gitlab-internal.bsc.es
User git
ProxyCommand nc -X connect -x hut:23080 %h %p
Host amdlogin1.bsc.es armlogin1.bsc.es hualogin1.bsc.es glogin1.bsc.es glogin2.bsc.es fpgalogin1.bsc.es
ProxyCommand nc -X connect -x hut:23080 %h %p
EOF
cat >> "$HOME/.ssh/known_hosts" << EOF
bscpm04.bsc.es ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPx4mC0etyyjYUT2Ztc/bs4ZXSbVMrogs1ZTP924PDgT
gitlab-internal.bsc.es ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIF9arsAOSRB06hdy71oTvJHG2Mg8zfebADxpvc37lZo3
EOF
. ${pkgs.nix}/etc/profile.d/nix-daemon.sh
# Required to load SSL certificate paths
. ${pkgs.cacert}/nix-support/setup-hook
'';
environmentVariables = {
ENV = "/etc/profile";
USER = "root";
NIX_REMOTE = "daemon";
PATH = "${config.system.path}/bin:/bin:/sbin:/usr/bin:/usr/sbin";
https_proxy = "http://localhost:23080";
http_proxy = "http://localhost:23080";
};
};
};
};
# DOCKER* chains are useless, override at FORWARD and nixos-fw
networking.firewall.extraCommands = ''
# Don't forward any traffic from docker
iptables -I FORWARD 1 -p all -i docker0 -j nixos-fw-log-refuse
# Allow incoming traffic from docker to 23080
iptables -A nixos-fw -p tcp -i docker0 -d hut --dport 23080 -j ACCEPT
'';
#systemd.services.gitlab-runner.serviceConfig.Shell = "${pkgs.bash}/bin/bash";
systemd.services.gitlab-runner.serviceConfig.DynamicUser = lib.mkForce false;
systemd.services.gitlab-runner.serviceConfig.User = "gitlab-runner";

View File

@@ -1,31 +0,0 @@
{ pkgs, config, lib, ... }:
let
gpfs-probe-script = pkgs.runCommand "gpfs-probe.sh" { }
''
cp ${./gpfs-probe.sh} $out;
chmod +x $out
''
;
in
{
# Use a new user to handle the SSH keys
users.groups.ssh-robot = { };
users.users.ssh-robot = {
description = "SSH Robot";
isNormalUser = true;
home = "/var/lib/ssh-robot";
};
systemd.services.gpfs-probe = {
description = "Daemon to report GPFS latency via SSH";
path = [ pkgs.openssh pkgs.netcat ];
after = [ "network.target" ];
wantedBy = [ "default.target" ];
serviceConfig = {
Type = "simple";
ExecStart = "${pkgs.socat}/bin/socat TCP4-LISTEN:9966,fork EXEC:${gpfs-probe-script}";
User = "ssh-robot";
Group = "ssh-robot";
};
};
}

View File

@@ -1,18 +0,0 @@
#!/bin/sh
N=500
t=$(timeout 5 ssh bsc015557@glogin2.bsc.es "timeout 3 command time -f %e touch /gpfs/projects/bsc15/bsc015557/gpfs.{1..$N} 2>&1; rm -f /gpfs/projects/bsc15/bsc015557/gpfs.{1..$N}")
if [ -z "$t" ]; then
t="5.00"
fi
cat <<EOF
HTTP/1.1 200 OK
Content-Type: text/plain; version=0.0.4; charset=utf-8; escaping=values
# HELP gpfs_touch_latency Time to create $N files.
# TYPE gpfs_touch_latency gauge
gpfs_touch_latency $t
EOF

13
m/hut/ipmi.yml Normal file
View File

@@ -0,0 +1,13 @@
modules:
default:
collectors:
- bmc
- ipmi
- chassis
lan:
collectors:
- ipmi
- chassis
user: ""
pass: ""

View File

@@ -1,22 +1,6 @@
{ config, lib, ... }:
{
imports = [
../module/slurm-exporter.nix
../module/meteocat-exporter.nix
../module/upc-qaire-exporter.nix
./gpfs-probe.nix
../module/nix-daemon-exporter.nix
];
age.secrets.grafanaJungleRobotPassword = {
file = ../../secrets/jungle-robot-password.age;
owner = "grafana";
mode = "400";
};
age.secrets.ipmiYml.file = ../../secrets/ipmi.yml.age;
services.grafana = {
enable = true;
settings = {
@@ -27,29 +11,14 @@
http_port = 2342;
http_addr = "127.0.0.1";
};
smtp = {
enabled = true;
from_address = "jungle-robot@bsc.es";
user = "jungle-robot";
# Read the password from a file, which is only readable by grafana user
# https://grafana.com/docs/grafana/latest/setup-grafana/configure-grafana/#file-provider
password = "$__file{${config.age.secrets.grafanaJungleRobotPassword.path}}";
host = "mail.bsc.es:465";
startTLS_policy = "NoStartTLS";
};
feature_toggles.publicDashboards = true;
"auth.anonymous".enabled = true;
log.level = "warn";
};
};
# Make grafana alerts also use the proxy
systemd.services.grafana.environment = config.networking.proxy.envVars;
services.prometheus = {
enable = true;
port = 9001;
retentionTime = "5y";
retentionTime = "1y";
listenAddress = "127.0.0.1";
};
@@ -78,13 +47,13 @@
enable = true;
group = "root";
user = "root";
configFile = config.age.secrets.ipmiYml.path;
# extraFlags = [ "--log.level=debug" ];
configFile = ./ipmi.yml;
#extraFlags = [ "--log.level=debug" ];
listenAddress = "127.0.0.1";
};
node = {
enable = true;
enabledCollectors = [ "systemd" "logind" ];
enabledCollectors = [ "systemd" ];
port = 9002;
listenAddress = "127.0.0.1";
};
@@ -92,11 +61,6 @@
enable = true;
listenAddress = "127.0.0.1";
};
blackbox = {
enable = true;
listenAddress = "127.0.0.1";
configFile = ./blackbox.yml;
};
};
scrapeConfigs = [
@@ -109,12 +73,6 @@
"127.0.0.1:9323"
"127.0.0.1:9252"
"127.0.0.1:${toString config.services.prometheus.exporters.smartctl.port}"
"127.0.0.1:9341" # Slurm exporter
"127.0.0.1:9966" # GPFS custom exporter
"127.0.0.1:9999" # Nix-daemon custom exporter
"127.0.0.1:9929" # Meteocat custom exporter
"127.0.0.1:9928" # UPC Qaire custom exporter
"127.0.0.1:${toString config.services.prometheus.exporters.blackbox.port}"
];
}];
}
@@ -128,74 +86,6 @@
];
}];
}
{
job_name = "blackbox-http";
metrics_path = "/probe";
params = { module = [ "http_2xx" ]; };
static_configs = [{
targets = [
"https://www.google.com/robots.txt"
"https://pm.bsc.es/"
"https://pm.bsc.es/gitlab/"
"https://jungle.bsc.es/"
"https://gitlab.bsc.es/"
];
}];
relabel_configs = [
{
# Takes the address and sets it in the "target=<xyz>" URL parameter
source_labels = [ "__address__" ];
target_label = "__param_target";
}
{
# Sets the "instance" label with the remote host we are querying
source_labels = [ "__param_target" ];
target_label = "instance";
}
{
# Shows the host target address instead of the blackbox address
target_label = "__address__";
replacement = "127.0.0.1:${toString config.services.prometheus.exporters.blackbox.port}";
}
];
}
{
job_name = "blackbox-icmp";
metrics_path = "/probe";
params = { module = [ "icmp" ]; };
static_configs = [{
targets = [
"1.1.1.1"
"8.8.8.8"
"ssfhead"
"anella-bsc.cesca.cat"
"upc-anella.cesca.cat"
"fox.ac.upc.edu"
"arenys5.ac.upc.edu"
];
}];
relabel_configs = [
{
# Takes the address and sets it in the "target=<xyz>" URL parameter
source_labels = [ "__address__" ];
target_label = "__param_target";
}
{
# Sets the "instance" label with the remote host we are querying
source_labels = [ "__param_target" ];
target_label = "instance";
}
{
# Shows the host target address instead of the blackbox address
target_label = "__address__";
replacement = "127.0.0.1:${toString config.services.prometheus.exporters.blackbox.port}";
}
];
}
{
job_name = "gitea";
static_configs = [{ targets = [ "127.0.0.1:3000" ]; }];
}
{
# Scrape the IPMI info of the hosts remotely via LAN
job_name = "ipmi-lan";
@@ -217,7 +107,7 @@
# Sets the "instance" label with the remote host we are querying
source_labels = [ "__param_target" ];
separator = ";";
regex = "(.*)-ipmi"; # Remove "-ipm̀i" at the end
regex = "(.*)";
target_label = "instance";
replacement = "\${1}";
action = "replace";
@@ -248,25 +138,6 @@
}
];
}
{
job_name = "ipmi-raccoon";
metrics_path = "/ipmi";
static_configs = [
{ targets = [ "127.0.0.1:9291" ]; }
];
params = {
target = [ "84.88.51.142" ];
module = [ "raccoon" ];
};
}
{
job_name = "raccoon";
static_configs = [
{
targets = [ "127.0.0.1:19002" ]; # Node exporter
}
];
}
];
};
}

View File

@@ -1,24 +0,0 @@
{ config, lib, ... }:
{
age.secrets.jungleRobotPassword = {
file = ../../secrets/jungle-robot-password.age;
group = "gitea";
mode = "440";
};
programs.msmtp = {
enable = true;
accounts = {
default = {
auth = true;
tls = true;
tls_starttls = false;
port = 465;
host = "mail.bsc.es";
user = "jungle-robot";
passwordeval = "cat ${config.age.secrets.jungleRobotPassword.path}";
from = "jungle-robot@bsc.es";
};
};
};
}

View File

@@ -1,73 +0,0 @@
{ theFlake, pkgs, ... }:
let
website = pkgs.stdenv.mkDerivation {
name = "jungle-web";
src = theFlake;
buildInputs = [ pkgs.hugo ];
buildPhase = ''
cd web
rm -rf public/
hugo
'';
installPhase = ''
cp -r public $out
'';
# Don't mess doc/
dontFixup = true;
};
in
{
networking.firewall.allowedTCPPorts = [ 80 ];
services.nginx = {
enable = true;
virtualHosts."jungle.bsc.es" = {
root = "${website}";
listen = [
{
addr = "0.0.0.0";
port = 80;
}
];
extraConfig = ''
set_real_ip_from 127.0.0.1;
set_real_ip_from 84.88.52.107;
real_ip_recursive on;
real_ip_header X-Forwarded-For;
location /git {
rewrite ^/git$ / break;
rewrite ^/git/(.*) /$1 break;
proxy_pass http://127.0.0.1:3000;
proxy_redirect http:// $scheme://;
}
location /cache {
rewrite ^/cache/(.*) /$1 break;
proxy_pass http://127.0.0.1:5000;
proxy_redirect http:// $scheme://;
}
location /lists {
proxy_pass http://127.0.0.1:8081;
proxy_redirect http:// $scheme://;
}
location /grafana {
proxy_pass http://127.0.0.1:2342;
proxy_redirect http:// $scheme://;
proxy_set_header Host $host;
# Websockets
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
}
location ~ ^/~(.+?)(/.*)?$ {
alias /ceph/home/$1/public_html$2;
index index.html index.htm;
autoindex on;
absolute_redirect off;
}
location /p/ {
alias /ceph/p/;
}
'';
};
};
}

View File

@@ -1,43 +0,0 @@
{ pkgs, lib, config, ... }:
let
p = pkgs.writeShellScriptBin "p" ''
set -e
cd /ceph
pastedir="p/$USER"
mkdir -p "$pastedir"
ext="txt"
if [ -n "$1" ]; then
ext="$1"
fi
out=$(mktemp "$pastedir/XXXXXXXX.$ext")
cat > "$out"
chmod go+r "$out"
echo "https://jungle.bsc.es/$out"
'';
in
{
environment.systemPackages = with pkgs; [ p ];
# Make sure we have a directory per user. We cannot use the nice
# systemd-tmpfiles-setup.service service because this is a remote FS, and it
# may not be mounted when it runs.
systemd.services.create-paste-dirs = let
# Take only normal users in hut
users = lib.filterAttrs (_: v: v.isNormalUser) config.users.users;
commands = lib.concatLists (lib.mapAttrsToList
(_: user: [
"install -d -o ${user.name} -g ${user.group} -m 0755 /ceph/p/${user.name}"
]) users);
script = pkgs.writeShellScript "create-paste-dirs.sh" (lib.concatLines commands);
in {
enable = true;
wants = [ "remote-fs.target" ];
after = [ "remote-fs.target" ];
wantedBy = [ "multi-user.target" ];
serviceConfig.ExecStart = script;
};
}

View File

@@ -1,19 +0,0 @@
{ lib, ... }:
{
services.postgresql = {
enable = true;
ensureDatabases = [ "perftestsdb" ];
ensureUsers = [
{ name = "anavarro"; ensureClauses.superuser = true; }
{ name = "rarias"; ensureClauses.superuser = true; }
{ name = "grafana"; }
];
authentication = ''
#type database DBuser auth-method
local perftestsdb rarias trust
local perftestsdb anavarro trust
local perftestsdb grafana trust
'';
};
}

View File

@@ -1,79 +0,0 @@
/*
* CC0-1.0 <https://creativecommons.org/publicdomain/zero/1.0/legalcode>
* Dark color scheme using 216 web-safe colors, inspired
* somewhat by the default color scheme in mutt.
* It reduces eyestrain for me, and energy usage for all:
* https://en.wikipedia.org/wiki/Light-on-dark_color_scheme
*/
* {
font-size: 14px;
font-family: monospace;
}
pre {
white-space: pre-wrap;
padding: 10px;
background: #f5f5f5;
}
hr {
margin: 30px 0;
}
body {
max-width: 120ex; /* 120 columns wide */
margin: 50px auto;
}
/*
* Underlined links add visual noise which make them hard-to-read.
* Use colors to make them stand out, instead.
*/
a:link {
color: #007;
text-decoration: none;
}
a:visited {
color:#504;
}
a:hover {
text-decoration: underline;
}
/* quoted text in emails gets a different color */
*.q { color:gray }
/*
* these may be used with cgit <https://git.zx2c4.com/cgit/>, too.
* (cgit uses <div>, public-inbox uses <span>)
*/
*.add { color:darkgreen } /* diff post-image lines */
*.del { color:darkred } /* diff pre-image lines */
*.head { color:black } /* diff header (metainformation) */
*.hunk { color:gray } /* diff hunk-header */
/*
* highlight 3.x colors (tested 3.18) for displaying blobs.
* This doesn't use most of the colors available, as I find too
* many colors overwhelming, so the default is commented out.
*/
.hl.num { color:#f30 } /* number */
.hl.esc { color:#f0f } /* escape character */
.hl.str { color:#f30 } /* string */
.hl.ppc { color:#f0f } /* preprocessor */
.hl.pps { color:#f30 } /* preprocessor string */
.hl.slc { color:#09f } /* single-line comment */
.hl.com { color:#09f } /* multi-line comment */
/* .hl.opt { color:#ccc } */ /* operator */
/* .hl.ipl { color:#ccc } */ /* interpolation */
/* keyword groups kw[a-z] */
.hl.kwa { color:#ff0 }
.hl.kwb { color:#0f0 }
.hl.kwc { color:#ff0 }
/* .hl.kwd { color:#ccc } */
/* line-number (unused by public-inbox) */
/* .hl.lin { color:#ccc } */

View File

@@ -1,47 +0,0 @@
{ lib, ... }:
{
services.public-inbox = {
enable = true;
http = {
enable = true;
port = 8081;
mounts = [ "/lists" ];
};
settings.publicinbox = {
css = [ "${./public-inbox.css}" ];
wwwlisting = "all";
};
inboxes = {
bscpkgs = {
url = "https://jungle.bsc.es/lists/bscpkgs";
address = [ "~rodarima/bscpkgs@lists.sr.ht" ];
watch = [ "imaps://jungle-robot%40gmx.com@imap.gmx.com/INBOX" ];
description = "Patches for bscpkgs";
listid = "~rodarima/bscpkgs.lists.sr.ht";
};
jungle = {
url = "https://jungle.bsc.es/lists/jungle";
address = [ "~rodarima/jungle@lists.sr.ht" ];
watch = [ "imaps://jungle-robot%40gmx.com@imap.gmx.com/INBOX" ];
description = "Patches for jungle";
listid = "~rodarima/jungle.lists.sr.ht";
};
};
};
# We need access to the network for the watch service, as we will fetch the
# emails directly from the IMAP server.
systemd.services.public-inbox-watch.serviceConfig = {
PrivateNetwork = lib.mkForce false;
RestrictAddressFamilies = lib.mkForce [ "AF_UNIX" "AF_INET" "AF_INET6" ];
KillSignal = "SIGKILL"; # Avoid slow shutdown
# Required for chmod(..., 02750) on directories by git, from
# systemd.exec(8):
# > Note that this restricts marking of any type of file system object with
# > these bits, including both regular files and directories (where the SGID
# > is a different meaning than for files, see documentation).
RestrictSUIDSGID = lib.mkForce false;
};
}

View File

@@ -1,15 +1,15 @@
- targets:
- owl1-ipmi
- owl2-ipmi
- xeon03-ipmi
- xeon04-ipmi
- koro-ipmi
- weasel-ipmi
- hut-ipmi
- eudy-ipmi
- 10.0.40.101
- 10.0.40.102
- 10.0.40.103
- 10.0.40.104
- 10.0.40.105
- 10.0.40.106
- 10.0.40.107
- 10.0.40.108
# Storage
- bay-ipmi
- oss01-ipmi
- lake2-ipmi
- 10.0.40.141
- 10.0.40.142
- 10.0.40.143
labels:
job: ipmi-lan

View File

@@ -2,11 +2,13 @@
{
imports = [
../common/ssf.nix
../common/main.nix
#(modulesPath + "/installer/netboot/netboot-minimal.nix")
../eudy/cpufreq.nix
../eudy/users.nix
../eudy/slurm.nix
./users.nix
./kernel.nix
];

View File

@@ -1,29 +1,9 @@
{ pkgs, lib, ... }:
let
#fcs-devel = pkgs.linuxPackages_custom {
# version = "6.2.8";
# src = /mnt/data/kernel/fcs/kernel/src;
# configfile = /mnt/data/kernel/fcs/kernel/configs/defconfig;
#};
kernel = nixos-fcsv4;
#fcsv1 = fcs-kernel "bc11660676d3d68ce2459b9fb5d5e654e3f413be" false;
#fcsv2 = fcs-kernel "db0f2eca0cd57a58bf456d7d2c7d5d8fdb25dfb1" false;
#fcsv1-lockdep = fcs-kernel "bc11660676d3d68ce2459b9fb5d5e654e3f413be" true;
#fcsv2-lockdep = fcs-kernel "db0f2eca0cd57a58bf456d7d2c7d5d8fdb25dfb1" true;
#fcs-kernel = gitCommit: lockdep: pkgs.linuxPackages_custom {
# version = "6.2.8";
# src = builtins.fetchGit {
# url = "git@bscpm03.bsc.es:ompss-kernel/linux.git";
# rev = gitCommit;
# ref = "fcs";
# };
# configfile = if lockdep then ./configs/lockdep else ./configs/defconfig;
#};
kernel = nixos-fcs;
nixos-fcs-kernel = lib.makeOverridable ({gitCommit, lockStat ? false, preempt ? false, branch ? "fcs"}: pkgs.linuxPackagesFor (pkgs.buildLinux rec {
nixos-fcs-kernel = {gitCommit, lockStat ? false, preempt ? false, branch ? "fcs"}: pkgs.linuxPackagesFor (pkgs.buildLinux rec {
version = "6.2.8";
src = builtins.fetchGit {
url = "git@bscpm03.bsc.es:ompss-kernel/linux.git";
@@ -40,13 +20,27 @@ let
};
kernelPatches = [];
extraMeta.branch = lib.versions.majorMinor version;
}));
});
nixos-fcs = nixos-fcs-kernel {gitCommit = "8a09822dfcc8f0626b209d6d2aec8b5da459dfee";};
nixos-fcs-lockstat = nixos-fcs.override {
nixos-fcsv1 = nixos-fcs-kernel {gitCommit = "bc11660676d3d68ce2459b9fb5d5e654e3f413be";};
nixos-fcsv2 = nixos-fcs-kernel {gitCommit = "db0f2eca0cd57a58bf456d7d2c7d5d8fdb25dfb1";};
nixos-fcsv3 = nixos-fcs-kernel {gitCommit = "6c17394890704c3345ac1a521bb547164b36b154";};
nixos-fcsv4 = nixos-fcs-kernel {gitCommit = "c94c3d946f33ac3e5782a02ee002cc1164c0cb4f";};
nixos-fcsv1-lockstat = nixos-fcs-kernel {
gitCommit = "bc11660676d3d68ce2459b9fb5d5e654e3f413be";
lockStat = true;
};
nixos-fcs-lockstat-preempt = nixos-fcs.override {
nixos-fcsv2-lockstat = nixos-fcs-kernel {
gitCommit = "db0f2eca0cd57a58bf456d7d2c7d5d8fdb25dfb1";
lockStat = true;
};
nixos-fcsv3-lockstat = nixos-fcs-kernel {
gitCommit = "6c17394890704c3345ac1a521bb547164b36b154";
lockStat = true;
};
nixos-fcsv3-lockstat-preempt = nixos-fcs-kernel {
gitCommit = "6c17394890704c3345ac1a521bb547164b36b154";
lockStat = true;
preempt = true;
};
@@ -66,5 +60,5 @@ in {
# enable memory overcommit, needed to build a taglibc system using nix after
# increasing the openblas memory footprint
boot.kernel.sysctl."vm.overcommit_memory" = 1;
boot.kernel.sysctl."vm.overcommit_memory" = lib.mkForce 1;
}

17
m/koro/users.nix Normal file
View File

@@ -0,0 +1,17 @@
{ ... }:
{
users.users = {
vlopez = {
uid = 4334;
isNormalUser = true;
home = "/home/Computational/vlopez";
description = "Victor López";
group = "Computational";
hashedPassword = "$6$0ZBkgIYE/renVqtt$1uWlJsb0FEezRVNoETTzZMx4X2SvWiOsKvi0ppWCRqI66S6TqMBXBdP4fcQyvRRBt0e4Z7opZIvvITBsEtO0f0";
openssh.authorizedKeys.keys = [
"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGMwlUZRf9jfG666Qa5Sb+KtEhXqkiMlBV2su3x/dXHq victor@arch"
];
};
};
}

View File

@@ -2,20 +2,20 @@
{
imports = [
../common/ssf.nix
../module/monitoring.nix
../common/main.nix
../common/monitoring.nix
];
boot.loader.grub.device = "/dev/disk/by-id/wwn-0x55cd2e414d53563a";
boot.kernel.sysctl = {
"kernel.yama.ptrace_scope" = lib.mkForce "1";
};
environment.systemPackages = with pkgs; [
ceph
];
services.slurm = {
client.enable = lib.mkForce false;
};
services.ceph = {
enable = true;
global = {
@@ -49,16 +49,6 @@
address = "10.0.42.42";
prefixLength = 24;
} ];
firewall = {
extraCommands = ''
# Accept all incoming TCP traffic from bay
iptables -A nixos-fw -p tcp -s bay -j nixos-fw-accept
# Accept monitoring requests from hut
iptables -A nixos-fw -p tcp -s hut --dport 9002 -j nixos-fw-accept
# Accept all Ceph traffic from the local network
iptables -A nixos-fw -p tcp -s 10.0.40.0/24 -m multiport --dport 3300,6789,6800:7568 -j nixos-fw-accept
'';
};
};
# Missing service for volumes, see:

View File

@@ -1,70 +0,0 @@
{
# In physical order from top to bottom (see note below)
ssf = {
# Switches for Ethernet and OmniPath
switch-C6-S1A-05 = { pos=42; size=1; model="Dell S3048-ON"; };
switch-opa = { pos=41; size=1; };
# SSF login
apex = { pos=39; size=2; label="SSFHEAD"; board="R2208WTTYSR"; contact="rodrigo.arias@bsc.es"; };
# Storage
bay = { pos=38; size=1; label="MDS01"; board="S2600WT2R"; sn="BQWL64850303"; contact="rodrigo.arias@bsc.es"; };
lake1 = { pos=37; size=1; label="OSS01"; board="S2600WT2R"; sn="BQWL64850234"; contact="rodrigo.arias@bsc.es"; };
lake2 = { pos=36; size=1; label="OSS02"; board="S2600WT2R"; sn="BQWL64850266"; contact="rodrigo.arias@bsc.es"; };
# Compute xeon
owl1 = { pos=35; size=1; label="SSF-XEON01"; board="S2600WTTR"; sn="BQWL64954172"; contact="rodrigo.arias@bsc.es"; };
owl2 = { pos=34; size=1; label="SSF-XEON02"; board="S2600WTTR"; sn="BQWL64756560"; contact="rodrigo.arias@bsc.es"; };
xeon03 = { pos=33; size=1; label="SSF-XEON03"; board="S2600WTTR"; sn="BQWL64750826"; contact="rodrigo.arias@bsc.es"; };
# Slot 34 empty
koro = { pos=31; size=1; label="SSF-XEON05"; board="S2600WTTR"; sn="BQWL64954293"; contact="rodrigo.arias@bsc.es"; };
weasel = { pos=30; size=1; label="SSF-XEON06"; board="S2600WTTR"; sn="BQWL64750846"; contact="antoni.navarro@bsc.es"; };
hut = { pos=29; size=1; label="SSF-XEON07"; board="S2600WTTR"; sn="BQWL64751184"; contact="rodrigo.arias@bsc.es"; };
eudy = { pos=28; size=1; label="SSF-XEON08"; board="S2600WTTR"; sn="BQWL64756586"; contact="aleix.rocanonell@bsc.es"; };
# 16 KNL nodes, 4 per chassis
knl01_04 = { pos=26; size=2; label="KNL01..KNL04"; board="HNS7200APX"; };
knl05_08 = { pos=24; size=2; label="KNL05..KNL18"; board="HNS7200APX"; };
knl09_12 = { pos=22; size=2; label="KNL09..KNL12"; board="HNS7200APX"; };
knl13_16 = { pos=20; size=2; label="KNL13..KNL16"; board="HNS7200APX"; };
# Slot 19 empty
# EPI (hw team, guessed order)
epi01 = { pos=18; size=1; contact="joan.cabre@bsc.es"; };
epi02 = { pos=17; size=1; contact="joan.cabre@bsc.es"; };
epi03 = { pos=16; size=1; contact="joan.cabre@bsc.es"; };
anon = { pos=14; size=2; }; # Unlabeled machine. Operative
# These are old and decommissioned (off)
power8 = { pos=12; size=2; label="BSCPOWER8N3"; decommissioned=true; };
powern1 = { pos=8; size=4; label="BSCPOWERN1"; decommissioned=true; };
gustafson = { pos=7; size=1; label="gustafson"; decommissioned=true; };
odap01 = { pos=3; size=4; label="ODAP01"; decommissioned=true; };
amhdal = { pos=2; size=1; label="AMHDAL"; decommissioned=true; }; # sic
moore = { pos=1; size=1; label="moore (earth)"; decommissioned=true; };
};
bsc2218 = {
raccoon = { board="W2600CR"; sn="QSIP22500829"; contact="rodrigo.arias@bsc.es"; };
tent = { label="SSF-XEON04"; board="S2600WTTR"; sn="BQWL64751229"; contact="rodrigo.arias@bsc.es"; };
};
upc = {
fox = { board="H13DSG-O-CPU"; sn="UM24CS600392"; prod="AS-4125GS-TNRT"; prod_sn="E508839X5103339"; contact="rodrigo.arias@bsc.es"; };
};
# NOTE: Position is specified in "U" units (44.45 mm) and starts at 1 from the
# bottom. Example:
#
# | ... | - [pos+size] <--- Label in chassis
# +--------+
# | node | - [pos+1]
# | 2U | - [pos]
# +------- +
# | ... | - [pos-1]
#
# NOTE: The board and sn refers to the FRU information (Board Product and
# Board Serial) via `ipmitool fru print 0`.
}

View File

@@ -3,6 +3,7 @@
# Mounts the /ceph filesystem at boot
{
environment.systemPackages = with pkgs; [
ceph
ceph-client
fio # For benchmarks
];

View File

@@ -1,3 +0,0 @@
{
services.nixseparatedebuginfod.enable = true;
}

View File

@@ -1,3 +0,0 @@
{
boot.binfmt.emulatedSystems = [ "armv7l-linux" "aarch64-linux" "powerpc64le-linux" "riscv64-linux" ];
}

View File

@@ -1,10 +0,0 @@
{ config, ... }:
{
nix.settings =
# Don't add hut as a cache to itself
assert config.networking.hostName != "hut";
{
extra-substituters = [ "http://hut/cache" ];
extra-trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
};
}

View File

@@ -1,24 +0,0 @@
{ config, lib, ... }:
with lib;
{
options = {
users.jungleUsers = mkOption {
type = types.attrsOf (types.anything // { check = (x: x ? "hosts"); });
description = ''
Same as users.users but with the extra `hosts` attribute, which controls
access to the nodes by `networking.hostName`.
'';
};
};
config = let
allowedUser = host: userConf: builtins.elem host userConf.hosts;
filterUsers = host: users: filterAttrs (n: v: allowedUser host v) users;
removeHosts = users: mapAttrs (n: v: builtins.removeAttrs v [ "hosts" ]) users;
currentHost = config.networking.hostName;
in {
users.users = removeHosts (filterUsers currentHost config.users.jungleUsers);
};
}

View File

@@ -1,17 +0,0 @@
{ config, lib, pkgs, ... }:
with lib;
{
systemd.services."prometheus-meteocat-exporter" = {
wantedBy = [ "multi-user.target" ];
after = [ "network.target" ];
serviceConfig = {
Restart = mkDefault "always";
PrivateTmp = mkDefault true;
WorkingDirectory = mkDefault "/tmp";
DynamicUser = mkDefault true;
ExecStart = "${pkgs.meteocat-exporter}/bin/meteocat-exporter";
};
};
}

View File

@@ -1,26 +0,0 @@
#!/bin/sh
# Locate nix daemon pid
nd=$(pgrep -o nix-daemon)
# Locate children of nix-daemon
pids1=$(tr ' ' '\n' < "/proc/$nd/task/$nd/children")
# For each children, locate 2nd level children
pids2=$(echo "$pids1" | xargs -I @ /bin/sh -c 'cat /proc/@/task/*/children' | tr ' ' '\n')
cat <<EOF
HTTP/1.1 200 OK
Content-Type: text/plain; version=0.0.4; charset=utf-8; escaping=values
# HELP nix_daemon_build Nix daemon derivation build state.
# TYPE nix_daemon_build gauge
EOF
for pid in $pids2; do
name=$(cat /proc/$pid/environ 2>/dev/null | tr '\0' '\n' | rg "^name=(.+)" - --replace '$1' | tr -dc ' [:alnum:]_\-\.')
user=$(ps -o uname= -p "$pid")
if [ -n "$name" -a -n "$user" ]; then
printf 'nix_daemon_build{user="%s",name="%s"} 1\n' "$user" "$name"
fi
done

View File

@@ -1,23 +0,0 @@
{ pkgs, config, lib, ... }:
let
script = pkgs.runCommand "nix-daemon-exporter.sh" { }
''
cp ${./nix-daemon-builds.sh} $out;
chmod +x $out
''
;
in
{
systemd.services.nix-daemon-exporter = {
description = "Daemon to export nix-daemon metrics";
path = [ pkgs.procps pkgs.ripgrep ];
wantedBy = [ "default.target" ];
serviceConfig = {
Type = "simple";
ExecStart = "${pkgs.socat}/bin/socat TCP4-LISTEN:9999,fork EXEC:${script}";
# Needed root to read the environment, potentially unsafe
User = "root";
Group = "root";
};
};
}

View File

@@ -1,20 +0,0 @@
{ lib, config, pkgs, ... }:
{
# Configure Nvidia driver to use with CUDA
hardware.nvidia.package = config.boot.kernelPackages.nvidiaPackages.production;
hardware.nvidia.open = lib.mkDefault (builtins.abort "hardware.nvidia.open not set");
hardware.graphics.enable = true;
nixpkgs.config.nvidia.acceptLicense = true;
services.xserver.videoDrivers = [ "nvidia" ];
# enable support for derivations which require nvidia-gpu to be available
# > requiredSystemFeatures = [ "cuda" ];
programs.nix-required-mounts.enable = true;
programs.nix-required-mounts.presets.nvidia-gpu.enable = true;
# They forgot to add the symlink
programs.nix-required-mounts.allowedPatterns.nvidia-gpu.paths = [
config.systemd.tmpfiles.settings.graphics-driver."/run/opengl-driver"."L+".argument
];
environment.systemPackages = [ pkgs.cudainfo ];
}

View File

@@ -1,68 +0,0 @@
{ config, lib, pkgs, ... }:
let
cfg = config.services.p;
in
{
options = {
services.p = {
enable = lib.mkOption {
type = lib.types.bool;
default = false;
description = "Whether to enable the p service.";
};
path = lib.mkOption {
type = lib.types.str;
default = "/var/lib/p";
description = "Where to save the pasted files on disk.";
};
url = lib.mkOption {
type = lib.types.str;
default = "https://jungle.bsc.es/p";
description = "URL prefix for the printed file.";
};
};
};
config = lib.mkIf cfg.enable {
environment.systemPackages = let
p = pkgs.writeShellScriptBin "p" ''
set -e
pastedir="${cfg.path}/$USER"
cd "$pastedir"
ext="txt"
if [ -n "$1" ]; then
ext="$1"
fi
out=$(mktemp "XXXXXXXX.$ext")
cat > "$out"
chmod go+r "$out"
echo "${cfg.url}/$USER/$out"
'';
in [ p ];
systemd.services.p = let
# Take only normal users
users = lib.filterAttrs (_: v: v.isNormalUser) config.users.users;
# Create a directory for each user
commands = lib.concatLists (lib.mapAttrsToList (_: user: [
"install -d -o ${user.name} -g ${user.group} -m 0755 ${cfg.path}/${user.name}"
]) users);
in {
description = "P service setup";
requires = [ "network-online.target" ];
#wants = [ "remote-fs.target" ];
#after = [ "remote-fs.target" ];
wantedBy = [ "multi-user.target" ];
serviceConfig = {
ExecStart = pkgs.writeShellScript "p-init.sh" (''
install -d -o root -g root -m 0755 ${cfg.path}
'' + (lib.concatLines commands));
};
};
};
}

View File

@@ -0,0 +1,69 @@
{ ... }:
{
# Don't make the nix store read-only, as this would prevent the overlay FS
# from being able to mount it.
boot.readOnlyNixStore = false;
# The nix-daemon.socket has an unnecessary dependency over the /nix/store
# mount point. But that mount point won't be provided until the network is
# ready. However, the network-address-eno1.service, has a dependency over
# sockets.target, causing a cycle.
# One solution is to make the nix-daemon.socket depend only on the socket
# patch (which is already covered by ConditionPathIsReadWrite =
# /nix/var/nix/daemon-socket), instead on the /nix/store.
#
# Using systemd.sockets.nix-daemon.unitConfig.RequiresMountsFor =
# "/nix/var/nix/daemon-socket" doesn't work, as the the mount options get
# added by systemd when the override config is merged with the one that Nix
# provides:
#
# owl2% sudo systemctl show nix-daemon.socket | grep RequiresMountsFor
# RequiresMountsFor=/nix/store /nix/var/nix/daemon-socket/socket /nix/var/nix/daemon-socket
#
# To fix this, the Nix package is patched to only depend on /nix/var instead.
# See ../../pkgs/overlay.nix for details.
# Mount the hut nix store via NFS in read-only mode.
fileSystems."/mnt/hut-nix-store" = {
device = "hut:/nix/store";
fsType = "nfs";
options = [ "ro" ];
};
# A workdir is also needed, so setup a permanent dir using tmpfiles.
systemd.tmpfiles.rules = [
"d /mnt/nix-work 0700 root root -"
];
# Mount an overlay in /nix/store using as lower layer the NFS store and upper
# layer the disk nix store. The destination is still the nix store in
# /nix/store (confusing). We need rw access, as the daemon need to write the
# lock files to build derivations locally. Use a systemd mount unit directly
# so we can specify the LazyUmount option and we avoid having it mounted
# in the stage1 before systemd.
systemd.mounts = [
{
what = "overlay";
type = "overlay";
where = "/nix/store";
# We need the local-fs.target to be ready, so the network interfaces can
# be configured to the network.target is reached. So make this a netdev
# mount.
options = "_netdev,lowerdir=/mnt/hut-nix-store,upperdir=/nix/store,workdir=/mnt/nix-work";
description = "Overlay /nix/store mount";
mountConfig = {
LazyUnmount = true;
};
# Run the unit after remote-fs-pre.target but before the remote-fs.target
after = [ "remote-fs-pre.target"];
before = [ "umount.target" "remote-fs.target" ];
# Install by using wantedBy over remote-fs.target
wantedBy = [ "remote-fs.target" ];
unitConfig = {
# We need to wait for the NFS mount
RequiresMountsFor = "/nix/store /mnt/hut-nix-store";
};
}
];
}

View File

@@ -1,28 +0,0 @@
{ config, lib, pkgs, ... }:
# See also: https://github.com/NixOS/nixpkgs/pull/112010
# And: https://github.com/NixOS/nixpkgs/pull/115839
with lib;
{
systemd.services."prometheus-slurm-exporter" = {
wantedBy = [ "multi-user.target" ];
after = [ "network.target" ];
serviceConfig = {
Restart = mkDefault "always";
PrivateTmp = mkDefault true;
WorkingDirectory = mkDefault "/tmp";
DynamicUser = mkDefault true;
ExecStart = ''
${pkgs.prometheus-slurm-exporter}/bin/prometheus-slurm-exporter --listen-address "127.0.0.1:9341"
'';
Environment = [
"PATH=${pkgs.slurm}/bin"
# We need to specify the slurm config to be able to talk to the slurmd
# daemon.
"SLURM_CONF=${config.services.slurm.etcSlurm}/slurm.conf"
];
};
};
}

View File

@@ -1,19 +0,0 @@
{ ... }:
{
# Mount the hut nix store via NFS
fileSystems."/mnt/hut-nix-store" = {
device = "hut:/nix/store";
fsType = "nfs";
options = [ "ro" ];
};
systemd.services.slurmd.serviceConfig = {
# When running a job, bind the hut store in /nix/store so the paths are
# available too.
# FIXME: This doesn't keep the programs in /run/current-system/sw/bin
# available in the store. Ideally they should be merged but the overlay FS
# doesn't work when the underlying directories change.
BindReadOnlyPaths = "/mnt/hut-nix-store:/nix/store";
};
}

View File

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

View File

@@ -1,17 +0,0 @@
{ config, lib, pkgs, ... }:
with lib;
{
systemd.services."prometheus-upc-qaire-exporter" = {
wantedBy = [ "multi-user.target" ];
after = [ "network.target" ];
serviceConfig = {
Restart = mkDefault "always";
PrivateTmp = mkDefault true;
WorkingDirectory = mkDefault "/tmp";
DynamicUser = mkDefault true;
ExecStart = "${pkgs.upc-qaire-exporter}/bin/upc-qaire-exporter";
};
};
}

View File

@@ -1,35 +0,0 @@
{config, ...}:
{
age.secrets.vpn-dac-login.file = ../../secrets/vpn-dac-login.age;
age.secrets.vpn-dac-client-key.file = ../../secrets/vpn-dac-client-key.age;
services.openvpn.servers = {
# systemctl status openvpn-dac.service
dac = {
config = ''
client
dev tun
proto tcp
remote vpn.ac.upc.edu 1194
remote vpn.ac.upc.edu 80
resolv-retry infinite
nobind
persist-key
persist-tun
ca ${./vpn-dac/ca.crt}
cert ${./vpn-dac/client.crt}
# Only key needs to be secret
key ${config.age.secrets.vpn-dac-client-key.path}
remote-cert-tls server
comp-lzo
verb 3
auth-user-pass ${config.age.secrets.vpn-dac-login.path}
reneg-sec 0
# Only route fox-ipmi
pull-filter ignore "route "
route 147.83.35.27 255.255.255.255
'';
};
};
}

View File

@@ -1,31 +0,0 @@
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----

View File

@@ -1,100 +0,0 @@
Certificate:
Data:
Version: 3 (0x2)
Serial Number: 2 (0x2)
Signature Algorithm: sha256WithRSAEncryption
Issuer: C=ES, ST=Barcelona, L=Barcelona, O=Universitat Politecnica de Catalunya, OU=Arquitectura de Computadors, CN=LCAC CA/name=LCAC/emailAddress=lcac@ac.upc.edu
Validity
Not Before: Jan 12 12:45:41 2016 GMT
Not After : Jan 12 12:45:41 2046 GMT
Subject: C=ES, ST=Barcelona, L=Barcelona, O=Universitat Politecnica de Catalunya, OU=Arquitectura de Computadors, CN=client/name=LCAC/emailAddress=lcac@ac.upc.edu
Subject Public Key Info:
Public Key Algorithm: rsaEncryption
Public-Key: (2048 bit)
Modulus:
00:97:99:fa:7a:0e:4d:e2:1d:a5:b1:a8:14:18:64:
c7:66:bf:de:99:1d:92:3b:86:82:4d:95:39:f7:a6:
56:49:97:14:4f:e3:37:00:6c:f4:d0:1d:56:79:e7:
19:b5:dd:36:15:8e:1d:57:7b:59:29:d2:11:bf:58:
48:e0:f7:41:3d:16:64:8d:a2:0b:4a:ac:fa:c6:83:
dc:10:2a:2c:d9:97:48:ee:11:2a:bc:4b:60:dd:b9:
2e:8f:45:ca:87:0b:38:65:1c:f8:a2:1d:f9:50:aa:
6e:60:f9:48:df:57:12:23:e1:e7:0c:81:5c:9f:c5:
b2:e6:99:99:95:30:6d:57:36:06:8c:fd:fb:f9:4f:
60:d2:3c:ba:ae:28:56:2f:da:58:5c:e8:c5:7b:ec:
76:d9:28:6e:fb:8c:07:f9:d7:23:c3:72:76:3c:fa:
dc:20:67:8f:cc:16:e0:91:07:d5:68:f9:20:4d:7d:
5c:2d:02:04:16:76:52:f3:53:be:a3:dc:0d:d5:fb:
6b:55:29:f3:52:35:c8:7d:99:d1:4a:94:be:b1:8e:
fd:85:18:25:eb:41:e9:56:da:af:62:84:20:0a:00:
17:94:92:94:91:6a:f8:54:37:17:ee:1e:bb:fb:93:
71:91:d9:e4:e9:b8:3b:18:7d:6d:7d:4c:ce:58:55:
f9:41
Exponent: 65537 (0x10001)
X509v3 extensions:
X509v3 Basic Constraints:
CA:FALSE
Netscape Comment:
Easy-RSA Generated Certificate
X509v3 Subject Key Identifier:
1B:88:06:D5:33:1D:5C:48:46:B5:DE:78:89:36:96:91:3A:74:43:18
X509v3 Authority Key Identifier:
keyid:DC:9E:CD:7D:5C:1F:53:78:41:1D:78:79:B0:69:96:3A:A6:B4:4E:EA
DirName:/C=ES/ST=Barcelona/L=Barcelona/O=Universitat Politecnica de Catalunya/OU=Arquitectura de Computadors/CN=LCAC CA/name=LCAC/emailAddress=lcac@ac.upc.edu
serial:91:F5:D7:C3:C0:A6:4E:61
X509v3 Extended Key Usage:
TLS Web Client Authentication
X509v3 Key Usage:
Digital Signature
X509v3 Subject Alternative Name:
DNS:client
Signature Algorithm: sha256WithRSAEncryption
42:e8:50:b2:e7:88:75:86:0b:bb:29:e3:aa:c6:0e:4c:e8:ea:
3d:0c:02:31:7f:3b:80:0c:3f:80:af:45:d6:62:27:a0:0e:e7:
26:09:12:97:95:f8:d9:9b:89:b5:ef:56:64:f1:de:82:74:e0:
31:0a:cc:90:0a:bd:50:b8:54:95:0a:ae:3b:40:df:76:b6:d1:
01:2e:f3:96:9f:52:d4:e9:14:6d:b7:14:9d:45:99:33:36:2a:
01:0b:15:1a:ed:55:dc:64:83:65:1a:06:42:d9:c7:dc:97:d4:
02:81:c2:58:2b:ea:e4:b7:ae:84:3a:e4:3f:f1:2e:fa:ec:f3:
40:5d:b8:6a:d5:5e:e1:e8:2f:e2:2f:48:a4:38:a1:4f:22:e3:
4f:66:94:aa:02:78:9a:2b:7a:5d:aa:aa:51:a5:e3:d0:91:e9:
1d:f9:08:ed:8b:51:c9:a6:af:46:85:b5:1c:ed:12:a1:28:33:
75:36:00:d8:5c:14:65:96:c0:28:7d:47:50:a4:89:5f:b0:72:
1a:4b:13:17:26:0f:f0:b8:65:3c:e9:96:36:f9:bf:90:59:33:
87:1f:01:03:25:f8:f0:3a:9b:33:02:d0:0a:43:b5:0a:cf:62:
a1:45:38:37:07:9d:9c:94:0b:31:c6:3c:34:b7:fc:5a:0c:e4:
bf:23:f6:7d
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----

View File

@@ -2,13 +2,10 @@
{
imports = [
../common/ssf.nix
../common/main.nix
../module/ceph.nix
../module/emulation.nix
../module/slurm-client.nix
../module/slurm-firewall.nix
../module/debuginfod.nix
../module/hut-substituter.nix
../module/shared-nix-store.nix
];
# Select the this using the ID to avoid mismatches

View File

@@ -2,13 +2,10 @@
{
imports = [
../common/ssf.nix
../common/main.nix
../module/ceph.nix
../module/emulation.nix
../module/slurm-client.nix
../module/slurm-firewall.nix
../module/debuginfod.nix
../module/hut-substituter.nix
../module/shared-nix-store.nix
];
# Select the this using the ID to avoid mismatches

View File

@@ -1,93 +0,0 @@
{ config, pkgs, lib, modulesPath, ... }:
{
imports = [
../common/base.nix
../module/emulation.nix
../module/debuginfod.nix
../module/ssh-hut-extern.nix
../module/nvidia.nix
../eudy/kernel/perf.nix
];
# Don't install Grub on the disk yet
boot.loader.grub.device = "nodev";
# Enable serial console
boot.kernelParams = [
"console=tty1"
"console=ttyS1,115200"
];
networking = {
hostName = "raccoon";
# Only BSC DNSs seem to be reachable from the office VLAN
nameservers = [ "84.88.52.35" "84.88.52.36" ];
defaultGateway = "84.88.51.129";
interfaces.eno0.ipv4.addresses = [ {
address = "84.88.51.152";
prefixLength = 25;
} ];
interfaces.enp5s0f1.ipv4.addresses = [ {
address = "10.0.44.1";
prefixLength = 24;
} ];
nat = {
enable = true;
internalInterfaces = [ "enp5s0f1" ];
externalInterface = "eno0";
};
hosts = {
"10.0.44.4" = [ "tent" ];
};
};
nix.settings = {
extra-substituters = [ "https://jungle.bsc.es/cache" ];
extra-trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
};
# Enable performance governor
powerManagement.cpuFreqGovernor = "performance";
hardware.nvidia.open = false; # Maxwell is older than Turing architecture
services.openssh.settings.X11Forwarding = true;
services.prometheus.exporters.node = {
enable = true;
enabledCollectors = [ "systemd" ];
port = 9002;
listenAddress = "127.0.0.1";
};
users.motd = ''
DO YOU BRING FEEDS?
'';
}

View File

@@ -1,14 +0,0 @@
modules:
http_2xx:
prober: http
timeout: 5s
http:
preferred_ip_protocol: "ip4"
follow_redirects: true
valid_status_codes: [] # Defaults to 2xx
method: GET
icmp:
prober: icmp
timeout: 5s
icmp:
preferred_ip_protocol: "ip4"

View File

@@ -1,80 +0,0 @@
{ config, pkgs, lib, ... }:
{
imports = [
../common/xeon.nix
../module/emulation.nix
../module/debuginfod.nix
../module/ssh-hut-extern.nix
./monitoring.nix
./nginx.nix
./nix-serve.nix
./gitlab-runner.nix
./gitea.nix
../hut/public-inbox.nix
../hut/msmtp.nix
../module/p.nix
../module/vpn-dac.nix
];
# Select the this using the ID to avoid mismatches
boot.loader.grub.device = "/dev/disk/by-id/wwn-0x55cd2e414d537675";
networking = {
hostName = "tent";
interfaces.eno1.ipv4.addresses = [
{
address = "10.0.44.4";
prefixLength = 24;
}
];
# Only BSC DNSs seem to be reachable from the office VLAN
nameservers = [ "84.88.52.35" "84.88.52.36" ];
search = [ "bsc.es" "ac.upc.edu" ];
defaultGateway = "10.0.44.1";
};
services.p.enable = true;
services.prometheus.exporters.node = {
enable = true;
enabledCollectors = [ "systemd" ];
port = 9002;
listenAddress = "127.0.0.1";
};
boot.swraid = {
enable = true;
mdadmConf = ''
DEVICE partitions
ARRAY /dev/md0 metadata=1.2 UUID=496db1e2:056a92aa:a544543f:40db379d
MAILADDR root
'';
};
fileSystems."/vault" = {
device = "/dev/disk/by-label/vault";
fsType = "ext4";
};
# Make a /vault/$USER directory for each user.
systemd.services.create-vault-dirs = let
# Take only normal users in tent
users = lib.filterAttrs (_: v: v.isNormalUser) config.users.users;
commands = lib.concatLists (lib.mapAttrsToList
(_: user: [
"install -d -o ${user.name} -g ${user.group} -m 0711 /vault/home/${user.name}"
]) users);
script = pkgs.writeShellScript "create-vault-dirs.sh" (lib.concatLines commands);
in {
enable = true;
wants = [ "local-fs.target" ];
after = [ "local-fs.target" ];
wantedBy = [ "multi-user.target" ];
serviceConfig.ExecStart = script;
};
# disable automatic garbage collector
nix.gc.automatic = lib.mkForce false;
}

View File

@@ -1,30 +0,0 @@
{ config, lib, ... }:
{
services.gitea = {
enable = true;
appName = "Gitea in the jungle";
settings = {
server = {
ROOT_URL = "https://jungle.bsc.es/git/";
LOCAL_ROOT_URL = "https://jungle.bsc.es/git/";
LANDING_PAGE = "explore";
};
metrics.ENABLED = true;
service = {
DISABLE_REGISTRATION = true;
REGISTER_MANUAL_CONFIRM = true;
ENABLE_NOTIFY_MAIL = true;
};
log.LEVEL = "Warn";
mailer = {
ENABLED = true;
FROM = "jungle-robot@bsc.es";
PROTOCOL = "sendmail";
SENDMAIL_PATH = "/run/wrappers/bin/sendmail";
SENDMAIL_ARGS = "--";
};
};
};
}

View File

@@ -1,93 +0,0 @@
{ pkgs, lib, config, ... }:
{
age.secrets.tent-gitlab-runner-pm-shell.file = ../../secrets/tent-gitlab-runner-pm-shell-token.age;
age.secrets.tent-gitlab-runner-pm-docker.file = ../../secrets/tent-gitlab-runner-pm-docker-token.age;
age.secrets.tent-gitlab-runner-bsc-docker.file = ../../secrets/tent-gitlab-runner-bsc-docker-token.age;
services.gitlab-runner = let sec = config.age.secrets; in {
enable = true;
settings.concurrent = 5;
services = {
# For gitlab.pm.bsc.es
gitlab-pm-shell = {
executor = "shell";
environmentVariables = {
SHELL = "${pkgs.bash}/bin/bash";
};
authenticationTokenConfigFile = sec.tent-gitlab-runner-pm-shell.path;
preGetSourcesScript = pkgs.writeScript "setup" ''
echo "This is the preGetSources script running, brace for impact"
env
'';
};
gitlab-pm-docker = {
authenticationTokenConfigFile = sec.tent-gitlab-runner-pm-docker.path;
executor = "docker";
dockerImage = "debian:stable";
};
# For gitlab.bsc.es
gitlab-bsc-docker = {
# gitlab.bsc.es still uses the old token mechanism
registrationConfigFile = sec.tent-gitlab-runner-bsc-docker.path;
tagList = [ "docker" "tent" "nix" ];
executor = "docker";
dockerImage = "alpine";
dockerVolumes = [
"/nix/store:/nix/store:ro"
"/nix/var/nix/db:/nix/var/nix/db:ro"
"/nix/var/nix/daemon-socket:/nix/var/nix/daemon-socket:ro"
];
dockerDisableCache = true;
registrationFlags = [
# Increase build log length to 64 MiB
"--output-limit 65536"
];
preBuildScript = pkgs.writeScript "setup-container" ''
mkdir -p -m 0755 /nix/var/log/nix/drvs
mkdir -p -m 0755 /nix/var/nix/gcroots
mkdir -p -m 0755 /nix/var/nix/profiles
mkdir -p -m 0755 /nix/var/nix/temproots
mkdir -p -m 0755 /nix/var/nix/userpool
mkdir -p -m 1777 /nix/var/nix/gcroots/per-user
mkdir -p -m 1777 /nix/var/nix/profiles/per-user
mkdir -p -m 0755 /nix/var/nix/profiles/per-user/root
mkdir -p -m 0700 "$HOME/.nix-defexpr"
mkdir -p -m 0700 "$HOME/.ssh"
cat >> "$HOME/.ssh/known_hosts" << EOF
bscpm04.bsc.es ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPx4mC0etyyjYUT2Ztc/bs4ZXSbVMrogs1ZTP924PDgT
gitlab-internal.bsc.es ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIF9arsAOSRB06hdy71oTvJHG2Mg8zfebADxpvc37lZo3
EOF
. ${pkgs.nix}/etc/profile.d/nix-daemon.sh
# Required to load SSL certificate paths
. ${pkgs.cacert}/nix-support/setup-hook
'';
environmentVariables = {
ENV = "/etc/profile";
USER = "root";
NIX_REMOTE = "daemon";
PATH = "${config.system.path}/bin:/bin:/sbin:/usr/bin:/usr/sbin";
};
};
};
};
systemd.services.gitlab-runner.serviceConfig = {
DynamicUser = lib.mkForce false;
User = "gitlab-runner";
Group = "gitlab-runner";
ExecStart = lib.mkForce
''${pkgs.gitlab-runner}/bin/gitlab-runner run --config ''${HOME}/.gitlab-runner/config.toml --listen-address "127.0.0.1:9252" --working-directory ''${HOME}'';
};
users.users.gitlab-runner = {
uid = config.ids.uids.gitlab-runner;
home = "/var/lib/gitlab-runner";
description = "Gitlab Runner";
group = "gitlab-runner";
extraGroups = [ "docker" ];
createHome = true;
};
users.groups.gitlab-runner.gid = config.ids.gids.gitlab-runner;
}

View File

@@ -1,217 +0,0 @@
{ config, lib, pkgs, ... }:
{
imports = [
../module/meteocat-exporter.nix
../module/upc-qaire-exporter.nix
../module/nix-daemon-exporter.nix
];
age.secrets.grafanaJungleRobotPassword = {
file = ../../secrets/jungle-robot-password.age;
owner = "grafana";
mode = "400";
};
services.grafana = {
enable = true;
settings = {
server = {
domain = "jungle.bsc.es";
root_url = "%(protocol)s://%(domain)s/grafana";
serve_from_sub_path = true;
http_port = 2342;
http_addr = "127.0.0.1";
};
smtp = {
enabled = true;
from_address = "jungle-robot@bsc.es";
user = "jungle-robot";
# Read the password from a file, which is only readable by grafana user
# https://grafana.com/docs/grafana/latest/setup-grafana/configure-grafana/#file-provider
password = "$__file{${config.age.secrets.grafanaJungleRobotPassword.path}}";
host = "mail.bsc.es:465";
startTLS_policy = "NoStartTLS";
};
feature_toggles.publicDashboards = true;
"auth.anonymous".enabled = true;
log.level = "warn";
};
};
services.prometheus = {
enable = true;
port = 9001;
retentionTime = "5y";
listenAddress = "127.0.0.1";
};
# We need access to the devices to monitor the disk space
systemd.services.prometheus-node-exporter.serviceConfig.PrivateDevices = lib.mkForce false;
systemd.services.prometheus-node-exporter.serviceConfig.ProtectHome = lib.mkForce "read-only";
# Credentials for IPMI exporter
age.secrets.ipmiYml = {
file = ../../secrets/ipmi.yml.age;
owner = "ipmi-exporter";
};
# Create an IPMI group and assign the ipmi0 device
users.groups.ipmi = {};
services.udev.extraRules = ''
SUBSYSTEM=="ipmi", KERNEL=="ipmi0", GROUP="ipmi", MODE="0660"
'';
# Add a new ipmi-exporter user that can read the ipmi0 device
users.users.ipmi-exporter = {
isSystemUser = true;
group = "ipmi";
};
# Disable dynamic user so we have the ipmi-exporter user available for the credentials
systemd.services.prometheus-ipmi-exporter.serviceConfig = {
DynamicUser = lib.mkForce false;
PrivateDevices = lib.mkForce false;
User = lib.mkForce "ipmi-exporter";
Group = lib.mkForce "ipmi";
RestrictNamespaces = lib.mkForce false;
# Fake uid to 0 so it shuts up
ExecStart = let
cfg = config.services.prometheus.exporters.ipmi;
in lib.mkForce (lib.concatStringsSep " " ([
"${pkgs.util-linux}/bin/unshare --map-user 0"
"${pkgs.prometheus-ipmi-exporter}/bin/ipmi_exporter"
"--web.listen-address ${cfg.listenAddress}:${toString cfg.port}"
"--config.file ${lib.escapeShellArg cfg.configFile}"
] ++ cfg.extraFlags));
};
services.prometheus = {
exporters = {
ipmi = {
enable = true;
configFile = config.age.secrets.ipmiYml.path;
#extraFlags = [ "--log.level=debug" ];
listenAddress = "127.0.0.1";
};
node = {
enable = true;
enabledCollectors = [ "logind" ];
port = 9002;
listenAddress = "127.0.0.1";
};
blackbox = {
enable = true;
listenAddress = "127.0.0.1";
configFile = ./blackbox.yml;
};
};
scrapeConfigs = [
{
job_name = "local";
static_configs = [{
targets = [
"127.0.0.1:9002" # Node exporter
#"127.0.0.1:9115" # Blackbox exporter
"127.0.0.1:9290" # IPMI exporter for local node
"127.0.0.1:9928" # UPC Qaire custom exporter
"127.0.0.1:9929" # Meteocat custom exporter
"127.0.0.1:9999" # Nix-daemon custom exporter
];
}];
}
{
job_name = "blackbox-http";
metrics_path = "/probe";
params = { module = [ "http_2xx" ]; };
static_configs = [{
targets = [
"https://www.google.com/robots.txt"
"https://pm.bsc.es/"
"https://pm.bsc.es/gitlab/"
"https://jungle.bsc.es/"
"https://gitlab.bsc.es/"
];
}];
relabel_configs = [
{
# Takes the address and sets it in the "target=<xyz>" URL parameter
source_labels = [ "__address__" ];
target_label = "__param_target";
}
{
# Sets the "instance" label with the remote host we are querying
source_labels = [ "__param_target" ];
target_label = "instance";
}
{
# Shows the host target address instead of the blackbox address
target_label = "__address__";
replacement = "127.0.0.1:9115";
}
];
}
{
job_name = "blackbox-icmp";
metrics_path = "/probe";
params = { module = [ "icmp" ]; };
static_configs = [{
targets = [
"1.1.1.1"
"8.8.8.8"
"ssfhead"
"raccoon"
"anella-bsc.cesca.cat"
"upc-anella.cesca.cat"
"fox.ac.upc.edu"
"fox-ipmi.ac.upc.edu"
"arenys5.ac.upc.edu"
"arenys0-2.ac.upc.edu"
"epi01.bsc.es"
"axle.bsc.es"
];
}];
relabel_configs = [
{
# Takes the address and sets it in the "target=<xyz>" URL parameter
source_labels = [ "__address__" ];
target_label = "__param_target";
}
{
# Sets the "instance" label with the remote host we are querying
source_labels = [ "__param_target" ];
target_label = "instance";
}
{
# Shows the host target address instead of the blackbox address
target_label = "__address__";
replacement = "127.0.0.1:9115";
}
];
}
{
job_name = "ipmi-raccoon";
metrics_path = "/ipmi";
static_configs = [
{ targets = [ "127.0.0.1:9290" ]; }
];
params = {
target = [ "raccoon-ipmi" ];
module = [ "raccoon" ];
};
}
{
job_name = "ipmi-fox";
metrics_path = "/ipmi";
static_configs = [
{ targets = [ "127.0.0.1:9290" ]; }
];
params = {
target = [ "fox-ipmi.ac.upc.edu" ];
module = [ "fox" ];
};
}
];
};
}

View File

@@ -1,73 +0,0 @@
{ theFlake, pkgs, ... }:
let
website = pkgs.stdenv.mkDerivation {
name = "jungle-web";
src = theFlake;
buildInputs = [ pkgs.hugo ];
buildPhase = ''
cd web
rm -rf public/
hugo
'';
installPhase = ''
cp -r public $out
'';
# Don't mess doc/
dontFixup = true;
};
in
{
networking.firewall.allowedTCPPorts = [ 80 ];
services.nginx = {
enable = true;
virtualHosts."jungle.bsc.es" = {
root = "${website}";
listen = [
{
addr = "0.0.0.0";
port = 80;
}
];
extraConfig = ''
set_real_ip_from 127.0.0.1;
set_real_ip_from 84.88.52.107;
real_ip_recursive on;
real_ip_header X-Forwarded-For;
location /git {
rewrite ^/git$ / break;
rewrite ^/git/(.*) /$1 break;
proxy_pass http://127.0.0.1:3000;
proxy_redirect http:// $scheme://;
}
location /cache {
rewrite ^/cache/(.*) /$1 break;
proxy_pass http://127.0.0.1:5000;
proxy_redirect http:// $scheme://;
}
location /lists {
proxy_pass http://127.0.0.1:8081;
proxy_redirect http:// $scheme://;
}
location /grafana {
proxy_pass http://127.0.0.1:2342;
proxy_redirect http:// $scheme://;
proxy_set_header Host $host;
# Websockets
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
}
location ~ ^/~(.+?)(/.*)?$ {
alias /vault/home/$1/public_html$2;
index index.html index.htm;
autoindex on;
absolute_redirect off;
}
location /p/ {
alias /var/lib/p/;
}
'';
};
};
}

View File

@@ -1,16 +0,0 @@
{ config, ... }:
{
age.secrets.nixServe.file = ../../secrets/nix-serve.age;
services.nix-serve = {
enable = true;
# Only listen locally, as we serve it via ssh
bindAddress = "127.0.0.1";
port = 5000;
secretKeyFile = config.age.secrets.nixServe.path;
# Public key:
# jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=
};
}

View File

@@ -1,28 +0,0 @@
{ lib, ... }:
{
imports = [
../common/ssf.nix
];
# Select this using the ID to avoid mismatches
boot.loader.grub.device = "/dev/disk/by-id/wwn-0x55cd2e414d5356ca";
# No swap, there is plenty of RAM
swapDevices = lib.mkForce [];
# Users with sudo access
users.groups.wheel.members = [ "abonerib" "anavarro" ];
networking = {
hostName = "weasel";
interfaces.eno1.ipv4.addresses = [ {
address = "10.0.40.6";
prefixLength = 24;
} ];
interfaces.ibp5s0.ipv4.addresses = [ {
address = "10.0.42.6";
prefixLength = 24;
} ];
};
}

405
pkgs/ceph.nix Normal file
View File

@@ -0,0 +1,405 @@
{ lib
, stdenv
, runCommand
, fetchurl
, fetchFromGitHub
, fetchPypi
# Build time
, cmake
, ensureNewerSourcesHook
, fmt
, git
, makeWrapper
, nasm
, pkg-config
, which
# Tests
, nixosTests
# Runtime dependencies
, arrow-cpp
, babeltrace
, boost179
, bzip2
, cryptsetup
, cunit
, doxygen
, gperf
, graphviz
, gtest
, icu
, libcap
, libcap_ng
, libnl
, libxml2
, lttng-ust
, lua
, lz4
, oath-toolkit
, openldap
, python310
, rdkafka
, rocksdb
, snappy
, sqlite
, utf8proc
, zlib
, zstd
# Optional Dependencies
, curl ? null
, expat ? null
, fuse ? null
, libatomic_ops ? null
, libedit ? null
, libs3 ? null
, yasm ? null
# Mallocs
, gperftools ? null
, jemalloc ? null
# Crypto Dependencies
, cryptopp ? null
, nspr ? null
, nss ? null
# Linux Only Dependencies
, linuxHeaders
, util-linux
, libuuid
, udev
, keyutils
, rdma-core
, rabbitmq-c
, libaio ? null
, libxfs ? null
, liburing ? null
, zfs ? null
, ...
}:
# We must have one crypto library
assert cryptopp != null || (nss != null && nspr != null);
let
shouldUsePkg = pkg: if pkg != null && pkg.meta.available then pkg else null;
optYasm = shouldUsePkg yasm;
optExpat = shouldUsePkg expat;
optCurl = shouldUsePkg curl;
optFuse = shouldUsePkg fuse;
optLibedit = shouldUsePkg libedit;
optLibatomic_ops = shouldUsePkg libatomic_ops;
optLibs3 = shouldUsePkg libs3;
optJemalloc = shouldUsePkg jemalloc;
optGperftools = shouldUsePkg gperftools;
optCryptopp = shouldUsePkg cryptopp;
optNss = shouldUsePkg nss;
optNspr = shouldUsePkg nspr;
optLibaio = shouldUsePkg libaio;
optLibxfs = shouldUsePkg libxfs;
optZfs = shouldUsePkg zfs;
# Downgrade rocksdb, 7.10 breaks ceph
rocksdb' = rocksdb.overrideAttrs {
version = "7.9.2";
src = fetchFromGitHub {
owner = "facebook";
repo = "rocksdb";
rev = "refs/tags/v7.9.2";
hash = "sha256-5P7IqJ14EZzDkbjaBvbix04ceGGdlWBuVFH/5dpD5VM=";
};
};
hasRadosgw = optExpat != null && optCurl != null && optLibedit != null;
# Malloc implementation (can be jemalloc, tcmalloc or null)
malloc = if optJemalloc != null then optJemalloc else optGperftools;
# We prefer nss over cryptopp
cryptoStr = if optNss != null && optNspr != null then "nss" else
if optCryptopp != null then "cryptopp" else "none";
cryptoLibsMap = {
nss = [ optNss optNspr ];
cryptopp = [ optCryptopp ];
none = [ ];
};
getMeta = description: with lib; {
homepage = "https://ceph.io/en/";
inherit description;
license = with licenses; [ lgpl21 gpl2 bsd3 mit publicDomain ];
maintainers = with maintainers; [ adev ak johanot krav ];
platforms = [ "x86_64-linux" "aarch64-linux" ];
};
ceph-common = with python.pkgs; buildPythonPackage {
pname = "ceph-common";
inherit src version;
sourceRoot = "ceph-${version}/src/python-common";
propagatedBuildInputs = [
pyyaml
];
nativeCheckInputs = [
pytestCheckHook
];
disabledTests = [
# requires network access
"test_valid_addr"
];
meta = getMeta "Ceph common module for code shared by manager modules";
};
# Watch out for python <> boost compatibility
python = python310.override {
packageOverrides = self: super: {
sqlalchemy = super.sqlalchemy.overridePythonAttrs rec {
version = "1.4.46";
src = fetchPypi {
pname = "SQLAlchemy";
inherit version;
hash = "sha256-aRO4JH2KKS74MVFipRkx4rQM6RaB8bbxj2lwRSAMSjA=";
};
disabledTestPaths = [
"test/aaa_profiling"
"test/ext/mypy"
];
};
};
};
boost = boost179.override {
enablePython = true;
inherit python;
};
# TODO: split this off in build and runtime environment
ceph-python-env = python.withPackages (ps: with ps; [
ceph-common
# build time
cython
# debian/control
bcrypt
cherrypy
influxdb
jinja2
kubernetes
natsort
numpy
pecan
prettytable
pyjwt
pyopenssl
python-dateutil
pyyaml
requests
routes
scikit-learn
scipy
setuptools
sphinx
virtualenv
werkzeug
# src/pybind/mgr/requirements-required.txt
cryptography
jsonpatch
# src/tools/cephfs/shell/setup.py
cmd2
colorama
]);
inherit (ceph-python-env.python) sitePackages;
version = "18.2.0";
src = fetchurl {
url = "https://download.ceph.com/tarballs/ceph-${version}.tar.gz";
hash = "sha256:0k9nl6xi5brva51rr14m7ig27mmmd7vrpchcmqc40q3c2khn6ns9";
};
in rec {
ceph = stdenv.mkDerivation {
pname = "ceph";
inherit src version;
nativeBuildInputs = [
cmake
fmt
git
makeWrapper
nasm
pkg-config
python
python.pkgs.python # for the toPythonPath function
python.pkgs.wrapPython
which
(ensureNewerSourcesHook { year = "1980"; })
# for building docs/man-pages presumably
doxygen
graphviz
];
enableParallelBuilding = true;
buildInputs = cryptoLibsMap.${cryptoStr} ++ [
arrow-cpp
babeltrace
boost
bzip2
ceph-python-env
cryptsetup
cunit
gperf
gtest
icu
libcap
libnl
libxml2
lttng-ust
lua
lz4
malloc
oath-toolkit
openldap
optLibatomic_ops
optLibs3
optYasm
rdkafka
rocksdb'
snappy
sqlite
utf8proc
zlib
zstd
] ++ lib.optionals stdenv.isLinux [
keyutils
libcap_ng
liburing
libuuid
linuxHeaders
optLibaio
optLibxfs
optZfs
rabbitmq-c
rdma-core
udev
util-linux
] ++ lib.optionals hasRadosgw [
optCurl
optExpat
optFuse
optLibedit
];
pythonPath = [ ceph-python-env "${placeholder "out"}/${ceph-python-env.sitePackages}" ];
preConfigure =''
substituteInPlace src/common/module.c --replace "/sbin/modinfo" "modinfo"
substituteInPlace src/common/module.c --replace "/sbin/modprobe" "modprobe"
substituteInPlace src/common/module.c --replace "/bin/grep" "grep"
# install target needs to be in PYTHONPATH for "*.pth support" check to succeed
# set PYTHONPATH, so the build system doesn't silently skip installing ceph-volume and others
export PYTHONPATH=${ceph-python-env}/${sitePackages}:$lib/${sitePackages}:$out/${sitePackages}
patchShebangs src/
'';
cmakeFlags = [
"-DCMAKE_INSTALL_DATADIR=${placeholder "lib"}/lib"
"-DWITH_CEPHFS_SHELL:BOOL=ON"
"-DWITH_SYSTEMD:BOOL=OFF"
# `WITH_JAEGER` requires `thrift` as a depenedncy (fine), but the build fails with:
# CMake Error at src/opentelemetry-cpp-stamp/opentelemetry-cpp-build-Release.cmake:49 (message):
# Command failed: 2
#
# 'make' 'opentelemetry_trace' 'opentelemetry_exporter_jaeger_trace'
#
# See also
#
# /build/ceph-18.2.0/build/src/opentelemetry-cpp/src/opentelemetry-cpp-stamp/opentelemetry-cpp-build-*.log
# and that file contains:
# /build/ceph-18.2.0/src/jaegertracing/opentelemetry-cpp/exporters/jaeger/src/TUDPTransport.cc: In member function 'virtual void opentelemetry::v1::exporter::jaeger::TUDPTransport::close()':
# /build/ceph-18.2.0/src/jaegertracing/opentelemetry-cpp/exporters/jaeger/src/TUDPTransport.cc:71:7: error: '::close' has not been declared; did you mean 'pclose'?
# 71 | ::THRIFT_CLOSESOCKET(socket_);
# | ^~~~~~~~~~~~~~~~~~
# Looks like `close()` is somehow not included.
# But the relevant code is already removed in `open-telemetry` 1.10: https://github.com/open-telemetry/opentelemetry-cpp/pull/2031
# So it's proably not worth trying to fix that for this Ceph version,
# and instead just disable Ceph's Jaeger support.
"-DWITH_JAEGER:BOOL=OFF"
"-DWITH_TESTS:BOOL=OFF"
# Use our own libraries, where possible
"-DWITH_SYSTEM_ARROW:BOOL=ON" # Only used if other options enable Arrow support.
"-DWITH_SYSTEM_BOOST:BOOL=ON"
"-DWITH_SYSTEM_GTEST:BOOL=ON"
"-DWITH_SYSTEM_ROCKSDB:BOOL=ON"
"-DWITH_SYSTEM_UTF8PROC:BOOL=ON"
"-DWITH_SYSTEM_ZSTD:BOOL=ON"
# TODO breaks with sandbox, tries to download stuff with npm
"-DWITH_MGR_DASHBOARD_FRONTEND:BOOL=OFF"
# WITH_XFS has been set default ON from Ceph 16, keeping it optional in nixpkgs for now
''-DWITH_XFS=${if optLibxfs != null then "ON" else "OFF"}''
] ++ lib.optional stdenv.isLinux "-DWITH_SYSTEM_LIBURING=ON";
postFixup = ''
wrapPythonPrograms
wrapProgram $out/bin/ceph-mgr --prefix PYTHONPATH ":" "$(toPythonPath ${placeholder "out"}):$(toPythonPath ${ceph-python-env})"
# Test that ceph-volume exists since the build system has a tendency to
# silently drop it with misconfigurations.
test -f $out/bin/ceph-volume
'';
outputs = [ "out" "lib" "dev" "doc" "man" ];
doCheck = false; # uses pip to install things from the internet
# Takes 7+h to build with 2 cores.
requiredSystemFeatures = [ "big-parallel" ];
meta = getMeta "Distributed storage system";
passthru = {
inherit version;
tests = {
inherit (nixosTests)
ceph-multi-node
ceph-single-node
ceph-single-node-bluestore;
};
};
};
ceph-client = runCommand "ceph-client-${version}" {
meta = getMeta "Tools needed to mount Ceph's RADOS Block Devices/Cephfs";
} ''
mkdir -p $out/{bin,etc,${sitePackages},share/bash-completion/completions}
cp -r ${ceph}/bin/{ceph,.ceph-wrapped,rados,rbd,rbdmap} $out/bin
cp -r ${ceph}/bin/ceph-{authtool,conf,dencoder,rbdnamer,syn} $out/bin
cp -r ${ceph}/bin/rbd-replay* $out/bin
cp -r ${ceph}/sbin/mount.ceph $out/bin
cp -r ${ceph}/sbin/mount.fuse.ceph $out/bin
ln -s bin $out/sbin
cp -r ${ceph}/${sitePackages}/* $out/${sitePackages}
cp -r ${ceph}/etc/bash_completion.d $out/share/bash-completion/completions
# wrapPythonPrograms modifies .ceph-wrapped, so lets just update its paths
substituteInPlace $out/bin/ceph --replace ${ceph} $out
substituteInPlace $out/bin/.ceph-wrapped --replace ${ceph} $out
'';
}

View File

@@ -1,12 +0,0 @@
HOSTCXX ?= g++
NVCC := nvcc -ccbin $(HOSTCXX)
CXXFLAGS := -m64
# Target rules
all: cudainfo
cudainfo: cudainfo.cpp
$(NVCC) $(CXXFLAGS) -o $@ $<
clean:
rm -f cudainfo cudainfo.o

View File

@@ -1,600 +0,0 @@
/*
* Copyright 1993-2015 NVIDIA Corporation. All rights reserved.
*
* Please refer to the NVIDIA end user license agreement (EULA) associated
* with this source code for terms and conditions that govern your use of
* this software. Any use, reproduction, disclosure, or distribution of
* this software and related documentation outside the terms of the EULA
* is strictly prohibited.
*
*/
/* This sample queries the properties of the CUDA devices present in the system via CUDA Runtime API. */
// Shared Utilities (QA Testing)
// std::system includes
#include <memory>
#include <iostream>
#include <cuda_runtime.h>
// This will output the proper CUDA error strings in the event that a CUDA host call returns an error
#define checkCudaErrors(val) check ( (val), #val, __FILE__, __LINE__ )
// CUDA Runtime error messages
#ifdef __DRIVER_TYPES_H__
static const char *_cudaGetErrorEnum(cudaError_t error)
{
switch (error)
{
case cudaSuccess:
return "cudaSuccess";
case cudaErrorMissingConfiguration:
return "cudaErrorMissingConfiguration";
case cudaErrorMemoryAllocation:
return "cudaErrorMemoryAllocation";
case cudaErrorInitializationError:
return "cudaErrorInitializationError";
case cudaErrorLaunchFailure:
return "cudaErrorLaunchFailure";
case cudaErrorPriorLaunchFailure:
return "cudaErrorPriorLaunchFailure";
case cudaErrorLaunchTimeout:
return "cudaErrorLaunchTimeout";
case cudaErrorLaunchOutOfResources:
return "cudaErrorLaunchOutOfResources";
case cudaErrorInvalidDeviceFunction:
return "cudaErrorInvalidDeviceFunction";
case cudaErrorInvalidConfiguration:
return "cudaErrorInvalidConfiguration";
case cudaErrorInvalidDevice:
return "cudaErrorInvalidDevice";
case cudaErrorInvalidValue:
return "cudaErrorInvalidValue";
case cudaErrorInvalidPitchValue:
return "cudaErrorInvalidPitchValue";
case cudaErrorInvalidSymbol:
return "cudaErrorInvalidSymbol";
case cudaErrorMapBufferObjectFailed:
return "cudaErrorMapBufferObjectFailed";
case cudaErrorUnmapBufferObjectFailed:
return "cudaErrorUnmapBufferObjectFailed";
case cudaErrorInvalidHostPointer:
return "cudaErrorInvalidHostPointer";
case cudaErrorInvalidDevicePointer:
return "cudaErrorInvalidDevicePointer";
case cudaErrorInvalidTexture:
return "cudaErrorInvalidTexture";
case cudaErrorInvalidTextureBinding:
return "cudaErrorInvalidTextureBinding";
case cudaErrorInvalidChannelDescriptor:
return "cudaErrorInvalidChannelDescriptor";
case cudaErrorInvalidMemcpyDirection:
return "cudaErrorInvalidMemcpyDirection";
case cudaErrorAddressOfConstant:
return "cudaErrorAddressOfConstant";
case cudaErrorTextureFetchFailed:
return "cudaErrorTextureFetchFailed";
case cudaErrorTextureNotBound:
return "cudaErrorTextureNotBound";
case cudaErrorSynchronizationError:
return "cudaErrorSynchronizationError";
case cudaErrorInvalidFilterSetting:
return "cudaErrorInvalidFilterSetting";
case cudaErrorInvalidNormSetting:
return "cudaErrorInvalidNormSetting";
case cudaErrorMixedDeviceExecution:
return "cudaErrorMixedDeviceExecution";
case cudaErrorCudartUnloading:
return "cudaErrorCudartUnloading";
case cudaErrorUnknown:
return "cudaErrorUnknown";
case cudaErrorNotYetImplemented:
return "cudaErrorNotYetImplemented";
case cudaErrorMemoryValueTooLarge:
return "cudaErrorMemoryValueTooLarge";
case cudaErrorInvalidResourceHandle:
return "cudaErrorInvalidResourceHandle";
case cudaErrorNotReady:
return "cudaErrorNotReady";
case cudaErrorInsufficientDriver:
return "cudaErrorInsufficientDriver";
case cudaErrorSetOnActiveProcess:
return "cudaErrorSetOnActiveProcess";
case cudaErrorInvalidSurface:
return "cudaErrorInvalidSurface";
case cudaErrorNoDevice:
return "cudaErrorNoDevice";
case cudaErrorECCUncorrectable:
return "cudaErrorECCUncorrectable";
case cudaErrorSharedObjectSymbolNotFound:
return "cudaErrorSharedObjectSymbolNotFound";
case cudaErrorSharedObjectInitFailed:
return "cudaErrorSharedObjectInitFailed";
case cudaErrorUnsupportedLimit:
return "cudaErrorUnsupportedLimit";
case cudaErrorDuplicateVariableName:
return "cudaErrorDuplicateVariableName";
case cudaErrorDuplicateTextureName:
return "cudaErrorDuplicateTextureName";
case cudaErrorDuplicateSurfaceName:
return "cudaErrorDuplicateSurfaceName";
case cudaErrorDevicesUnavailable:
return "cudaErrorDevicesUnavailable";
case cudaErrorInvalidKernelImage:
return "cudaErrorInvalidKernelImage";
case cudaErrorNoKernelImageForDevice:
return "cudaErrorNoKernelImageForDevice";
case cudaErrorIncompatibleDriverContext:
return "cudaErrorIncompatibleDriverContext";
case cudaErrorPeerAccessAlreadyEnabled:
return "cudaErrorPeerAccessAlreadyEnabled";
case cudaErrorPeerAccessNotEnabled:
return "cudaErrorPeerAccessNotEnabled";
case cudaErrorDeviceAlreadyInUse:
return "cudaErrorDeviceAlreadyInUse";
case cudaErrorProfilerDisabled:
return "cudaErrorProfilerDisabled";
case cudaErrorProfilerNotInitialized:
return "cudaErrorProfilerNotInitialized";
case cudaErrorProfilerAlreadyStarted:
return "cudaErrorProfilerAlreadyStarted";
case cudaErrorProfilerAlreadyStopped:
return "cudaErrorProfilerAlreadyStopped";
/* Since CUDA 4.0*/
case cudaErrorAssert:
return "cudaErrorAssert";
case cudaErrorTooManyPeers:
return "cudaErrorTooManyPeers";
case cudaErrorHostMemoryAlreadyRegistered:
return "cudaErrorHostMemoryAlreadyRegistered";
case cudaErrorHostMemoryNotRegistered:
return "cudaErrorHostMemoryNotRegistered";
/* Since CUDA 5.0 */
case cudaErrorOperatingSystem:
return "cudaErrorOperatingSystem";
case cudaErrorPeerAccessUnsupported:
return "cudaErrorPeerAccessUnsupported";
case cudaErrorLaunchMaxDepthExceeded:
return "cudaErrorLaunchMaxDepthExceeded";
case cudaErrorLaunchFileScopedTex:
return "cudaErrorLaunchFileScopedTex";
case cudaErrorLaunchFileScopedSurf:
return "cudaErrorLaunchFileScopedSurf";
case cudaErrorSyncDepthExceeded:
return "cudaErrorSyncDepthExceeded";
case cudaErrorLaunchPendingCountExceeded:
return "cudaErrorLaunchPendingCountExceeded";
case cudaErrorNotPermitted:
return "cudaErrorNotPermitted";
case cudaErrorNotSupported:
return "cudaErrorNotSupported";
/* Since CUDA 6.0 */
case cudaErrorHardwareStackError:
return "cudaErrorHardwareStackError";
case cudaErrorIllegalInstruction:
return "cudaErrorIllegalInstruction";
case cudaErrorMisalignedAddress:
return "cudaErrorMisalignedAddress";
case cudaErrorInvalidAddressSpace:
return "cudaErrorInvalidAddressSpace";
case cudaErrorInvalidPc:
return "cudaErrorInvalidPc";
case cudaErrorIllegalAddress:
return "cudaErrorIllegalAddress";
/* Since CUDA 6.5*/
case cudaErrorInvalidPtx:
return "cudaErrorInvalidPtx";
case cudaErrorInvalidGraphicsContext:
return "cudaErrorInvalidGraphicsContext";
case cudaErrorStartupFailure:
return "cudaErrorStartupFailure";
case cudaErrorApiFailureBase:
return "cudaErrorApiFailureBase";
}
return "<unknown>";
}
#endif
template< typename T >
void check(T result, char const *const func, const char *const file, int const line)
{
if (result)
{
fprintf(stderr, "CUDA error at %s:%d code=%d(%s) \"%s\" \n",
file, line, static_cast<unsigned int>(result), _cudaGetErrorEnum(result), func);
cudaDeviceReset();
// Make sure we call CUDA Device Reset before exiting
exit(EXIT_FAILURE);
}
}
int *pArgc = NULL;
char **pArgv = NULL;
#if CUDART_VERSION < 5000
// CUDA-C includes
#include <cuda.h>
// This function wraps the CUDA Driver API into a template function
template <class T>
inline void getCudaAttribute(T *attribute, CUdevice_attribute device_attribute, int device)
{
CUresult error = cuDeviceGetAttribute(attribute, device_attribute, device);
if (CUDA_SUCCESS != error) {
fprintf(stderr, "cuSafeCallNoSync() Driver API error = %04d from file <%s>, line %i.\n",
error, __FILE__, __LINE__);
// cudaDeviceReset causes the driver to clean up all state. While
// not mandatory in normal operation, it is good practice. It is also
// needed to ensure correct operation when the application is being
// profiled. Calling cudaDeviceReset causes all profile data to be
// flushed before the application exits
cudaDeviceReset();
exit(EXIT_FAILURE);
}
}
#endif /* CUDART_VERSION < 5000 */
// Beginning of GPU Architecture definitions
inline int ConvertSMVer2Cores(int major, int minor)
{
// Defines for GPU Architecture types (using the SM version to determine the # of cores per SM
typedef struct {
int SM; // 0xMm (hexidecimal notation), M = SM Major version, and m = SM minor version
int Cores;
} sSMtoCores;
sSMtoCores nGpuArchCoresPerSM[] = {
{ 0x20, 32 }, // Fermi Generation (SM 2.0) GF100 class
{ 0x21, 48 }, // Fermi Generation (SM 2.1) GF10x class
{ 0x30, 192}, // Kepler Generation (SM 3.0) GK10x class
{ 0x32, 192}, // Kepler Generation (SM 3.2) GK10x class
{ 0x35, 192}, // Kepler Generation (SM 3.5) GK11x class
{ 0x37, 192}, // Kepler Generation (SM 3.7) GK21x class
{ 0x50, 128}, // Maxwell Generation (SM 5.0) GM10x class
{ 0x52, 128}, // Maxwell Generation (SM 5.2) GM20x class
{ -1, -1 }
};
int index = 0;
while (nGpuArchCoresPerSM[index].SM != -1) {
if (nGpuArchCoresPerSM[index].SM == ((major << 4) + minor)) {
return nGpuArchCoresPerSM[index].Cores;
}
index++;
}
// If we don't find the values, we default use the previous one to run properly
printf("MapSMtoCores for SM %d.%d is undefined. Default to use %d Cores/SM\n", major, minor, nGpuArchCoresPerSM[index-1].Cores);
return nGpuArchCoresPerSM[index-1].Cores;
}
////////////////////////////////////////////////////////////////////////////////
// Program main
////////////////////////////////////////////////////////////////////////////////
int
main(int argc, char **argv)
{
pArgc = &argc;
pArgv = argv;
printf("%s Starting...\n\n", argv[0]);
printf(" CUDA Device Query (Runtime API) version (CUDART static linking)\n\n");
int deviceCount = 0;
cudaError_t error_id = cudaGetDeviceCount(&deviceCount);
if (error_id != cudaSuccess) {
printf("cudaGetDeviceCount failed: %s (%d)\n",
cudaGetErrorString(error_id), (int) error_id);
printf("Result = FAIL\n");
exit(EXIT_FAILURE);
}
// This function call returns 0 if there are no CUDA capable devices.
if (deviceCount == 0)
printf("There are no available device(s) that support CUDA\n");
else
printf("Detected %d CUDA Capable device(s)\n", deviceCount);
int dev, driverVersion = 0, runtimeVersion = 0;
for (dev = 0; dev < deviceCount; ++dev) {
cudaSetDevice(dev);
cudaDeviceProp deviceProp;
cudaGetDeviceProperties(&deviceProp, dev);
printf("\nDevice %d: \"%s\"\n", dev, deviceProp.name);
// Console log
cudaDriverGetVersion(&driverVersion);
cudaRuntimeGetVersion(&runtimeVersion);
printf(" CUDA Driver Version / Runtime Version %d.%d / %d.%d\n", driverVersion/1000, (driverVersion%100)/10, runtimeVersion/1000, (runtimeVersion%100)/10);
printf(" CUDA Capability Major/Minor version number: %d.%d\n", deviceProp.major, deviceProp.minor);
printf(" Total amount of global memory: %.0f MBytes (%llu bytes)\n",
(float)deviceProp.totalGlobalMem/1048576.0f, (unsigned long long) deviceProp.totalGlobalMem);
printf(" (%2d) Multiprocessors, (%3d) CUDA Cores/MP: %d CUDA Cores\n",
deviceProp.multiProcessorCount,
ConvertSMVer2Cores(deviceProp.major, deviceProp.minor),
ConvertSMVer2Cores(deviceProp.major, deviceProp.minor) * deviceProp.multiProcessorCount);
printf(" GPU Max Clock rate: %.0f MHz (%0.2f GHz)\n", deviceProp.clockRate * 1e-3f, deviceProp.clockRate * 1e-6f);
#if CUDART_VERSION >= 5000
// This is supported in CUDA 5.0 (runtime API device properties)
printf(" Memory Clock rate: %.0f Mhz\n", deviceProp.memoryClockRate * 1e-3f);
printf(" Memory Bus Width: %d-bit\n", deviceProp.memoryBusWidth);
if (deviceProp.l2CacheSize) {
printf(" L2 Cache Size: %d bytes\n", deviceProp.l2CacheSize);
}
#else
// This only available in CUDA 4.0-4.2 (but these were only exposed in the CUDA Driver API)
int memoryClock;
getCudaAttribute<int>(&memoryClock, CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE, dev);
printf(" Memory Clock rate: %.0f Mhz\n", memoryClock * 1e-3f);
int memBusWidth;
getCudaAttribute<int>(&memBusWidth, CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH, dev);
printf(" Memory Bus Width: %d-bit\n", memBusWidth);
int L2CacheSize;
getCudaAttribute<int>(&L2CacheSize, CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE, dev);
if (L2CacheSize) {
printf(" L2 Cache Size: %d bytes\n", L2CacheSize);
}
#endif
printf(" Maximum Texture Dimension Size (x,y,z) 1D=(%d), 2D=(%d, %d), 3D=(%d, %d, %d)\n",
deviceProp.maxTexture1D , deviceProp.maxTexture2D[0], deviceProp.maxTexture2D[1],
deviceProp.maxTexture3D[0], deviceProp.maxTexture3D[1], deviceProp.maxTexture3D[2]);
printf(" Maximum Layered 1D Texture Size, (num) layers 1D=(%d), %d layers\n",
deviceProp.maxTexture1DLayered[0], deviceProp.maxTexture1DLayered[1]);
printf(" Maximum Layered 2D Texture Size, (num) layers 2D=(%d, %d), %d layers\n",
deviceProp.maxTexture2DLayered[0], deviceProp.maxTexture2DLayered[1], deviceProp.maxTexture2DLayered[2]);
printf(" Total amount of constant memory: %lu bytes\n", deviceProp.totalConstMem);
printf(" Total amount of shared memory per block: %lu bytes\n", deviceProp.sharedMemPerBlock);
printf(" Total number of registers available per block: %d\n", deviceProp.regsPerBlock);
printf(" Warp size: %d\n", deviceProp.warpSize);
printf(" Maximum number of threads per multiprocessor: %d\n", deviceProp.maxThreadsPerMultiProcessor);
printf(" Maximum number of threads per block: %d\n", deviceProp.maxThreadsPerBlock);
printf(" Max dimension size of a thread block (x,y,z): (%d, %d, %d)\n",
deviceProp.maxThreadsDim[0],
deviceProp.maxThreadsDim[1],
deviceProp.maxThreadsDim[2]);
printf(" Max dimension size of a grid size (x,y,z): (%d, %d, %d)\n",
deviceProp.maxGridSize[0],
deviceProp.maxGridSize[1],
deviceProp.maxGridSize[2]);
printf(" Maximum memory pitch: %lu bytes\n", deviceProp.memPitch);
printf(" Texture alignment: %lu bytes\n", deviceProp.textureAlignment);
printf(" Concurrent copy and kernel execution: %s with %d copy engine(s)\n", (deviceProp.deviceOverlap ? "Yes" : "No"), deviceProp.asyncEngineCount);
printf(" Run time limit on kernels: %s\n", deviceProp.kernelExecTimeoutEnabled ? "Yes" : "No");
printf(" Integrated GPU sharing Host Memory: %s\n", deviceProp.integrated ? "Yes" : "No");
printf(" Support host page-locked memory mapping: %s\n", deviceProp.canMapHostMemory ? "Yes" : "No");
printf(" Alignment requirement for Surfaces: %s\n", deviceProp.surfaceAlignment ? "Yes" : "No");
printf(" Device has ECC support: %s\n", deviceProp.ECCEnabled ? "Enabled" : "Disabled");
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
printf(" CUDA Device Driver Mode (TCC or WDDM): %s\n", deviceProp.tccDriver ? "TCC (Tesla Compute Cluster Driver)" : "WDDM (Windows Display Driver Model)");
#endif
printf(" Device supports Unified Addressing (UVA): %s\n", deviceProp.unifiedAddressing ? "Yes" : "No");
printf(" Device PCI Domain ID / Bus ID / location ID: %d / %d / %d\n", deviceProp.pciDomainID, deviceProp.pciBusID, deviceProp.pciDeviceID);
const char *sComputeMode[] = {
"Default (multiple host threads can use ::cudaSetDevice() with device simultaneously)",
"Exclusive (only one host thread in one process is able to use ::cudaSetDevice() with this device)",
"Prohibited (no host thread can use ::cudaSetDevice() with this device)",
"Exclusive Process (many threads in one process is able to use ::cudaSetDevice() with this device)",
"Unknown",
NULL
};
printf(" Compute Mode:\n");
printf(" < %s >\n", sComputeMode[deviceProp.computeMode]);
}
// If there are 2 or more GPUs, query to determine whether RDMA is supported
if (deviceCount >= 2)
{
cudaDeviceProp prop[64];
int gpuid[64]; // we want to find the first two GPU's that can support P2P
int gpu_p2p_count = 0;
for (int i=0; i < deviceCount; i++)
{
checkCudaErrors(cudaGetDeviceProperties(&prop[i], i));
// Only boards based on Fermi or later can support P2P
if ((prop[i].major >= 2)
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
// on Windows (64-bit), the Tesla Compute Cluster driver for windows must be enabled to supprot this
&& prop[i].tccDriver
#endif
)
{
// This is an array of P2P capable GPUs
gpuid[gpu_p2p_count++] = i;
}
}
// Show all the combinations of support P2P GPUs
int can_access_peer_0_1, can_access_peer_1_0;
if (gpu_p2p_count >= 2)
{
for (int i = 0; i < gpu_p2p_count-1; i++)
{
for (int j = 1; j < gpu_p2p_count; j++)
{
checkCudaErrors(cudaDeviceCanAccessPeer(&can_access_peer_0_1, gpuid[i], gpuid[j]));
printf("> Peer access from %s (GPU%d) -> %s (GPU%d) : %s\n", prop[gpuid[i]].name, gpuid[i],
prop[gpuid[j]].name, gpuid[j] ,
can_access_peer_0_1 ? "Yes" : "No");
}
}
for (int j = 1; j < gpu_p2p_count; j++)
{
for (int i = 0; i < gpu_p2p_count-1; i++)
{
checkCudaErrors(cudaDeviceCanAccessPeer(&can_access_peer_1_0, gpuid[j], gpuid[i]));
printf("> Peer access from %s (GPU%d) -> %s (GPU%d) : %s\n", prop[gpuid[j]].name, gpuid[j],
prop[gpuid[i]].name, gpuid[i] ,
can_access_peer_1_0 ? "Yes" : "No");
}
}
}
}
// csv masterlog info
// *****************************
// exe and CUDA driver name
printf("\n");
std::string sProfileString = "deviceQuery, CUDA Driver = CUDART";
char cTemp[128];
// driver version
sProfileString += ", CUDA Driver Version = ";
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
sprintf_s(cTemp, 10, "%d.%d", driverVersion/1000, (driverVersion%100)/10);
#else
sprintf(cTemp, "%d.%d", driverVersion/1000, (driverVersion%100)/10);
#endif
sProfileString += cTemp;
// Runtime version
sProfileString += ", CUDA Runtime Version = ";
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
sprintf_s(cTemp, 10, "%d.%d", runtimeVersion/1000, (runtimeVersion%100)/10);
#else
sprintf(cTemp, "%d.%d", runtimeVersion/1000, (runtimeVersion%100)/10);
#endif
sProfileString += cTemp;
// Device count
sProfileString += ", NumDevs = ";
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
sprintf_s(cTemp, 10, "%d", deviceCount);
#else
sprintf(cTemp, "%d", deviceCount);
#endif
sProfileString += cTemp;
// Print Out all device Names
for (dev = 0; dev < deviceCount; ++dev)
{
#if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
sprintf_s(cTemp, 13, ", Device%d = ", dev);
#else
sprintf(cTemp, ", Device%d = ", dev);
#endif
cudaDeviceProp deviceProp;
cudaGetDeviceProperties(&deviceProp, dev);
sProfileString += cTemp;
sProfileString += deviceProp.name;
}
sProfileString += "\n";
printf("%s", sProfileString.c_str());
printf("Result = PASS\n");
// finish
// cudaDeviceReset causes the driver to clean up all state. While
// not mandatory in normal operation, it is good practice. It is also
// needed to ensure correct operation when the application is being
// profiled. Calling cudaDeviceReset causes all profile data to be
// flushed before the application exits
cudaDeviceReset();
return 0;
}

View File

@@ -1,43 +0,0 @@
{
stdenv
, cudatoolkit
, cudaPackages
, autoAddDriverRunpath
, strace
}:
stdenv.mkDerivation (finalAttrs: {
name = "cudainfo";
src = ./.;
buildInputs = [
cudatoolkit # Required for nvcc
cudaPackages.cuda_cudart.static # Required for -lcudart_static
autoAddDriverRunpath
];
installPhase = ''
mkdir -p $out/bin
cp -a cudainfo $out/bin
'';
passthru.gpuCheck = stdenv.mkDerivation {
name = "cudainfo-test";
requiredSystemFeatures = [ "cuda" ];
dontBuild = true;
nativeCheckInputs = [
finalAttrs.finalPackage # The cudainfo package from above
strace # When it fails, it will show the trace
];
dontUnpack = true;
doCheck = true;
checkPhase = ''
if ! cudainfo; then
set -x
cudainfo=$(command -v cudainfo)
ldd $cudainfo
readelf -d $cudainfo
strace -f $cudainfo
set +x
fi
'';
installPhase = "touch $out";
};
})

View File

@@ -1,25 +0,0 @@
{ python3Packages, lib }:
python3Packages.buildPythonApplication rec {
pname = "meteocat-exporter";
version = "1.0";
src = ./.;
doCheck = false;
build-system = with python3Packages; [
setuptools
];
dependencies = with python3Packages; [
beautifulsoup4
lxml
prometheus-client
];
meta = with lib; {
description = "MeteoCat Prometheus Exporter";
platforms = platforms.linux;
};
}

View File

@@ -1,54 +0,0 @@
#!/usr/bin/env python3
import time
from prometheus_client import start_http_server, Gauge
from bs4 import BeautifulSoup
from urllib import request
# Configuration -------------------------------------------
meteo_station = "X8" # Barcelona - Zona Universitària
listening_port = 9929
update_period = 60 * 5 # Each 5 min
# ---------------------------------------------------------
metric_tmin = Gauge('meteocat_temp_min', 'Min temperature')
metric_tmax = Gauge('meteocat_temp_max', 'Max temperature')
metric_tavg = Gauge('meteocat_temp_avg', 'Average temperature')
metric_srad = Gauge('meteocat_solar_radiation', 'Solar radiation')
def update(st):
url = 'https://www.meteo.cat/observacions/xema/dades?codi=' + st
response = request.urlopen(url)
data = response.read()
soup = BeautifulSoup(data, 'lxml')
table = soup.find("table", {"class" : "tblperiode"})
rows = table.find_all('tr')
row = rows[-1] # Take the last row
row_data = []
header = row.find('th')
header_text = header.text.strip()
row_data.append(header_text)
for col in row.find_all('td'):
row_data.append(col.text)
try:
# Sometimes it will return '(s/d)' and fail to parse
metric_tavg.set(float(row_data[1]))
metric_tmax.set(float(row_data[2]))
metric_tmin.set(float(row_data[3]))
metric_srad.set(float(row_data[10]))
#print("ok: temp_avg={}".format(float(row_data[1])))
except:
print("cannot parse row: {}".format(row))
metric_tavg.set(float("nan"))
metric_tmax.set(float("nan"))
metric_tmin.set(float("nan"))
metric_srad.set(float("nan"))
if __name__ == '__main__':
start_http_server(port=listening_port, addr="localhost")
while True:
try:
update(meteo_station)
except:
print("update failed")
time.sleep(update_period)

View File

@@ -1,11 +0,0 @@
#!/usr/bin/env python
from setuptools import setup, find_packages
setup(name='meteocat-exporter',
version='1.0',
# Modules to import from other scripts:
packages=find_packages(),
# Executables
scripts=["meteocat-exporter"],
)

11
pkgs/nix-socket.patch Normal file
View File

@@ -0,0 +1,11 @@
--- a/misc/systemd/nix-daemon.socket.in 1970-01-01 01:00:01.000000000 +0100
+++ b/misc/systemd/nix-daemon.socket.in 2023-09-18 17:53:32.351760208 +0200
@@ -1,7 +1,7 @@
[Unit]
Description=Nix Daemon Socket
Before=multi-user.target
-RequiresMountsFor=@storedir@
+RequiresMountsFor=@localstatedir@
ConditionPathIsReadWrite=@localstatedir@/nix/daemon-socket
[Socket]

View File

@@ -1,56 +1,39 @@
final: prev:
{
# Set MPICH as default
mpi = final.mpich;
bsc = prev.bsc.extend (bscFinal: bscPrev: {
# Set MPICH as default
mpi = bscFinal.mpich;
# Configure the network for MPICH
mpich = with final; let
# pmix comes with the libraries in .out and headers in .dev
pmixAll = symlinkJoin {
name = "pmix-all";
paths = [ pmix.dev pmix.out ];
};
in prev.mpich.overrideAttrs (old: {
buildInput = old.buildInputs ++ [
libfabric
pmixAll
];
configureFlags = [
"--enable-shared"
"--enable-sharedlib"
"--with-pm=no"
"--with-device=ch4:ofi"
"--with-pmi=pmix"
"--with-pmix=${pmixAll}"
"--with-libfabric=${libfabric}"
"--enable-g=log"
] ++ lib.optionals (lib.versionAtLeast gfortran.version "10") [
"FFLAGS=-fallow-argument-mismatch" # https://github.com/pmodels/mpich/issues/4300
"FCFLAGS=-fallow-argument-mismatch"
];
# Configure the network for MPICH
mpich = with final; prev.mpich.overrideAttrs (old: {
buildInput = old.buildInputs ++ [
libfabric
pmix
];
configureFlags = [
"--enable-shared"
"--enable-sharedlib"
"--with-pm=no"
"--with-device=ch4:ofi"
"--with-pmi=pmix"
"--with-pmix=${final.pmix}"
"--with-libfabric=${final.libfabric}"
"--enable-g=log"
] ++ lib.optionals (lib.versionAtLeast gfortran.version "10") [
"FFLAGS=-fallow-argument-mismatch" # https://github.com/pmodels/mpich/issues/4300
"FCFLAGS=-fallow-argument-mismatch"
];
});
});
slurm = prev.slurm.overrideAttrs (old: {
patches = (old.patches or []) ++ [
# See https://bugs.schedmd.com/show_bug.cgi?id=19324
./slurm-rank-expansion.patch
];
# Install also the pam_slurm_adopt library to restrict users from accessing
# nodes with no job allocated.
postBuild = (old.postBuild or "") + ''
pushd contribs/pam_slurm_adopt
make "PAM_DIR=$out/lib/security"
popd
'';
postInstall = (old.postInstall or "") + ''
pushd contribs/pam_slurm_adopt
make "PAM_DIR=$out/lib/security" install
popd
'';
});
# Update ceph to 18.2.0 until it lands in nixpkgs, see:
# https://github.com/NixOS/nixpkgs/pull/247849
inherit (prev.callPackage ./ceph.nix {
lua = prev.lua5_4;
fmt = prev.fmt_8;
}) ceph ceph-client;
prometheus-slurm-exporter = prev.callPackage ./slurm-exporter.nix { };
meteocat-exporter = prev.callPackage ./meteocat-exporter/default.nix { };
upc-qaire-exporter = prev.callPackage ./upc-qaire-exporter/default.nix { };
cudainfo = prev.callPackage ./cudainfo/default.nix { };
nix = prev.nix.overrideAttrs (old: {
patches = old.patches ++ [ ./nix-socket.patch ];
});
}

View File

@@ -1,22 +0,0 @@
{ buildGoModule, fetchFromGitHub, lib }:
buildGoModule rec {
pname = "prometheus-slurm-exporter";
version = "0.20";
src = fetchFromGitHub {
rev = version;
owner = "vpenso";
repo = pname;
sha256 = "sha256-KS9LoDuLQFq3KoKpHd8vg1jw20YCNRJNJrnBnu5vxvs=";
};
vendorHash = "sha256-A1dd9T9SIEHDCiVT2UwV6T02BSLh9ej6LC/2l54hgwI=";
doCheck = false;
meta = with lib; {
description = "Prometheus SLURM Exporter";
homepage = "https://github.com/vpenso/prometheus-slurm-exporter";
platforms = platforms.linux;
};
}

Some files were not shown because too many files have changed in this diff Show More