Monitor nix-daemon in tent

Reviewed-by: Aleix Boné <abonerib@bsc.es>
Reviewed-by: Rodrigo Arias Mallo <rodrigo.arias@bsc.es>

flake.nix

@@ -18,6 +18,7 @@ in
   {
     nixosConfigurations = {
       hut     = mkConf "hut";
+      tent    = mkConf "tent";
       owl1    = mkConf "owl1";
       owl2    = mkConf "owl2";
       eudy    = mkConf "eudy";
@@ -25,6 +26,7 @@ in
       bay     = mkConf "bay";
       lake2   = mkConf "lake2";
       raccoon = mkConf "raccoon";
+      fox     = mkConf "fox";
     };
 
     packages.x86_64-linux = self.nixosConfigurations.hut.pkgs // {

keys.nix

@@ -9,9 +9,12 @@ rec {
     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";
   };
 
   hostGroup = with hosts; rec {
+    untrusted  = [ fox ];
     compute    = [ owl1 owl2 ];
     playground = [ eudy koro ];
     storage    = [ bay lake2 ];
@@ -23,7 +26,8 @@ rec {
   };
 
   admins = {
-    rarias = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIE1oZTPtlEXdGt0Ak+upeCIiBdaDQtcmuWoTUCVuSVIR rarias@hut";
-    root   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIII/1TNArcwA6D47mgW4TArwlxQRpwmIGiZDysah40Gb root@hut";
+    "rarias@hut"  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIE1oZTPtlEXdGt0Ak+upeCIiBdaDQtcmuWoTUCVuSVIR rarias@hut";
+    "rarias@tent" = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIwlWSBTZi74WTz5xn6gBvTmCoVltmtIAeM3RMmkh4QZ rarias@tent";
+    root          = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIII/1TNArcwA6D47mgW4TArwlxQRpwmIGiZDysah40Gb root@hut";
   };
 }

m/bay/configuration.nix

@@ -2,7 +2,7 @@
 
 {
   imports = [
-    ../common/xeon.nix
+    ../common/ssf.nix
     ../module/monitoring.nix
   ];
 

m/common/base/nix.nix

@@ -23,6 +23,7 @@
       trusted-users = [ "@wheel" ];
       flake-registry = pkgs.writeText "global-registry.json"
         ''{"flakes":[],"version":2}'';
+      keep-outputs = true;
     };
 
     gc = {

m/common/base/ssh.nix

@@ -8,20 +8,10 @@ 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 hut:23080 %h %p
-
-    # Connect to BSC machines via hut proxy too
-    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
-  '';
-
   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";
   };

m/common/base/users.nix

@@ -20,6 +20,7 @@
       rarias = {
         uid = 1880;
         isNormalUser = true;
+        linger = true;
         home = "/home/Computational/rarias";
         description = "Rodrigo Arias";
         group = "Computational";
@@ -39,7 +40,7 @@
         home = "/home/Computational/arocanon";
         description = "Aleix Roca";
         group = "Computational";
-        extraGroups = [ "wheel" ];
+        extraGroups = [ "wheel" "tracing" ];
         hashedPassword = "$6$hliZiW4tULC/tH7p$pqZarwJkNZ7vS0G5llWQKx08UFG9DxDYgad7jplMD8WkZh5k58i4dfPoWtnEShfjTO6JHiIin05ny5lmSXzGM/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIF3zeB5KSimMBAjvzsp1GCkepVaquVZGPYwRIzyzaCba aleix@bsc"
@@ -55,7 +56,7 @@
         home = "/home/Computational/rpenacob";
         description = "Raúl Peñacoba";
         group = "Computational";
-        hosts = [ "owl1" "owl2" "hut" ];
+        hosts = [ "owl1" "owl2" "hut" "tent" ];
         hashedPassword = "$6$TZm3bDIFyPrMhj1E$uEDXoYYd1z2Wd5mMPfh3DZAjP7ztVjJ4ezIcn82C0ImqafPA.AnTmcVftHEzLB3tbe2O4SxDyPSDEQgJ4GOtj/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFYfXg37mauGeurqsLpedgA2XQ9d4Nm0ZGo/hI1f7wwH rpenacob@bsc"
@@ -68,7 +69,7 @@
         home = "/home/Computational/anavarro";
         description = "Antoni Navarro";
         group = "Computational";
-        hosts = [ "hut" "raccoon" ];
+        hosts = [ "hut" "tent" "raccoon" ];
         hashedPassword = "$6$QdNDsuLehoZTYZlb$CDhCouYDPrhoiB7/seu7RF.Gqg4zMQz0n5sA4U1KDgHaZOxy2as9pbIGeF8tOHJKRoZajk5GiaZv0rZMn7Oq31";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAILWjRSlKgzBPZQhIeEtk6Lvws2XNcYwHcwPv4osSgst5 anavarro@ssfhead"
@@ -81,7 +82,7 @@
         home = "/home/Computational/abonerib";
         description = "Aleix Boné";
         group = "Computational";
-        hosts = [ "owl1" "owl2" "hut" "raccoon" ];
+        hosts = [ "owl1" "owl2" "hut" "tent" "raccoon" ];
         hashedPassword = "$6$V1EQWJr474whv7XJ$OfJ0wueM2l.dgiJiiah0Tip9ITcJ7S7qDvtSycsiQ43QBFyP4lU0e0HaXWps85nqB4TypttYR4hNLoz3bz662/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIIFiqXqt88VuUfyANkZyLJNiuroIITaGlOOTMhVDKjf abonerib@bsc"
@@ -107,16 +108,43 @@
         home = "/home/Computational/dbautist";
         description = "Dylan Bautista Cases";
         group = "Computational";
-        hosts = [ "hut" ];
+        hosts = [ "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 = [ "hut" "tent" ];
+        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 = [ "hut" "tent" "fox" ];
+        hashedPassword = "$6$oB0Tcn99DcM4Ch$Vn1A0ulLTn/8B2oFPi9wWl/NOsJzaFAWjqekwcuC9sMC7cgxEVb.Nk5XSzQ2xzYcNe5MLtmzkVYnRS1CqP39Y0";
+        openssh.authorizedKeys.keys = [
+          "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKGt0ESYxekBiHJQowmKpfdouw0hVm3N7tUMtAaeLejK vincent@varch"
+        ];
+      };
     };
 
     groups = {
       Computational = { gid = 564; };
+      tracing = { };
     };
   };
 }

m/common/ssf.nix

@@ -0,0 +1,9 @@
+{
+  # Provides the base system for a xeon node in the SSF rack.
+  imports = [
+    ./xeon.nix
+    ./ssf/fs.nix
+    ./ssf/net.nix
+    ./ssf/ssh.nix
+  ];
+}

m/common/ssf/net.nix

@@ -11,7 +11,7 @@
 
     proxy = {
       default = "http://hut:23080/";
-      noProxy = "127.0.0.1,localhost,internal.domain,10.0.40.40";
+      noProxy = "127.0.0.1,localhost,internal.domain,10.0.40.40,hut";
       # Don't set all_proxy as go complains and breaks the gitlab runner, see:
       # https://github.com/golang/go/issues/16715
       allProxy = null;
@@ -34,37 +34,37 @@
       # 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
+      10.0.40.141             bay-ipmi mds01-ipmi0 mds01-ipmi
       
       # 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
+      10.0.40.142             oss01-ipmi0 oss01-ipmi
       
       # 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
+      10.0.40.143             lake2-ipmi oss02-ipmi0 oss02-ipmi
       
       # 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
+      10.0.40.101             owl1-ipmi xeon01-ipmi0 xeon01-ipmi
       
       # 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
+      10.0.40.102             owl2-ipmi xeon02-ipmi0 xeon02-ipmi
       
       # 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
+      10.0.40.103             xeon03-ipmi0 xeon03-ipmi
       
       # 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
+      10.0.40.104             xeon04-ipmi0 xeon04-ipmi
       
       # Node Entry for node: xeon05 (ID=19)
       10.0.40.5               koro xeon05 xeon05-eth0
@@ -74,17 +74,17 @@
       # 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
+      10.0.40.106             xeon06-ipmi0 xeon06-ipmi
       
       # 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
+      10.0.40.107             hut-ipmi xeon07-ipmi0 xeon07-ipmi
       
       # 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
+      10.0.40.108             eudy-ipmi xeon08-ipmi0 xeon08-ipmi
     '';
   };
 }

m/common/ssf/ssh.nix

@@ -0,0 +1,8 @@
+{
+  # Connect to intranet git hosts via proxy
+  programs.ssh.extraConfig = ''
+    # Connect to BSC machines via hut proxy too
+    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
+  '';
+}

m/common/xeon.nix

@@ -1,9 +1,7 @@
 {
-  # Provides the base system for a xeon node.
+  # Provides the base system for a xeon node, not necessarily in the SSF rack.
   imports = [
     ./base.nix
-    ./xeon/fs.nix
     ./xeon/console.nix
-    ./xeon/net.nix
   ];
 }

m/eudy/configuration.nix

@@ -2,7 +2,7 @@
 
 {
   imports = [
-    ../common/xeon.nix
+    ../common/ssf.nix
     #(modulesPath + "/installer/netboot/netboot-minimal.nix")
 
     ./kernel/kernel.nix

m/fox/configuration.nix

@@ -0,0 +1,75 @@
+{ lib, config, pkgs, ... }:
+
+{
+  imports = [
+    ../common/base.nix
+    ../common/xeon/console.nix
+    ../module/emulation.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" ];
+
+  hardware.cpu.amd.updateMicrocode = lib.mkDefault config.hardware.enableRedistributableFirmware;
+  hardware.cpu.intel.updateMicrocode = lib.mkForce false;
+
+  # Use performance for benchmarks
+  powerManagement.cpuFreqGovernor = "performance";
+
+  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=" ];
+  };
+
+  # Configure Nvidia driver to use with CUDA
+  hardware.nvidia.package = config.boot.kernelPackages.nvidiaPackages.production;
+  hardware.graphics.enable = true;
+  nixpkgs.config.allowUnfree = true;
+  nixpkgs.config.nvidia.acceptLicense = true;
+  services.xserver.videoDrivers = [ "nvidia" ];
+
+  # 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;
+  };
+}

m/hut/configuration.nix

@@ -2,7 +2,7 @@
 
 {
   imports = [
-    ../common/xeon.nix
+    ../common/ssf.nix
 
     ../module/ceph.nix
     ../module/debuginfod.nix
@@ -56,6 +56,11 @@
         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
+      '';
     };
   };
 

m/hut/gitlab-runner.nix

@@ -1,8 +1,9 @@
 { pkgs, lib, config, ... }:
 
 {
-  age.secrets.gitlabRunnerShellToken.file = ../../secrets/gitlab-runner-shell-token.age;
-  age.secrets.gitlabRunnerDockerToken.file = ../../secrets/gitlab-runner-docker-token.age;
+  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;
 
   services.gitlab-runner = {
     enable = true;
@@ -21,21 +22,90 @@
           "--docker-network-mode host"
         ];
         environmentVariables = {
-          https_proxy = "http://localhost:23080";
-          http_proxy = "http://localhost:23080";
+          https_proxy = "http://hut:23080";
+          http_proxy = "http://hut:23080";
         };
       };
     in {
       # For pm.bsc.es/gitlab
       gitlab-pm-shell = common-shell // {
-        authenticationTokenConfigFile = config.age.secrets.gitlabRunnerShellToken.path;
+        authenticationTokenConfigFile = config.age.secrets.gitlab-pm-shell.path;
       };
       gitlab-pm-docker = common-docker // {
-        authenticationTokenConfigFile = config.age.secrets.gitlabRunnerDockerToken.path;
+        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;
+        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 > "$HOME/.ssh/config" << EOF
+          Host bscpm04.bsc.es gitlab-internal.bsc.es
+            User git
+            ProxyCommand nc -X connect -x hut:23080 %h %p
+          Host amdlogin1.bsc.es armlogin1.bsc.es hualogin1.bsc.es glogin1.bsc.es glogin2.bsc.es fpgalogin1.bsc.es
+            ProxyCommand nc -X connect -x hut:23080 %h %p
+          EOF
+          cat >> "$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";
+        };
       };
     };
   };
 
+  # 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";

m/hut/ipmi.yml

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

m/hut/monitoring.nix

@@ -3,7 +3,10 @@
 {
   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 = {
@@ -12,6 +15,8 @@
     mode = "400";
   };
 
+  age.secrets.ipmiYml.file = ../../secrets/ipmi.yml.age;
+
   services.grafana = {
     enable = true;
     settings = {
@@ -44,7 +49,7 @@
   services.prometheus = {
     enable = true;
     port = 9001;
-    retentionTime = "1y";
+    retentionTime = "5y";
     listenAddress = "127.0.0.1";
   };
 
@@ -73,8 +78,8 @@
         enable = true;
         group = "root";
         user = "root";
-        configFile = ./ipmi.yml;
-        #extraFlags = [ "--log.level=debug" ];
+        configFile = config.age.secrets.ipmiYml.path;
+        # extraFlags = [ "--log.level=debug" ];
         listenAddress = "127.0.0.1";
       };
       node = {
@@ -106,6 +111,9 @@
             "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}"
           ];
         }];
@@ -161,6 +169,9 @@
             "8.8.8.8"
             "ssfhead"
             "anella-bsc.cesca.cat"
+            "upc-anella.cesca.cat"
+            "fox.ac.upc.edu"
+            "arenys5.ac.upc.edu"
           ];
         }];
         relabel_configs = [
@@ -206,7 +217,7 @@
             # Sets the "instance" label with the remote host we are querying
             source_labels = [ "__param_target" ];
             separator = ";";
-            regex = "(.*)";
+            regex = "(.*)-ipmi"; # Remove "-ipm̀i" at the end
             target_label = "instance";
             replacement = "\${1}";
             action = "replace";
@@ -248,6 +259,14 @@
           module = [ "raccoon" ];
         };
       }
+      {
+        job_name = "raccoon";
+        static_configs = [
+          {
+            targets = [ "127.0.0.1:19002" ]; # Node exporter
+          }
+        ];
+      }
     ];
   };
 }

m/hut/nginx.nix

@@ -12,16 +12,19 @@ let
     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 = "127.0.0.1";
+          addr = "0.0.0.0";
           port = 80;
         }
       ];
@@ -38,7 +41,7 @@ in
           proxy_redirect http:// $scheme://;
         }
         location /cache {
-          rewrite ^/cache(.*) /$1 break;
+          rewrite ^/cache/(.*) /$1 break;
           proxy_pass http://127.0.0.1:5000;
           proxy_redirect http:// $scheme://;
         }

m/hut/targets.yml

@@ -1,15 +1,15 @@
 - targets:
-  - 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
+  - owl1-ipmi
+  - owl2-ipmi
+  - xeon03-ipmi
+  - xeon04-ipmi
+  - koro-ipmi
+  - xeon06-ipmi
+  - hut-ipmi
+  - eudy-ipmi
   # Storage
-  - 10.0.40.141
-  - 10.0.40.142
-  - 10.0.40.143
+  - bay-ipmi
+  - oss01-ipmi
+  - lake2-ipmi
   labels:
     job: ipmi-lan

m/koro/configuration.nix

@@ -2,7 +2,7 @@
 
 {
   imports = [
-    ../common/xeon.nix
+    ../common/ssf.nix
     #(modulesPath + "/installer/netboot/netboot-minimal.nix")
 
     ../eudy/cpufreq.nix

m/lake2/configuration.nix

@@ -2,7 +2,7 @@
 
 {
   imports = [
-    ../common/xeon.nix
+    ../common/ssf.nix
     ../module/monitoring.nix
   ];
 

m/map.nix

@@ -0,0 +1,70 @@
+{
+  # 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
+    ssfhead = { pos=39; size=2; label="SSFHEAD"; board="R2208WTTYSR"; contact="operations@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"; };
+    xeon06 = { 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`.
+}

m/module/hut-substituter.nix

@@ -0,0 +1,10 @@
+{ 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=" ];
+    };
+}

m/module/meteocat-exporter.nix

@@ -0,0 +1,17 @@
+{ 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";
+    };
+  };
+}

m/module/nix-daemon-builds.sh

@@ -0,0 +1,26 @@
+#!/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

m/module/nix-daemon-exporter.nix

@@ -0,0 +1,23 @@
+{ 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";
+    };
+  };
+}

m/module/p.nix

@@ -0,0 +1,68 @@
+{ 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));
+      };
+    };
+  };
+}

m/module/slurm-client.nix

@@ -47,8 +47,7 @@ in {
     ];
 
     partitionName = [
-      "owl Nodes=owl[1-2] Default=YES DefaultTime=01:00:00 MaxTime=INFINITE State=UP"
-      "all Nodes=owl[1-2],hut Default=NO DefaultTime=01:00:00 MaxTime=INFINITE State=UP"
+      "owl Nodes=owl[1-2]     Default=YES DefaultTime=01:00:00 MaxTime=INFINITE State=UP"
     ];
 
     # See slurm.conf(5) for more details about these options.
@@ -91,9 +90,29 @@ in {
       # 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";

m/module/ssh-hut-extern.nix

@@ -0,0 +1,9 @@
+{
+  programs.ssh.extraConfig = ''
+    Host ssfhead
+      HostName ssflogin.bsc.es
+    Host hut
+      ProxyJump ssfhead
+      HostName xeon07
+  '';
+}

m/module/upc-qaire-exporter.nix

@@ -0,0 +1,17 @@
+{ 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";
+    };
+  };
+}

m/owl1/configuration.nix

@@ -2,12 +2,13 @@
 
 {
   imports = [
-    ../common/xeon.nix
+    ../common/ssf.nix
     ../module/ceph.nix
     ../module/emulation.nix
     ../module/slurm-client.nix
     ../module/slurm-firewall.nix
     ../module/debuginfod.nix
+    ../module/hut-substituter.nix
   ];
 
   # Select the this using the ID to avoid mismatches

m/owl2/configuration.nix

@@ -2,12 +2,13 @@
 
 {
   imports = [
-    ../common/xeon.nix
+    ../common/ssf.nix
     ../module/ceph.nix
     ../module/emulation.nix
     ../module/slurm-client.nix
     ../module/slurm-firewall.nix
     ../module/debuginfod.nix
+    ../module/hut-substituter.nix
   ];
 
   # Select the this using the ID to avoid mismatches

m/raccoon/configuration.nix

@@ -3,6 +3,10 @@
 {
   imports = [
     ../common/base.nix
+    ../module/emulation.nix
+    ../module/debuginfod.nix
+    ../module/ssh-hut-extern.nix
+    ../eudy/kernel/perf.nix
   ];
 
   # Don't install Grub on the disk yet
@@ -23,8 +27,28 @@
       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";
+
   # Configure Nvidia driver to use with CUDA
   hardware.nvidia.package = config.boot.kernelPackages.nvidiaPackages.production;
   hardware.graphics.enable = true;
@@ -32,6 +56,18 @@
   nixpkgs.config.nvidia.acceptLicense = true;
   services.xserver.videoDrivers = [ "nvidia" ];
 
+  # Disable garbage collection for now
+  nix.gc.automatic = lib.mkForce false;
+
+  services.openssh.settings.X11Forwarding = true;
+
+  services.prometheus.exporters.node = {
+    enable = true;
+    enabledCollectors = [ "systemd" ];
+    port = 9002;
+    listenAddress = "127.0.0.1";
+  };
+
   users.motd = ''
     ⠀⠀⠀⠀⠀⠀⠀⣀⣀⣄⣠⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
     ⠀⠀⠀⠀⠀⠀⢰⠇⡀⠀⠙⠻⡿⣦⣀⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⡀⠀⠀⠀⠀

m/tent/blackbox.yml

@@ -0,0 +1,14 @@
+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"

m/tent/configuration.nix

@@ -0,0 +1,78 @@
+{ 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
+    ../module/p.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" ];
+    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;
+}

m/tent/gitea.nix

@@ -0,0 +1,29 @@
+{ 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 = {
+        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 = "--";
+      };
+    };
+  };
+}

m/tent/gitlab-runner.nix

@@ -0,0 +1,85 @@
+{ pkgs, lib, config, ... }:
+
+{
+  age.secrets.tent-gitlab-runner-pm-shell.file = ../../secrets/tent-gitlab-runner-pm-shell-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 = "${pkgs.bash}/bin/bash";
+        };
+        authenticationTokenConfigFile = sec.tent-gitlab-runner-pm-shell.path;
+        preGetSourcesScript = pkgs.writeScript "setup" ''
+          echo "This is the preGetSources script running, brace for impact"
+          env
+        '';
+      };
+      gitlab-bsc-docker = {
+        # gitlab.bsc.es still uses the old token mechanism
+        registrationConfigFile = sec.tent-gitlab-runner-bsc-docker.path;
+        tagList = [ "docker" "tent" "nix" ];
+        executor = "docker";
+        dockerImage = "alpine";
+        dockerVolumes = [
+          "/nix/store:/nix/store:ro"
+          "/nix/var/nix/db:/nix/var/nix/db:ro"
+          "/nix/var/nix/daemon-socket:/nix/var/nix/daemon-socket:ro"
+        ];
+        dockerDisableCache = true;
+        registrationFlags = [
+          # Increase build log length to 64 MiB
+          "--output-limit 65536"
+        ];
+        preBuildScript = pkgs.writeScript "setup-container" ''
+          mkdir -p -m 0755 /nix/var/log/nix/drvs
+          mkdir -p -m 0755 /nix/var/nix/gcroots
+          mkdir -p -m 0755 /nix/var/nix/profiles
+          mkdir -p -m 0755 /nix/var/nix/temproots
+          mkdir -p -m 0755 /nix/var/nix/userpool
+          mkdir -p -m 1777 /nix/var/nix/gcroots/per-user
+          mkdir -p -m 1777 /nix/var/nix/profiles/per-user
+          mkdir -p -m 0755 /nix/var/nix/profiles/per-user/root
+          mkdir -p -m 0700 "$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;
+}

m/tent/monitoring.nix

@@ -0,0 +1,205 @@
+{ 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"
+            "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" ];
+        };
+      }
+    ];
+  };
+}

m/tent/nginx.nix

@@ -0,0 +1,73 @@
+{ 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/;
+        }
+      '';
+    };
+  };
+}

m/tent/nix-serve.nix

@@ -0,0 +1,16 @@
+{ 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=
+  };
+}

pkgs/meteocat-exporter/default.nix

@@ -0,0 +1,25 @@
+{ 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;
+  };
+}

pkgs/meteocat-exporter/meteocat-exporter

@@ -0,0 +1,54 @@
+#!/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)

pkgs/meteocat-exporter/setup.py

@@ -0,0 +1,11 @@
+#!/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"],
+     )

pkgs/overlay.nix

@@ -39,7 +39,21 @@ final: prev:
       # 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
+    '';
   });
 
   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 { };
 }

pkgs/upc-qaire-exporter/default.nix

@@ -0,0 +1,24 @@
+{ python3Packages, lib }:
+
+python3Packages.buildPythonApplication rec {
+  pname = "upc-qaire-exporter";
+  version = "1.0";
+
+  src = ./.;
+
+  doCheck = false;
+
+  build-system = with python3Packages; [
+    setuptools
+  ];
+
+  dependencies = with python3Packages; [
+    prometheus-client
+    requests
+  ];
+
+  meta = with lib; {
+    description = "UPC Qaire Prometheus Exporter";
+    platforms = platforms.linux;
+  };
+}

pkgs/upc-qaire-exporter/setup.py

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

pkgs/upc-qaire-exporter/upc-qaire-exporter

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+
+import time
+from prometheus_client import start_http_server, Gauge
+import requests, json
+from datetime import datetime, timedelta
+
+# Configuration -------------------------------------------
+listening_port = 9928
+update_period = 60 * 5 # Each 5 min
+# ---------------------------------------------------------
+
+metric_temp = Gauge('upc_c6_s302_temp', 'UPC C6 S302 temperature sensor')
+
+def genparams():
+    d = {}
+    d['topic'] = 'TEMPERATURE'
+    d['shift_dates_to'] = ''
+    d['datapoints'] = 301
+    d['devicesAndColors'] = '1148418@@@#40ACB6'
+
+    now = datetime.now()
+
+    d['fromDate'] = now.strftime('%d/%m/%Y')
+    d['toDate'] = now.strftime('%d/%m/%Y')
+    d['serviceFrequency'] = 'NONE'
+
+    # WTF!
+    for i in range(7):
+        for j in range(48):
+            key = 'week.days[{}].hours[{}].value'.format(i, j)
+            d[key] = 'OPEN'
+
+    return d
+
+def measure():
+    # First we need to load session
+    s = requests.Session()
+    r = s.get("https://upc.edu/sirena")
+    if r.status_code != 200:
+        print("bad HTTP status code on new session: {}".format(r.status_code))
+        return
+
+    if s.cookies.get("JSESSIONID") is None:
+        print("cannot get JSESSIONID")
+        return
+
+    # Now we can pull the data
+    url = "https://upcsirena.app.dexma.com/l_12535/analysis/by_datapoints/data.json"
+    r = s.post(url, data=genparams())
+
+    if r.status_code != 200:
+        print("bad HTTP status code on data: {}".format(r.status_code))
+        return
+
+    #print(r.text)
+    j = json.loads(r.content)
+
+    # Just take the last one
+    last = j['data']['chartElementList'][-1]
+    temp = last['values']['1148418-Temperatura']
+
+    return temp
+
+if __name__ == '__main__':
+    start_http_server(port=listening_port, addr="localhost")
+    while True:
+        try:
+            metric_temp.set(measure())
+        except:
+            print("measure failed")
+            metric_temp.set(float("nan"))
+
+        time.sleep(update_period)

secrets/ceph-user.age

@@ -1,21 +1,19 @@
 age-encryption.org/v1
--> ssh-ed25519 AY8zKw J00a6ZOhkupkhLU5WQ0kD05HEF4KKsSs2hwjHKbnnHU
-J14VoNOCqLpScVO7OLXbqTcLI4tcVUHt5cqY/XQmbGs
--> ssh-ed25519 sgAamA k8R/bSUdvVmlBI6yHPi5NBQPBGM36lPJwsir8DFGgxE
-4ZKC3gYvic6AVrNGgNjwztbUzhxP8ViX5O3wFo9wlrk
--> ssh-ed25519 HY2yRg 966xf2fTnA6Wq0uYXbXZQOManqITJcCbQS9LZCGEOh4
-Qg5echQSrzqeDqvaMx+5fqi8XyTjAeCsY/UFJX6YnDs
--> ssh-ed25519 tcumPQ e0U2okrGIoUpLfPYjIRx1V92rE3hZW13nJef+l3kBQg
-LejAUKBl+tPhwocCF00ZHTzFISnwX8og8GvemiMIcyo
--> ssh-ed25519 JJ1LWg QkzTsPq9Gdh+FNz/a4bDb9LQOreFyxeTC51UNd1fsj0
-ayrlKenETfQzH1Z9drVEWqszQebicGVJve0/pCnxAE8
--> ssh-ed25519 CAWG4Q lJLW9+dxvyoD4hYzeXeE/4rzJ6HIeEQOB1+fbhV3xw0
-T2RrVCtTuQvya9HiJB7txk3QGrntpsMX9Tt1cyXoW5E
--> ssh-ed25519 MSF3dg JOZkFb2CfqWKvZIz7lYxXWgv8iEVDkQF8hInDMZvknc
-MHDWxjUw4dNiC1h4MrU9uKKcI3rwkxABm0+5FYMZkok
--> ~8m;7f-grease
-lDIullfC98RhpTZ4Mk87Td+VtPmwPdgz+iIilpKugUkmV5r4Uqd7yE+5ArA6ekr/
-G/X4EA
---- Cz4sv9ZunBcVdZCozdTh1zlg1zIASjk2MjYeYfcN9eA
-<EFBFBD>N	<09>$[H<><48>Q<EFBFBD><51><EFBFBD>
-d<EFBFBD><EFBFBD><EFBFBD>'<27><><EFBFBD>7<EFBFBD><1F>Ͳ)<29><><EFBFBD><17>x9y<39><79><EFBFBD>E<04><><EFBFBD>M7^<5E>[<5B>M<EFBFBD>+<2B>&<26><><EFBFBD><0E>$8tM<74>в
+-> ssh-ed25519 AY8zKw xeyzSqfio6SMS9SqywR+7II80D12Oha9T5zOgAIABSQ
+ST26VaF2G1xv9l7d3jWKG32ssOivfwx+p9jLLV7ZFnU
+-> ssh-ed25519 sgAamA HrRx+x7NjXKVDaealWFo+Q8zMAdzoj6nTBxw0KMi3jE
+nlcEVTDTe1mPeS16/t9GYRnSSkm5EjpeiBZPIC/2f8U
+-> ssh-ed25519 HY2yRg NDp5vUeX35rDV78DFQi9fsc71pQNVE8YQ1StCp+YjTg
+MdUAWHd1k6Jed2pp7Wct/DgF6ShqXFwNxPaXeBOLAcs
+-> ssh-ed25519 tcumPQ d0zVVB8t7W9KUapOsnsrvpAj7LgM9zS0yCv8SQnF0g8
+aAPaWRTEBEQgmCkRG69NuWZ/lEva7vH+L8ifQSE0Z1I
+-> ssh-ed25519 JJ1LWg 4l8GZNdGOSbqKvmKq1q1aPvjeQIwpgbJj4DBYBse7x4
+rNhTiZlwzyOiCLzYRSzJ5AHebbv94dOgl1UyNmDJD8A
+-> ssh-ed25519 CAWG4Q vGhwJDLJIAU8BpV6GP8Dnz2pvTAMufY4v4nvrr2O9yw
+hNZZFDYUMPQNM5+qcc5arIgqQw0PXuqq1WWDTpE+EHo
+-> ssh-ed25519 xA739A 8eEi9S5dMWPVR4fKVZdV5eHBOJVf2Ap+3qHSYtYHYgc
+GcgzvJiqsNyZTVk12Z0FEnqB4LgfQ1xjKQwXdto1Hjs
+-> ssh-ed25519 MSF3dg oUY9IjDR6hi1qbrCV5z5IcYj85cMppxO94iqkD60Eww
+cBzFGrhh+kWjIi0llw2RqACU1pa7XT9kqWkSeAY8VGI
+--- q7AaMOj7ZaS+Mf6trWK56o/1q/c2urrQBPAqk4PtATA
+~<7E><>k-/<2F>Xw<58><77><1D>V<EFBFBD>(<18><>Z<EFBFBD>d\<5C><>t<EFBFBD>'q<><71><EFBFBD>3<EFBFBD><33>R<EFBFBD>a\yFW<46>

secrets/gitea-runner-token.age

@@ -1,9 +1,11 @@
 age-encryption.org/v1
--> ssh-ed25519 HY2yRg DQdgCk16Yu524BsrWVf0krnwWzDM6SeaJCgQipOfwCA
-Ab9ocqra/UWJZI+QGMlxUhBu5AzqfjPgXl+ENIiHYGs
--> ssh-ed25519 CAWG4Q KF9rGCenb3nf+wyz2hyVs/EUEbsmUs5R+1fBxlCibC8
-7++Kxbr3FHVdVfnFdHYdAuR0Tgfd+sRcO6WRss6LhEw
--> ssh-ed25519 MSF3dg aUe4DhRsu4X8CFOEAnD/XM/o/0qHYSB522woCaAVh0I
-GRcs5cm2YqA/lGhUtbpboBaz7mfgiLaCr+agaB7vACU
---- 9Q7Ou+Pxq+3RZilCb2dKC/pCFjZEt4rp5KnTUUU7WJ8
-1<12>
Mw4<77><34>	<09>:H<>@<40>/<2F>gLtM<74>,<2C>ƥ<>*<2A><>z<EFBFBD>NV5<56>m<EFBFBD><6D>N<EFBFBD>o<EFBFBD><6F>j1$<24>T<EFBFBD>G_<47>E{<7B>%<25><>1ǯ<17><>H<EFBFBD><EFBFBD>A<EFBFBD>p<EFBFBD>
+-> ssh-ed25519 HY2yRg WUMWvyagPalsy7u1RaEFAwJvFowso1/quNBo+nAkxhQ
+OHcebB7koPKhy58A6qngEVNWckkWChyEK3dwgy8EL5o
+-> ssh-ed25519 CAWG4Q Yx/HLIryUNE2BaqTl84FrNRy4XLCY2TRkRgbA9k3qU4
+LZljfuLS5yMVVK6N57iC6cKEaFP6Hh2OkvWJjuFg8q0
+-> ssh-ed25519 xA739A DOXjPRttSWz51Sr7KfjgKfAtaIYMo3foB1Ywqw9HYDY
+CA5puXK/1HDOitA2XHBI3OdKmZ7BzHst4DyuWGMC6hE
+-> ssh-ed25519 MSF3dg +2LetdIiIZUk7wtHNS1tYsLo4ypwqZ9gpg77RQrnzHU
+yIUu8BVbF3dhUx3531RR50/cJQd9gd8VfKUQzEeT/iQ
+--- oY/wQ+RjZO2CmKZtbQ0yOVZ5fv2+AlvvkRu1UDfCNAA
+_8`G<>=C7@x&<26><>\Ft<46>)<29><><EFBFBD><EFBFBD><EFBFBD>cPe<50><65>%<25>ֽ[zX-0<>[<11><><EFBFBD>ɲ<><C9B2>tz<74><7A>;%<25><><EFBFBD><EFBFBD><EFBFBD>~<7E>H0<48>؃*XD<58>;<3B><>

secrets/gitlab-runner-docker-token.age

@@ -1,9 +1,11 @@
 age-encryption.org/v1
--> ssh-ed25519 HY2yRg 0sEIUEJBJQ0k0rBfHaOEbq1pNBqsPin4Xq85v0ds9jY
-4wzjLapoOcq53nT2K3hSGED4jTDXci25GLHkl/fL4EI
--> ssh-ed25519 CAWG4Q f68ZbJGwXuCZVnqhwbh+8dh0X/MCdjEd+sVtPyBu/hU
-u2TQreyWQvP6PGuwuUNKA/AL68560flqSlaItN3k41I
--> ssh-ed25519 MSF3dg HdrtRW2j7mfkLH0/4aJK5R0cWdjf56HYtEZgzHi9EAs
-A6MF6tXmSUq2RF2bpmav0GFTRERwluSZGh2snP/KqkA
---- drsezqi7J/g8gm6N10SkfeAWnYct99WUraB5djLJqpo
-g<EFBFBD>
+-> ssh-ed25519 HY2yRg 6C5Cv7ILdBrpMkCTT/insUY0kyQWbfgU500Ai8ePOXY
+tMw6ehFrsq2dvDEXkLOJwrNZfI28trlr9uy3xW/fzpA
+-> ssh-ed25519 CAWG4Q x/j+364IYURgt7fhIPBzabbWMEg08nX8MRrJM/1Q6RU
+AL5Ut2rDr3UXcQXMZJ53ZMf5wMHmT83whx0ntJfW/WU
+-> ssh-ed25519 xA739A QjXftBsoGV1rVeHSKcsjp+HMpRVsaHOeeGdDcF6ZWg4
+ovVoYPaPn3liGPAxHWY37CBIUFjAXurv6jMWs2He3HQ
+-> ssh-ed25519 MSF3dg FG0CQOj9fRlneW5QrWiy5ksRpicUwHqX9QMpZWhDImw
+L20n1vZRepsRPT4xM6TO6PcI/MJxw4mBLUF0EPv9Uhs
+--- DEi7iuzkniq0JPatJ5f2KhrhxWid7ojHpvNfUCGxFtk
+<EFBFBD><EFBFBD>%	n<><6E>!;^Q<>
rqG<71>:<3A>jC.8l<38>|<7C><>o<EFBFBD><1E><>$LYy<59>N<EFBFBD>b<EFBFBD><1E><>:<14>{<7B><><EFBFBD>fާxTS\<5C>t<04>U<EFBFBD><55>\F<>)%<25><><EFBFBD>KL<4B>㙇p<E39987>:><3E><><EFBFBD><EFBFBD>&<1B>)<0B>Q<EFBFBD>1<>H܃V<DC83>Sޑ<53>n<>

secrets/jungle-robot-password.age

@@ -1,10 +1,13 @@
 age-encryption.org/v1
--> ssh-ed25519 HY2yRg 3L1Y5upc5qN6fgiFAox5rD/W8n0eQUv5mT39QAdO5Ac
-XkWsmPmzRgHjsvJgsDKJRgHZ7/sBZFmd1Doppj/y390
--> ssh-ed25519 CAWG4Q v03Qr+fckdIpsxvQG/viKxlF8WNpO4XUe//QcPzH4k0
-afUwi3ccDCRfUxPDdF7ZkoL+0UX1XwqVtiyabDWjVQk
--> ssh-ed25519 MSF3dg c2hEUk4LslJpiL7v/4UpT8fK7ZiBJ8+uRhZ/vBoRUDE
-YX9EpnJpHo1eDsZtapTVY6jD+81kb588Oik4NoY9jro
---- LhUkopNtCsyHCLzEYzBFs+vekOkAR4B3VBaiMF/ZF8w
-o˝<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>C<EFBFBD><EFBFBD>H<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>y<EFBFBD>LؔItM<74><4D><EFBFBD><EFBFBD>IױsM<12>\<5C>1-<2D>K<EFBFBD><4B><10><>G:<><7F><02><>
-<EFBFBD>g<16><><EFBFBD>bpF<70>Ӷ<EFBFBD>%Y<>
+-> ssh-ed25519 HY2yRg 0tpCZ5yI339pgPKGh3HJ8cnkhKlMoyYiKR1mo1cvkm0
+EVVpJ8nyw/W9B65Tw59IjJC5Pb4uQX5LGnzPcf/hUs0
+-> ssh-ed25519 G5LX5w YaDAKeAAunommW6q6+hTjrjaadmB17OG89t1Dx/T5z4
+tJXdciiBTz9V+0nf1sGAk4vSlOgfeEgrKr+oDJ/4ays
+-> ssh-ed25519 CAWG4Q i/cpMcOaZpH7aqwsR/fZiVL9CreL9dkk5F5S9dXrQBY
+uU8G51pMH00ywaIVY+AzjpiqzanUYpn9ANRabugSXbE
+-> ssh-ed25519 xA739A DTiXqnCz1zNgyLt8VvnOkVLDwfa0qJpUBQw9Ms/qHHA
+wKjSYYOUEJkPisxT6MNW1eoYk++ECrs1ib9uEYXsAQY
+-> ssh-ed25519 MSF3dg JmvJsExWPW4b6RT62mz4Wscx7EsyDPVf91A9ps9+shM
+67jZYnxJpQAhnRWnTOXs+Cu445dRCpDzIGGp1xYuF3s
+--- QmdvzR7QqRPxS1fHc8rR/PDZxN8u+BVKAVvE8cMLhqc
+<EFBFBD><EFBFBD><02><>EG<45><0B>Q<<3C><><EFBFBD><EFBFBD><EFBFBD>Kl<4B>U,<11><><EFBFBD><EFBFBD>[-<2D><>º<1A><Uc<55>e<EFBFBD><65><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>)<06><><05><>"f<>˖<EFBFBD><CB96><19>Z<EFBFBD>'C

secrets/nix-serve.age

@@ -1,12 +1,13 @@
 age-encryption.org/v1
--> ssh-ed25519 HY2yRg d144D+VvxhYgKtH//uD2qNuVnYX6bh74YqkyM3ZjBwU
-0IeVmFAf4U8Sm0d01O6ZwJ1V2jl/mSMl4wF0MP5LrIg
--> ssh-ed25519 CAWG4Q H4nKxue/Cj/3KUF5A+/ygHMjjArwgx3SIWwXcqFtyUo
-4k5NJkLUrueLYiPkr2LAwQLWmuaOIsDmV/86ravpleU
--> ssh-ed25519 MSF3dg HpgUAFHLPs4w0cdJHqTwf8lySkTeV9O9NnBf49ClDHs
-foPIUUgAYe1YSDy6+aMfjN7xv9xud9fDmhRlIztHoEo
--> vLkF\<-grease
-3GRT+W8gYSpjl/a6Ix9+g9UJnTpl1ZH/oucfR801vfE8y77DV2Jxz/XJwzxYxKG5
-YEhiTGMNbXw/V7E5aVSz6Bdc
---- GtiHKCZdHByq9j0BSLd544PhbEwTN138E8TFdxipeiA
-<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>G$S<><53><EFBFBD>RA<52><41><EFBFBD>Th]n<>8<EFBFBD>,<2C>H<EFBFBD>s<EFBFBD><73><EFBFBD>=p<><70><EFBFBD>'<27><><EFBFBD>+<2B>j<><6A><EFBFBD><EFBFBD>9<EFBFBD>)<29>:<3A>)<15><><EFBFBD>Y<EFBFBD><59><EFBFBD>8<EFBFBD>I<EFBFBD><49>8:ol<6F><6C><EFBFBD><1F><><EFBFBD>Z<EFBFBD><5A>3<>PM<50>F;<3B>rY<72><59><EFBFBD><EFBFBD><1F>$<24><>y<EFBFBD>L<>ٜ<EFBFBD>Μ<1B><>U<EFBFBD>s16Ǿ<>L<EFBFBD>b<EFBFBD><62><EFBFBD>
+-> ssh-ed25519 HY2yRg T/Qom1qxE0M+FuvsXD/KZ6Usfp6v3Xwx043kDgxbCz4
+6GRg0QjuHd2+d6lJfZqqPMPMjS91HEcJ/W0KRV6Et50
+-> ssh-ed25519 G5LX5w pzg0wK+Q6KZP67CkyZNYbNcahlq9SIuFN18H85ARykU
+aDSrO49tg/a3GOAJR96lh803bXoZqp/G6VMiSvf91vw
+-> ssh-ed25519 CAWG4Q X+F/6LF8VUUoV72iCLzKKpYGRDoUHuBy1E+yr29RKEo
+c779vpt/fiN7n0kGAc5jA9fWkzCPrthlNZdN4p6csrk
+-> ssh-ed25519 xA739A sbg087VKj/gcycV9JrBNCoCfB4kRMDSVo3EtfpRVDyg
+Lv5ges1KmxGwvz4UPZCD0v4YN2ms2Q3wmrJ14XCKYsQ
+-> ssh-ed25519 MSF3dg pCLeyeWYbnNWQwwlGcsKz0KZ4BaaYKCGjo0XOPpo+no
+IsNxFoB2nTxyThJxtAxSA6gauXHGQJnVefs/K2MZ+DM
+--- tgB3F+k1/PQt+r5Cz+FqH31hCZFvr0Y8uZVKkdA80yo
+60.<2E><><19><0F><><EFBFBD><EFBFBD>(<28>s<EFBFBD>?68<36><38>Q<EFBFBD>I<><49><EFBFBD>d<EFBFBD><64><EFBFBD>gb<67><62><EFBFBD><EFBFBD><EFBFBD><04>`<60><><13><>A<EFBFBD><EFBFBD>z<L}<7D>2&w<0B>!<21><>6<EFBFBD> ;F<><46>r<EFBFBD>BR\<5C><><1B>ً<02>h"<22>"<22><>~q<>×<EFBFBD><C397><EFBFBD>1ƾ<31><C6BE>!({0<>^<5E><>Q<05>1e<31><0F><><EFBFBD><EFBFBD>୏<><E0AD8F>+<2B>

secrets/secrets.nix

@@ -2,6 +2,8 @@ let
   keys = import ../keys.nix;
   adminsKeys = builtins.attrValues keys.admins;
   hut = [ keys.hosts.hut ] ++ adminsKeys;
+  mon = [ keys.hosts.hut keys.hosts.tent ] ++ adminsKeys;
+  tent = [ keys.hosts.tent ] ++ adminsKeys;
   # Only expose ceph keys to safe nodes and admins
   safe = keys.hostGroup.safe ++ adminsKeys;
 in
@@ -9,8 +11,14 @@ in
   "gitea-runner-token.age".publicKeys = hut;
   "gitlab-runner-docker-token.age".publicKeys = hut;
   "gitlab-runner-shell-token.age".publicKeys = hut;
-  "nix-serve.age".publicKeys = hut;
-  "jungle-robot-password.age".publicKeys = hut;
+  "gitlab-bsc-docker-token.age".publicKeys = hut;
+  "nix-serve.age".publicKeys = mon;
+  "jungle-robot-password.age".publicKeys = mon;
+  "ipmi.yml.age".publicKeys = mon;
+
+  "tent-gitlab-runner-pm-docker-token.age".publicKeys = tent;
+  "tent-gitlab-runner-pm-shell-token.age".publicKeys = tent;
+  "tent-gitlab-runner-bsc-docker-token.age".publicKeys = tent;
 
   "ceph-user.age".publicKeys = safe;
   "munge-key.age".publicKeys = safe;

secrets/tent-gitlab-runner-pm-shell-token.age

@@ -0,0 +1,13 @@
+age-encryption.org/v1
+-> ssh-ed25519 G5LX5w V9bHLoGuY4stRwbzVS9Qa0L9yoY+UoCoXc+dJJQW/Ag
+2ut9GfdJ3KBCqZRaloZCQsl8MLfaZAZxqj6JtPJzu2k
+-> ssh-ed25519 CAWG4Q OAqnIfMECpKglZ7aF9tv/PQinG1Ou2+IEZ+nf4dtQjg
+dANdMLe4iI0d6Xd/dIMpZK+mgw2+VmJFQScHaIxD7WI
+-> ssh-ed25519 xA739A nVNF4Y6VSa5PP6FFBJpVmoFYYseoFx5F2wJU+Pwk+Xk
+A5CiuTSNlX9Y76qhYgblBdJl3zPhtjWho2oL5/sIKu0
+-> ssh-ed25519 MSF3dg /WMsGnBGzquIMyw06gHKpSS4OUxheulT59kxi+/pxxU
+ppwcv7RLzUbQUM7j0Tb9rRVT9XyPMhqYr2fr4S0nTJY
+--- zOe0Ko0oxArbmxePMPDVAT0pDju7IeOAih7sNrDcoVs
+i<EFBFBD>k<EFBFBD>A
+hODV<44>w!<21><0C><>E݈<45><DD88>+<2B><>`<60><><EFBFBD><EFBFBD>C<><43>5<EFBFBD>L<EFBFBD>A<EFBFBD>t<1A>M^
<01>E<<1B>HI<48>_<EFBFBD>nn<6E><6E><EFBFBD>o<EFBFBD>?<3F>j-<05>
+A<1B>nԔί<1B>>Z<><5A>z<EFBFBD><7A><EFBFBD>dT<64><54>b"<22>(@<40><>{_ځC

web/content/access/index.md

@@ -11,7 +11,7 @@ access to the login machine using a resource petition in the BSC intranet.
 
 Then, to request access to the machines we will need some information about you:
 
-1. Which machines you want access to (hut, owl1, owl2, eudy, koro...)
+1. Which machines you want access to ([hut](/hut), [fox](/fox), owl1, owl2, eudy, koro...)
 1. Your user name and user id (to match the NFS permissions)
 1. Your real name and surname (for identification purposes)
 1. The salted hash of your login password, generated with `mkpasswd -m sha-512`

web/content/doc/_index.md

@@ -0,0 +1,10 @@
+---
+title: "Docs"
+description: "Documentation for users of jungle machines"
+date: 2023-09-15
+---
+
+If this is the first time you use any of the jungle machines with NixOS, follow
+the [quick start guide](quickstart).
+
+

web/content/doc/quickstart.md

@@ -0,0 +1,234 @@
+---
+title: "Quick start"
+date: 2023-09-15
+---
+
+This documentation will guide you on how to build custom packages of software
+and use them in the jungle machines. It has been designed to reduce the friction
+from users coming from module systems.
+
+You should be able to access the jungle machines, otherwise [request
+access](/access).
+
+## Changes from other HPC machines
+
+Users of other machines have been using the Lmod tool (module load ...) to add
+or remove programs from their environment, as well as manually building their
+own software for too many years.
+
+While we cannot prevent users from continuing to use this tedious mechanism, we
+have designed the jungle machines to be much easier to operate by using the nix
+package manager.
+
+### Freedom to install packages
+
+When a user wanted to install a package, it was forced to either do it on its
+own directory, or request a system administrator to install it in a shared
+directory, so other users can also use that package.
+
+This situation is gone, each user can install any package of software by
+themselves, without requiring any other authorization. When two users request
+the same package, the same copy will be provided.
+
+A new package will be downloaded if it is available (someone already built it)
+or will be built from source on demand.
+
+### No changes over time
+
+All users retain the same versions of the packages they request until they
+decide to update them.
+
+## Using nix to manage packages
+
+In this chapter we show how to install packages and enter a development shell to
+build new programs from source. The examples are done from the hut machine,
+read [this page](/access) to request access.
+
+### Installing binaries
+
+To temporarily install new packages, use:
+
+```text
+hut% nix shell jungle#gcc jungle#cowsay jungle#ovni
+```
+
+Notice that the packages are described as two parts divided by the `#` symbol.
+The first part defines where to take the package from and the second part is
+the name of the package. For now we will use `jungle#<package>`. You can find
+many more packages here:
+
+<https://search.nixos.org/packages>
+
+You will now enter a new shell, where those requested package **binaries are
+available in $PATH**:
+
+```text
+hut% cowsay hello world
+ _____________
+< hello world >
+ -------------
+        \   ^__^
+         \  (oo)\_______
+            (__)\       )\/\
+                ||----w |
+                ||     ||
+
+hut% ovniver
+LD_LIBRARY_PATH not set
+libovni: build v1.11.0 (a7103f8), dynamic v1.11.0 (a7103f8)
+
+hut% gcc --version
+gcc (GCC) 13.3.0
+Copyright (C) 2023 Free Software Foundation, Inc.
+This is free software; see the source for copying conditions.  There is NO
+warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+```
+
+### Building programs
+
+The above method only loads new binaries in the `$PATH`. If we try to build a
+program that includes headers or links with a library, it will fail to find
+them:
+
+```text
+hut$ cat test.c
+#include <ovni.h>
+
+int main()
+{
+        ovni_version_check();
+        return 0;
+}
+hut% gcc test.c -lovni -o test
+test.c:1:10: fatal error: ovni.h: No such file or directory
+    1 | #include <ovni.h>
+      |          ^~~~~~~~
+compilation terminated.
+```
+
+We could manually add the full path to the ovni include directory with `-I` and
+the libraries with `-L`, but there is a tool that already perform these steps
+automatically for us, `nix develop`.
+
+Let's go back to our original shell first, where those packages are not
+available anymore:
+
+```
+hut% ps
+    PID TTY          TIME CMD
+2356260 pts/1    00:00:01 zsh
+2457268 pts/1    00:00:00 zsh
+2457297 pts/1    00:00:00 ps
+hut% exit
+hut% ovniver
+ovniver: command not found
+```
+
+### Creating a flake.nix
+
+To define which packages we want, we will write a small file that list them, a
+flake.nix file.
+
+First, we will create a new directory where we are going to be working:
+
+```
+hut% mkdir example
+hut% cd exmple
+```
+
+Then place this flake.nix file:
+
+```nix
+{
+  inputs.jungle.url = "jungle";
+  outputs = { self, jungle }:  
+  let
+    pkgs = jungle.outputs.packages.x86_64-linux;
+  in {
+    devShells.x86_64-linux.default = pkgs.mkShell {
+      pname = "devshell";
+      buildInputs = with pkgs; [
+        ovni gcc cowsay # more packages here...
+      ];
+    };
+  };
+}
+```
+
+
+Now enter the shell with:
+
+```
+hut% nix develop
+warning: creating lock file '/home/Computational/rarias/example/flake.lock':
+• Added input 'jungle':
+    'path:/nix/store/27srv8haj6vv4ywrbmw0a8vds561m8rq-source?lastModified=1739479441&narHash=sha256-Kgjs8SO1w9NbPBu8ghwzCxYJ9kvWpoQOT%2BXwPvA9DcU%3D&rev=76396c0d67ef0cf32377d5c1894bb695293bca9d' (2025-02-13)
+• Added input 'jungle/agenix':
+    'github:ryantm/agenix/f6291c5935fdc4e0bef208cfc0dcab7e3f7a1c41?narHash=sha256-b%2Buqzj%2BWa6xgMS9aNbX4I%2BsXeb5biPDi39VgvSFqFvU%3D' (2024-08-10)
+• Added input 'jungle/agenix/darwin':
+    'github:lnl7/nix-darwin/4b9b83d5a92e8c1fbfd8eb27eda375908c11ec4d?narHash=sha256-gzGLZSiOhf155FW7262kdHo2YDeugp3VuIFb4/GGng0%3D' (2023-11-24)
+• Added input 'jungle/agenix/darwin/nixpkgs':
+    follows 'jungle/agenix/nixpkgs'
+• Added input 'jungle/agenix/home-manager':
+    'github:nix-community/home-manager/3bfaacf46133c037bb356193bd2f1765d9dc82c1?narHash=sha256-7ulcXOk63TIT2lVDSExj7XzFx09LpdSAPtvgtM7yQPE%3D' (2023-12-20)
+• Added input 'jungle/agenix/home-manager/nixpkgs':
+    follows 'jungle/agenix/nixpkgs'
+• Added input 'jungle/agenix/nixpkgs':
+    follows 'jungle/nixpkgs'
+• Added input 'jungle/agenix/systems':
+    'github:nix-systems/default/da67096a3b9bf56a91d16901293e51ba5b49a27e?narHash=sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768%3D' (2023-04-09)
+• Added input 'jungle/bscpkgs':
+    'git+https://git.sr.ht/~rodarima/bscpkgs?ref=refs/heads/master&rev=6782fc6c5b5a29e84a7f2c2d1064f4bcb1288c0f' (2024-11-29)
+• Added input 'jungle/bscpkgs/nixpkgs':
+    follows 'jungle/nixpkgs'
+• Added input 'jungle/nixpkgs':
+    'github:NixOS/nixpkgs/9c6b49aeac36e2ed73a8c472f1546f6d9cf1addc?narHash=sha256-i/UJ5I7HoqmFMwZEH6vAvBxOrjjOJNU739lnZnhUln8%3D' (2025-01-14)
+
+hut$ 
+```
+
+Notice that long list of messages is Nix creating a new flake.lock file with the
+current state of the packages. Next invocations will use the same packages as
+described by the lock file.
+
+### Building a program from nix develop
+
+Now let's try again building our test program:
+
+```text
+hut$ cat test.c
+#include <ovni.h>
+
+int main()
+{
+        ovni_version_check();
+        return 0;
+}
+hut$ gcc test.c -o test -lovni
+hut$ ldd test
+        linux-vdso.so.1 (0x00007ffff7fc4000)
+        libovni.so.1 => /nix/store/sqk972akjv0q8dchn8ccjln2llzyyfd0-ovni-1.11.0/lib/libovni.so.1 (0x00007ffff7fab000)
+        libc.so.6 => /nix/store/nqb2ns2d1lahnd5ncwmn6k84qfd7vx2k-glibc-2.40-36/lib/libc.so.6 (0x00007ffff7db2000)
+        /nix/store/nqb2ns2d1lahnd5ncwmn6k84qfd7vx2k-glibc-2.40-36/lib/ld-linux-x86-64.so.2 => /nix/store/nqb2ns2d1lahnd5ncwmn6k84qfd7vx2k-glibc-2.40-36/lib64/ld-linux-x86-64.so.2 (0x00007ffff7fc6000)
+hut$ ./test
+```
+
+Now the ovni.h header and the libovni library are found and the program is
+successfully built, linked and executed.
+
+You can add more packages as needed in your flake.nix:
+
+```nix
+  buildInputs = with pkgs; [
+    ovni gcc cowsay # more packages here...
+  ];
+```
+
+Make sure you exit the develop shell first, and then enter again with `nix
+develop`.
+
+## Remember
+
+- `nix shell` places binaries in the `$PATH`.
+- `nix develop` enters a development shell where both binaries and the libraries
+  and includes are available so you can build new programs.

web/content/fox/_index.md

@@ -0,0 +1,97 @@
+---
+title: "Fox"
+description: "AMD Genoa 9684X with 2 NVIDIA RTX4000 GPUs"
+date: 2025-02-12
+---
+
+![Fox](fox.jpg)
+
+Picture by [Joanne Redwood](https://web.archive.org/web/20191109175146/https://www.inaturalist.org/photos/6568074),
+[CC0](http://creativecommons.org/publicdomain/zero/1.0/deed.en).
+
+The *fox* machine is a big GPU server that is configured to run heavy workloads.
+It has two fast AMD CPUs with large cache and 2 reasonable NVIDIA GPUs. Here are
+the detailed specifications:
+
+- 2x AMD GENOA X 9684X DP/UP 96C/192T 2.55G 1,150M 400W SP5 3D V-cach
+- 24x 32GB DDR5-4800 ECC RDIMM (total 768 GiB of RAM)
+- 1x 2.5" SSD SATA3 MICRON 5400 MAX 480GB
+- 2x 2.5" KIOXIA CM7-R 1.92TB NVMe GEN5 PCIe 5x4
+- 2x NVIDIA RTX4000 ADA Gen 20GB GDDR6 PCIe 4.0
+
+## Access
+
+To access the machine, request a SLURM session from [hut](/hut) using the `fox`
+partition:
+
+    hut% salloc -p fox
+
+Then connect via ssh:
+
+    hut% ssh fox
+    fox%
+
+Follow [these steps](/access) if you don't have access to hut or fox.
+
+## CUDA
+
+To use CUDA, you can use the following `flake.nix` placed in a new directory to
+load all the required dependencies:
+
+```nix
+{
+  inputs.jungle.url = "jungle";
+
+  outputs = { jungle, ... }: {
+    devShell.x86_64-linux = let
+      pkgs = jungle.nixosConfigurations.fox.pkgs;
+    in pkgs.mkShell {
+      name = "cuda-env-shell";
+      buildInputs = with pkgs; [
+        git gitRepo gnupg autoconf curl
+        procps gnumake util-linux m4 gperf unzip
+
+        # Cuda packages (more at https://search.nixos.org/packages)
+        cudatoolkit linuxPackages.nvidia_x11
+        cudaPackages.cuda_cudart.static
+        cudaPackages.libcusparse
+
+        libGLU libGL
+        xorg.libXi xorg.libXmu freeglut
+        xorg.libXext xorg.libX11 xorg.libXv xorg.libXrandr zlib
+        ncurses5 stdenv.cc binutils
+      ];
+      shellHook = ''
+        export CUDA_PATH=${pkgs.cudatoolkit}
+        export LD_LIBRARY_PATH=/var/run/opengl-driver/lib
+        export SMS=50
+      '';
+    };
+  };
+}
+```
+
+Then just run `nix develop` from the same directory:
+
+    % mkdir cuda
+    % cd cuda
+    % vim flake.nix
+    [...]
+    % nix develop
+    $ nvcc -V
+    nvcc: NVIDIA (R) Cuda compiler driver
+    Copyright (c) 2005-2024 NVIDIA Corporation
+    Built on Tue_Feb_27_16:19:38_PST_2024
+    Cuda compilation tools, release 12.4, V12.4.99
+    Build cuda_12.4.r12.4/compiler.33961263_0
+
+## Filesystems
+
+The machine has several file systems available.
+
+- `$HOME`: Mounted via NFS across all nodes. It is slow and has low capacity.
+  Don't abuse.
+- `/ceph/home/$USER`: Shared Ceph file system across jungle nodes. Slow but high
+  capacity. Stores three redundant copies of every file.
+- `/nvme{0,1}/$USER`: The two local NVME disks, very fast and large capacity.
+- `/tmp`: tmpfs, fast but not backed by a disk. Will be erased on reboot.

web/content/hut/_index.md

@@ -13,6 +13,115 @@ which is available at `hut` or `xeon07`. It runs the following services:
 - Grafana: to plot the data in the web browser.
 - Slurmctld: to manage the SLURM nodes.
 - Gitlab runner: to run CI jobs from Gitlab.
+- Nix binary cache: to serve cached nix builds
 
 This node is prone to interruptions from all the services it runs, so it is not
 a good candidate for low noise executions.
+
+# Binary cache
+
+We provide a binary cache in `hut`, with the aim of avoiding unnecessary
+recompilation of packages.
+
+The cache should contain common packages from bscpkgs, but we don't provide
+any guarantee that of what will be available in the cache, or for how long.
+We recommend following the latest version of the `jungle` flake to avoid cache
+misses.
+
+## Usage
+
+### From NixOS
+
+In NixOS, we can add the cache through the `nix.settings` option, which will
+enable it for all builds in the system.
+
+```nix
+{ ... }: {
+  nix.settings = {
+    extra-substituters = [ "https://jungle.bsc.es/cache" ];
+    extra-trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
+  };
+}
+```
+
+### Interactively
+
+The cache can also be specified in a per-command basis through the flags
+`--substituters` and `--trusted-public-keys`:
+
+```sh
+nix build --substituters "https://jungle.bsc.es/cache" --trusted-public-keys "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" <...>
+```
+
+Note: you'll have to be a trusted user.
+
+### Nix configuration file (non-nixos)
+
+If using nix outside of NixOS, you'll have to update `/etc/nix/nix.conf`
+
+```
+# echo "extra-substituters = https://jungle.bsc.es/cache" >> /etc/nix/nix.conf
+# echo "extra-trusted-public-keys = jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" >> /etc/nix/nix.conf
+```
+
+### Hint in flakes
+
+By adding the configuration below to a `flake.nix`, when someone uses the flake,
+`nix` will interactively ask to trust and use the provided binary cache:
+
+```nix
+{
+  nixConfig = {
+    extra-substituters = [
+      "https://jungle.bsc.es/cache"
+    ];
+    extra-trusted-public-keys = [
+      "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0="
+    ];
+  };
+  outputs = { ... }: {
+    ...
+  };
+}
+```
+
+### Querying the cache
+
+Check if the cache is available:
+```sh
+$ curl https://jungle.bsc.es/cache/nix-cache-info
+StoreDir: /nix/store
+WantMassQuery: 1
+Priority: 30
+```
+
+Prevent nix from building locally:
+```bash
+nix build --max-jobs 0 <...>
+```
+
+Check if a package is in cache:
+```bash
+# Do a raw eval on the <package>.outPath (this should not build the package)
+$ nix eval --raw jungle#openmp.outPath
+/nix/store/dwnn4dgm1m4184l4xbi0qfrprji9wjmi-openmp-2024.11
+# Take the hash (everything from / to - in the basename) and curl <hash>.narinfo
+# if it exists in the cache, it will return HTTP 200 and some information
+# if not, it will return 404
+$ curl https://jungle.bsc.es/cache/dwnn4dgm1m4184l4xbi0qfrprji9wjmi.narinfo
+StorePath: /nix/store/dwnn4dgm1m4184l4xbi0qfrprji9wjmi-openmp-2024.11
+URL: nar/dwnn4dgm1m4184l4xbi0qfrprji9wjmi-17imkdfqzmnb013d14dx234bx17bnvws8baf3ii1xra5qi2y1wiz.nar
+Compression: none
+NarHash: sha256:17imkdfqzmnb013d14dx234bx17bnvws8baf3ii1xra5qi2y1wiz
+NarSize: 1519328
+References: 4gk773fqcsv4fh2rfkhs9bgfih86fdq8-gcc-13.3.0-lib nqb2ns2d1lahnd5ncwmn6k84qfd7vx2k-glibc-2.40-36
+Deriver: vcn0x8hikc4mvxdkvrdxp61bwa5r7lr6-openmp-2024.11.drv
+Sig: jungle.bsc.es:GDTOUEs1jl91wpLbb+gcKsAZjpKdARO9j5IQqb3micBeqzX2M/NDtKvgCS1YyiudOUdcjwa3j+hyzV2njokcCA==
+# In oneline:
+$ curl "https://jungle.bsc.es/cache/$(nix eval --raw jungle#<package>.outPath | cut -d '/' -f4 | cut -d '-' -f1).narinfo"
+```
+
+#### References
+
+- https://nix.dev/guides/recipes/add-binary-cache.html
+- https://nixos.wiki/wiki/Binary_Cache

web/content/paste/_index.md

@@ -5,13 +5,13 @@ author: "Rodrigo Arias Mallo"
 date: 2024-09-20
 ---
 
-The hut machine provides a paste service using the program `p` (as in paste).
+The tent machine provides a paste service using the program `p` (as in paste).
 
-You can use it directly from the hut machine or remotely if you have [SSH
-access](/access) to hut using the following alias:
+You can use it directly from the tent machine or remotely if you have [SSH
+access](/access) to tent using the following alias:
 
 ```
-alias p="ssh hut p"
+alias p="ssh tent p"
 ```
 
 You can add it to bashrc or zshrc for persistent installation.
@@ -19,7 +19,7 @@ You can add it to bashrc or zshrc for persistent installation.
 ## Usage
 
 The `p` command reads from the standard input, uploads the content to a file
-in the ceph filesystem and prints the URL to access it. It only accepts an
+in the local filesystem and prints the URL to access it. It only accepts an
 optional argument, which is the extension of the file that will be stored on
 disk (without the dot). By default it uses the `txt` extension, so plain text
 can be read in the browser directly.
@@ -28,21 +28,21 @@ can be read in the browser directly.
 p [extension]
 ```
 
-To remove files, go to `/ceph/p/$USER` and remove them manually.
+To remove files, go to `/var/lib/p/$USER` and remove them manually.
 
 ## Examples
 
 Share a text file, in this case the source of p itself:
 
 ```
-hut% p < m/hut/p.nix
+tent% p < m/tent/p.nix
 https://jungle.bsc.es/p/rarias/okbtG130.txt
 ```
 
 Paste the last dmesg lines directly from a pipe:
 
 ```
-hut% dmesg | tail -5 | p
+tent% dmesg | tail -5 | p
 https://jungle.bsc.es/p/rarias/luX4STm9.txt
 ```
 

web/hugo.toml

@@ -3,32 +3,38 @@ languageCode = 'en-us'
 title = 'The jungle'
 theme = 'PaperMod'
 
+[[menu.main]]
+identifier = "doc"
+name = "Docs"
+url = "/doc/"
+weight = 10
+
 [[menu.main]]
 identifier = "grafana"
 name = "Grafana"
 url = "/grafana/"
-weight = 10
+weight = 20
 
 [[menu.main]]
 identifier = "Git"
 name = "Git"
 url = "/git/"
-weight = 20
+weight = 30
 
 [[menu.main]]
 identifier = "Lists"
 name = "Lists"
 url = "/lists/"
-weight = 30
+weight = 40
 
 [[menu.main]]
 identifier = "Paste"
 name = "Paste"
 url = "/paste/"
-weight = 40
+weight = 50
 
 [[menu.main]]
 identifier = "Posts"
 name = "Posts"
 url = "/posts/"
-weight = 50
+weight = 60