Set keep-outputs to true in all machines

From the documentation of keep-outputs, setting it to true would prevent
the GC from removing build time dependencies:

If true, the garbage collector will keep the outputs of non-garbage
derivations. If false (default), outputs will be deleted unless they are
GC roots themselves (or reachable from other roots).

In general, outputs must be registered as roots separately. However,
even if the output of a derivation is registered as a root, the
collector will still delete store paths that are used only at build time
(e.g., the C compiler, or source tarballs downloaded from the network).
To prevent it from doing so, set this option to true.

See: https://nix.dev/manual/nix/2.24/command-ref/conf-file.html#conf-keep-outputs

flake.nix

@@ -18,7 +18,6 @@ in
   {
     nixosConfigurations = {
       hut     = mkConf "hut";
-      tent    = mkConf "tent";
       owl1    = mkConf "owl1";
       owl2    = mkConf "owl2";
       eudy    = mkConf "eudy";

keys.nix

@@ -9,12 +9,11 @@ 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";
+    fox   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIDa9lId4rB/EKGkkCCVOy0cuId2SYLs+8W8kx0kmpO1y fox";
   };
 
   hostGroup = with hosts; rec {
-    untrusted  = [ fox ];
-    compute    = [ owl1 owl2 ];
+    compute    = [ owl1 owl2 fox ];
     playground = [ eudy koro ];
     storage    = [ bay lake2 ];
     monitor    = [ hut ];

m/bay/configuration.nix

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

m/common/base/ssh.nix

@@ -8,6 +8,17 @@ 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 bscpm04.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";

m/common/base/users.nix

@@ -20,7 +20,6 @@
       rarias = {
         uid = 1880;
         isNormalUser = true;
-        linger = true;
         home = "/home/Computational/rarias";
         description = "Rodrigo Arias";
         group = "Computational";
@@ -40,7 +39,7 @@
         home = "/home/Computational/arocanon";
         description = "Aleix Roca";
         group = "Computational";
-        extraGroups = [ "wheel" "tracing" ];
+        extraGroups = [ "wheel" ];
         hashedPassword = "$6$hliZiW4tULC/tH7p$pqZarwJkNZ7vS0G5llWQKx08UFG9DxDYgad7jplMD8WkZh5k58i4dfPoWtnEShfjTO6JHiIin05ny5lmSXzGM/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIF3zeB5KSimMBAjvzsp1GCkepVaquVZGPYwRIzyzaCba aleix@bsc"
@@ -56,7 +55,7 @@
         home = "/home/Computational/rpenacob";
         description = "Raúl Peñacoba";
         group = "Computational";
-        hosts = [ "owl1" "owl2" "hut" "tent" ];
+        hosts = [ "owl1" "owl2" "hut" ];
         hashedPassword = "$6$TZm3bDIFyPrMhj1E$uEDXoYYd1z2Wd5mMPfh3DZAjP7ztVjJ4ezIcn82C0ImqafPA.AnTmcVftHEzLB3tbe2O4SxDyPSDEQgJ4GOtj/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFYfXg37mauGeurqsLpedgA2XQ9d4Nm0ZGo/hI1f7wwH rpenacob@bsc"
@@ -69,7 +68,7 @@
         home = "/home/Computational/anavarro";
         description = "Antoni Navarro";
         group = "Computational";
-        hosts = [ "hut" "tent" "raccoon" "fox" ];
+        hosts = [ "hut" "raccoon" "fox" ];
         hashedPassword = "$6$QdNDsuLehoZTYZlb$CDhCouYDPrhoiB7/seu7RF.Gqg4zMQz0n5sA4U1KDgHaZOxy2as9pbIGeF8tOHJKRoZajk5GiaZv0rZMn7Oq31";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAILWjRSlKgzBPZQhIeEtk6Lvws2XNcYwHcwPv4osSgst5 anavarro@ssfhead"
@@ -82,7 +81,7 @@
         home = "/home/Computational/abonerib";
         description = "Aleix Boné";
         group = "Computational";
-        hosts = [ "owl1" "owl2" "hut" "tent" "raccoon" "fox" ];
+        hosts = [ "owl1" "owl2" "hut" "raccoon" "fox" ];
         hashedPassword = "$6$V1EQWJr474whv7XJ$OfJ0wueM2l.dgiJiiah0Tip9ITcJ7S7qDvtSycsiQ43QBFyP4lU0e0HaXWps85nqB4TypttYR4hNLoz3bz662/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIIFiqXqt88VuUfyANkZyLJNiuroIITaGlOOTMhVDKjf abonerib@bsc"
@@ -108,7 +107,7 @@
         home = "/home/Computational/dbautist";
         description = "Dylan Bautista Cases";
         group = "Computational";
-        hosts = [ "hut" "tent" "raccoon" ];
+        hosts = [ "hut" ];
         hashedPassword = "$6$a2lpzMRVkG9nSgIm$12G6.ka0sFX1YimqJkBAjbvhRKZ.Hl090B27pdbnQOW0wzyxVWySWhyDDCILjQELky.HKYl9gqOeVXW49nW7q/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIAb+EQBoS98zrCwnGKkHKwMLdYABMTqv7q9E0+T0QmkS dbautist@bsc-848818791"
@@ -121,7 +120,7 @@
         home = "/home/Computational/dalvare1";
         description = "David Álvarez";
         group = "Computational";
-        hosts = [ "hut" "tent" "fox" ];
+        hosts = [ "hut" "fox" ];
         hashedPassword = "$6$mpyIsV3mdq.rK8$FvfZdRH5OcEkUt5PnIUijWyUYZvB1SgeqxpJ2p91TTe.3eQIDTcLEQ5rxeg.e5IEXAZHHQ/aMsR5kPEujEghx0";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGEfy6F4rF80r4Cpo2H5xaWqhuUZzUsVsILSKGJzt5jF dalvare1@ssfhead"
@@ -134,7 +133,7 @@
         home = "/home/Computational/varcila";
         description = "Vincent Arcila";
         group = "Computational";
-        hosts = [ "hut" "tent" "fox" ];
+        hosts = [ "hut" "fox" ];
         hashedPassword = "$6$oB0Tcn99DcM4Ch$Vn1A0ulLTn/8B2oFPi9wWl/NOsJzaFAWjqekwcuC9sMC7cgxEVb.Nk5XSzQ2xzYcNe5MLtmzkVYnRS1CqP39Y0";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKGt0ESYxekBiHJQowmKpfdouw0hVm3N7tUMtAaeLejK vincent@varch"
@@ -144,7 +143,6 @@
 
     groups = {
       Computational = { gid = 564; };
-      tracing = { };
     };
   };
 }

m/common/ssf.nix

@@ -1,9 +0,0 @@
-{
-  # 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/ssh.nix

@@ -1,8 +0,0 @@
-{
-  # 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

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

m/common/xeon/net.nix

@@ -85,6 +85,10 @@
       10.0.40.8               eudy xeon08 xeon08-eth0
       10.0.42.8               eudy-ib xeon08-ib0
       10.0.40.108             eudy-ipmi xeon08-ipmi0 xeon08-ipmi
+
+      # fox
+      10.0.40.26              fox
+      10.0.40.126             fox-ipmi
     '';
   };
 }

m/eudy/configuration.nix

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

m/fox/configuration.nix

@@ -2,9 +2,11 @@
 
 {
   imports = [
-    ../common/base.nix
-    ../common/xeon/console.nix
+    ../common/xeon.nix
+    ../module/ceph.nix
     ../module/emulation.nix
+    ../module/slurm-client.nix
+    ../module/slurm-firewall.nix
   ];
 
   # Select the this using the ID to avoid mismatches
@@ -20,30 +22,11 @@
   hardware.cpu.intel.updateMicrocode = lib.mkForce false;
 
   networking = {
-    defaultGateway = "147.83.30.130";
-    nameservers = [ "8.8.8.8" ];
     hostName = "fox";
-    interfaces.enp1s0f0np0.ipv4.addresses = [
-      {
-        # UPC network
-        # 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
-        address = "147.83.30.141";
-        prefixLength = 26; # 255.255.255.192
-      }
-    ];
-    extraHosts = ''
-      147.83.30.141   fox.ac.upc.edu
-      147.83.35.27    fox-ipmi.ac.upc.edu
-    '';
+    interfaces.enp1s0f0np0.ipv4.addresses = [ {
+      address = "10.0.40.26";
+      prefixLength = 24;
+    } ];
   };
 
   # Configure Nvidia driver to use with CUDA
@@ -73,4 +56,20 @@
     wantedBy = [ "multi-user.target" ];
     serviceConfig.ExecStart = script;
   };
+
+  # Only allow SSH connections from users who have a SLURM allocation
+  # See: https://slurm.schedmd.com/pam_slurm_adopt.html
+  security.pam.services.sshd.rules.account.slurm = {
+    control = "required";
+    enable = true;
+    modulePath = "${pkgs.slurm}/lib/security/pam_slurm_adopt.so";
+    args = [ "log_level=debug5" ];
+    order = 999999; # Make it last one
+  };
+
+  # Disable systemd session (pam_systemd.so) as it will conflict with the
+  # pam_slurm_adopt.so module. What happens is that the shell is first adopted
+  # into the slurmstepd task and then into the systemd session, which is not
+  # what we want, otherwise it will linger even if all jobs are gone.
+  security.pam.services.sshd.startSession = lib.mkForce false;
 }

m/hut/configuration.nix

@@ -2,7 +2,7 @@
 
 {
   imports = [
-    ../common/ssf.nix
+    ../common/xeon.nix
 
     ../module/ceph.nix
     ../module/debuginfod.nix

m/hut/monitoring.nix

@@ -3,10 +3,7 @@
 {
   imports = [
     ../module/slurm-exporter.nix
-    ../module/meteocat-exporter.nix
-    ../module/upc-qaire-exporter.nix
     ./gpfs-probe.nix
-    ./nix-daemon-exporter.nix
   ];
 
   age.secrets.grafanaJungleRobotPassword = {
@@ -111,9 +108,6 @@
             "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}"
           ];
         }];
@@ -169,9 +163,6 @@
             "8.8.8.8"
             "ssfhead"
             "anella-bsc.cesca.cat"
-            "upc-anella.cesca.cat"
-            "fox.ac.upc.edu"
-            "arenys5.ac.upc.edu"
           ];
         }];
         relabel_configs = [
@@ -267,6 +258,17 @@
           }
         ];
       }
+      {
+        job_name = "ipmi-fox";
+        metrics_path = "/ipmi";
+        static_configs = [
+          { targets = [ "127.0.0.1:9290" ]; }
+        ];
+        params = {
+          target = [ "fox-ipmi" ];
+          module = [ "fox" ];
+        };
+      }
     ];
   };
 }

m/hut/nix-daemon-builds.sh

@@ -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

m/hut/nix-daemon-exporter.nix

@@ -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";
-    };
-  };
-}

m/koro/configuration.nix

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

m/lake2/configuration.nix

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

m/map.nix

@@ -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
-    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/meteocat-exporter.nix

@@ -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";
-    };
-  };
-}

m/module/slurm-client.nix

@@ -43,11 +43,13 @@ in {
     clusterName = "jungle";
     nodeName = [
       "owl[1,2]  Sockets=2 CoresPerSocket=14 ThreadsPerCore=2 Feature=owl"
+      "fox       Sockets=2 CoresPerSocket=96 ThreadsPerCore=1 Feature=fox"
       "hut       Sockets=2 CoresPerSocket=14 ThreadsPerCore=2"
     ];
 
     partitionName = [
       "owl Nodes=owl[1-2]     Default=YES DefaultTime=01:00:00 MaxTime=INFINITE State=UP"
+      "fox Nodes=fox          Default=NO  DefaultTime=01:00:00 MaxTime=INFINITE State=UP"
     ];
 
     # See slurm.conf(5) for more details about these options.
@@ -75,7 +77,7 @@ in {
       SuspendTimeout=60
       ResumeProgram=${resumeProgram}
       ResumeTimeout=300
-      SuspendExcNodes=hut
+      SuspendExcNodes=hut,fox
 
       # Turn the nodes off after 1 hour of inactivity
       SuspendTime=3600

m/module/ssh-hut-extern.nix

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

m/module/upc-qaire-exporter.nix

@@ -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";
-    };
-  };
-}

m/owl1/configuration.nix

@@ -2,7 +2,7 @@
 
 {
   imports = [
-    ../common/ssf.nix
+    ../common/xeon.nix
     ../module/ceph.nix
     ../module/emulation.nix
     ../module/slurm-client.nix

m/owl2/configuration.nix

@@ -2,7 +2,7 @@
 
 {
   imports = [
-    ../common/ssf.nix
+    ../common/xeon.nix
     ../module/ceph.nix
     ../module/emulation.nix
     ../module/slurm-client.nix

m/raccoon/configuration.nix

@@ -3,10 +3,6 @@
 {
   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
@@ -27,18 +23,6 @@
       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 = {
@@ -46,9 +30,6 @@
     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;
@@ -56,18 +37,6 @@
   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/configuration.nix

@@ -1,70 +0,0 @@
-{ config, pkgs, lib, ... }:
-
-{
-  imports = [
-    ../common/xeon.nix
-    ../module/emulation.nix
-    ../module/debuginfod.nix
-    ../module/ssh-hut-extern.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" ];
-    defaultGateway = "10.0.44.1";
-  };
-
-  nix.settings = {
-    substituters = [ "https://jungle.bsc.es/cache" ];
-    trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
-  };
-
-  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 ${user.group} -m 0711 /vault/${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;
-  };
-}

pkgs/meteocat-exporter/default.nix

@@ -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;
-  };
-}

pkgs/meteocat-exporter/meteocat-exporter

@@ -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)

pkgs/meteocat-exporter/setup.py

@@ -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"],
-     )

pkgs/overlay.nix

@@ -54,6 +54,4 @@ final: prev:
   });
 
   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

@@ -1,24 +0,0 @@
-{ 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

@@ -1,11 +0,0 @@
-#!/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

@@ -1,74 +0,0 @@
-#!/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/gitlab-bsc-docker-token.age

@@ -1,10 +1,11 @@
 age-encryption.org/v1
--> ssh-ed25519 HY2yRg XPOFoZqY+AnKC77jrgNqAm1ADphurfuhO4NRrfiuUDc
-iCfMMpGHyaYHGy6ci8sqjUtcPeteLlyvLGEF79VPOEc
--> ssh-ed25519 CAWG4Q 6OsGrnM+/c5lTN81Rvp166K+ygmSIFeSYzXxYg25KGE
-Av1zTw2zK4Gufzti9kQaye7C362GCiDRRHzCqBLR33g
--> ssh-ed25519 MSF3dg 8CHqJ7mEDvjvqbmF+eE6Em1Wi6eHAzEUpiExC1gm7S0
-bdwzYHw3RAbdHq+RsiFUP++sQ586VUlSnAzAOhiQUjI
---- gA5XSUfjUBol938sC5DbUf8PvQUIr2pNkS2nL95OF9c
-<EFBFBD><EFBFBD><EFBFBD>Ea1G7<47><37>ݩ[R<><52>\{~$Go<47>cQ<63>wKP&<26><><EFBFBD>w<EFBFBD><77><EFBFBD>6]
-<EFBFBD><EFBFBD>ѣ<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>^z<7A>̄ 1k<31><6B><03><><EFBFBD><EFBFBD><EFBFBD>Y<EFBFBD><59>2<15>p<>2<EFBFBD><32>K<EFBFBD><4B><EFBFBD><EFBFBD>nok<>/X<><58>pt''<27><>$0co=<3D><EFBFBD>
+-> ssh-ed25519 HY2yRg WSdjyQPzBJ4JbzQpGeq1AAYpWKoXmLI1ZtmNmM5QOzs
+qGDlDT31DQF1DdHen0+5+52DdsQlabJdA2pOB5O1I6g
+-> ssh-ed25519 CAWG4Q wioWMDxQjN+d4JdIbCwZg0DLQu1OH2mV6gukRprjuAs
+670fE61hidOEh20hHiQAhP0+CjDF0WMBNzgwkGT8Yqg
+-> ssh-ed25519 MSF3dg DN19uvAEtqq4708P6HpuX9i/o/qAvHX6dj69dCF2H1o
+4Lu9GnjiFLMeXJ2C7aVPJsCHCQVlhylNWJi896Av92s
+--- 7cKBwOYNOUZ2h3/kAY09aSMASZSxX7hZIT4kvlIiT6w
+<EFBFBD>6<EFBFBD><02><><EFBFBD><06>fQF5=<3D>bX+<2B>v e`<60>7/<2F><05>A~P<><50>Ѧ7<15><>
+<EFBFBD><EFBFBD>A<EFBFBD>)<29>h<05><>=oZ<6F>$<24>^<5E>V0<56>/܅<>r
+k<EFBFBD>u<EFBFBD>bĶ:R<><52>>^g<><67><06>ik_*%<0B>a7<61>KG<4B><47><EFBFBD><EFBFBD><EFBFBD><EFBFBD>&<26>PI<50><49>n

secrets/gitlab-runner-docker-token.age

@@ -1,9 +1,10 @@
 age-encryption.org/v1
--> ssh-ed25519 HY2yRg pXNTB/ailRwSEJG1pXvrzzpz5HqkDZdWVWnOH7JGeQ4
-NzA+2fxfkNRy/u+Zq96A02K1Vxy0ETYZjMkDVTKyCY8
--> ssh-ed25519 CAWG4Q 7CLJWn+EAxoWDduXaOSrHaBFHQ4GIpYP/62FFTj3ZTI
-vSYV1pQg2qI2ngCzM0nCZAnqdz1tbT4hM5m+/TyGU2c
--> ssh-ed25519 MSF3dg Akmp4NcZcDuaYHta/Vej6zulNSrAOCd5lmSV+OiBGC4
-qTxqVzTyywur+GjtUQdbaIUdH1fqCqPe6qPf8iHRa4w
---- uCKNqD1TmZZThOzlpsecBKx/k+noIWhCVMr/pzNwBr8
-r'<27>Ƌs4<15>˺<EFBFBD>Aĥ<41>P<05>L<EFBFBD><4C>7`	<09><02><>)H<><48>-<2D>0<EFBFBD>AH<41>5<16><><1F><>L<EFBFBD>Qe<51><65>H2b<32><1D>B޲<42>CJG<4A>"-S<><1C>\<5C><><0C>
H<n<>V
+-> ssh-ed25519 HY2yRg GdmdkW+BqqwBgu30b846jv3J7jtCM+a3rgOERuA050A
+FeGqM75jG9egesR+yyVKHm0/M+uBBp5Hclg4+qN0BR8
+-> ssh-ed25519 CAWG4Q a0wTWHgulQUYDAMZmXf3dOf6PdYgCqNtSylzWVVRNVM
+Bx+WSYaiY4ZwlSZJo2a1XPMQmbKOU7F0tKAqVRLBOPo
+-> ssh-ed25519 MSF3dg KccUvZZUbxbCrRWUWrX8KcHF6vQ5FV/BqUqI59G7dj4
+CFr7GXpZ9rPgy7HBfOyiYF9FnZUw6KcZwq9f7/0KaU8
+--- E0Rp6RR/8+o0jvB1lRdhnlabxvI6uu/IgL2ZpPXzTc8
+<EFBFBD><13>#<23><>H<EFBFBD>$<24>F;<3B><EFBFBD><7F>%<25><>6<><02>2<EFBFBD><32>rfX<66>\Dn <20>ш<EFBFBD>ȉ<EFBFBD>x<EFBFBD><78>><3E><>&;<3B>c<EFBFBD>U<EFBFBD>I=<3D><>M<EFBFBD><4D><EFBFBD>?T<><54>Ǹ<EFBFBD><16>"px<70>ӭ\s<><73><EFBFBD>bF<62><46><EFBFBD><EFBFBD>WD<>{<7B>
+AW>?U<><55><EFBFBD><17><>HԳ

secrets/gitlab-runner-shell-token.age

@@ -1,9 +1,9 @@
 age-encryption.org/v1
--> ssh-ed25519 HY2yRg s6iI9f25xulF4KXt+XY07kXXPKxXo7f2Ql/OTHN55Hk
-WO4Fd2H9c+HL3+XhUF3BmEZVILlcchGxSrSmL2OEdGw
--> ssh-ed25519 CAWG4Q TBkdpx8k8K1NvW3wcvaF7omKFwEJ2DxWJp3tIOTjwCA
-LcYgWRix23AQnw0OQ7f8+8S3J84CHUElX1vKZSETiLE
--> ssh-ed25519 MSF3dg WzrF8kjTP7BXXDjmUp7kPCKguthAW12RPo6Vy2RMmh4
-8C3mT9ktudCTANDxhyNszUkbeDG6X4wOJdx825++dYM
---- /w3YQ2UeTi67H1JR0GsdPz2KoLN2Y7BIZfFY+//AWjY
-<EFBFBD>ӣ-`P<>@<40><>ބ<><DE84><EFBFBD>)9<>9l<EFBFBD><EFBFBD><EFBFBD><EFBFBD>Zf<EFBFBD><EFBFBD>V?I>΍<>w鉐<77>z40 <20>2{i@<40>Z<EFBFBD><5A>x<EFBFBD><78>AHn<48>%<25><><0C>ʤ<EFBFBD>/W<EFBFBD><EFBFBD>Ĕ<EFBFBD>l<EFBFBD><EFBFBD><EFBFBD><EFBFBD>}<7D>&<08>얶<EFBFBD>(<EFBFBD><EFBFBD><EFBFBD>K<EFBFBD><EFBFBD><EFBFBD>S<EFBFBD><EFBFBD>o<EFBFBD>z<EFBFBD>=<1F>d
+-> ssh-ed25519 HY2yRg xWRxJGWSzA5aplRYCYLB6aBwrUrQQJ2MtDYaD75V5nI
+J07XF3NQiaYKKKNRcNWi9MloJD2wXHd+2K7bo6lF+QU
+-> ssh-ed25519 CAWG4Q jNWymbyCczcm8RcaIEbFQBlOMALsuxTl4+pLUi0aR20
+z5NixlrRD+Y7Z/aFPs6hiDW4/lp8CBQCeJYpbuG9yYM
+-> ssh-ed25519 MSF3dg QsUQloEKN3k1G49FQnNR/Do6ILgGpjFcw3zu5kk1Ako
+IHwyFWUEWqCStNcFprnpBa8L5J6zKIsn+7HcgGRv3sM
+--- oUia0fsL6opeYWACyXtHAu/Ld+bUIt/7S1VszYTvwgU
+<EFBFBD><EFBFBD>V<EFBFBD><16>*<2A>t<1B>2-<2D>7<><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>h<EFBFBD>&<26><>͢_!տ+<2B><><EFBFBD><EFBFBD>(<28><0F><11>n<EFBFBD><6E>	<09><>(<28><19><EFBFBD>/}<EFBFBD><EFBFBD><EFBFBD><EFBFBD>C<EFBFBD>Nͷ|<04>N<>u<EFBFBD>5<EFBFBD>ù勚K<E58B9A><EFBFBD>l<EFBFBD>"<EFBFBD><EFBFBD>klOX<EFBFBD>y<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>A<EFBFBD><EFBFBD>e<><65>$