Monitor GPFS scratch partition

flake.lock

@@ -10,11 +10,11 @@
         "systems": "systems"
       },
       "locked": {
-        "lastModified": 1750173260,
+        "lastModified": 1723293904,
-        "narHash": "sha256-9P1FziAwl5+3edkfFcr5HeGtQUtrSdk/MksX39GieoA=",
+        "narHash": "sha256-b+uqzj+Wa6xgMS9aNbX4I+sXeb5biPDi39VgvSFqFvU=",
         "owner": "ryantm",
         "repo": "agenix",
-        "rev": "531beac616433bac6f9e2a19feb8e99a22a66baf",
+        "rev": "f6291c5935fdc4e0bef208cfc0dcab7e3f7a1c41",
         "type": "github"
       },
       "original": {
@@ -30,11 +30,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1749650500,
+        "lastModified": 1732868163,
-        "narHash": "sha256-2MHfVPV6RA7qPSCtXh4+KK0F0UjN+J4z8//+n6NK7Xs=",
+        "narHash": "sha256-qck4h298AgcNI6BnGhEwl26MTLXjumuJVr+9kak7uPo=",
         "ref": "refs/heads/master",
-        "rev": "9d1944c658929b6f98b3f3803fead4d1b91c4405",
+        "rev": "6782fc6c5b5a29e84a7f2c2d1064f4bcb1288c0f",
-        "revCount": 961,
+        "revCount": 952,
         "type": "git",
         "url": "https://git.sr.ht/~rodarima/bscpkgs"
       },
@@ -51,11 +51,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1744478979,
+        "lastModified": 1700795494,
-        "narHash": "sha256-dyN+teG9G82G+m+PX/aSAagkC+vUv0SgUw3XkPhQodQ=",
+        "narHash": "sha256-gzGLZSiOhf155FW7262kdHo2YDeugp3VuIFb4/GGng0=",
         "owner": "lnl7",
         "repo": "nix-darwin",
-        "rev": "43975d782b418ebf4969e9ccba82466728c2851b",
+        "rev": "4b9b83d5a92e8c1fbfd8eb27eda375908c11ec4d",
         "type": "github"
       },
       "original": {
@@ -73,11 +73,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1745494811,
+        "lastModified": 1703113217,
-        "narHash": "sha256-YZCh2o9Ua1n9uCvrvi5pRxtuVNml8X2a03qIFfRKpFs=",
+        "narHash": "sha256-7ulcXOk63TIT2lVDSExj7XzFx09LpdSAPtvgtM7yQPE=",
         "owner": "nix-community",
         "repo": "home-manager",
-        "rev": "abfad3d2958c9e6300a883bd443512c55dfeb1be",
+        "rev": "3bfaacf46133c037bb356193bd2f1765d9dc82c1",
         "type": "github"
       },
       "original": {
@@ -88,16 +88,16 @@
     },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1752436162,
+        "lastModified": 1736867362,
-        "narHash": "sha256-Kt1UIPi7kZqkSc5HVj6UY5YLHHEzPBkgpNUByuyxtlw=",
+        "narHash": "sha256-i/UJ5I7HoqmFMwZEH6vAvBxOrjjOJNU739lnZnhUln8=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "dfcd5b901dbab46c9c6e80b265648481aafb01f8",
+        "rev": "9c6b49aeac36e2ed73a8c472f1546f6d9cf1addc",
         "type": "github"
       },
       "original": {
         "owner": "NixOS",
-        "ref": "nixos-25.05",
+        "ref": "nixos-24.11",
         "repo": "nixpkgs",
         "type": "github"
       }

flake.nix

@@ -1,6 +1,6 @@
 {
   inputs = {
-    nixpkgs.url = "github:NixOS/nixpkgs/nixos-25.05";
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-24.11";
     agenix.url = "github:ryantm/agenix";
     agenix.inputs.nixpkgs.follows = "nixpkgs";
     bscpkgs.url = "git+https://git.sr.ht/~rodarima/bscpkgs";
@@ -27,8 +27,6 @@ in
       lake2   = mkConf "lake2";
       raccoon = mkConf "raccoon";
       fox     = mkConf "fox";
-      apex    = mkConf "apex";
-      weasel  = mkConf "weasel";
     };
 
     packages.x86_64-linux = self.nixosConfigurations.hut.pkgs // {

keys.nix

@@ -2,28 +2,25 @@
 # here all the public keys
 rec {
   hosts = {
-    hut    = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICO7jIp6JRnRWTMDsTB/aiaICJCl4x8qmKMPSs4lCqP1 hut";
+    hut   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICO7jIp6JRnRWTMDsTB/aiaICJCl4x8qmKMPSs4lCqP1 hut";
-    owl1   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIMqMEXO0ApVsBA6yjmb0xP2kWyoPDIWxBB0Q3+QbHVhv owl1";
+    owl1  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIMqMEXO0ApVsBA6yjmb0xP2kWyoPDIWxBB0Q3+QbHVhv owl1";
-    owl2   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHurEYpQzNHqWYF6B9Pd7W8UPgF3BxEg0BvSbsA7BAdK owl2";
+    owl2  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHurEYpQzNHqWYF6B9Pd7W8UPgF3BxEg0BvSbsA7BAdK owl2";
-    eudy   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIL+WYPRRvZupqLAG0USKmd/juEPmisyyJaP8hAgYwXsG eudy";
+    eudy  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIL+WYPRRvZupqLAG0USKmd/juEPmisyyJaP8hAgYwXsG eudy";
-    koro   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIImiTFDbxyUYPumvm8C4mEnHfuvtBY1H8undtd6oDd67 koro";
+    koro  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIImiTFDbxyUYPumvm8C4mEnHfuvtBY1H8undtd6oDd67 koro";
-    bay    = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICvGBzpRQKuQYHdlUQeAk6jmdbkrhmdLwTBqf3el7IgU bay";
+    bay   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICvGBzpRQKuQYHdlUQeAk6jmdbkrhmdLwTBqf3el7IgU bay";
-    lake2  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINo66//S1yatpQHE/BuYD/Gfq64TY7ZN5XOGXmNchiO0 lake2";
+    lake2 = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINo66//S1yatpQHE/BuYD/Gfq64TY7ZN5XOGXmNchiO0 lake2";
-    fox    = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIDwItIk5uOJcQEVPoy/CVGRzfmE1ojrdDcI06FrU4NFT fox";
+    fox   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIDwItIk5uOJcQEVPoy/CVGRzfmE1ojrdDcI06FrU4NFT fox";
-    tent   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFAtTpHtdYoelbknD/IcfBlThwLKJv/dSmylOgpg3FRM tent";
+    tent  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFAtTpHtdYoelbknD/IcfBlThwLKJv/dSmylOgpg3FRM tent";
-    apex   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIBvUFjSfoxXnKwXhEFXx5ckRKJ0oewJ82mRitSMNMKjh apex";
-    weasel = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFLJrQ8BF6KcweQV8pLkSbFT+tbDxSG9qxrdQE65zJZp weasel";
   };
 
   hostGroup = with hosts; rec {
     untrusted  = [ fox ];
     compute    = [ owl1 owl2 ];
-    playground = [ eudy koro weasel ];
+    playground = [ eudy koro ];
     storage    = [ bay lake2 ];
     monitor    = [ hut ];
-    login      = [ apex ];
 
-    system     = storage ++ monitor ++ login;
+    system     = storage ++ monitor;
     safe       = system ++ compute;
     all        = safe ++ playground;
   };

m/apex/configuration.nix

@@ -1,86 +0,0 @@
-{ lib, config, pkgs, ... }:
-
-{
-  imports = [
-    ../common/xeon.nix
-    ../common/ssf/hosts.nix
-    ../module/ceph.nix
-    ../module/power-policy.nix
-    ./nfs.nix
-  ];
-
-  power.policy = "always-on";
-
-  # Don't install grub MBR for now
-  boot.loader.grub.device = "nodev";
-
-  boot.initrd.kernelModules = [
-    "megaraid_sas" # For HW RAID
-  ];
-
-  environment.systemPackages = with pkgs; [
-    storcli # To manage HW RAID
-  ];
-
-  fileSystems."/home" = {
-    device = "/dev/disk/by-label/home";
-    fsType = "ext4";
-  };
-
-  # No swap, there is plenty of RAM
-  swapDevices = lib.mkForce [];
-
-  networking = {
-    hostName = "apex";
-    defaultGateway = "84.88.53.233";
-    nameservers = [ "8.8.8.8" ];
-
-    # Public facing interface
-    interfaces.eno1.ipv4.addresses = [ {
-      address = "84.88.53.236";
-      prefixLength = 29;
-    } ];
-
-    # Internal LAN to our Ethernet switch
-    interfaces.eno2.ipv4.addresses = [ {
-      address = "10.0.40.30";
-      prefixLength = 24;
-    } ];
-
-    # Infiniband over Omnipath switch (disconnected for now)
-    # interfaces.ibp5s0 = {};
-
-    nat = {
-      enable = true;
-      internalInterfaces = [ "eno2" ];
-      externalInterface = "eno1";
-    };
-  };
-
-  # Use SSH tunnel to reach internal hosts
-  programs.ssh.extraConfig = ''
-    Host bscpm04.bsc.es gitlab-internal.bsc.es knights3.bsc.es
-      ProxyCommand nc -X connect -x localhost:23080 %h %p
-    Host raccoon
-      HostName knights3.bsc.es
-      ProxyCommand nc -X connect -x localhost:23080 %h %p
-    Host tent
-      ProxyJump raccoon
-  '';
-
-  networking.firewall = {
-    extraCommands = ''
-      # Blackhole BSC vulnerability scanner (OpenVAS) as it is spamming our
-      # logs. Insert as first position so we also protect SSH.
-      iptables -I nixos-fw 1 -p tcp -s 192.168.8.16 -j nixos-fw-refuse
-      # Same with opsmonweb01.bsc.es which seems to be trying to access via SSH
-      iptables -I nixos-fw 2 -p tcp -s 84.88.52.176 -j nixos-fw-refuse
-    '';
-  };
-
-  # Use tent for cache
-  nix.settings = {
-    extra-substituters = [ "https://jungle.bsc.es/cache" ];
-    extra-trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
-  };
-}

m/apex/nfs.nix

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

m/common/base.nix

@@ -11,7 +11,6 @@
     ./base/net.nix
     ./base/nix.nix
     ./base/ntp.nix
-    ./base/power-policy.nix
     ./base/rev.nix
     ./base/ssh.nix
     ./base/users.nix

m/common/base/august-shutdown.nix

@@ -1,12 +1,12 @@
 {
-  # Shutdown all machines on August 3rd at 22:00, so we can protect the
+  # Shutdown all machines on August 2nd at 11:00 AM, so we can protect the
   # hardware from spurious electrical peaks on the yearly electrical cut for
   # manteinance that starts on August 4th.
   systemd.timers.august-shutdown = {
-    description = "Shutdown on August 3rd for maintenance";
+    description = "Shutdown on August 2nd for maintenance";
     wantedBy = [ "timers.target" ];
     timerConfig = {
-      OnCalendar = "*-08-03 22:00:00";
+      OnCalendar = "*-08-02 11:00:00";
       RandomizedDelaySec = "10min";
       Unit = "systemd-poweroff.service";
     };

m/common/base/env.nix

@@ -3,8 +3,8 @@
 {
   environment.systemPackages = with pkgs; [
     vim wget git htop tmux pciutils tcpdump ripgrep nix-index nixos-option
-    nix-diff ipmitool freeipmi ethtool lm_sensors cmake gnumake file tree
+    nix-diff ipmitool freeipmi ethtool lm_sensors ix cmake gnumake file tree
-    ncdu config.boot.kernelPackages.perf ldns pv
+    ncdu config.boot.kernelPackages.perf ldns
     # From bsckgs overlay
     osumb
   ];

m/common/base/net.nix

@@ -1,4 +1,4 @@
-{ pkgs, lib, ... }:
+{ pkgs, ... }:
 
 {
   networking = {
@@ -10,11 +10,8 @@
       allowedTCPPorts = [ 22 ];
     };
 
-    # Make sure we use iptables
-    nftables.enable = lib.mkForce false;
-
     hosts = {
-      "84.88.53.236" = [ "apex" "ssfhead.bsc.es" "ssfhead" ];
+      "84.88.53.236" = [ "ssfhead.bsc.es" "ssfhead" ];
       "84.88.51.152" = [ "raccoon" ];
       "84.88.51.142" = [ "raccoon-ipmi" ];
     };

m/common/base/nix.nix

@@ -6,8 +6,6 @@
     (import ../../../pkgs/overlay.nix)
   ];
 
-  nixpkgs.config.allowUnfree = true;
-
   nix = {
     nixPath = [
       "nixpkgs=${nixpkgs}"

m/common/base/power-policy.nix

@@ -1,9 +0,0 @@
-{
-  imports = [
-    ../../module/power-policy.nix
-  ];
-
-  # By default, keep the machines off as we don't know if the AC will be working
-  # once the electricity comes back.
-  power.policy = "always-off";
-}

m/common/base/users.nix

@@ -56,7 +56,7 @@
         home = "/home/Computational/rpenacob";
         description = "Raúl Peñacoba";
         group = "Computational";
-        hosts = [ "apex" "owl1" "owl2" "hut" "tent" "fox" ];
+        hosts = [ "owl1" "owl2" "hut" "tent" "fox" ];
         hashedPassword = "$6$TZm3bDIFyPrMhj1E$uEDXoYYd1z2Wd5mMPfh3DZAjP7ztVjJ4ezIcn82C0ImqafPA.AnTmcVftHEzLB3tbe2O4SxDyPSDEQgJ4GOtj/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFYfXg37mauGeurqsLpedgA2XQ9d4Nm0ZGo/hI1f7wwH rpenacob@bsc"
@@ -69,10 +69,10 @@
         home = "/home/Computational/anavarro";
         description = "Antoni Navarro";
         group = "Computational";
-        hosts = [ "apex" "hut" "tent" "raccoon" "fox" "weasel" ];
+        hosts = [ "hut" "tent" "raccoon" "fox" ];
-        hashedPassword = "$6$EgturvVYXlKgP43g$gTN78LLHIhaF8hsrCXD.O6mKnZSASWSJmCyndTX8QBWT6wTlUhcWVAKz65lFJPXjlJA4u7G1ydYQ0GG6Wk07b1";
+        hashedPassword = "$6$QdNDsuLehoZTYZlb$CDhCouYDPrhoiB7/seu7RF.Gqg4zMQz0n5sA4U1KDgHaZOxy2as9pbIGeF8tOHJKRoZajk5GiaZv0rZMn7Oq31";
         openssh.authorizedKeys.keys = [
-          "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIMsbM21uepnJwPrRe6jYFz8zrZ6AYMtSEvvt4c9spmFP toni@delltoni"
+          "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAILWjRSlKgzBPZQhIeEtk6Lvws2XNcYwHcwPv4osSgst5 anavarro@ssfhead"
         ];
       };
 
@@ -82,7 +82,7 @@
         home = "/home/Computational/abonerib";
         description = "Aleix Boné";
         group = "Computational";
-        hosts = [ "apex" "owl1" "owl2" "hut" "tent" "raccoon" "fox" "weasel" ];
+        hosts = [ "owl1" "owl2" "hut" "tent" "raccoon" "fox" ];
         hashedPassword = "$6$V1EQWJr474whv7XJ$OfJ0wueM2l.dgiJiiah0Tip9ITcJ7S7qDvtSycsiQ43QBFyP4lU0e0HaXWps85nqB4TypttYR4hNLoz3bz662/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIIFiqXqt88VuUfyANkZyLJNiuroIITaGlOOTMhVDKjf abonerib@bsc"
@@ -95,7 +95,7 @@
         home = "/home/Computational/vlopez";
         description = "Victor López";
         group = "Computational";
-        hosts = [ "apex" "koro" ];
+        hosts = [ "koro" ];
         hashedPassword = "$6$0ZBkgIYE/renVqtt$1uWlJsb0FEezRVNoETTzZMx4X2SvWiOsKvi0ppWCRqI66S6TqMBXBdP4fcQyvRRBt0e4Z7opZIvvITBsEtO0f0";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGMwlUZRf9jfG666Qa5Sb+KtEhXqkiMlBV2su3x/dXHq victor@arch"
@@ -108,7 +108,7 @@
         home = "/home/Computational/dbautist";
         description = "Dylan Bautista Cases";
         group = "Computational";
-        hosts = [ "apex" "hut" "tent" "raccoon" ];
+        hosts = [ "hut" "tent" "raccoon" ];
         hashedPassword = "$6$a2lpzMRVkG9nSgIm$12G6.ka0sFX1YimqJkBAjbvhRKZ.Hl090B27pdbnQOW0wzyxVWySWhyDDCILjQELky.HKYl9gqOeVXW49nW7q/";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIAb+EQBoS98zrCwnGKkHKwMLdYABMTqv7q9E0+T0QmkS dbautist@bsc-848818791"
@@ -121,7 +121,7 @@
         home = "/home/Computational/dalvare1";
         description = "David Álvarez";
         group = "Computational";
-        hosts = [ "apex" "hut" "tent" "fox" ];
+        hosts = [ "hut" "tent" "fox" ];
         hashedPassword = "$6$mpyIsV3mdq.rK8$FvfZdRH5OcEkUt5PnIUijWyUYZvB1SgeqxpJ2p91TTe.3eQIDTcLEQ5rxeg.e5IEXAZHHQ/aMsR5kPEujEghx0";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGEfy6F4rF80r4Cpo2H5xaWqhuUZzUsVsILSKGJzt5jF dalvare1@ssfhead"
@@ -134,7 +134,7 @@
         home = "/home/Computational/varcila";
         description = "Vincent Arcila";
         group = "Computational";
-        hosts = [ "apex" "hut" "tent" "fox" ];
+        hosts = [ "hut" "tent" "fox" ];
         hashedPassword = "$6$oB0Tcn99DcM4Ch$Vn1A0ulLTn/8B2oFPi9wWl/NOsJzaFAWjqekwcuC9sMC7cgxEVb.Nk5XSzQ2xzYcNe5MLtmzkVYnRS1CqP39Y0";
         openssh.authorizedKeys.keys = [
           "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKGt0ESYxekBiHJQowmKpfdouw0hVm3N7tUMtAaeLejK vincent@varch"

m/common/ssf.nix

@@ -3,7 +3,6 @@
   imports = [
     ./xeon.nix
     ./ssf/fs.nix
-    ./ssf/hosts.nix
     ./ssf/net.nix
     ./ssf/ssh.nix
   ];

m/common/ssf/hosts.nix

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

m/common/ssf/net.nix

@@ -9,6 +9,14 @@
     defaultGateway = "10.0.40.30";
     nameservers = ["8.8.8.8"];
 
+    proxy = {
+      default = "http://hut:23080/";
+      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;
+    };
+
     firewall = {
       extraCommands = ''
         # Prevent ssfhead from contacting our slurmd daemon
@@ -19,5 +27,64 @@
         iptables -A nixos-fw -p tcp -s 10.0.40.0/24 --dport 60000:61000 -j nixos-fw-accept
       '';
     };
+
+    extraHosts = ''
+      10.0.40.30              ssfhead
+      
+      # 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 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 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 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 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 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 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 xeon04-ipmi
+      
+      # Node Entry for node: xeon05 (ID=19)
+      10.0.40.5               koro xeon05 xeon05-eth0
+      10.0.42.5               koro-ib xeon05-ib0
+      10.0.40.105             koro-ipmi xeon05-ipmi0
+      
+      # Node Entry for node: xeon06 (ID=20)
+      10.0.40.6               xeon06 xeon06-eth0
+      10.0.42.6               xeon06-ib0
+      10.0.40.106             xeon06-ipmi0 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 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 xeon08-ipmi
+    '';
   };
 }

m/common/ssf/ssh.nix

@@ -1,16 +1,8 @@
 {
-  # Use SSH tunnel to apex to reach internal hosts
+  # Connect to intranet git hosts via proxy
   programs.ssh.extraConfig = ''
-    Host tent
+    # Connect to BSC machines via hut proxy too
-      ProxyJump raccoon
+    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
-    # Access raccoon via the HTTP proxy
-    Host raccoon knights3.bsc.es
-      HostName knights3.bsc.es
-      ProxyCommand=ssh apex 'nc -X connect -x localhost:23080 %h %p'
-
-    # Make sure we can reach gitlab even if we don't have SSH access to raccoon
-    Host bscpm04.bsc.es gitlab-internal.bsc.es
-      ProxyCommand=ssh apex 'nc -X connect -x localhost:23080 %h %p'
   '';
 }

m/fox/configuration.nix

@@ -5,16 +5,8 @@
     ../common/base.nix
     ../common/xeon/console.nix
     ../module/emulation.nix
-    ../module/nvidia.nix
-    ../module/power-policy.nix
   ];
 
-  power.policy = "always-on";
-
-  # Don't turn off on August as UPC has different dates.
-  # Fox works fine on power cuts.
-  systemd.timers.august-shutdown.enable = false;
-
   # Select the this using the ID to avoid mismatches
   boot.loader.grub.device = "/dev/disk/by-id/wwn-0x500a07514b0c1103";
 
@@ -61,8 +53,12 @@
     extra-trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
   };
 
-  # Recommended for new graphics cards
+  # Configure Nvidia driver to use with CUDA
-  hardware.nvidia.open = true;
+  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"; };

m/hut/blackbox.yml

@@ -3,12 +3,160 @@ modules:
     prober: http
     timeout: 5s
     http:
+      proxy_url: "http://127.0.0.1:23080"
+      skip_resolve_phase_with_proxy: true
       follow_redirects: true
-      preferred_ip_protocol: "ip4"
       valid_status_codes: []  # Defaults to 2xx
       method: GET
+  http_with_proxy:
+    prober: http
+    http:
+      proxy_url: "http://127.0.0.1:3128"
+      skip_resolve_phase_with_proxy: true
+  http_with_proxy_and_headers:
+    prober: http
+    http:
+      proxy_url: "http://127.0.0.1:3128"
+      proxy_connect_header:
+        Proxy-Authorization:
+          - Bearer token
+  http_post_2xx:
+    prober: http
+    timeout: 5s
+    http:
+      method: POST
+      headers:
+        Content-Type: application/json
+      body: '{}'
+  http_post_body_file:
+    prober: http
+    timeout: 5s
+    http:
+      method: POST
+      body_file: "/files/body.txt"
+  http_basic_auth_example:
+    prober: http
+    timeout: 5s
+    http:
+      method: POST
+      headers:
+        Host: "login.example.com"
+      basic_auth:
+        username: "username"
+        password: "mysecret"
+  http_2xx_oauth_client_credentials:
+    prober: http
+    timeout: 5s
+    http:
+      valid_http_versions: ["HTTP/1.1", "HTTP/2"]
+      follow_redirects: true
+      preferred_ip_protocol: "ip4"
+      valid_status_codes:
+        - 200
+        - 201
+      oauth2:
+        client_id: "client_id"
+        client_secret: "client_secret"
+        token_url: "https://api.example.com/token"
+        endpoint_params:
+          grant_type: "client_credentials"
+  http_custom_ca_example:
+    prober: http
+    http:
+      method: GET
+      tls_config:
+        ca_file: "/certs/my_cert.crt"
+  http_gzip:
+    prober: http
+    http:
+      method: GET
+      compression: gzip
+  http_gzip_with_accept_encoding:
+    prober: http
+    http:
+      method: GET
+      compression: gzip
+      headers:
+        Accept-Encoding: gzip
+  tls_connect:
+    prober: tcp
+    timeout: 5s
+    tcp:
+      tls: true
+  tcp_connect_example:
+    prober: tcp
+    timeout: 5s
+  imap_starttls:
+    prober: tcp
+    timeout: 5s
+    tcp:
+      query_response:
+        - expect: "OK.*STARTTLS"
+        - send: ". STARTTLS"
+        - expect: "OK"
+        - starttls: true
+        - send: ". capability"
+        - expect: "CAPABILITY IMAP4rev1"
+  smtp_starttls:
+    prober: tcp
+    timeout: 5s
+    tcp:
+      query_response:
+        - expect: "^220 ([^ ]+) ESMTP (.+)$"
+        - send: "EHLO prober\r"
+        - expect: "^250-STARTTLS"
+        - send: "STARTTLS\r"
+        - expect: "^220"
+        - starttls: true
+        - send: "EHLO prober\r"
+        - expect: "^250-AUTH"
+        - send: "QUIT\r"
+  irc_banner_example:
+    prober: tcp
+    timeout: 5s
+    tcp:
+      query_response:
+        - send: "NICK prober"
+        - send: "USER prober prober prober :prober"
+        - expect: "PING :([^ ]+)"
+          send: "PONG ${1}"
+        - expect: "^:[^ ]+ 001"
   icmp:
     prober: icmp
     timeout: 5s
     icmp:
       preferred_ip_protocol: "ip4"
+  dns_udp_example:
+    prober: dns
+    timeout: 5s
+    dns:
+      query_name: "www.prometheus.io"
+      query_type: "A"
+      valid_rcodes:
+        - NOERROR
+      validate_answer_rrs:
+        fail_if_matches_regexp:
+          - ".*127.0.0.1"
+        fail_if_all_match_regexp:
+          - ".*127.0.0.1"
+        fail_if_not_matches_regexp:
+          - "www.prometheus.io.\t300\tIN\tA\t127.0.0.1"
+        fail_if_none_matches_regexp:
+          - "127.0.0.1"
+      validate_authority_rrs:
+        fail_if_matches_regexp:
+          - ".*127.0.0.1"
+      validate_additional_rrs:
+        fail_if_matches_regexp:
+          - ".*127.0.0.1"
+  dns_soa:
+    prober: dns
+    dns:
+      query_name: "prometheus.io"
+      query_type: "SOA"
+  dns_tcp_example:
+    prober: dns
+    dns:
+      transport_protocol: "tcp" # defaults to "udp"
+      preferred_ip_protocol: "ip4" # defaults to "ip6"
+      query_name: "www.prometheus.io"

m/hut/gpfs-probe.sh

@@ -2,10 +2,20 @@
 
 N=500
 
-t=$(timeout 5 ssh bsc015557@glogin2.bsc.es "timeout 3 command time -f %e touch /gpfs/projects/bsc15/bsc015557/gpfs.{1..$N} 2>&1; rm -f /gpfs/projects/bsc15/bsc015557/gpfs.{1..$N}")
+t_proj=$(timeout 5 ssh bsc015557@glogin2.bsc.es "timeout 3 command time -f %e touch /gpfs/projects/bsc15/bsc015557/gpfs.{1..$N} 2>&1; rm -f /gpfs/projects/bsc15/bsc015557/gpfs.{1..$N}")
+t_scratch=$(timeout 5 ssh bsc015557@glogin2.bsc.es "timeout 3 command time -f %e touch /gpfs/scratch/bsc15/rodrigo/probe/gpfs.{1..$N} 2>&1; rm -f /gpfs/scratch/bsc15/rodrigo/probe/gpfs.{1..$N}")
+t_home=$(timeout 5 ssh bsc015557@glogin2.bsc.es "timeout 3 command time -f %e touch /home/bsc/bsc015557/.gpfs/{1..$N} 2>&1; rm -f /home/bsc/bsc015557/.gpfs/{1..$N}")
 
-if [ -z "$t" ]; then
+if [ -z "$t_proj" ]; then
-  t="5.00"
+  t_proj="5.00"
+fi
+
+if [ -z "$t_scratch" ]; then
+  t_scratch="5.00"
+fi
+
+if [ -z "$t_home" ]; then
+  t_home="5.00"
 fi
 
 cat <<EOF
@@ -14,5 +24,7 @@ Content-Type: text/plain; version=0.0.4; charset=utf-8; escaping=values
 
 # HELP gpfs_touch_latency Time to create $N files.
 # TYPE gpfs_touch_latency gauge
-gpfs_touch_latency $t
+gpfs_touch_latency{partition="projects"} $t_proj
+gpfs_touch_latency{partition="home"} $t_home
+gpfs_touch_latency{partition="scratch"} $t_scratch
 EOF

m/hut/monitoring.nix

@@ -267,6 +267,14 @@
           }
         ];
       }
+      {
+        job_name = "tent";
+        static_configs = [
+          {
+            targets = [ "127.0.0.1:29002" ]; # Node exporter
+          }
+        ];
+      }
     ];
   };
 }

m/hut/targets.yml

@@ -4,7 +4,7 @@
   - xeon03-ipmi
   - xeon04-ipmi
   - koro-ipmi
-  - weasel-ipmi
+  - xeon06-ipmi
   - hut-ipmi
   - eudy-ipmi
   # Storage

m/map.nix

@@ -6,7 +6,7 @@
     switch-opa = { pos=41; size=1; };
 
     # SSF login
-    apex = { pos=39; size=2; label="SSFHEAD"; board="R2208WTTYSR"; contact="rodrigo.arias@bsc.es"; };
+    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"; };
@@ -19,7 +19,7 @@
     xeon03 = { pos=33; size=1; label="SSF-XEON03"; board="S2600WTTR"; sn="BQWL64750826"; contact="rodrigo.arias@bsc.es"; };
     # Slot 34 empty
     koro   = { pos=31; size=1; label="SSF-XEON05"; board="S2600WTTR"; sn="BQWL64954293"; contact="rodrigo.arias@bsc.es"; };
-    weasel = { pos=30; size=1; label="SSF-XEON06"; board="S2600WTTR"; sn="BQWL64750846"; contact="antoni.navarro@bsc.es"; };
+    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"; };
 

m/module/nvidia.nix

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

m/module/power-policy.nix

@@ -1,33 +0,0 @@
-{ config, lib, pkgs, ... }:
-
-with lib;
-
-let
-  cfg = config.power.policy;
-in
-{
-  options = {
-    power.policy = mkOption {
-      type = types.nullOr (types.enum [ "always-on" "previous" "always-off" ]);
-      default = null;
-      description = "Set power policy to use via IPMI.";
-    };
-  };
-
-  config = mkIf (cfg != null) {
-    systemd.services."power-policy" = {
-      description = "Set power policy to use via IPMI";
-      wantedBy = [ "multi-user.target" ];
-      unitConfig = {
-        StartLimitBurst = "10";
-        StartLimitIntervalSec = "10m";
-      };
-      serviceConfig = {
-        ExecStart = "${pkgs.ipmitool}/bin/ipmitool chassis policy ${cfg}";
-        Type = "oneshot";
-        Restart = "on-failure";
-        RestartSec = "5s";
-      };
-    };
-  };
-}

m/module/ssh-hut-extern.nix

@@ -1,8 +1,9 @@
 {
   programs.ssh.extraConfig = ''
-    Host apex ssfhead
+    Host ssfhead
       HostName ssflogin.bsc.es
     Host hut
-      ProxyJump apex
+      ProxyJump ssfhead
+      HostName xeon07
   '';
 }

m/raccoon/configuration.nix

@@ -6,13 +6,9 @@
     ../module/emulation.nix
     ../module/debuginfod.nix
     ../module/ssh-hut-extern.nix
-    ../module/nvidia.nix
-    ../module/power-policy.nix
     ../eudy/kernel/perf.nix
   ];
 
-  power.policy = "always-on";
-
   # Don't install Grub on the disk yet
   boot.loader.grub.device = "nodev";
 
@@ -53,7 +49,15 @@
   # Enable performance governor
   powerManagement.cpuFreqGovernor = "performance";
 
-  hardware.nvidia.open = false; # Maxwell is older than Turing architecture
+  # 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" ];
+
+  # Disable garbage collection for now
+  nix.gc.automatic = lib.mkForce false;
 
   services.openssh.settings.X11Forwarding = true;
 

m/weasel/configuration.nix

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

pkgs/cudainfo/Makefile

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

pkgs/cudainfo/cudainfo.cpp

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

pkgs/cudainfo/default.nix

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

pkgs/mpich-fix-hwtopo.patch

@@ -0,0 +1,36 @@
+diff --git a/src/util/mpir_hwtopo.c b/src/util/mpir_hwtopo.c
+index 33e88bc..ee3641c 100644
+--- a/src/util/mpir_hwtopo.c
++++ b/src/util/mpir_hwtopo.c
+@@ -200,18 +200,6 @@ int MPII_hwtopo_init(void)
+ #ifdef HAVE_HWLOC
+     bindset = hwloc_bitmap_alloc();
+     hwloc_topology_init(&hwloc_topology);
+-    char *xmlfile = MPIR_pmi_get_jobattr("PMI_hwloc_xmlfile");
+-    if (xmlfile != NULL) {
+-        int rc;
+-        rc = hwloc_topology_set_xml(hwloc_topology, xmlfile);
+-        if (rc == 0) {
+-            /* To have hwloc still actually call OS-specific hooks, the
+-             * HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM has to be set to assert that the loaded
+-             * file is really the underlying system. */
+-            hwloc_topology_set_flags(hwloc_topology, HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM);
+-        }
+-        MPL_free(xmlfile);
+-    }
+
+     hwloc_topology_set_io_types_filter(hwloc_topology, HWLOC_TYPE_FILTER_KEEP_ALL);
+     if (!hwloc_topology_load(hwloc_topology)) 
+
+--- a/src/mpi/init/local_proc_attrs.c
++++ b/src/mpi/init/local_proc_attrs.c
+@@ -79,10 +79,6 @@ int MPII_init_local_proc_attrs(int *p_thread_required)
+     /* Set the number of tag bits. The device may override this value. */
+     MPIR_Process.tag_bits = MPIR_TAG_BITS_DEFAULT;
+
+-    char *requested_kinds = MPIR_pmi_get_jobattr("PMI_mpi_memory_alloc_kinds");
+-    MPIR_get_supported_memory_kinds(requested_kinds, &MPIR_Process.memory_alloc_kinds);
+-    MPL_free(requested_kinds);
+-
+     return mpi_errno;
+ }

pkgs/overlay.nix

@@ -11,6 +11,10 @@ final: prev:
       paths = [ pmix.dev pmix.out ];
     };
   in prev.mpich.overrideAttrs (old: {
+    patches = (old.patches or []) ++ [
+      # See https://github.com/pmodels/mpich/issues/6946
+      ./mpich-fix-hwtopo.patch
+    ];
     buildInput = old.buildInputs ++ [
       libfabric
       pmixAll
@@ -52,5 +56,4 @@ 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 { };
-  cudainfo = prev.callPackage ./cudainfo/default.nix { };
 }

secrets/gitea-runner-token.age

@@ -1,11 +1,11 @@
 age-encryption.org/v1
--> ssh-ed25519 HY2yRg d7+nvfAcdC3GjJxipXFrsfGGyP5jAY+gRWRV+4FVYAM
+-> ssh-ed25519 HY2yRg WUMWvyagPalsy7u1RaEFAwJvFowso1/quNBo+nAkxhQ
-CG7r0bRGgnUWcdfDnpe7HwZ3L/y7b5iuJuqvf15b3/Y
+OHcebB7koPKhy58A6qngEVNWckkWChyEK3dwgy8EL5o
--> ssh-ed25519 CAWG4Q X0vITOErz4wkR3VQYOcVlnrkHtwe+ytdZz1Hcrs4vVs
+-> ssh-ed25519 CAWG4Q Yx/HLIryUNE2BaqTl84FrNRy4XLCY2TRkRgbA9k3qU4
-6IWYOhXLQ+BnML9YfLLHJYEO2CZ/uEc9IBqhoWvjDHI
+LZljfuLS5yMVVK6N57iC6cKEaFP6Hh2OkvWJjuFg8q0
--> ssh-ed25519 xA739A p5e/0AJtZ0+zbRvkB/usLuxusY8xXRx9Ksi/LQlcIHw
+-> ssh-ed25519 xA739A DOXjPRttSWz51Sr7KfjgKfAtaIYMo3foB1Ywqw9HYDY
-M4S/qlzT9POyJx4gY9lmycstUcdwG2cinN4OlV22zzo
+CA5puXK/1HDOitA2XHBI3OdKmZ7BzHst4DyuWGMC6hE
--> ssh-ed25519 MSF3dg Ydl7uBWzBx6sAaxbzC3x8qiaU3ysGqV4rUFLpHCEV30
+-> ssh-ed25519 MSF3dg +2LetdIiIZUk7wtHNS1tYsLo4ypwqZ9gpg77RQrnzHU
-/1AUHBhCNOs9i7LJbmzwQDHsu+ybzYf6+coztKk5E3U
+yIUu8BVbF3dhUx3531RR50/cJQd9gd8VfKUQzEeT/iQ
---- kYt15WxClpT7PXD1oFe9GqJU+OswjH7y9wIc8/GzZ7M
+--- oY/wQ+RjZO2CmKZtbQ0yOVZ5fv2+AlvvkRu1UDfCNAA
-<EFBFBD><EFBFBD>h<>ߓ<><EFBFBD><EFBFBD>`<EFBFBD><EFBFBD><EFBFBD>V4F<EFBFBD><EFBFBD>_k)^<5E>m$uj:ѳ<><D1B3><17><><EFBFBD>}<7D>Z]$U]<12>u<EFBFBD> <20>0<EFBFBD><30><EFBFBD>v8<76>?<3F>X<EFBFBD>P<EFBFBD>g%d<>#<23>d9{rAi<EFBFBD><EFBFBD>
+_8`G<>=C7@x&<26><>\Ft<46>)<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>cPe<EFBFBD><EFBFBD>%<25>ֽ[zX-0<>[<11><><EFBFBD>ɲ<><C9B2>tz<74><7A>;%<25><><EFBFBD><EFBFBD><EFBFBD>~<7E>H0<48>؃*XD<58>;<EFBFBD><EFBFBD>

secrets/jungle-robot-password.age

@@ -1,13 +1,13 @@
 age-encryption.org/v1
--> ssh-ed25519 HY2yRg rsbyYULV9S/kz4OzBLQIVfyotgKrzPzvjPNVw69coTo
+-> ssh-ed25519 HY2yRg 0tpCZ5yI339pgPKGh3HJ8cnkhKlMoyYiKR1mo1cvkm0
-i9fgGAYTPxJ4Ulft3xzwNPF8v85Ae9ePMNWp593vSfA
+EVVpJ8nyw/W9B65Tw59IjJC5Pb4uQX5LGnzPcf/hUs0
--> ssh-ed25519 G5LX5w mhB3iiqV2e+tT31FCREX2Bqq2F2g+vTYvjCuyGSeJxs
+-> ssh-ed25519 G5LX5w YaDAKeAAunommW6q6+hTjrjaadmB17OG89t1Dx/T5z4
-Ep9zZykCGFW841S2mnllEi0oPnRiRuYIGtv6ckp+IBg
+tJXdciiBTz9V+0nf1sGAk4vSlOgfeEgrKr+oDJ/4ays
--> ssh-ed25519 CAWG4Q M0AJEZuiC6FnRy8rAJQ9T9dCXfIfLXGk0uBGhYOxRSg
+-> ssh-ed25519 CAWG4Q i/cpMcOaZpH7aqwsR/fZiVL9CreL9dkk5F5S9dXrQBY
-5jSRNTi0c6we/oLBdUy1am5saH/5Nh1fmVqYajXFbGc
+uU8G51pMH00ywaIVY+AzjpiqzanUYpn9ANRabugSXbE
--> ssh-ed25519 xA739A Zf9tUKg4S4UuWMGEtAWVg0pa6vTzKIl2Ty39IjEG2mE
+-> ssh-ed25519 xA739A DTiXqnCz1zNgyLt8VvnOkVLDwfa0qJpUBQw9Ms/qHHA
-RCSkVFyO2ZuDlAHung9bTeM91aTXxNRJ779kE0C6pK4
+wKjSYYOUEJkPisxT6MNW1eoYk++ECrs1ib9uEYXsAQY
--> ssh-ed25519 MSF3dg QLiG9s3mgfO6HnQ8/ReizkGllsjYebIL5ZthSVcD7Ao
+-> ssh-ed25519 MSF3dg JmvJsExWPW4b6RT62mz4Wscx7EsyDPVf91A9ps9+shM
-YdzcodBarrdg6R96Ys01aEPoeYygbT56yz90BMFfr0U
+67jZYnxJpQAhnRWnTOXs+Cu445dRCpDzIGGp1xYuF3s
---- fS/rGOP3IGG8b3bCDy26nBL0P1rtqC70CmKOGDsg8Tw
+--- QmdvzR7QqRPxS1fHc8rR/PDZxN8u+BVKAVvE8cMLhqc
-;Y<><59>M<EFBFBD>_<EFBFBD><5F><EFBFBD>Zꙺ:<3A>]Ez89z
e<><65><EFBFBD>	<09><>D
<01>X<EFBFBD><19><><EFBFBD><EFBFBD><EFBFBD><EFBFBD>9{<7B>x^<5E><><EFBFBD>L<>l<EFBFBD><6C><EFBFBD><0B>㦑9R<39>VhWs
+<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

@@ -1,14 +1,13 @@
 age-encryption.org/v1
--> ssh-ed25519 HY2yRg tdVrzL3EryCEDJSiAjHfr3AC6rhyKLLe9ZaKKa/fyEk
+-> ssh-ed25519 HY2yRg T/Qom1qxE0M+FuvsXD/KZ6Usfp6v3Xwx043kDgxbCz4
-kIbJjp/odUkQ9E2fXpk4zratLieyMNdNLHYGQt8+860
+6GRg0QjuHd2+d6lJfZqqPMPMjS91HEcJ/W0KRV6Et50
--> ssh-ed25519 G5LX5w A0wBDwowrQyByfinVVrypH5VyvyKk3O3O8+2JnVgcCI
+-> ssh-ed25519 G5LX5w pzg0wK+Q6KZP67CkyZNYbNcahlq9SIuFN18H85ARykU
-kLiXfQkC+8QycLyyM/6dAKEE6SGxSZJS7PuOTQr10XE
+aDSrO49tg/a3GOAJR96lh803bXoZqp/G6VMiSvf91vw
--> ssh-ed25519 CAWG4Q HkbFgDtrbuv+KCwULZppiy88ZHl3kHcdlTVTOfMKTzM
+-> ssh-ed25519 CAWG4Q X+F/6LF8VUUoV72iCLzKKpYGRDoUHuBy1E+yr29RKEo
-KMGdQl8Gl51gUp1bxEa41a0VBBiHWD81/9C75NX/pzA
+c779vpt/fiN7n0kGAc5jA9fWkzCPrthlNZdN4p6csrk
--> ssh-ed25519 xA739A XfYFE5jPFvcoTMXtwJgs3+HPLQxRmvz1W7yqE7jSYGE
+-> ssh-ed25519 xA739A sbg087VKj/gcycV9JrBNCoCfB4kRMDSVo3EtfpRVDyg
-497iDMqiIx1u+cBu8KZDNF2SPpGCrVqjGdUPD8kEjE4
+Lv5ges1KmxGwvz4UPZCD0v4YN2ms2Q3wmrJ14XCKYsQ
--> ssh-ed25519 MSF3dg Vbxxsmfoywpi4W9WUMzgay3Nd1UBigliYHD7Wew9AHM
+-> ssh-ed25519 MSF3dg pCLeyeWYbnNWQwwlGcsKz0KZ4BaaYKCGjo0XOPpo+no
-aLt5GN8jJWbbrHfs1321tQz44lBaATe0BipT/EGc80I
+IsNxFoB2nTxyThJxtAxSA6gauXHGQJnVefs/K2MZ+DM
---- JHESkz0eGNPo3ZEGALVH4xsQ4p1O/6ShlfOw58fjH1k
+--- 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>
-<EFBFBD>AwN<EFBFBD>g<EFBFBD><EFBFBD><EFBFBD><EFBFBD>C<EFBFBD><EFBFBD><EFBFBD>Ԣְ7<EFBFBD>	ǟ4#0<><30><EFBFBD>ss<73><73><EFBFBD>-*<2A><19>$Z<><5A><EFBFBD><EFBFBD><EFBFBD>[*<2A><>
ia<69>{<7B>?=<3D><08><>v-E<EE9495>7<EFBFBD><37><10>0<EFBFBD><30>]<5D><>q0<71>)q"K<><4B><EFBFBD>{BZs<7F><73><EFBFBD><EFBFBD>*<2A>l<EFBFBD><6C>9-E+<02><>8<(<28><><EFBFBD>a*$dN<64><4E>xd

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

@@ -1,12 +1,13 @@
 age-encryption.org/v1
--> ssh-ed25519 G5LX5w 5K0mzfJGvAB2LGmoQ9ZLbWooVEX6F4+fQdo1JUoB3FM
+-> ssh-ed25519 G5LX5w V9bHLoGuY4stRwbzVS9Qa0L9yoY+UoCoXc+dJJQW/Ag
-AKGa507bUrYjXFaMQ1MXTDBFYsdS6zbs+flmxYN0UNo
+2ut9GfdJ3KBCqZRaloZCQsl8MLfaZAZxqj6JtPJzu2k
--> ssh-ed25519 CAWG4Q 8KzLc949on8iN1pK8q11OpCIeO71t6b0zxCLHhcQ6ns
+-> ssh-ed25519 CAWG4Q OAqnIfMECpKglZ7aF9tv/PQinG1Ou2+IEZ+nf4dtQjg
-uy7z6RdIuoUes+Uap3k5eoFFuu/DcSrEBwq4V4C/ygc
+dANdMLe4iI0d6Xd/dIMpZK+mgw2+VmJFQScHaIxD7WI
--> ssh-ed25519 xA739A SLx5cKo0fdAHj+cLpJ4FYTWTUTyDsCqKQOufDu3xnGo
+-> ssh-ed25519 xA739A nVNF4Y6VSa5PP6FFBJpVmoFYYseoFx5F2wJU+Pwk+Xk
-VnS/WsiSaf6RpXuhgfij4pYu4p9hlJl1oXrfYY9rKlQ
+A5CiuTSNlX9Y76qhYgblBdJl3zPhtjWho2oL5/sIKu0
--> ssh-ed25519 MSF3dg c5ZXvdNxNfZU3HeWsttuhy+UC5JxWN/IFuCuCGbksn4
+-> ssh-ed25519 MSF3dg /WMsGnBGzquIMyw06gHKpSS4OUxheulT59kxi+/pxxU
-vcKlIirf+VvERX71YpmwW6zp6ClhlG2PR4R8LIN7cQo
+ppwcv7RLzUbQUM7j0Tb9rRVT9XyPMhqYr2fr4S0nTJY
---- pJKICDaYAlxqNnvHIuzB3Yk7tv0ZNYflGTQD+Zk/8+4
+--- zOe0Ko0oxArbmxePMPDVAT0pDju7IeOAih7sNrDcoVs
-<EFBFBD>h/\J<>J
+i<EFBFBD>k<EFBFBD>A
-<EFBFBD>0?<3F> <20>p<EFBFBD><70><EFBFBD>@܉7<DC89><37>3<EFBFBD><33><EFBFBD><EFBFBD>z<EFBFBD><7A><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>a<EFBFBD><61>'<27>,ka<6B>I<EFBFBD>XXOZ<4F>I\<5C><><EFBFBD><EFBFBD><EFBFBD>	<09>BP<42><50>/cUɿ~B<><42>S'Q<><51><EFBFBD><EFBFBD>f<06><><EFBFBD>er<65><72><EFBFBD><EFBFBD>^<5E><><EFBFBD><EFBFBD>8l<38><6C>V<EFBFBD>E<EFBFBD><45><EFBFBD>
+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-<EFBFBD>
+A<1B>nԔί<1B>>Z<><5A>z<EFBFBD><7A><EFBFBD>dT<64><54>b"<22>(@<40><>{_ځC