Remove extra flush commands on firewall stop

They are not needed as they are already flushed when the firewall starts or stops.
Prevent accidental use of nftables
2025-07-11 16:13:35 +02:00 · 2025-07-11 16:12:44 +02:00 · 2025-07-11 16:06:38 +02:00 · 2025-07-11 11:34:54 +02:00 · 2025-07-11 11:34:50 +02:00 · 2025-07-11 11:10:07 +02:00
23 changed files with 98 additions and 821 deletions
--- a/flake.lock
+++ b/flake.lock
@@ -10,11 +10,11 @@
        "systems": "systems"
      },
      "locked": {
-        "lastModified": 1750173260,
-        "narHash": "sha256-9P1FziAwl5+3edkfFcr5HeGtQUtrSdk/MksX39GieoA=",
+        "lastModified": 1723293904,
+        "narHash": "sha256-b+uqzj+Wa6xgMS9aNbX4I+sXeb5biPDi39VgvSFqFvU=",
        "owner": "ryantm",
        "repo": "agenix",
-        "rev": "531beac616433bac6f9e2a19feb8e99a22a66baf",
+        "rev": "f6291c5935fdc4e0bef208cfc0dcab7e3f7a1c41",
        "type": "github"
      },
      "original": {
@@ -30,11 +30,11 @@
        ]
      },
      "locked": {
-        "lastModified": 1749650500,
-        "narHash": "sha256-2MHfVPV6RA7qPSCtXh4+KK0F0UjN+J4z8//+n6NK7Xs=",
+        "lastModified": 1732868163,
+        "narHash": "sha256-qck4h298AgcNI6BnGhEwl26MTLXjumuJVr+9kak7uPo=",
        "ref": "refs/heads/master",
-        "rev": "9d1944c658929b6f98b3f3803fead4d1b91c4405",
-        "revCount": 961,
+        "rev": "6782fc6c5b5a29e84a7f2c2d1064f4bcb1288c0f",
+        "revCount": 952,
        "type": "git",
        "url": "https://git.sr.ht/~rodarima/bscpkgs"
      },
@@ -51,11 +51,11 @@
        ]
      },
      "locked": {
-        "lastModified": 1744478979,
-        "narHash": "sha256-dyN+teG9G82G+m+PX/aSAagkC+vUv0SgUw3XkPhQodQ=",
+        "lastModified": 1700795494,
+        "narHash": "sha256-gzGLZSiOhf155FW7262kdHo2YDeugp3VuIFb4/GGng0=",
        "owner": "lnl7",
        "repo": "nix-darwin",
-        "rev": "43975d782b418ebf4969e9ccba82466728c2851b",
+        "rev": "4b9b83d5a92e8c1fbfd8eb27eda375908c11ec4d",
        "type": "github"
      },
      "original": {
@@ -73,11 +73,11 @@
        ]
      },
      "locked": {
-        "lastModified": 1745494811,
-        "narHash": "sha256-YZCh2o9Ua1n9uCvrvi5pRxtuVNml8X2a03qIFfRKpFs=",
+        "lastModified": 1703113217,
+        "narHash": "sha256-7ulcXOk63TIT2lVDSExj7XzFx09LpdSAPtvgtM7yQPE=",
        "owner": "nix-community",
        "repo": "home-manager",
-        "rev": "abfad3d2958c9e6300a883bd443512c55dfeb1be",
+        "rev": "3bfaacf46133c037bb356193bd2f1765d9dc82c1",
        "type": "github"
      },
      "original": {
@@ -88,16 +88,16 @@
    },
    "nixpkgs": {
      "locked": {
-        "lastModified": 1752436162,
-        "narHash": "sha256-Kt1UIPi7kZqkSc5HVj6UY5YLHHEzPBkgpNUByuyxtlw=",
+        "lastModified": 1736867362,
+        "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"
      }
--- a/flake.nix
+++ b/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";
@@ -28,7 +28,6 @@ in
      raccoon = mkConf "raccoon";
      fox     = mkConf "fox";
      apex    = mkConf "apex";
-      weasel  = mkConf "weasel";
    };

    packages.x86_64-linux = self.nixosConfigurations.hut.pkgs // {
--- a/keys.nix
+++ b/keys.nix
@@ -2,23 +2,22 @@
 # here all the public keys
 rec {
  hosts = {
-    hut    = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICO7jIp6JRnRWTMDsTB/aiaICJCl4x8qmKMPSs4lCqP1 hut";
-    owl1   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIMqMEXO0ApVsBA6yjmb0xP2kWyoPDIWxBB0Q3+QbHVhv owl1";
-    owl2   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHurEYpQzNHqWYF6B9Pd7W8UPgF3BxEg0BvSbsA7BAdK owl2";
-    eudy   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIL+WYPRRvZupqLAG0USKmd/juEPmisyyJaP8hAgYwXsG eudy";
-    koro   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIImiTFDbxyUYPumvm8C4mEnHfuvtBY1H8undtd6oDd67 koro";
-    bay    = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICvGBzpRQKuQYHdlUQeAk6jmdbkrhmdLwTBqf3el7IgU bay";
-    lake2  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINo66//S1yatpQHE/BuYD/Gfq64TY7ZN5XOGXmNchiO0 lake2";
-    fox    = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIDwItIk5uOJcQEVPoy/CVGRzfmE1ojrdDcI06FrU4NFT fox";
-    tent   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFAtTpHtdYoelbknD/IcfBlThwLKJv/dSmylOgpg3FRM tent";
-    apex   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIBvUFjSfoxXnKwXhEFXx5ckRKJ0oewJ82mRitSMNMKjh apex";
-    weasel = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFLJrQ8BF6KcweQV8pLkSbFT+tbDxSG9qxrdQE65zJZp weasel";
+    hut   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICO7jIp6JRnRWTMDsTB/aiaICJCl4x8qmKMPSs4lCqP1 hut";
+    owl1  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIMqMEXO0ApVsBA6yjmb0xP2kWyoPDIWxBB0Q3+QbHVhv owl1";
+    owl2  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHurEYpQzNHqWYF6B9Pd7W8UPgF3BxEg0BvSbsA7BAdK owl2";
+    eudy  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIL+WYPRRvZupqLAG0USKmd/juEPmisyyJaP8hAgYwXsG eudy";
+    koro  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIImiTFDbxyUYPumvm8C4mEnHfuvtBY1H8undtd6oDd67 koro";
+    bay   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICvGBzpRQKuQYHdlUQeAk6jmdbkrhmdLwTBqf3el7IgU bay";
+    lake2 = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINo66//S1yatpQHE/BuYD/Gfq64TY7ZN5XOGXmNchiO0 lake2";
+    fox   = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIDwItIk5uOJcQEVPoy/CVGRzfmE1ojrdDcI06FrU4NFT fox";
+    tent  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFAtTpHtdYoelbknD/IcfBlThwLKJv/dSmylOgpg3FRM tent";
+    apex  = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIBvUFjSfoxXnKwXhEFXx5ckRKJ0oewJ82mRitSMNMKjh apex";
  };

  hostGroup = with hosts; rec {
    untrusted  = [ fox ];
    compute    = [ owl1 owl2 ];
-    playground = [ eudy koro weasel ];
+    playground = [ eudy koro ];
    storage    = [ bay lake2 ];
    monitor    = [ hut ];
    login      = [ apex ];
--- a/m/apex/configuration.nix
+++ b/m/apex/configuration.nix
@@ -5,12 +5,9 @@
    ../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";

@@ -64,20 +61,8 @@
    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" ];
--- a/m/common/base.nix
+++ b/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
--- a/m/common/base/august-shutdown.nix
+++ b/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";
    };
--- a/m/common/base/env.nix
+++ b/m/common/base/env.nix
@@ -3,7 +3,7 @@
 {
  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
    # From bsckgs overlay
    osumb
--- a/m/common/base/power-policy.nix
+++ b/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";
-}
--- a/m/common/base/users.nix
+++ b/m/common/base/users.nix
@@ -69,10 +69,10 @@
        home = "/home/Computational/anavarro";
        description = "Antoni Navarro";
        group = "Computational";
-        hosts = [ "apex" "hut" "tent" "raccoon" "fox" "weasel" ];
-        hashedPassword = "$6$EgturvVYXlKgP43g$gTN78LLHIhaF8hsrCXD.O6mKnZSASWSJmCyndTX8QBWT6wTlUhcWVAKz65lFJPXjlJA4u7G1ydYQ0GG6Wk07b1";
+        hosts = [ "apex" "hut" "tent" "raccoon" "fox" ];
+        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 = [ "apex" "owl1" "owl2" "hut" "tent" "raccoon" "fox" ];
        hashedPassword = "$6$V1EQWJr474whv7XJ$OfJ0wueM2l.dgiJiiah0Tip9ITcJ7S7qDvtSycsiQ43QBFyP4lU0e0HaXWps85nqB4TypttYR4hNLoz3bz662/";
        openssh.authorizedKeys.keys = [
          "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIIFiqXqt88VuUfyANkZyLJNiuroIITaGlOOTMhVDKjf abonerib@bsc"
--- a/m/common/ssf/hosts.nix
+++ b/m/common/ssf/hosts.nix
@@ -16,7 +16,7 @@
    "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" ];
+    "10.0.40.6" = [ "xeon06" ]; "10.0.42.6" = [ "xeon06-ib" ]; "10.0.40.106" = [ "xeon06-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" ];
  };
--- a/m/fox/configuration.nix
+++ b/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
-  hardware.nvidia.open = true;
+  # Configure Nvidia driver to use with CUDA
+  hardware.nvidia.package = config.boot.kernelPackages.nvidiaPackages.production;
+  hardware.graphics.enable = true;
+  nixpkgs.config.allowUnfree = true;
+  nixpkgs.config.nvidia.acceptLicense = true;
+  services.xserver.videoDrivers = [ "nvidia" ];

  # Mount NVME disks
  fileSystems."/nvme0" = { device = "/dev/disk/by-label/nvme0"; fsType = "ext4"; };
--- a/m/hut/targets.yml
+++ b/m/hut/targets.yml
@@ -4,7 +4,7 @@
  - xeon03-ipmi
  - xeon04-ipmi
  - koro-ipmi
-  - weasel-ipmi
+  - xeon06-ipmi
  - hut-ipmi
  - eudy-ipmi
  # Storage
--- a/m/map.nix
+++ b/m/map.nix
@@ -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"; };

--- a/m/module/nvidia.nix
+++ b/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 ];
-}
--- a/m/module/power-policy.nix
+++ b/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";
-      };
-    };
-  };
-}
--- a/m/module/ssh-hut-extern.nix
+++ b/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
  '';
 }
--- a/m/raccoon/configuration.nix
+++ b/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;

--- a/m/weasel/configuration.nix
+++ b/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;
-    } ];
-  };
-}
--- a/pkgs/cudainfo/Makefile
+++ b/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
--- a/pkgs/cudainfo/cudainfo.cpp
+++ b/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;
-}
--- a/pkgs/cudainfo/default.nix
+++ b/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";
-  };
-})
--- a/pkgs/mpich-fix-hwtopo.patch
+++ b/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;
+ }
--- a/pkgs/overlay.nix
+++ b/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 { };
 }
Author	SHA1	Message	Date
Rodrigo Arias Mallo	4e9be9a8d3	Remove extra flush commands on firewall stop They are not needed as they are already flushed when the firewall starts or stops.	2025-07-11 16:13:35 +02:00
Rodrigo Arias Mallo	afe2c4d7b1	Prevent accidental use of nftables	2025-07-11 16:12:44 +02:00
Rodrigo Arias Mallo	41cb22131f	Add proxy configuration for internal hosts Access internal hosts via apex proxy. From the compute nodes we first open an SSH connection to apex, and then tunnel it through the HTTP proxy with netcat. This way we allow reaching internal GitLab repositories without requiring the user to have credentials in the remote host, while we can use multiple remotes to provide redundancy.	2025-07-11 16:06:38 +02:00
Rodrigo Arias Mallo	730748c8da	Remove unused blackbox configuration modules	2025-07-11 11:34:54 +02:00
Rodrigo Arias Mallo	9ec0e872b3	Use IPv4 in blackbox probes Otherwise they simply fail as IPv6 doesn't work.	2025-07-11 11:34:50 +02:00
Rodrigo Arias Mallo	5956e37661	Make NFS mount async to improve latency Don't wait to flush writes, as we don't care about consistency on a crash: > This option allows the NFS server to violate the NFS protocol and > reply to requests before any changes made by that request have been > committed to stable storage (e.g. disc drive). > > Using this option usually improves performance, but at the cost that > an unclean server restart (i.e. a crash) can cause data to be lost or > corrupted.	2025-07-11 11:10:07 +02:00
Rodrigo Arias Mallo	3df9a41e8f	Disable root_squash from NFS Allows root to read files in the NFS export, so we can directly run `nixos-rebuild switch` from /home.	2025-07-11 10:42:42 +02:00
Rodrigo Arias Mallo	6947ccb853	Remove SSH proxy to access BSC clusters We now have direct connection to them.	2025-07-11 10:22:04 +02:00
Rodrigo Arias Mallo	58a64f64e0	Add users to apex machine They need to be able to login to apex to access any other machine from the SSF rack.	2025-07-10 13:09:41 +02:00
Rodrigo Arias Mallo	676329978b	Remove proxy from hut HTTP probes	2025-07-10 13:09:41 +02:00
Rodrigo Arias Mallo	1268ebd81a	Remove proxy configuration from environment All machines have now direct connection with the outside world.	2025-07-10 13:09:41 +02:00
Rodrigo Arias Mallo	6093e83393	Add storcli utility to apex	2025-07-10 13:09:41 +02:00
Rodrigo Arias Mallo	bf972f6ae8	Add new configuration for apex	2025-07-10 13:09:34 +02:00