Monitor fox and gateway via ICMP

Fox should reply once the machine is connected to the UPC network.
Monitoring also the gateway allows us to estimate if the whole network
is down or just fox.

flake.nix

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

m/bay/configuration.nix

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

m/common/base/ssh.nix

@@ -8,6 +8,17 @@ in
   # Enable the OpenSSH daemon.
   services.openssh.enable = true;
 
+  # Connect to intranet git hosts via proxy
+  programs.ssh.extraConfig = ''
+    Host bscpm02.bsc.es bscpm03.bsc.es bscpm04.bsc.es gitlab-internal.bsc.es alya.gitlab.bsc.es
+      User git
+      ProxyCommand nc -X connect -x hut:23080 %h %p
+
+    # Connect to BSC machines via hut proxy too
+    Host amdlogin1.bsc.es armlogin1.bsc.es hualogin1.bsc.es glogin1.bsc.es glogin2.bsc.es fpgalogin1.bsc.es
+      ProxyCommand nc -X connect -x hut:23080 %h %p
+  '';
+
   programs.ssh.knownHosts = hostsKeys // {
     "gitlab-internal.bsc.es".publicKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIF9arsAOSRB06hdy71oTvJHG2Mg8zfebADxpvc37lZo3";
     "bscpm03.bsc.es".publicKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIM2NuSUPsEhqz1j5b4Gqd+MWFnRqyqY57+xMvBUqHYUS";

m/common/base/users.nix

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

m/common/ssf.nix

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

m/common/ssf/ssh.nix

@@ -1,8 +0,0 @@
-{
-  # Connect to intranet git hosts via proxy
-  programs.ssh.extraConfig = ''
-    # Connect to BSC machines via hut proxy too
-    Host amdlogin1.bsc.es armlogin1.bsc.es hualogin1.bsc.es glogin1.bsc.es glogin2.bsc.es fpgalogin1.bsc.es
-      ProxyCommand nc -X connect -x hut:23080 %h %p
-  '';
-}

m/common/xeon.nix

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

m/common/xeon/net.nix

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

m/eudy/configuration.nix

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

m/fox/configuration.nix

@@ -41,8 +41,12 @@
       }
     ];
     extraHosts = ''
+      # Fox UPC
       147.83.30.141   fox.ac.upc.edu
       147.83.35.27    fox-ipmi.ac.upc.edu
+      # Fox BSC
+      10.0.40.26      fox
+      10.0.40.126     fox-ipmi
     '';
   };
 

m/hut/configuration.nix

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

m/hut/monitoring.nix

@@ -169,7 +169,6 @@
             "8.8.8.8"
             "ssfhead"
             "anella-bsc.cesca.cat"
-            "upc-anella.cesca.cat"
             "fox.ac.upc.edu"
             "arenys5.ac.upc.edu"
           ];
@@ -267,6 +266,17 @@
           }
         ];
       }
+      {
+        job_name = "ipmi-fox";
+        metrics_path = "/ipmi";
+        static_configs = [
+          { targets = [ "127.0.0.1:9290" ]; }
+        ];
+        params = {
+          target = [ "fox-ipmi" ];
+          module = [ "fox" ];
+        };
+      }
     ];
   };
 }

m/koro/configuration.nix

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

m/lake2/configuration.nix

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

m/map.nix

@@ -1,70 +0,0 @@
-{
-  # In physical order from top to bottom (see note below)
-  ssf = {
-    # Switches for Ethernet and OmniPath
-    switch-C6-S1A-05 = { pos=42; size=1; model="Dell S3048-ON"; };
-    switch-opa = { pos=41; size=1; };
-
-    # SSF login
-    ssfhead = { pos=39; size=2; label="SSFHEAD"; board="R2208WTTYSR"; contact="operations@bsc.es"; };
-
-    # Storage
-    bay   = { pos=38; size=1; label="MDS01"; board="S2600WT2R"; sn="BQWL64850303"; contact="rodrigo.arias@bsc.es"; };
-    lake1 = { pos=37; size=1; label="OSS01"; board="S2600WT2R"; sn="BQWL64850234"; contact="rodrigo.arias@bsc.es"; };
-    lake2 = { pos=36; size=1; label="OSS02"; board="S2600WT2R"; sn="BQWL64850266"; contact="rodrigo.arias@bsc.es"; };
-
-    # Compute xeon
-    owl1   = { pos=35; size=1; label="SSF-XEON01"; board="S2600WTTR"; sn="BQWL64954172"; contact="rodrigo.arias@bsc.es"; };
-    owl2   = { pos=34; size=1; label="SSF-XEON02"; board="S2600WTTR"; sn="BQWL64756560"; contact="rodrigo.arias@bsc.es"; };
-    xeon03 = { pos=33; size=1; label="SSF-XEON03"; board="S2600WTTR"; sn="BQWL64750826"; contact="rodrigo.arias@bsc.es"; };
-    # Slot 34 empty
-    koro   = { pos=31; size=1; label="SSF-XEON05"; board="S2600WTTR"; sn="BQWL64954293"; contact="rodrigo.arias@bsc.es"; };
-    xeon06 = { pos=30; size=1; label="SSF-XEON06"; board="S2600WTTR"; sn="BQWL64750846"; contact="antoni.navarro@bsc.es"; };
-    hut    = { pos=29; size=1; label="SSF-XEON07"; board="S2600WTTR"; sn="BQWL64751184"; contact="rodrigo.arias@bsc.es"; };
-    eudy   = { pos=28; size=1; label="SSF-XEON08"; board="S2600WTTR"; sn="BQWL64756586"; contact="aleix.rocanonell@bsc.es"; };
-
-    # 16 KNL nodes, 4 per chassis
-    knl01_04 = { pos=26; size=2; label="KNL01..KNL04"; board="HNS7200APX"; };
-    knl05_08 = { pos=24; size=2; label="KNL05..KNL18"; board="HNS7200APX"; };
-    knl09_12 = { pos=22; size=2; label="KNL09..KNL12"; board="HNS7200APX"; };
-    knl13_16 = { pos=20; size=2; label="KNL13..KNL16"; board="HNS7200APX"; };
-
-    # Slot 19 empty
-
-    # EPI (hw team, guessed order)
-    epi01 = { pos=18; size=1; contact="joan.cabre@bsc.es"; };
-    epi02 = { pos=17; size=1; contact="joan.cabre@bsc.es"; };
-    epi03 = { pos=16; size=1; contact="joan.cabre@bsc.es"; };
-    anon  = { pos=14; size=2; }; # Unlabeled machine. Operative
-
-    # These are old and decommissioned (off)
-    power8    = { pos=12; size=2; label="BSCPOWER8N3";   decommissioned=true; };
-    powern1   = { pos=8;  size=4; label="BSCPOWERN1";    decommissioned=true; };
-    gustafson = { pos=7;  size=1; label="gustafson";     decommissioned=true; };
-    odap01    = { pos=3;  size=4; label="ODAP01";        decommissioned=true; };
-    amhdal    = { pos=2;  size=1; label="AMHDAL";        decommissioned=true; }; # sic
-    moore     = { pos=1;  size=1; label="moore (earth)"; decommissioned=true; };
-  };
-
-  bsc2218 = {
-    raccoon = { board="W2600CR"; sn="QSIP22500829"; contact="rodrigo.arias@bsc.es"; };
-    tent    = { label="SSF-XEON04"; board="S2600WTTR"; sn="BQWL64751229"; contact="rodrigo.arias@bsc.es"; };
-  };
-
-  upc = {
-    fox = { board="H13DSG-O-CPU"; sn="UM24CS600392"; prod="AS-4125GS-TNRT"; prod_sn="E508839X5103339"; contact="rodrigo.arias@bsc.es"; };
-  };
-
-  # NOTE: Position is specified in "U" units (44.45 mm) and starts at 1 from the
-  # bottom. Example:
-  #
-  #  |   ...  | - [pos+size] <--- Label in chassis
-  #  +--------+
-  #  |  node  | - [pos+1]
-  #  |   2U   | - [pos]
-  #  +------- +
-  #  |   ...  | - [pos-1]
-  #
-  # NOTE: The board and sn refers to the FRU information (Board Product and
-  # Board Serial) via `ipmitool fru print 0`.
-}

m/module/ssh-hut-extern.nix

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

m/owl1/configuration.nix

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

m/owl2/configuration.nix

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

m/raccoon/configuration.nix

@@ -3,10 +3,6 @@
 {
   imports = [
     ../common/base.nix
-    ../module/emulation.nix
-    ../module/debuginfod.nix
-    ../module/ssh-hut-extern.nix
-    ../eudy/kernel/perf.nix
   ];
 
   # Don't install Grub on the disk yet
@@ -27,18 +23,6 @@
       address = "84.88.51.152";
       prefixLength = 25;
     } ];
-    interfaces.enp5s0f1.ipv4.addresses = [ {
-      address = "10.0.44.1";
-      prefixLength = 24;
-    } ];
-    nat = {
-      enable = true;
-      internalInterfaces = [ "enp5s0f1" ];
-      externalInterface = "eno0";
-    };
-    hosts = {
-      "10.0.44.4" = [ "tent" ];
-    };
   };
 
   nix.settings = {
@@ -46,9 +30,6 @@
     trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
   };
 
-  # Enable performance governor
-  powerManagement.cpuFreqGovernor = "performance";
-
   # Configure Nvidia driver to use with CUDA
   hardware.nvidia.package = config.boot.kernelPackages.nvidiaPackages.production;
   hardware.graphics.enable = true;
@@ -56,18 +37,6 @@
   nixpkgs.config.nvidia.acceptLicense = true;
   services.xserver.videoDrivers = [ "nvidia" ];
 
-  # Disable garbage collection for now
-  nix.gc.automatic = lib.mkForce false;
-
-  services.openssh.settings.X11Forwarding = true;
-
-  services.prometheus.exporters.node = {
-    enable = true;
-    enabledCollectors = [ "systemd" ];
-    port = 9002;
-    listenAddress = "127.0.0.1";
-  };
-
   users.motd = ''
     ⠀⠀⠀⠀⠀⠀⠀⣀⣀⣄⣠⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
     ⠀⠀⠀⠀⠀⠀⢰⠇⡀⠀⠙⠻⡿⣦⣀⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⡀⠀⠀⠀⠀

m/tent/configuration.nix

@@ -1,45 +0,0 @@
-{ config, pkgs, ... }:
-
-{
-  imports = [
-    ../common/xeon.nix
-    ../module/emulation.nix
-    ../module/debuginfod.nix
-    ../module/ssh-hut-extern.nix
-  ];
-
-  # Select the this using the ID to avoid mismatches
-  boot.loader.grub.device = "/dev/disk/by-id/wwn-0x55cd2e414d537675";
-
-  networking = {
-    hostName = "tent";
-    interfaces.eno1.ipv4.addresses = [
-      {
-        address = "10.0.44.4";
-        prefixLength = 24;
-      }
-    ];
-
-    # Only BSC DNSs seem to be reachable from the office VLAN
-    nameservers = [ "84.88.52.35" "84.88.52.36" ];
-    defaultGateway = "10.0.44.1";
-  };
-
-  nix.settings = {
-    substituters = [ "https://jungle.bsc.es/cache" ];
-    trusted-public-keys = [ "jungle.bsc.es:pEc7MlAT0HEwLQYPtpkPLwRsGf80ZI26aj29zMw/HH0=" ];
-  };
-
-  services.prometheus.exporters.node = {
-    enable = true;
-    enabledCollectors = [ "systemd" ];
-    port = 9002;
-    listenAddress = "127.0.0.1";
-  };
-
-  programs.ssh.extraConfig = ''
-    Host hut
-      ProxyJump ssfhead
-      HostName xeon07
-  '';
-}