ofborg: enable nginx for certs

Flake lock file updates:

• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/e2f08f4d8b3ecb5cf5c9fd9cb2d53bb3c71807da' (2024-10-05)
  → 'github:NixOS/nixpkgs/7ffd9ae656aec493492b44d0ddfb28e79a1ea25d' (2024-11-02)

.envrc

@@ -1,2 +1,11 @@
+#!/usr/bin/env bash
+# the shebang is ignored, but nice for editors
+
 # shellcheck shell=bash
-use flake
+if type -P lorri &>/dev/null; then
+  eval "$(lorri direnv --flake .)"
+else
+  echo 'while direnv evaluated .envrc, could not find the command "lorri" [https://github.com/nix-community/lorri]'
+  use flake
+fi
+

common/admins.nix

@@ -19,12 +19,14 @@ in
       "thubrecht"
       "winter"
       "yuka"
+      "ckie"
     ];
 
     lix-infra.members = [
       "raito"
       "hexchen"
       "jade"
+      "pennae"
     ];
   };
   bagel.users = genAttrs [
@@ -39,5 +41,7 @@ in
     "thubrecht"
     "winter"
     "yuka"
+    "ckie"
+    "pennae"
   ] (name: {});
 }

common/base-server.nix

@@ -7,6 +7,7 @@
   nixpkgs.overlays = import ../overlays;
 
   nix.package = lib.mkDefault pkgs.lix;
+  system.tools.nixos-option.enable = false;
   services.openssh.enable = lib.mkForce true;
 
   networking.nftables.enable = true;

common/ssh-keys.nix

@@ -61,7 +61,12 @@
       "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKiXXYkhRh+s7ixZ8rvG8ntIqd6FELQ9hh7HoaHQJRPU"
     ];
     thubrecht = [ "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPM1jpXR7BWQa7Sed7ii3SbvIPRRlKb3G91qC0vOwfJn" ];
-    yuka = [ "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKath4/fDnlv/4fzxkPrQN1ttmoPRNu/m9bEtdPJBDfY cardno:16_933_242" ];
+    yuka = [ "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIxQ3NYBi8v1f/vhxLKDcA6upmX0pctRDbnK6SER5OUR yureka" ];
     winter = [ "sk-ssh-ed25519@openssh.com AAAAGnNrLXNzaC1lZDI1NTE5QG9wZW5zc2guY29tAAAAIH/LDRUG+U+++UmlxvA2kspioTjktQZ8taDcHq8gVlkfAAAABHNzaDo=" ];
+    ckie = [ "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIH3uTwzSSMAPg84fwbNp2cq9+BdLFeA1VzDGth4zCAbz https://mei.puppycat.house" ];
+    pennae = [
+      "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIC5Wf5/IbyFpdziWfwxkQqxOf3r1L9pYn6xQBEKFwmMY"
+      "sk-ssh-ed25519@openssh.com AAAAGnNrLXNzaC1lZDI1NTE5QG9wZW5zc2guY29tAAAAIK8icXjHkb4XzbIVN3djH4CE7RvgGd+3xbG4cgh0Yls5AAAABHNzaDo="
+    ];
   };
 }

common/zsh.nix

@@ -1,5 +1,4 @@
 { lib, pkgs, config, ... }: {
-  users.defaultUserShell = pkgs.zsh;
   programs.zsh = {
     enable = true;
     enableCompletion = true;

flake.lock

@@ -27,16 +27,17 @@
       "inputs": {
         "crane": "crane",
         "flake-compat": "flake-compat_2",
-        "flake-utils": "flake-utils_2",
+        "flake-parts": "flake-parts_2",
+        "nix-github-actions": "nix-github-actions_2",
         "nixpkgs": "nixpkgs",
         "nixpkgs-stable": "nixpkgs-stable"
       },
       "locked": {
-        "lastModified": 1711742460,
+        "lastModified": 1730257295,
-        "narHash": "sha256-0O4v6e4a1toxXZ2gf5INhg4WPE5C5T+SVvsBt+45Mcc=",
+        "narHash": "sha256-OQl+aAsKiyygvpzck1u0sZf/R4T9zM903CgNDFmmzA8=",
         "owner": "zhaofengli",
         "repo": "attic",
-        "rev": "4dbdbee45728d8ce5788db6461aaaa89d98081f0",
+        "rev": "48c8b395bfbc6b76c7eae74df6c74351255a095c",
         "type": "github"
       },
       "original": {
@@ -49,11 +50,11 @@
     "bats-assert": {
       "flake": false,
       "locked": {
-        "lastModified": 1636059754,
+        "lastModified": 1692829535,
-        "narHash": "sha256-ewME0l27ZqfmAwJO4h5biTALc9bDLv7Bl3ftBzBuZwk=",
+        "narHash": "sha256-oDqhUQ6Xg7a3xx537SWLGRzqP3oKKeyY4UYGCdz9z/Y=",
         "owner": "bats-core",
         "repo": "bats-assert",
-        "rev": "34551b1d7f8c7b677c1a66fc0ac140d6223409e5",
+        "rev": "e2d855bc78619ee15b0c702b5c30fb074101159f",
         "type": "github"
       },
       "original": {
@@ -65,11 +66,11 @@
     "bats-support": {
       "flake": false,
       "locked": {
-        "lastModified": 1548869839,
+        "lastModified": 1693050811,
-        "narHash": "sha256-Gr4ntadr42F2Ks8Pte2D4wNDbijhujuoJi4OPZnTAZU=",
+        "narHash": "sha256-PxJaH16+QrsfZqtkWVt5K6TwJB5gjIXnbGo+MB84WIU=",
         "owner": "bats-core",
         "repo": "bats-support",
-        "rev": "d140a65044b2d6810381935ae7f0c94c7023c8c3",
+        "rev": "9bf10e876dd6b624fe44423f0b35e064225f7556",
         "type": "github"
       },
       "original": {
@@ -87,11 +88,11 @@
         "treefmt-nix": "treefmt-nix"
       },
       "locked": {
-        "lastModified": 1728162115,
+        "lastModified": 1730064416,
-        "narHash": "sha256-O95Nv81XlYZjltq009951gwYHGo+Kjt9EBhh/6cYGDw=",
+        "narHash": "sha256-Opbtu9hKijGkEx+GYbSu3MJms3lFxZmAGTFyckguWMM=",
         "ref": "refs/heads/forkos",
-        "rev": "ed8f940717724af853efcafcd82cf4d10f32ede5",
+        "rev": "79137b14f3cb376204f739f44b05aebfc288ca89",
-        "revCount": 298,
+        "revCount": 310,
         "type": "git",
         "url": "https://git.lix.systems/lix-project/buildbot-nix.git"
       },
@@ -125,17 +126,18 @@
       "inputs": {
         "flake-compat": "flake-compat",
         "flake-utils": "flake-utils",
+        "nix-github-actions": "nix-github-actions",
         "nixpkgs": [
           "nixpkgs"
         ],
         "stable": "stable"
       },
       "locked": {
-        "lastModified": 1711386353,
+        "lastModified": 1731527002,
-        "narHash": "sha256-gWEpb8Hybnoqb4O4tmpohGZk6+aerAbJpywKcFIiMlg=",
+        "narHash": "sha256-dI9I6suECoIAmbS4xcrqF8r2pbmed8WWm5LIF1yWPw8=",
         "owner": "zhaofengli",
         "repo": "colmena",
-        "rev": "cd65ef7a25cdc75052fbd04b120aeb066c3881db",
+        "rev": "e3ad42138015fcdf2524518dd564a13145c72ea1",
         "type": "github"
       },
       "original": {
@@ -153,11 +155,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1702918879,
+        "lastModified": 1722960479,
-        "narHash": "sha256-tWJqzajIvYcaRWxn+cLUB9L9Pv4dQ3Bfit/YjU5ze3g=",
+        "narHash": "sha256-NhCkJJQhD5GUib8zN9JrmYGMwt4lCRp6ZVNzIiYCl0Y=",
         "owner": "ipetkov",
         "repo": "crane",
-        "rev": "7195c00c272fdd92fc74e7d5a0a2844b9fadb2fb",
+        "rev": "4c6c77920b8d44cd6660c1621dea6b3fc4b4c4f4",
         "type": "github"
       },
       "original": {
@@ -167,18 +169,12 @@
       }
     },
     "crane_2": {
-      "inputs": {
-        "nixpkgs": [
-          "grapevine",
-          "nixpkgs"
-        ]
-      },
       "locked": {
-        "lastModified": 1716569590,
+        "lastModified": 1730060262,
-        "narHash": "sha256-5eDbq8TuXFGGO3mqJFzhUbt5zHVTf5zilQoyW5jnJwo=",
+        "narHash": "sha256-RMgSVkZ9H03sxC+Vh4jxtLTCzSjPq18UWpiM0gq6shQ=",
         "owner": "ipetkov",
         "repo": "crane",
-        "rev": "109987da061a1bf452f435f1653c47511587d919",
+        "rev": "498d9f122c413ee1154e8131ace5a35a80d8fa76",
         "type": "github"
       },
       "original": {
@@ -219,11 +215,11 @@
         "rust-analyzer-src": "rust-analyzer-src"
       },
       "locked": {
-        "lastModified": 1716359173,
+        "lastModified": 1730442928,
-        "narHash": "sha256-pYcjP6Gy7i6jPWrjiWAVV0BCQp+DdmGaI/k65lBb/kM=",
+        "narHash": "sha256-U1DWb5c3EfkA7pqx5V1H4AWRA+EaE6UJ0lIRvK1RxgM=",
         "owner": "nix-community",
         "repo": "fenix",
-        "rev": "b6fc5035b28e36a98370d0eac44f4ef3fd323df6",
+        "rev": "87b4d20f896c99018dde4702a9c6157b516f2a76",
         "type": "github"
       },
       "original": {
@@ -252,11 +248,11 @@
     "flake-compat_2": {
       "flake": false,
       "locked": {
-        "lastModified": 1673956053,
+        "lastModified": 1696426674,
-        "narHash": "sha256-4gtG9iQuiKITOjNQQeQIpoIB6b16fm+504Ch3sNKLd8=",
+        "narHash": "sha256-kvjfFW7WAETZlt09AgDn1MrtKzP7t90Vf7vypd3OL1U=",
         "owner": "edolstra",
         "repo": "flake-compat",
-        "rev": "35bb57c0c8d8b62bbfd284272c928ceb64ddbde9",
+        "rev": "0f9255e01c2351cc7d116c072cb317785dd33b33",
         "type": "github"
       },
       "original": {
@@ -320,6 +316,28 @@
       }
     },
     "flake-parts_2": {
+      "inputs": {
+        "nixpkgs-lib": [
+          "grapevine",
+          "attic",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1722555600,
+        "narHash": "sha256-XOQkdLafnb/p9ij77byFQjDf5m5QYl9b2REiVClC+x4=",
+        "owner": "hercules-ci",
+        "repo": "flake-parts",
+        "rev": "8471fe90ad337a8074e957b69ca4d0089218391d",
+        "type": "github"
+      },
+      "original": {
+        "owner": "hercules-ci",
+        "repo": "flake-parts",
+        "type": "github"
+      }
+    },
+    "flake-parts_3": {
       "inputs": {
         "nixpkgs-lib": [
           "hydra",
@@ -341,6 +359,23 @@
         "type": "github"
       }
     },
+    "flake-parts_4": {
+      "inputs": {
+        "nixpkgs-lib": "nixpkgs-lib"
+      },
+      "locked": {
+        "lastModified": 1727826117,
+        "narHash": "sha256-K5ZLCyfO/Zj9mPFldf3iwS6oZStJcU4tSpiXTMYaaL0=",
+        "owner": "hercules-ci",
+        "repo": "flake-parts",
+        "rev": "3d04084d54bedc3d6b8b736c70ef449225c361b1",
+        "type": "github"
+      },
+      "original": {
+        "id": "flake-parts",
+        "type": "indirect"
+      }
+    },
     "flake-utils": {
       "locked": {
         "lastModified": 1659877975,
@@ -357,30 +392,15 @@
       }
     },
     "flake-utils_2": {
-      "locked": {
-        "lastModified": 1667395993,
-        "narHash": "sha256-nuEHfE/LcWyuSWnS8t12N1wc105Qtau+/OdUAjtQ0rA=",
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "rev": "5aed5285a952e0b949eb3ba02c12fa4fcfef535f",
-        "type": "github"
-      },
-      "original": {
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "type": "github"
-      }
-    },
-    "flake-utils_3": {
       "inputs": {
         "systems": "systems_2"
       },
       "locked": {
-        "lastModified": 1710146030,
+        "lastModified": 1726560853,
-        "narHash": "sha256-SZ5L6eA7HJ/nmkzGG7/ISclqe6oZdOZTNoesiInkXPQ=",
+        "narHash": "sha256-X6rJYSESBVr3hBoH0WbKE5KvhPU5bloyZ2L4K60/fPQ=",
         "owner": "numtide",
         "repo": "flake-utils",
-        "rev": "b1d9ab70662946ef0850d488da1c9019f3a9752a",
+        "rev": "c1dfcf08411b08f6b8615f7d8971a2bfa81d5e8a",
         "type": "github"
       },
       "original": {
@@ -390,21 +410,6 @@
         "type": "github"
       }
     },
-    "flake-utils_4": {
-      "locked": {
-        "lastModified": 1634851050,
-        "narHash": "sha256-N83GlSGPJJdcqhUxSCS/WwW5pksYf3VP1M13cDRTSVA=",
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "rev": "c91f3de5adaf1de973b797ef7485e441a65b8935",
-        "type": "github"
-      },
-      "original": {
-        "owner": "numtide",
-        "repo": "flake-utils",
-        "type": "github"
-      }
-    },
     "gerrit-dashboard": {
       "flake": false,
       "locked": {
@@ -427,20 +432,21 @@
         "crane": "crane_2",
         "fenix": "fenix",
         "flake-compat": "flake-compat_3",
-        "flake-utils": "flake-utils_3",
+        "flake-utils": "flake-utils_2",
         "nix-filter": "nix-filter",
         "nixpkgs": [
           "nixpkgs"
         ],
+        "rocksdb": "rocksdb",
         "rust-manifest": "rust-manifest"
       },
       "locked": {
         "host": "gitlab.computer.surgery",
-        "lastModified": 1727994504,
+        "lastModified": 1731820516,
-        "narHash": "sha256-FC6M1KKX58HbU9LG+cG6EJRr02J9lE/o0iiDi6m1gv8=",
+        "narHash": "sha256-BJiFq5meQMwOLhVS9/m2HCZoNUIN5u5weJXr94dkIRU=",
         "owner": "matrix",
         "repo": "grapevine-fork",
-        "rev": "5a490a4397f0c6a36dab1cb631dadc67a849deab",
+        "rev": "887e59cf03efb70bfa68b56dda32c411ba6cd5fa",
         "type": "gitlab"
       },
       "original": {
@@ -480,11 +486,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1728163965,
+        "lastModified": 1728321752,
-        "narHash": "sha256-vHA2qZWoTY4DQUWFktq8DYfCOlm8rd1bNZpiIzpFBCk=",
+        "narHash": "sha256-GbBAoBF7ZObz0IP+g0LZKxMafpMvNKjTEu9haiZbV54=",
         "ref": "refs/heads/main",
-        "rev": "e4d466ffcdc0e43f3bd005de3913a7e9ed4a58f5",
+        "rev": "ee1234c15cdcb427dbd4828e0add09d02cd606c9",
-        "revCount": 4216,
+        "revCount": 4220,
         "type": "git",
         "url": "https://git.lix.systems/lix-project/hydra.git"
       },
@@ -505,11 +511,11 @@
         "pre-commit-hooks": "pre-commit-hooks"
       },
       "locked": {
-        "lastModified": 1728159440,
+        "lastModified": 1728163191,
-        "narHash": "sha256-8DW+VfSIk5xYpYj1VDKMmUjXhMooIlAOwYG4J9PLbbg=",
+        "narHash": "sha256-SW0IEBsPN1EysqzvfDT+8Kimtzy03O1BxQQm7ZB6fRY=",
         "ref": "refs/heads/main",
-        "rev": "7ff60b7445ccb599edcbf0078d181034f61a0859",
+        "rev": "ed9b7f4f84fd60ad8618645cc1bae2d686ff0db6",
-        "revCount": 16318,
+        "revCount": 16323,
         "type": "git",
         "url": "https://git.lix.systems/lix-project/lix"
       },
@@ -520,12 +526,12 @@
     },
     "nix-eval-jobs": {
       "inputs": {
-        "flake-parts": "flake-parts_2",
+        "flake-parts": "flake-parts_3",
         "lix": [
           "hydra",
           "lix"
         ],
-        "nix-github-actions": "nix-github-actions",
+        "nix-github-actions": "nix-github-actions_3",
         "nixpkgs": [
           "hydra",
           "nixpkgs"
@@ -548,11 +554,11 @@
     },
     "nix-filter": {
       "locked": {
-        "lastModified": 1710156097,
+        "lastModified": 1730207686,
-        "narHash": "sha256-1Wvk8UP7PXdf8bCCaEoMnOT1qe5/Duqgj+rL8sRQsSM=",
+        "narHash": "sha256-SCHiL+1f7q9TAnxpasriP6fMarWE5H43t25F5/9e28I=",
         "owner": "numtide",
         "repo": "nix-filter",
-        "rev": "3342559a24e85fc164b295c3444e8a139924675b",
+        "rev": "776e68c1d014c3adde193a18db9d738458cd2ba4",
         "type": "github"
       },
       "original": {
@@ -583,6 +589,49 @@
       }
     },
     "nix-github-actions": {
+      "inputs": {
+        "nixpkgs": [
+          "colmena",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1729742964,
+        "narHash": "sha256-B4mzTcQ0FZHdpeWcpDYPERtyjJd/NIuaQ9+BV1h+MpA=",
+        "owner": "nix-community",
+        "repo": "nix-github-actions",
+        "rev": "e04df33f62cdcf93d73e9a04142464753a16db67",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-community",
+        "repo": "nix-github-actions",
+        "type": "github"
+      }
+    },
+    "nix-github-actions_2": {
+      "inputs": {
+        "nixpkgs": [
+          "grapevine",
+          "attic",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1729742964,
+        "narHash": "sha256-B4mzTcQ0FZHdpeWcpDYPERtyjJd/NIuaQ9+BV1h+MpA=",
+        "owner": "nix-community",
+        "repo": "nix-github-actions",
+        "rev": "e04df33f62cdcf93d73e9a04142464753a16db67",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-community",
+        "repo": "nix-github-actions",
+        "type": "github"
+      }
+    },
+    "nix-github-actions_3": {
       "inputs": {
         "nixpkgs": [
           "hydra",
@@ -622,11 +671,11 @@
     },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1711401922,
+        "lastModified": 1726042813,
-        "narHash": "sha256-QoQqXoj8ClGo0sqD/qWKFWezgEwUL0SUh37/vY2jNhc=",
+        "narHash": "sha256-LnNKCCxnwgF+575y0pxUdlGZBO/ru1CtGHIqQVfvjlA=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "07262b18b97000d16a4bdb003418bd2fb067a932",
+        "rev": "159be5db480d1df880a0135ca0bfed84c2f88353",
         "type": "github"
       },
       "original": {
@@ -636,6 +685,18 @@
         "type": "github"
       }
     },
+    "nixpkgs-lib": {
+      "locked": {
+        "lastModified": 1727825735,
+        "narHash": "sha256-0xHYkMkeLVQAMa7gvkddbPqpxph+hDzdu1XdGPJR+Os=",
+        "type": "tarball",
+        "url": "https://github.com/NixOS/nixpkgs/archive/fb192fec7cc7a4c26d51779e9bab07ce6fa5597a.tar.gz"
+      },
+      "original": {
+        "type": "tarball",
+        "url": "https://github.com/NixOS/nixpkgs/archive/fb192fec7cc7a4c26d51779e9bab07ce6fa5597a.tar.gz"
+      }
+    },
     "nixpkgs-regression": {
       "locked": {
         "lastModified": 1643052045,
@@ -654,32 +715,32 @@
     },
     "nixpkgs-stable": {
       "locked": {
-        "lastModified": 1711460390,
+        "lastModified": 1724316499,
-        "narHash": "sha256-akSgjDZL6pVHEfSE6sz1DNSXuYX6hq+P/1Z5IoYWs7E=",
+        "narHash": "sha256-Qb9MhKBUTCfWg/wqqaxt89Xfi6qTD3XpTzQ9eXi3JmE=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "44733514b72e732bd49f5511bd0203dea9b9a434",
+        "rev": "797f7dc49e0bc7fab4b57c021cdf68f595e47841",
         "type": "github"
       },
       "original": {
         "owner": "NixOS",
-        "ref": "nixos-23.11",
+        "ref": "nixos-24.05",
         "repo": "nixpkgs",
         "type": "github"
       }
     },
     "nixpkgs_2": {
       "locked": {
-        "lastModified": 1728093190,
+        "lastModified": 1731676054,
-        "narHash": "sha256-CAZF2NRuHmqTtRTNAruWpHA43Gg2UvuCNEIzabP0l6M=",
+        "narHash": "sha256-OZiZ3m8SCMfh3B6bfGC/Bm4x3qc1m2SVEAlkV6iY7Yg=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "e2f08f4d8b3ecb5cf5c9fd9cb2d53bb3c71807da",
+        "rev": "5e4fbfb6b3de1aa2872b76d49fafc942626e2add",
         "type": "github"
       },
       "original": {
         "owner": "NixOS",
-        "ref": "nixpkgs-unstable",
+        "ref": "nixos-unstable",
         "repo": "nixpkgs",
         "type": "github"
       }
@@ -700,6 +761,23 @@
         "type": "github"
       }
     },
+    "rocksdb": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1730475155,
+        "narHash": "sha256-u5uuShM2SxHc9/zL4UU56IhCcR/ZQbzde0LgOYS44bM=",
+        "owner": "facebook",
+        "repo": "rocksdb",
+        "rev": "3c27a3dde0993210c5cc30d99717093f7537916f",
+        "type": "github"
+      },
+      "original": {
+        "owner": "facebook",
+        "ref": "v9.7.4",
+        "repo": "rocksdb",
+        "type": "github"
+      }
+    },
     "root": {
       "inputs": {
         "agenix": "agenix",
@@ -722,11 +800,11 @@
     "rust-analyzer-src": {
       "flake": false,
       "locked": {
-        "lastModified": 1716107283,
+        "lastModified": 1730386175,
-        "narHash": "sha256-NJgrwLiLGHDrCia5AeIvZUHUY7xYGVryee0/9D3Ir1I=",
+        "narHash": "sha256-0Uq+/B8eu7pw8B8pxuGdFYKjcVLwNMcHfDxU9sXh7rg=",
         "owner": "rust-lang",
         "repo": "rust-analyzer",
-        "rev": "21ec8f523812b88418b2bfc64240c62b3dd967bd",
+        "rev": "0ba893e1a00d92557ac91efb771d72eee36ca687",
         "type": "github"
       },
       "original": {
@@ -750,16 +828,16 @@
     },
     "stable": {
       "locked": {
-        "lastModified": 1696039360,
+        "lastModified": 1730883749,
-        "narHash": "sha256-g7nIUV4uq1TOVeVIDEZLb005suTWCUjSY0zYOlSBsyE=",
+        "narHash": "sha256-mwrFF0vElHJP8X3pFCByJR365Q2463ATp2qGIrDUdlE=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "32dcb45f66c0487e92db8303a798ebc548cadedc",
+        "rev": "dba414932936fde69f0606b4f1d87c5bc0003ede",
         "type": "github"
       },
       "original": {
         "owner": "NixOS",
-        "ref": "nixos-23.05",
+        "ref": "nixos-24.05",
         "repo": "nixpkgs",
         "type": "github"
       }
@@ -767,11 +845,11 @@
     "stateless-uptime-kuma": {
       "flake": false,
       "locked": {
-        "lastModified": 1727622797,
+        "lastModified": 1728243069,
-        "narHash": "sha256-JRvy5zsPsk1ChmEB1UHKOlnzAKCPdtBLCcx+LXh3e4c=",
+        "narHash": "sha256-l9fgwesnmFxasCaYUCD7L9bGGJXytLuwtx3CZMgpwJg=",
         "ref": "refs/heads/master",
-        "rev": "390363e6a977d71a96c53d7f8b252038dfee2e2e",
+        "rev": "880f444ff7862d6127b051cf1a993ad1585b1652",
-        "revCount": 23,
+        "revCount": 25,
         "type": "git",
         "url": "https://git.dgnum.eu/DGNum/stateless-uptime-kuma.git"
       },
@@ -810,22 +888,38 @@
         "type": "github"
       }
     },
+    "systems_3": {
+      "locked": {
+        "lastModified": 1681028828,
+        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
+        "owner": "nix-systems",
+        "repo": "default",
+        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-systems",
+        "repo": "default",
+        "type": "github"
+      }
+    },
     "terranix": {
       "inputs": {
         "bats-assert": "bats-assert",
         "bats-support": "bats-support",
-        "flake-utils": "flake-utils_4",
+        "flake-parts": "flake-parts_4",
         "nixpkgs": [
           "nixpkgs"
         ],
+        "systems": "systems_3",
         "terranix-examples": "terranix-examples"
       },
       "locked": {
-        "lastModified": 1695406838,
+        "lastModified": 1728959489,
-        "narHash": "sha256-xiUfVD6rtsVWFotVtUW3Q1nQh4obKzgvpN1wqZuGXvM=",
+        "narHash": "sha256-1Pu2j5xsBTuoyga08ZVf+rKp3FOMmJh/0fXen/idOrA=",
         "owner": "terranix",
         "repo": "terranix",
-        "rev": "fc9077ca02ab5681935dbf0ecd725c4d889b9275",
+        "rev": "7734e2ee6a1472807a33ce1e7da794bed2aaf91c",
         "type": "github"
       },
       "original": {
@@ -836,11 +930,11 @@
     },
     "terranix-examples": {
       "locked": {
-        "lastModified": 1636300201,
+        "lastModified": 1637156952,
-        "narHash": "sha256-0n1je1WpiR6XfCsvi8ZK7GrpEnMl+DpwhWaO1949Vbc=",
+        "narHash": "sha256-KqvXIe1yiKOEP9BRYqNQN+LOWPCsWojh0WjEgv5jfEI=",
         "owner": "terranix",
         "repo": "terranix-examples",
-        "rev": "a934aa1cf88f6bd6c6ddb4c77b77ec6e1660bd5e",
+        "rev": "921680efb8af0f332d8ad73718d53907f9483e24",
         "type": "github"
       },
       "original": {

flake.nix

@@ -2,7 +2,7 @@
   description = "Bagel cooking infrastructure";
 
   inputs = {
-    nixpkgs.url = "github:NixOS/nixpkgs/nixpkgs-unstable";
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
 
     terranix.url = "github:terranix/terranix";
     terranix.inputs.nixpkgs.follows = "nixpkgs";
@@ -199,8 +199,6 @@
 
       build01-aarch64-lix.imports = lixInfraModules ++ [ ./hosts/build01-aarch64-lix ];
       buildbot-lix.imports = lixInfraModules ++ [ ./hosts/buildbot-lix ];
-      # This is Lix's Garage S3.
-      cache-lix.imports = lixInfraModules ++ [ ./hosts/cache-lix ];
     } // builders;
 
     hydraJobs = builtins.mapAttrs (n: v: v.config.system.build.netbootDir or v.config.system.build.toplevel) self.nixosConfigurations;

hosts/build-coord/hardware.nix

@@ -38,7 +38,7 @@
 
   zramSwap = {
     enable = true;
-    memoryPercent = 25;
+    memoryPercent = 100;
   };
 
   networking.useNetworkd = true;

hosts/buildbot-lix/default.nix

@@ -38,7 +38,9 @@
       port = 2022;
       username = "buildbot";
     };
-    cors.allowedOrigin = "*.lix.systems";
+    cors.allowedOrigins = [
+      "https://*.lix.systems"
+    ];
     projects = [
       "lix"
       "lix-installer"

hosts/buildbot/default.nix

@@ -36,13 +36,15 @@
         port = cfgGerrit.port;
         username = "buildbot";
       };
-    cors.allowedOrigin = "*.forkos.org";
+    cors.allowedOrigins = [
+      "https://*.forkos.org"
+    ];
     projects = [
       "buildbot-test"
       "nixpkgs"
       "infra"
     ];
-    builders = [ "builder-10" ];
+    builders = [ "builder-9" ];
   };
 
   i18n.defaultLocale = "en_US.UTF-8";

hosts/cache-lix/default.nix

@@ -1,125 +0,0 @@
-# Configuration for a virtual machine in Raito's micro-DC basement.
-# 8 vCPU (2014 grade Xeon though)
-# 8GB RAM
-# 100GB SSD
-# 1TB HDD
-# All specifications can be upgraded to a certain extent, just ask Raito.
-# Hosts the Garage S3 instance for the Lix project.
-# Our "binary cache".
-#
-# vim: et:ts=2:sw=2:
-#
-{ config, pkgs, lib, ... }: {
-  networking.hostName = "cache";
-  networking.domain = "lix.systems";
-
-  system.stateVersion = "24.05";
-
-  zramSwap.enable = true;
-  i18n.defaultLocale = "en_US.UTF-8";
-
-  # All the objects are stored there.
-  # Metadata is on the fast SSD.
-  fileSystems."/data" = {
-    device = "/dev/disk/by-label/data";
-    fsType = "ext4";
-  };
-
-  bagel.s3 = {
-    rootDomain = "lix.systems";
-    garage.enable = true;
-    web = {
-      buckets = [
-        "install"
-        "cache"
-        "releases"
-        "docs"
-      ];
-      subdomains = {
-        "cache.lix.systems" = "cache";
-        "install.lix.systems" = "install";
-      };
-    };
-    reverse-proxy = {
-      enable = true;
-      buckets = [
-        "docs"
-        "releases"
-        "install"
-      ];
-      web = {
-        "releases.lix.systems" = "releases";
-        "docs.lix.systems" = "docs";
-      };
-    };
-  };
-
-  # Fix up the manual path so it enables having multiple manuals
-  services.nginx.virtualHosts."docs.lix.systems".locations.${''~ ^/manual/nightly(/[^\s]*)$''} =
-  {
-    extraConfig = ''
-      return 301 /manual/lix/nightly$1;
-    '';
-  };
-
-  systemd.network.links."10-nat-lan".matchConfig.MACAddress = "BC:24:11:1E:7C:9B";
-  systemd.network.networks."10-wan".networkConfig.Address = [ "2001:bc8:38ee:100::210/56" ];
-  systemd.network.links."10-wan".matchConfig.MACAddress = "BC:24:11:42:72:79";
-
-  nixpkgs.hostPlatform = lib.mkDefault "x86_64-linux";
-
-  # Debugging stuff.
-  virtualisation.vmVariant = {
-    systemd.network.enable = lib.mkForce false;
-    networking.useDHCP = true;
-
-    environment.systemPackages = with pkgs; [
-      tcpdump
-    ];
-
-    system.activationScripts.agenixInstall.text = lib.mkForce ''
-      echo "lol gotcha"
-      _agenix_generation="$(basename "$(readlink ${config.age.secretsDir})" || echo 0)"
-      (( ++_agenix_generation ))
-      p=${config.age.secretsMountPoint}/$_agenix_generation
-      > $p/garage
-      echo "GARAGE_RPC_SECRET=$(${lib.getExe pkgs.openssl.bin} rand -hex 32)" >> $p/garage
-      echo "GARAGE_METRICS_TOKEN=$(${lib.getExe pkgs.openssl.bin} rand -base64 32)" >> $p/garage
-      echo "GARAGE_ADMIN_TOKEN=$(${lib.getExe pkgs.openssl.bin} rand -base64 32)" >> $p/garage
-
-      ln -sfT /var/secrets/garage-s3-api-key $p/s3-revproxy-api-key-env
-      ln -sfT $p ${config.age.secretsDir}
-    '';
-    virtualisation.forwardPorts = [
-      {
-        from = "host";
-        guest.port = 443;
-        host.port = 4043;
-        proto = "tcp";
-      }
-      {
-        from = "host";
-        guest.port = 1337;
-        host.port = 1337;
-        proto = "tcp";
-      }
-      {
-        from = "host";
-        guest.port = 22;
-        host.port = 2022;
-        proto = "tcp";
-      }
-    ];
-
-    security.acme = {
-      defaults.server = "http://127.0.0.1/failfailfail";
-      extraLegoFlags = ["--lol-fail"];
-      extraLegoRenewFlags = ["--lol-fail"];
-      extraLegoRunFlags = ["--lol-fail"];
-    };
-
-    systemd.tmpfiles.rules = [
-      "d /data/s3 700 garage - - -"
-    ];
-  };
-}

hosts/gerrit01/default.nix

@@ -23,6 +23,9 @@
     };
   };
 
+  # Block all these crawlers!!
+  bagel.services.nginx.crawler-blocker.enable = true;
+
   fileSystems."/gerrit-data" = {
     device = "/dev/disk/by-uuid/d1062305-0dea-4740-9a27-b6b1691862a4";
     fsType = "ext4";
@@ -121,7 +124,7 @@
     };
   };
 
-  age.secrets.s3-channel-staging-keys.file = ../../secrets/s3-channel-staging-keys.age;
+  age.secrets.s3-channel-staging-keys.file = ../../secrets/floral/s3-channel-staging-keys.age;
   bagel.nixpkgs.channel-scripts = {
     enable = true;
     otlp.enable = true;

overlays/pyroscope/default.nix

@@ -1,9 +1,10 @@
 { lib
-, buildGoModule
+, buildGo122Module
 , fetchFromGitHub
 }:
 
-buildGoModule rec {
+# FIXME: update, remove this pin
+buildGo122Module rec {
   pname = "pyroscope";
   version = "1.7.1";
 

services/block-crawlers/blocked-ua.txt

@@ -0,0 +1,40 @@
+AI2Bot
+Ai2Bot-Dolma
+Amazonbot
+anthropic-ai
+Applebot
+Applebot-Extended
+Bytespider
+CCBot
+ChatGPT-User
+Claude-Web
+ClaudeBot
+cohere-ai
+Diffbot
+FacebookBot
+facebookexternalhit
+FriendlyCrawler
+Google-Extended
+GoogleOther
+GoogleOther-Image
+GoogleOther-Video
+GPTBot
+iaskspider/2.0
+ICC-Crawler
+ImagesiftBot
+img2dataset
+ISSCyberRiskCrawler
+Kangaroo Bot
+Meta-ExternalAgent
+Meta-ExternalFetcher
+OAI-SearchBot
+omgili
+omgilibot
+PerplexityBot
+PetalBot
+Scrapy
+Sidetrade indexer bot
+Timpibot
+VelenPublicWebCrawler
+Webzio-Extended
+YouBot

services/block-crawlers/default.nix

@@ -0,0 +1,32 @@
+{ pkgs, config, lib, ... }:
+let
+  inherit (lib) mkEnableOption mkIf mkOption types concatStringsSep mkDefault splitString;
+  cfg = config.bagel.services.nginx.crawler-blocker;
+  mkRobotsFile = blockedUAs: pkgs.writeText "robots.txt" ''
+    ${concatStringsSep "\n" (map (ua: "User-agent: ${ua}") blockedUAs)}
+    Disallow: /
+  '';
+in
+{
+  options = {
+    bagel.services.nginx.crawler-blocker = {
+      enable = mkEnableOption "the crawler blocker";
+
+      userAgents = mkOption {
+        type = types.listOf types.str;
+        default = splitString "\n" (builtins.readFile ./blocked-ua.txt);
+      };
+    };
+
+    services.nginx.virtualHosts = mkOption {
+      type = types.attrsOf (types.submodule {
+        config = {
+          locations."= /robots.txt" = mkIf cfg.enable (mkDefault {
+            alias = mkRobotsFile cfg.userAgents;
+          });
+        };
+      });
+    };
+  };
+}
+

services/buildbot/default.nix

@@ -53,9 +53,9 @@ in
       };
     };
 
-    cors.allowedOrigin = mkOption {
+    cors.allowedOrigins = mkOption {
-      type = types.str;
+      type = types.listOf types.str;
-      example = "*.forkos.org";
+      example = [ "*.forkos.org" ];
       description = "Allowed origin for Buildbot and NGINX for CORS without the protocol";
     };
 
@@ -100,6 +100,7 @@ in
     };
 
     services.nginx = {
+      recommendedProxySettings = true;
       appendHttpConfig = ''
         # Our session stuff is too big with the TWISTED_COOKIE in addition.
         # Default is usually 4k or 8k.
@@ -109,8 +110,8 @@ in
         forceSSL = true;
         enableACME = true;
         extraConfig = ''
+          # This is needed so that logged-in users in Buildbot can include their credentials in their requests.
           add_header Access-Control-Allow-Credentials 'true' always;
-          add_header Access-Control-Allow-Origin 'https://${cfg.cors.allowedOrigin}' always;
         '';
       };
     };
@@ -155,9 +156,8 @@ in
       # we can replace all of this with automatic localworker generation on buildbot-nix side.
       workersFile = config.age.secrets.buildbot-workers.path;
 
-      allowedOrigins = [
+      # We rely on NGINX to do the CORS dance.
-        cfg.cors.allowedOrigin
+      allowedOrigins = cfg.cors.allowedOrigins;
-      ];
 
       buildMachines = map (n: {
           hostName = nodes.${n}.config.networking.fqdn;
@@ -194,6 +194,32 @@ in
       RestartSteps = 10;
     };
 
+    services.postgresql.settings = {
+      # DB Version: 15
+      # OS Type: linux
+      # DB Type: web
+      # Total Memory (RAM): 64 GB
+      # CPUs num: 16
+      # Connections num: 100
+      # Data Storage: ssd
+      max_connections = 100;
+      shared_buffers = "16GB";
+      effective_cache_size = "48GB";
+      maintenance_work_mem = "2GB";
+      checkpoint_completion_target = 0.9;
+      wal_buffers = "16MB";
+      default_statistics_target = 100;
+      random_page_cost = 1.1;
+      effective_io_concurrency = 200;
+      work_mem = "41943kB";
+      huge_pages = "try";
+      min_wal_size = "1GB";
+      max_wal_size = "4GB";
+      max_worker_processes = 16;
+      max_parallel_workers_per_gather = 4;
+      max_parallel_workers = 16;
+      max_parallel_maintenance_workers = 4;
+    };
 
     nix.settings.keep-derivations = true;
     nix.gc = {

services/buildbot/lix.nix

@@ -21,7 +21,8 @@ in
       sshUser = "nix";
       systems = [ "aarch64-linux" ];
       publicHostKey = ssh-keys.machines.build02-aarch64-lix;
-      supportedFeatures = nodes.build02-aarch64-lix.config.nix.settings.system-features;
+      # TODO: use build02 features.
+      supportedFeatures = nodes.build01-aarch64-lix.config.nix.settings.system-features;
     }
     {
       hostName = "build01.aarch64-darwin.lix.systems";

services/default.nix

@@ -1,5 +1,6 @@
 {
   imports = [
+    ./block-crawlers
     ./gerrit
     ./channel-scripts
     ./hydra

services/gerrit/default.nix

@@ -129,7 +129,9 @@ in
       serverId = "9e5216ad-038d-4d74-a4e8-716515834a94";
 
       builtinPlugins = [
-        "gitiles"
+        # Disable gitiles as it generates too much traffic.
+        # Prefer git.forkos.org.
+        # "gitiles"
         "codemirror-editor"
         "reviewnotes"
         "download-commands"
@@ -141,7 +143,9 @@ in
       plugins = with pkgs.gerritPlugins; [
         oauth
         metrics-reporter-prometheus
-        # Buildbot checks plugin (writeText because services.gerrit.plugins expects packages)
+        # Theme plugin
+        (pkgs.concatText "theme.js" [ ./theme.js ])
+        # Buildbot checks plugin
         (pkgs.runCommand "checks.js" {
           BASE_URI = builtins.toJSON "https://buildbot.forkos.org";
           SUPPORTED_PROJECTS = builtins.toJSON [
@@ -326,7 +330,7 @@ in
       };
     };
 
-    age.secrets.gerrit-prometheus-bearer-token.file = ../../secrets/gerrit-prometheus-bearer-token.age;
+    age.secrets.gerrit-prometheus-bearer-token.file = ../../secrets/floral/gerrit-prometheus-bearer-token.age;
     bagel.monitoring.grafana-agent.exporters.gerrit = {
       port = 4778;  # grrt
       bearerTokenFile = config.age.secrets.gerrit-prometheus-bearer-token.path;

services/gerrit/git-gc-preserve.nix

@@ -57,6 +57,7 @@ in
           name = "git-gc-preserve-${name}";
           value = {
             description = "Git-GC-Preserve Service - ${name}";
+            path = [ pkgs.util-linux ];
             serviceConfig = {
               WorkingDirectory = gcConfig.repoPath;
               Type = "oneshot";

services/gerrit/theme.js

@@ -0,0 +1,69 @@
+/* Set up theming for Floral.
+ * vim: set et ts=2 sw=2:
+ */
+Gerrit.install((plugin) => {
+  const stylesheet = new CSSStyleSheet();
+  stylesheet.replace(`
+    html {
+      --header-title-content: 'floral.systems';
+
+      --blue-50: #f3f4fb;
+      --blue-100: #e3e6f6;
+      --blue-200: #ced5ef;
+      --blue-300: #acb8e4;
+      --blue-400: #8495d6;
+      --blue-500: #6775ca;
+      --blue-600: #5158bb;
+      --blue-700: #494bac;
+      --blue-800: #41408d;
+      --blue-900: #383870;
+      --blue-950: #252546;
+
+      --coral-50: #fff1f1;
+      --coral-100: #ffe0e0;
+      --coral-200: #ffc5c5;
+      --coral-300: #ff9e9d;
+      --coral-400: #ff6665;
+      --coral-500: #fe4a49;
+      --coral-600: #ec1716;
+      --coral-700: #c70f0e;
+      --coral-800: #a41110;
+      --coral-900: #881514;
+      --coral-950: #4a0505;
+
+      --teal-50: #eefbf5;
+      --teal-100: #d6f5e5;
+      --teal-200: #b1e9d0;
+      --teal-300: #7ed7b5;
+      --teal-400: #49be95;
+      --teal-500: #27a27b;
+      --teal-600: #188162;
+      --teal-700: #136951;
+      --teal-800: #125342;
+      --teal-900: #104437;
+      --teal-950: #08261f;
+
+      --zinc-50: #fafafa;
+      --zinc-100: #f4f4f5;
+      --zinc-200: #e4e4e7;
+      --zinc-300: #d4d4d8;
+      --zinc-400: #a1a1aa;
+      --zinc-500: #71717a;
+      --zinc-600: #52525b;
+      --zinc-700: #3f3f46;
+      --zinc-800: #27272a;
+      --zinc-900: #18181b;
+      --zinc-950: #09090b;
+    }
+    html.lightTheme {
+      --header-background-color: var(--teal-700);
+      --header-text-color: var(--coral-50);
+    }
+    html.darkTheme {
+      --header-background-color: var(--teal-900);
+      --header-text-color: var(--coral-50);
+    }
+  `).then(() => {
+    document.adoptedStyleSheets = [...document.adoptedStyleSheets, stylesheet];
+  });
+});

services/gerrit/www.nix

@@ -29,10 +29,6 @@ in
             # NGINX should not give up super fast. Things can take time.
             proxy_read_timeout 3600;
           }
-
-          location = /robots.txt {
-            return 200 'User-agent: *\nAllow: /';
-          }
         '';
       };
 

services/lix-s3/default.nix

@@ -1,33 +0,0 @@
-{ config, lib, ... }:
-let
-  inherit (lib) mkOption types;
-  cfg = config.bagel.s3;
-in
-{
-  options.bagel.s3 = {
-    rootDomain = mkOption {
-      type = types.str;
-    };
-
-    webRootDomain = mkOption {
-      type = types.str;
-      default = "web.${cfg.rootDomain}";
-    };
-
-    s3RootDomain = mkOption {
-      type = types.str;
-      default = "s3.${cfg.rootDomain}";
-    };
-  };
-
-  imports = [
-    # Generic frontend stuff
-    # e.g. static redirects, etc.
-    ./web.nix
-    # Garage implementation for our S3
-    # In the future, we could be using Ceph store.
-    ./garage.nix
-    # S3 reverse proxy
-    ./s3-revproxy.nix
-  ];
-}

services/lix-s3/garage-ephemeral-key.nix

@@ -1,63 +0,0 @@
-{ wrap }:
-{ lib, pkgs, config, ... }:
-let
-  garage-ephemeral-key = pkgs.writers.writePython3Bin
-    "garage-ephemeral-key"
-    { libraries = [ pkgs.python3.pkgs.requests ]; }
-    (builtins.readFile ./garage_ephemeral_key.py);
-
-  # the usual copy pasta of systemd-analyze security satisfying rules
-  containment = {
-    DynamicUser = true;
-    CapabilityBoundingSet = "";
-    NoNewPrivileges = true;
-    PrivateTmp = true;
-    PrivateUsers = true;
-    PrivateDevices = true;
-    ProtectHome = true;
-    ProtectClock = true;
-    ProtectProc = "noaccess";
-    ProcSubset = "pid";
-    UMask = "0077";
-    ProtectKernelLogs = true;
-    ProtectKernelModules = true;
-    ProtectKernelTunables = true;
-    ProtectControlGroups = true;
-    ProtectHostname = true;
-    RestrictSUIDSGID = true;
-    RestrictRealtime = true;
-    RestrictNamespaces = true;
-    LockPersonality = true;
-    RemoveIPC = true;
-    SystemCallFilter = [ "@system-service" "~@privileged" ];
-    RestrictAddressFamilies = [ "AF_INET" "AF_INET6" ];
-    MemoryDenyWriteExecute = true;
-    SystemCallArchitectures = "native";
-  };
-in
-{
-  _file = ./garage-ephemeral-key.nix;
-
-  environment.systemPackages = [
-    (wrap garage-ephemeral-key "garage-ephemeral-key")
-  ];
-
-  # Clean expired ephemeral keys every 2 minutes
-  systemd.timers.garage-ephemeral-key-clean = {
-    wantedBy = [ "multi-user.target" ];
-    timerConfig = {
-      # Every 2 minutes.
-      OnCalendar = "*-*-* *:00/2";
-    };
-  };
-
-  systemd.services.garage-ephemeral-key-clean = {
-    after = [ "garage.service" ];
-    wants = [ "garage.service" ];
-    serviceConfig = {
-      ExecStart = "${lib.getExe garage-ephemeral-key} clean";
-
-      EnvironmentFile = config.age.secrets.garage.path;
-    } // containment;
-  };
-}

services/lix-s3/garage.nix

@@ -1,106 +0,0 @@
-{ config, pkgs, lib, ... }:
-let
-  cfg = config.bagel.s3.garage;
-  inherit (lib) mkEnableOption mkIf mkOption types;
-  # TODO: send me back upstream to cl.forkos.org.
-  wrap = pkg: name: pkgs.writeShellScriptBin name ''
-    set -a
-    [[ -z "''${GARAGE_RPC_SECRET:-}" ]] && source ${config.age.secrets.garage.path}
-    set +a
-    exec ${lib.getExe pkg} "$@"
-  '';
-  # TODO: generalize this idea
-  rootDomains = {
-    lix = "lix.systems";
-    floral = "floral.systems";
-  };
-in
-{
-  options.bagel.s3.garage = {
-    enable = mkEnableOption "the Garage implementation of S3";
-    tenant = mkOption {
-      type = types.enum [ "lix" "floral" ];
-    };
-
-    api.address = mkOption {
-      type = types.str;
-      default = "127.0.0.1:3900";
-    };
-
-    rootDomain = mkOption {
-      type = types.str;
-      default = rootDomains.${cfg.tenant};
-    };
-
-    dataDir = mkOption {
-      type = types.str;
-    };
-
-    metadataDir = mkOption {
-      default = "/var/lib/garage/metadata";
-    };
-  };
-
-  imports = [
-    (import ./garage-ephemeral-key.nix { inherit wrap; })
-  ];
-
-  config = mkIf cfg.enable {
-    bagel.secrets.files = [
-      "garage-environment"
-    ];
-
-    services.garage = {
-      enable = true;
-      # Slightly evil, but we have to wrap it here so the garage cli Just
-      # Works(tm) from the shell. It will no-op in the wrapper if the env is
-      # already set.
-      package = wrap pkgs.garage_0_9 "garage";
-
-      settings = {
-        data_dir = cfg.dataDir;
-        metadata_dir = cfg.metadataDir;
-
-        db_engine = "lmdb";
-
-        replication_mode = "none";
-        compression_level = 7;
-
-        rpc_bind_addr = "[::]:3901";
-        rpc_public_addr = "127.0.0.1:3901";
-
-        s3_api = {
-          s3_region = "garage";
-          api_bind_addr = cfg.api.address;
-          root_domain = ".s3.${cfg.rootDomain}";
-        };
-
-        s3_web = {
-          bind_addr = "127.0.0.1:3902";
-          root_domain = ".web.${cfg.rootDomain}";
-          index = "index.html";
-        };
-
-        k2v_api.api_bind_addr = "[::]:3904";
-        # FIXME(raito): api bind address should be secured.
-        # admin.api_bind_addr = "[${wnlib.generateIPv6Address "monitoring" "cache"}]:3903";
-      };
-
-      environmentFile = config.age.secrets.garage-environment.path;
-    };
-
-    systemd.services.garage.serviceConfig = {
-      User = "garage";
-      ReadWriteDirectories = [
-        cfg.dataDir
-      ];
-      StateDirectory = "garage";
-    };
-
-    users.users.garage = {
-      isSystemUser = true;
-      group = "garage";
-    };
-    users.groups.garage = { };
-  };
-}

services/lix-s3/s3-revproxy.nix

@@ -1,106 +0,0 @@
-{ lib, config, ... }:
-let
-  inherit (lib) mkOption mkIf types mapAttrs;
-  cfgParent = config.bagel.s3;
-  cfg = config.bagel.s3.reverse-proxy;
-  mkTarget = { name, bucket ? name }: {
-    mount = {
-      host = "${name}.${cfgParent.webRootDomain}";
-      path = [ "/" ];
-    };
-    actions.GET = {
-      enabled = true;
-      config = {
-        # e.g. /2.90 will 404, so it will redirect to /2.90/ if it is a directory
-        redirectWithTrailingSlashForNotFoundFile = true;
-        indexDocument = "index.html";
-      };
-    };
-
-    bucket = {
-      name = bucket;
-      region = "garage";
-      s3Endpoint = "https://${cfgParent.s3RootDomain}";
-      credentials = {
-        accessKey.env = "AWS_ACCESS_KEY_ID";
-        secretKey.env = "AWS_SECRET_KEY";
-      };
-    };
-  };
-in
-{
-  options.bagel.s3.reverse-proxy = {
-    targets = mkOption {
-      type = types.attrsOf (types.submodule ({ name, ... }: {
-        bucket = mkOption {
-          type = types.str;
-          default = name;
-        };
-      }));
-      default = { };
-    };
-
-    port = mkOption {
-      type = types.port;
-      default = 10652;
-    };
-  };
-
-  config = mkIf cfg.enable {
-    age.secrets.s3-revproxy-api-key-env.file = ./s3-revproxy-env.age;
-    # this solves garage supporting neither anonymous access nor automatic
-    # directory indexing by simply ignoring garage's web server and replacing it
-    # with overengineered golang instead.
-    services.s3-revproxy = {
-      enable = true;
-      settings = {
-        templates = {
-          helpers = [ ./s3-revproxy-templates/_helpers.tpl ];
-          notFoundError = {
-            headers = {
-              "Content-Type" = "{{ template \"main.headers.contentType\" . }}";
-            };
-            status = "404";
-          };
-          folderList = {
-            path = ./s3-revproxy-templates/folder-list.tpl;
-            headers = {
-              "Content-Type" = "{{ template \"main.headers.contentType\" . }}";
-            };
-            # empty s3 directories are not real and cannot hurt you.
-            # due to redirectWithTrailingSlashForNotFoundFile, garbage file names
-            # get redirected as folders, which then appear as empty, yielding
-            # poor UX.
-            status = ''
-              {{- if eq (len .Entries) 0 -}}
-                404
-              {{- else -}}
-                200
-              {{- end -}}
-            '';
-          };
-        };
-        /* For metrics and debugging (e.g. pulling the config)
-        internalServer = {
-          listenAddr = "127.0.0.1";
-          port = 1337;
-        };
-        */
-        server = {
-          listenAddr = "127.0.0.1";
-          port = cfg.port;
-
-          # it's going right into nginx, so no point
-          compress.enabled = false;
-          cors = {
-            enabled = true;
-            allowMethods = [ "GET" ];
-            allowOrigins = [ "*" ];
-          };
-        };
-        targets = mapAttrs mkTarget cfg.targets;
-      };
-      environmentFile = config.age.secrets.s3-revproxy-api-key-env.path;
-    };
-  };
-}

services/lix-s3/web.nix

@@ -1,81 +0,0 @@
-{ config, lib, ... }:
-# TODO: move to wildcard TLS.
-let
-  cfgParent = config.bagel.s3;
-  cfg = config.bagel.s3.web;
-
-  buckets = [ "install" "cache" "releases" "docs" ];
-  mkWebLocationBlock = host: {
-    proxyPass = "http://127.0.0.1:3902";
-    extraConfig = ''
-      proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-      proxy_set_header Host ${host};
-    '';
-  };
-  mkDirectSubdomain = subdomain: {
-    enableACME = true;
-    forceSSL = true;
-    locations."/" = mkWebLocationBlock "${subdomain}.${webHost}";
-  };
-
-  # Makes a subdomain that gets proxied through s3-proxy to provide directory
-  # listings and reasonable 404 pages.
-  # This is not used on cache, since there a directory listing for cache is a
-  # liability at best.
-  mkProxiedSubdomain = subdomain: {
-    enableACME = true;
-    forceSSL = true;
-    locations."/" = {
-      recommendedProxySettings = true;
-      proxyPass = "http://127.0.0.1:${toString s3RevproxyPort}/";
-    };
-  };
-in
-{
-  options.bagel.s3.web = {
-
-  };
-
-  config = {
-    services.nginx = {
-      enable = true;
-
-      virtualHosts = {
-        ${host} = {
-          enableACME = true;
-          forceSSL = true;
-
-          serverAliases = builtins.map (b: "${b}.${host}") buckets;
-
-          locations."/" = {
-            proxyPass = "http://127.0.0.1:3900";
-
-            extraConfig = ''
-              proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-              proxy_set_header Host $host;
-
-              # Disable buffering to a temporary file.
-              proxy_max_temp_file_size 0;
-              client_max_body_size 20G;
-            '';
-          };
-        };
-
-        ${webHost} = {
-          enableACME = true;
-          forceSSL = true;
-          locations."/" = mkWebLocationBlock "$host";
-
-          # Create a subdomain for each bucket; and include special aliases
-          # for our special buckets 'cache' and 'install'.
-          serverAliases =
-            (builtins.map (b: "${b}.${webHost}") buckets);
-        };
-      };
-    };
-
-    networking.firewall.allowedTCPPorts = [
-      80 443
-    ];
-  };
-}

services/matrix/default.nix

@@ -32,6 +32,11 @@ in
           ];
           server_name = "forkos.org";
           database.backend = "rocksdb";
+
+          server_discovery = {
+            server.authority = "matrix.forkos.org:443";
+            client.base_url = "https://matrix.forkos.org";
+          };
         };
       };
 
@@ -48,18 +53,7 @@ in
           "forkos.org" = {
             forceSSL = true;
             enableACME = true;
-            locations = {
+            locations."/.well-known/matrix".proxyPass = "http://grapevine";
-              "= /.well-known/matrix/server".extraConfig = ''
-                add_header Content-Type application/json;
-                add_header Access-Control-Allow-Origin *;
-                return 200 '{"m.server": "matrix.forkos.org:443"}';
-              '';
-              "= /.well-known/matrix/client".extraConfig = ''
-                add_header Content-Type application/json;
-                add_header Access-Control-Allow-Origin *;
-                return 200 '{"m.homeserver": {"base_url": "https://matrix.forkos.org/"}, "m.identity_server": {"base_url": "https://matrix.org/"}, "org.matrix.msc3575.proxy": {"url": "https://matrix.forkos.org"}}';
-              '';
-            };
           };
         };
       };

services/monitoring/exporters/postgres.nix

@@ -23,6 +23,9 @@ in
     };
 
     services.postgresql.settings.shared_preload_libraries = "pg_stat_statements";
+    systemd.services.postgresql.postStart = lib.mkAfter ''
+      ${config.services.postgresql.package}/bin/psql -U postgres -c "CREATE EXTENSION IF NOT EXISTS pg_stat_statements;";
+    '';
 
     bagel.monitoring.grafana-agent.exporters.postgres.port = 9104;
   };

services/monitoring/lgtm/alerts/forkos.yaml

@@ -1,11 +1,11 @@
 groups:
-  - name: ForkOS automation
+    - name: ForkOS automation
-    rules:
+      rules:
-      - alert: SyncFailedTooOften
+        - alert: SyncFailedTooOften
-        expr: 'changes(node_systemd_unit_state{name=~"ows.*.service",state="failed"}[24h]) > 2'
+          expr: 'changes(node_systemd_unit_state{name=~"ows.*.service",state="failed"}[1d]) > 2'
-        for: 30m
+          for: 30m
-        labels:
+          labels:
-          severity: critical
+            severity: critical
-        annotations:
+          annotations:
-          summary: "Synchronization job {{ $labels.name }} has failed more than twice in the last 24 hours"
+            description: On {{ $labels.instance }}, the synchronization job has failed more than twice in the last 24 hours, check if there's a conflict or a stdenv change.
-          description: "On {{ $labels.instance }}, the synchronization job has failed more than twice in the last 24 hours, check if there's a conflict or a stdenv change."
+            summary: Synchronization job {{ $labels.name }} has failed more than twice in the last 24 hours

services/monitoring/lgtm/alerts/postgres.yml

@@ -1,102 +1,118 @@
 groups:
-- name: PostgreSQL
+    - name: PostgreSQL
-  rules:
+      rules:
-
+        - alert: PostgresqlTableNotAutoVacuumed
-    - alert: PostgresqlTableNotAutoVacuumed
+          expr: '(pg_stat_user_tables_last_autovacuum > 0) and (time() - pg_stat_user_tables_last_autovacuum) > 60 * 60 * 24 * 10'
-      expr: '(pg_stat_user_tables_last_autovacuum > 0) and (time() - pg_stat_user_tables_last_autovacuum) > 60 * 60 * 24 * 10'
+          labels:
-      for: 0m
+            severity: warning
-      labels:
+          annotations:
-        severity: warning
+            description: |-
-      annotations:
+                Table {{ $labels.relname }} has not been auto vacuumed for 10 days
-        summary: Postgresql table not auto vacuumed (instance {{ $labels.instance }})
+                  VALUE = {{ $value }}
-        description: "Table {{ $labels.relname }} has not been auto vacuumed for 10 days\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+                  LABELS = {{ $labels }}
-
+            summary: Postgresql table not auto vacuumed (instance {{ $labels.instance }})
-    - alert: PostgresqlTableNotAutoAnalyzed
+        - alert: PostgresqlTableNotAutoAnalyzed
-      expr: '(pg_stat_user_tables_last_autoanalyze > 0) and (time() - pg_stat_user_tables_last_autoanalyze) > 24 * 60 * 60 * 10'
+          expr: '(pg_stat_user_tables_last_autoanalyze > 0) and (time() - pg_stat_user_tables_last_autoanalyze) > 24 * 60 * 60 * 10'
-      for: 0m
+          labels:
-      labels:
+            severity: warning
-        severity: warning
+          annotations:
-      annotations:
+            description: |-
-        summary: Postgresql table not auto analyzed (instance {{ $labels.instance }})
+                Table {{ $labels.relname }} has not been auto analyzed for 10 days
-        description: "Table {{ $labels.relname }} has not been auto analyzed for 10 days\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+                  VALUE = {{ $value }}
-
+                  LABELS = {{ $labels }}
-    - alert: PostgresqlDeadLocks
+            summary: Postgresql table not auto analyzed (instance {{ $labels.instance }})
-      expr: 'increase(pg_stat_database_deadlocks{datname!~"template.*|postgres"}[1m]) > 5'
+        - alert: PostgresqlDeadLocks
-      for: 0m
+          expr: 'increase(pg_stat_database_deadlocks{datname!~"template.*|postgres"}[1m]) > 5'
-      labels:
+          labels:
-        severity: warning
+            severity: warning
-      annotations:
+          annotations:
-        summary: Postgresql dead locks (instance {{ $labels.instance }})
+            description: |-
-        description: "PostgreSQL has dead-locks\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+                PostgreSQL has dead-locks
-
+                  VALUE = {{ $value }}
-    - alert: PostgresqlHighRollbackRate
+                  LABELS = {{ $labels }}
-      expr: 'sum by (namespace,datname) ((rate(pg_stat_database_xact_rollback{datname!~"template.*|postgres",datid!="0"}[3m])) / ((rate(pg_stat_database_xact_rollback{datname!~"template.*|postgres",datid!="0"}[3m])) + (rate(pg_stat_database_xact_commit{datname!~"template.*|postgres",datid!="0"}[3m])))) > 0.02'
+            summary: Postgresql dead locks (instance {{ $labels.instance }})
-      for: 0m
+        - alert: PostgresqlHighRollbackRate
-      labels:
+          expr: 'sum by (namespace, datname) ((rate(pg_stat_database_xact_rollback{datid!="0",datname!~"template.*|postgres"}[3m])) / ((rate(pg_stat_database_xact_rollback{datid!="0",datname!~"template.*|postgres"}[3m])) + (rate(pg_stat_database_xact_commit{datid!="0",datname!~"template.*|postgres"}[3m])))) > 0.02'
-        severity: warning
+          labels:
-      annotations:
+            severity: warning
-        summary: Postgresql high rollback rate (instance {{ $labels.instance }})
+          annotations:
-        description: "Ratio of transactions being aborted compared to committed is > 2 %\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+            description: |-
-
+                Ratio of transactions being aborted compared to committed is > 2 %
-    - alert: PostgresqlHighRateStatementTimeout
+                  VALUE = {{ $value }}
-      expr: 'rate(postgresql_errors_total{type="statement_timeout"}[1m]) > 3'
+                  LABELS = {{ $labels }}
-      for: 0m
+            summary: Postgresql high rollback rate (instance {{ $labels.instance }})
-      labels:
+        - alert: PostgresqlHighRateStatementTimeout
-        severity: critical
+          expr: 'rate(postgresql_errors_total{type="statement_timeout"}[1m]) > 3'
-      annotations:
+          labels:
-        summary: Postgresql high rate statement timeout (instance {{ $labels.instance }})
+            severity: critical
-        description: "Postgres transactions showing high rate of statement timeouts\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+          annotations:
-
+            description: |-
-    - alert: PostgresqlHighRateDeadlock
+                Postgres transactions showing high rate of statement timeouts
-      expr: 'increase(postgresql_errors_total{type="deadlock_detected"}[1m]) > 1'
+                  VALUE = {{ $value }}
-      for: 0m
+                  LABELS = {{ $labels }}
-      labels:
+            summary: Postgresql high rate statement timeout (instance {{ $labels.instance }})
-        severity: critical
+        - alert: PostgresqlHighRateDeadlock
-      annotations:
+          expr: 'increase(postgresql_errors_total{type="deadlock_detected"}[1m]) > 1'
-        summary: Postgresql high rate deadlock (instance {{ $labels.instance }})
+          labels:
-        description: "Postgres detected deadlocks\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+            severity: critical
-
+          annotations:
-    - alert: PostgresqlTooManyDeadTuples
+            description: |-
-      expr: '((pg_stat_user_tables_n_dead_tup > 10000) / (pg_stat_user_tables_n_live_tup + pg_stat_user_tables_n_dead_tup)) >= 0.1'
+                Postgres detected deadlocks
-      for: 2m
+                  VALUE = {{ $value }}
-      labels:
+                  LABELS = {{ $labels }}
-        severity: warning
+            summary: Postgresql high rate deadlock (instance {{ $labels.instance }})
-      annotations:
+        - alert: PostgresqlTooManyDeadTuples
-        summary: Postgresql too many dead tuples (instance {{ $labels.instance }})
+          expr: '((pg_stat_user_tables_n_dead_tup > 10000) / (pg_stat_user_tables_n_live_tup + pg_stat_user_tables_n_dead_tup)) >= 0.1'
-        description: "PostgreSQL dead tuples is too large\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+          for: 2m
-
+          labels:
-    - alert: PostgresqlTooManyLocksAcquired
+            severity: warning
-      expr: '((sum (pg_locks_count)) / (pg_settings_max_locks_per_transaction * pg_settings_max_connections)) > 0.20'
+          annotations:
-      for: 2m
+            description: |-
-      labels:
+                PostgreSQL dead tuples is too large
-        severity: critical
+                  VALUE = {{ $value }}
-      annotations:
+                  LABELS = {{ $labels }}
-        summary: Postgresql too many locks acquired (instance {{ $labels.instance }})
+            summary: Postgresql too many dead tuples (instance {{ $labels.instance }})
-        description: "Too many locks acquired on the database. If this alert happens frequently, we may need to increase the postgres setting max_locks_per_transaction.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        - alert: PostgresqlTooManyLocksAcquired
-
+          expr: '((sum(pg_locks_count)) / (pg_settings_max_locks_per_transaction * pg_settings_max_connections)) > 0.2'
-    - alert: PostgresqlBloatIndexHigh(>80%)
+          for: 2m
-      expr: 'pg_bloat_btree_bloat_pct > 80 and on (idxname) (pg_bloat_btree_real_size > 100000000)'
+          labels:
-      for: 1h
+            severity: critical
-      labels:
+          annotations:
-        severity: warning
+            description: |-
-      annotations:
+                Too many locks acquired on the database. If this alert happens frequently, we may need to increase the postgres setting max_locks_per_transaction.
-        summary: Postgresql bloat index high (> 80%) (instance {{ $labels.instance }})
+                  VALUE = {{ $value }}
-        description: "The index {{ $labels.idxname }} is bloated. You should execute `REINDEX INDEX CONCURRENTLY {{ $labels.idxname }};`\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+                  LABELS = {{ $labels }}
-
+            summary: Postgresql too many locks acquired (instance {{ $labels.instance }})
-    - alert: PostgresqlBloatTableHigh(>80%)
+        - alert: PostgresqlBloatIndexHigh(>80%)
-      expr: 'pg_bloat_table_bloat_pct > 80 and on (relname) (pg_bloat_table_real_size > 200000000)'
+          expr: 'pg_bloat_btree_bloat_pct > 80 and on (idxname) (pg_bloat_btree_real_size > 1e+08)'
-      for: 1h
+          for: 1h
-      labels:
+          labels:
-        severity: warning
+            severity: warning
-      annotations:
+          annotations:
-        summary: Postgresql bloat table high (> 80%) (instance {{ $labels.instance }})
+            description: |-
-        description: "The table {{ $labels.relname }} is bloated. You should execute `VACUUM {{ $labels.relname }};`\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+                The index {{ $labels.idxname }} is bloated. You should execute `REINDEX INDEX CONCURRENTLY {{ $labels.idxname }};`
-
+                  VALUE = {{ $value }}
-    - alert: PostgresqlInvalidIndex
+                  LABELS = {{ $labels }}
-      expr: 'pg_genaral_index_info_pg_relation_size{indexrelname=~".*ccnew.*"}'
+            summary: Postgresql bloat index high (> 80%) (instance {{ $labels.instance }})
-      for: 6h
+        - alert: PostgresqlBloatTableHigh(>80%)
-      labels:
+          expr: 'pg_bloat_table_bloat_pct > 80 and on (relname) (pg_bloat_table_real_size > 2e+08)'
-        severity: warning
+          for: 1h
-      annotations:
+          labels:
-        summary: Postgresql invalid index (instance {{ $labels.instance }})
+            severity: warning
-        description: "The table {{ $labels.relname }} has an invalid index: {{ $labels.indexrelname }}. You should execute `DROP INDEX {{ $labels.indexrelname }};`\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+          annotations:
+            description: |-
+                The table {{ $labels.relname }} is bloated. You should execute `VACUUM {{ $labels.relname }};`
+                  VALUE = {{ $value }}
+                  LABELS = {{ $labels }}
+            summary: Postgresql bloat table high (> 80%) (instance {{ $labels.instance }})
+        - alert: PostgresqlInvalidIndex
+          expr: 'pg_genaral_index_info_pg_relation_size{indexrelname=~".*ccnew.*"}'
+          for: 6h
+          labels:
+            severity: warning
+          annotations:
+            description: |-
+                The table {{ $labels.relname }} has an invalid index: {{ $labels.indexrelname }}. You should execute `DROP INDEX {{ $labels.indexrelname }};`
+                  VALUE = {{ $value }}
+                  LABELS = {{ $labels }}
+            summary: Postgresql invalid index (instance {{ $labels.instance }})

services/monitoring/lgtm/alerts/resources.yaml

@@ -1,76 +1,100 @@
 groups:
-  - name: Host & hardware
+    - name: Host & hardware
-    rules:
+      rules:
-      - alert: HostOutOfMemory
+        - alert: HostOutOfMemory
-        expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
+          expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}
-        for: 2m
+          for: 2m
-        labels:
+          labels:
-          severity: warning
+            severity: warning
-        annotations:
+          annotations:
-          summary: Host out of memory (instance {{ $labels.instance }})
+            description: |-
-          description: "Node memory is filling up (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+                Node memory is filling up (< 10% left)
-      - alert: HostMemoryUnderMemoryPressure
+                  VALUE = {{ $value }}
-        expr: (rate(node_vmstat_pgmajfault[1m]) > 1000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
+                  LABELS = {{ $labels }}
-        for: 2m
+            summary: Host out of memory (instance {{ $labels.instance }})
-        labels:
+        - alert: HostMemoryUnderMemoryPressure
-          severity: warning
+          expr: (rate(node_vmstat_pgmajfault[1m]) > 1000) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}
-        annotations:
+          for: 2m
-          summary: Host memory under memory pressure (instance {{ $labels.instance }})
+          labels:
-          description: "The node is under heavy memory pressure. High rate of major page faults\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+            severity: warning
-      - alert: HostMemoryIsUnderutilized
+          annotations:
-        expr: (100 - (avg_over_time(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
+            description: |-
-        for: 1w
+                The node is under heavy memory pressure. High rate of major page faults
-        labels:
+                  VALUE = {{ $value }}
-          severity: info
+                  LABELS = {{ $labels }}
-        annotations:
+            summary: Host memory under memory pressure (instance {{ $labels.instance }})
-          summary: Host Memory is underutilized (instance {{ $labels.instance }})
+        - alert: HostMemoryIsUnderutilized
-          description: "Node memory is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+          expr: (100 - (avg_over_time(node_memory_MemAvailable_bytes[30m]) / node_memory_MemTotal_bytes * 100) < 20) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}
-      - alert: HostOutOfDiskSpace
+          for: 1w
-        expr: ((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
+          labels:
-        for: 2m
+            severity: info
-        labels:
+          annotations:
-          severity: warning
+            description: |-
-        annotations:
+                Node memory is < 20% for 1 week. Consider reducing memory space. (instance {{ $labels.instance }})
-          summary: Host out of disk space (instance {{ $labels.instance }})
+                  VALUE = {{ $value }}
-          description: "Disk is almost full (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+                  LABELS = {{ $labels }}
-      - alert: HostDiskWillFillIn24Hours
+            summary: Host Memory is underutilized (instance {{ $labels.instance }})
-        expr: ((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
+        - alert: HostOutOfDiskSpace
-        for: 2m
+          expr: ((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and on (instance, device, mountpoint) node_filesystem_readonly == 0) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}
-        labels:
+          for: 2m
-          severity: warning
+          labels:
-        annotations:
+            severity: warning
-          summary: Host disk will fill in 24 hours (instance {{ $labels.instance }})
+          annotations:
-          description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+            description: |-
-      - alert: HostCpuIsUnderutilized
+                Disk is almost full (< 10% left)
-        expr: (100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
+                  VALUE = {{ $value }}
-        for: 1w
+                  LABELS = {{ $labels }}
-        labels:
+            summary: Host out of disk space (instance {{ $labels.instance }})
-          severity: info
+        - alert: HostDiskWillFillIn24Hours
-        annotations:
+          expr: ((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and on (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and on (instance, device, mountpoint) node_filesystem_readonly == 0) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}
-          summary: Host CPU is underutilized (instance {{ $labels.instance }})
+          for: 2m
-          description: "CPU load is < 20% for 1 week. Consider reducing the number of CPUs.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+          labels:
-      - alert: HostCpuStealNoisyNeighbor
+            severity: warning
-        expr: (avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
+          annotations:
-        for: 0m
+            description: |-
-        labels:
+                Filesystem is predicted to run out of space within the next 24 hours at current write rate
-          severity: warning
+                  VALUE = {{ $value }}
-        annotations:
+                  LABELS = {{ $labels }}
-          summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
+            summary: Host disk will fill in 24 hours (instance {{ $labels.instance }})
-          description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+        - alert: HostCpuIsUnderutilized
-      - alert: HostOomKillDetected
+          expr: (100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}
-        expr: (increase(node_vmstat_oom_kill[1m]) > 0) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
+          for: 1w
-        for: 0m
+          labels:
-        labels:
+            severity: info
-          severity: warning
+          annotations:
-        annotations:
+            description: |-
-          summary: Host OOM kill detected (instance {{ $labels.instance }})
+                CPU load is < 20% for 1 week. Consider reducing the number of CPUs.
-          description: "OOM kill detected\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+                  VALUE = {{ $value }}
-      - alert: HostNetworkInterfaceSaturated
+                  LABELS = {{ $labels }}
-        expr: ((rate(node_network_receive_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"} > 0.8 < 10000) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
+            summary: Host CPU is underutilized (instance {{ $labels.instance }})
-        for: 1m
+        - alert: HostCpuStealNoisyNeighbor
-        labels:
+          expr: (avg by (instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}
-          severity: warning
+          labels:
-        annotations:
+            severity: warning
-          summary: Host Network Interface Saturated (instance {{ $labels.instance }})
+          annotations:
-          description: "The network interface \"{{ $labels.device }}\" on \"{{ $labels.instance }}\" is getting overloaded.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+            description: |-
-
+                CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.
+                  VALUE = {{ $value }}
+                  LABELS = {{ $labels }}
+            summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
+        - alert: HostOomKillDetected
+          expr: (increase(node_vmstat_oom_kill[1m]) > 0) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}
+          labels:
+            severity: warning
+          annotations:
+            description: |-
+                OOM kill detected
+                  VALUE = {{ $value }}
+                  LABELS = {{ $labels }}
+            summary: Host OOM kill detected (instance {{ $labels.instance }})
+        - alert: HostNetworkInterfaceSaturated
+          expr: ((rate(node_network_receive_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*|^vnet.*|^veth.*|^tun.*"} > 0.8 < 10000) * on (instance) group_left (nodename) node_uname_info{nodename=~".+"}
+          for: 1m
+          labels:
+            severity: warning
+          annotations:
+            description: |-
+                The network interface "{{ $labels.device }}" on "{{ $labels.instance }}" is getting overloaded.
+                  VALUE = {{ $value }}
+                  LABELS = {{ $labels }}
+            summary: Host Network Interface Saturated (instance {{ $labels.instance }})

services/monitoring/lgtm/dashboards/postgres2.json

@@ -20,7 +20,6 @@
   "fiscalYearStartMonth": 0,
   "gnetId": 9628,
   "graphTooltip": 0,
-  "id": 27,
   "links": [],
   "liveNow": false,
   "panels": [
@@ -101,6 +100,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "mean"
@@ -112,14 +112,14 @@
         "textMode": "name",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_static{hostname=\"$hostname\"}",
+          "expr": "pg_static{tenant=\"$tenant\",hostname=\"$hostname\"}",
           "format": "time_series",
           "instant": true,
           "intervalFactor": 1,
@@ -182,6 +182,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "mean"
@@ -193,14 +194,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_postmaster_start_time_seconds{hostname=\"$hostname\"} * 1000",
+          "expr": "pg_postmaster_start_time_seconds{tenant=\"$tenant\",hostname=\"$hostname\"} * 1000",
           "format": "time_series",
           "intervalFactor": 2,
           "legendFormat": "",
@@ -261,6 +262,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -272,14 +274,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "SUM(pg_stat_database_tup_fetched{datname=~\"$datname\", hostname=~\"$hostname\"})",
+          "expr": "SUM(pg_stat_database_tup_fetched{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\"})",
           "format": "time_series",
           "intervalFactor": 2,
           "refId": "A",
@@ -340,6 +342,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -351,14 +354,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "SUM(pg_stat_database_tup_inserted{datname=~\"$datname\", hostname=~\"$hostname\"})",
+          "expr": "SUM(pg_stat_database_tup_inserted{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\"})",
           "format": "time_series",
           "intervalFactor": 2,
           "refId": "A",
@@ -419,6 +422,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -430,14 +434,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "SUM(pg_stat_database_tup_updated{datname=~\"$datname\", hostname=~\"$hostname\"})",
+          "expr": "SUM(pg_stat_database_tup_updated{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\"})",
           "format": "time_series",
           "intervalFactor": 2,
           "refId": "A",
@@ -498,6 +502,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "mean"
@@ -509,14 +514,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_settings_max_connections{hostname=\"$hostname\"}",
+          "expr": "pg_settings_max_connections{tenant=\"$tenant\",hostname=\"$hostname\"}",
           "format": "time_series",
           "intervalFactor": 1,
           "refId": "A"
@@ -602,6 +607,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -613,14 +619,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_settings_shared_buffers_bytes{hostname=\"$hostname\"}",
+          "expr": "pg_settings_shared_buffers_bytes{tenant=\"$tenant\",hostname=\"$hostname\"}",
           "format": "time_series",
           "intervalFactor": 1,
           "refId": "A"
@@ -680,6 +686,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -691,14 +698,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_settings_effective_cache_size_bytes{hostname=\"$hostname\"}",
+          "expr": "pg_settings_effective_cache_size_bytes{tenant=\"$tenant\",hostname=\"$hostname\"}",
           "format": "time_series",
           "intervalFactor": 1,
           "refId": "A"
@@ -758,6 +765,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -769,14 +777,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_settings_maintenance_work_mem_bytes{hostname=\"$hostname\"}",
+          "expr": "pg_settings_maintenance_work_mem_bytes{tenant=\"$tenant\",hostname=\"$hostname\"}",
           "format": "time_series",
           "intervalFactor": 1,
           "refId": "A"
@@ -836,6 +844,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -847,14 +856,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_settings_work_mem_bytes{hostname=\"$hostname\"}",
+          "expr": "pg_settings_work_mem_bytes{tenant=\"$tenant\",hostname=\"$hostname\"}",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "",
@@ -916,6 +925,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -927,14 +937,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_settings_max_wal_size_bytes{hostname=\"$hostname\"}",
+          "expr": "pg_settings_max_wal_size_bytes{tenant=\"$tenant\",hostname=\"$hostname\"}",
           "format": "time_series",
           "intervalFactor": 1,
           "refId": "A"
@@ -994,6 +1004,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -1005,14 +1016,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_settings_random_page_cost{hostname=\"$hostname\"}",
+          "expr": "pg_settings_random_page_cost{tenant=\"$tenant\",hostname=\"$hostname\"}",
           "format": "time_series",
           "intervalFactor": 1,
           "refId": "A"
@@ -1072,6 +1083,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -1083,7 +1095,7 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
@@ -1150,6 +1162,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "mean"
@@ -1161,14 +1174,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_settings_max_worker_processes{hostname=\"$hostname\"}",
+          "expr": "pg_settings_max_worker_processes{tenant=\"$tenant\",hostname=\"$hostname\"}",
           "format": "time_series",
           "intervalFactor": 1,
           "refId": "A"
@@ -1228,6 +1241,7 @@
         "graphMode": "none",
         "justifyMode": "auto",
         "orientation": "horizontal",
+        "percentChangeColorMode": "standard",
         "reduceOptions": {
           "calcs": [
             "lastNotNull"
@@ -1239,14 +1253,14 @@
         "textMode": "auto",
         "wideLayout": true
       },
-      "pluginVersion": "11.0.0",
+      "pluginVersion": "11.2.1",
       "targets": [
         {
           "datasource": {
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_settings_max_parallel_workers{hostname=\"$hostname\"}",
+          "expr": "pg_settings_max_parallel_workers{tenant=\"$tenant\",hostname=\"$hostname\"}",
           "format": "time_series",
           "intervalFactor": 1,
           "refId": "A"
@@ -1298,6 +1312,7 @@
             "axisLabel": "",
             "axisPlacement": "auto",
             "barAlignment": 0,
+            "barWidthFactor": 0.6,
             "drawStyle": "points",
             "fillOpacity": 10,
             "gradientMode": "none",
@@ -1372,7 +1387,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_stat_activity_count{datname=~\"$datname\", hostname=~\"$hostname\", state=\"active\"} !=0",
+          "expr": "pg_stat_activity_count{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\", state=\"active\"} !=0",
           "format": "time_series",
           "interval": "",
           "intervalFactor": 2,
@@ -1401,6 +1416,7 @@
             "axisLabel": "",
             "axisPlacement": "auto",
             "barAlignment": 0,
+            "barWidthFactor": 0.6,
             "drawStyle": "line",
             "fillOpacity": 10,
             "gradientMode": "none",
@@ -1474,7 +1490,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_database_xact_commit{hostname=\"$hostname\", datname=~\"$datname\"}[5m])",
+          "expr": "irate(pg_stat_database_xact_commit{tenant=\"$tenant\",hostname=\"$hostname\", datname=~\"$datname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{datname}} commits",
@@ -1485,7 +1501,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_database_xact_rollback{hostname=\"$hostname\", datname=~\"$datname\"}[5m])",
+          "expr": "irate(pg_stat_database_xact_rollback{tenant=\"$tenant\",hostname=\"$hostname\", datname=~\"$datname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{datname}} rollbacks",
@@ -1512,6 +1528,7 @@
             "axisLabel": "",
             "axisPlacement": "auto",
             "barAlignment": 0,
+            "barWidthFactor": 0.6,
             "drawStyle": "line",
             "fillOpacity": 10,
             "gradientMode": "none",
@@ -1585,7 +1602,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_stat_database_tup_updated{datname=~\"$datname\", hostname=~\"$hostname\"} != 0",
+          "expr": "pg_stat_database_tup_updated{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\"} != 0",
           "format": "time_series",
           "intervalFactor": 2,
           "legendFormat": "{{datname}}",
@@ -1613,6 +1630,7 @@
             "axisLabel": "",
             "axisPlacement": "auto",
             "barAlignment": 0,
+            "barWidthFactor": 0.6,
             "drawStyle": "line",
             "fillOpacity": 10,
             "gradientMode": "none",
@@ -1686,7 +1704,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_stat_database_tup_fetched{datname=~\"$datname\", hostname=~\"$hostname\"} != 0",
+          "expr": "pg_stat_database_tup_fetched{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\"} != 0",
           "format": "time_series",
           "intervalFactor": 2,
           "legendFormat": "{{datname}}",
@@ -1714,6 +1732,7 @@
             "axisLabel": "",
             "axisPlacement": "auto",
             "barAlignment": 0,
+            "barWidthFactor": 0.6,
             "drawStyle": "line",
             "fillOpacity": 10,
             "gradientMode": "none",
@@ -1787,7 +1806,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_stat_database_tup_inserted{datname=~\"$datname\", hostname=~\"$hostname\"} != 0",
+          "expr": "pg_stat_database_tup_inserted{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\"} != 0",
           "format": "time_series",
           "intervalFactor": 2,
           "legendFormat": "{{datname}}",
@@ -1815,6 +1834,7 @@
             "axisLabel": "",
             "axisPlacement": "auto",
             "barAlignment": 0,
+            "barWidthFactor": 0.6,
             "drawStyle": "line",
             "fillOpacity": 10,
             "gradientMode": "none",
@@ -1890,7 +1910,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_locks_count{datname=~\"$datname\", hostname=~\"$hostname\", mode=~\"$mode\"} != 0",
+          "expr": "pg_locks_count{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\", mode=~\"$mode\"} != 0",
           "format": "time_series",
           "intervalFactor": 2,
           "legendFormat": "{{datname}},{{mode}}",
@@ -1948,8 +1968,7 @@
             "mode": "absolute",
             "steps": [
               {
-                "color": "green",
+                "color": "green"
-                "value": null
               },
               {
                 "color": "red",
@@ -1991,7 +2010,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_stat_database_tup_returned{datname=~\"$datname\", hostname=~\"$hostname\"} != 0",
+          "expr": "pg_stat_database_tup_returned{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\"} != 0",
           "format": "time_series",
           "intervalFactor": 2,
           "legendFormat": "{{datname}}",
@@ -2050,8 +2069,7 @@
             "mode": "absolute",
             "steps": [
               {
-                "color": "green",
+                "color": "green"
-                "value": null
               },
               {
                 "color": "red",
@@ -2092,7 +2110,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_stat_activity_count{datname=~\"$datname\", hostname=~\"$hostname\", state=~\"idle|idle in transaction|idle in transaction (aborted)\"}",
+          "expr": "pg_stat_activity_count{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\", state=~\"idle|idle in transaction|idle in transaction (aborted)\"}",
           "format": "time_series",
           "intervalFactor": 2,
           "legendFormat": "{{datname}}, s: {{state}}",
@@ -2150,8 +2168,7 @@
             "mode": "absolute",
             "steps": [
               {
-                "color": "green",
+                "color": "green"
-                "value": null
               },
               {
                 "color": "red",
@@ -2193,7 +2210,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_stat_database_tup_deleted{datname=~\"$datname\", hostname=~\"$hostname\"} != 0",
+          "expr": "pg_stat_database_tup_deleted{datname=~\"$datname\", tenant=\"$tenant\",hostname=~\"$hostname\"} != 0",
           "format": "time_series",
           "intervalFactor": 2,
           "legendFormat": "{{datname}}",
@@ -2252,8 +2269,7 @@
             "mode": "absolute",
             "steps": [
               {
-                "color": "green",
+                "color": "green"
-                "value": null
               },
               {
                 "color": "red",
@@ -2294,7 +2310,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "pg_stat_database_blks_hit{hostname=\"$hostname\", datname=~\"$datname\"} / (pg_stat_database_blks_read{hostname=\"$hostname\", datname=~\"$datname\"} + pg_stat_database_blks_hit{hostname=\"$hostname\", datname=~\"$datname\"})",
+          "expr": "pg_stat_database_blks_hit{tenant=\"$tenant\",hostname=\"$hostname\", datname=~\"$datname\"} / (pg_stat_database_blks_read{tenant=\"$tenant\",hostname=\"$hostname\", datname=~\"$datname\"} + pg_stat_database_blks_hit{tenant=\"$tenant\",hostname=\"$hostname\", datname=~\"$datname\"})",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ datname }}",
@@ -2351,8 +2367,7 @@
             "mode": "absolute",
             "steps": [
               {
-                "color": "green",
+                "color": "green"
-                "value": null
               },
               {
                 "color": "red",
@@ -2395,7 +2410,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_bgwriter_buffers_backend{hostname=\"$hostname\"}[5m])",
+          "expr": "irate(pg_stat_bgwriter_buffers_backend{tenant=\"$tenant\",hostname=\"$hostname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "buffers_backend",
@@ -2406,7 +2421,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_bgwriter_buffers_alloc{hostname=\"$hostname\"}[5m])",
+          "expr": "irate(pg_stat_bgwriter_buffers_alloc{tenant=\"$tenant\",hostname=\"$hostname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "buffers_alloc",
@@ -2417,7 +2432,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_bgwriter_buffers_backend_fsync{hostname=\"$hostname\"}[5m])",
+          "expr": "irate(pg_stat_bgwriter_buffers_backend_fsync{tenant=\"$tenant\",hostname=\"$hostname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "backend_fsync",
@@ -2428,7 +2443,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_bgwriter_buffers_checkpoint{hostname=\"$hostname\"}[5m])",
+          "expr": "irate(pg_stat_bgwriter_buffers_checkpoint{tenant=\"$tenant\",hostname=\"$hostname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "buffers_checkpoint",
@@ -2439,7 +2454,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_bgwriter_buffers_clean{hostname=\"$hostname\"}[5m])",
+          "expr": "irate(pg_stat_bgwriter_buffers_clean{tenant=\"$tenant\",hostname=\"$hostname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "buffers_clean",
@@ -2497,8 +2512,7 @@
             "mode": "absolute",
             "steps": [
               {
-                "color": "green",
+                "color": "green"
-                "value": null
               },
               {
                 "color": "red",
@@ -2540,7 +2554,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_database_conflicts{hostname=\"$hostname\", datname=~\"$datname\"}[5m])",
+          "expr": "irate(pg_stat_database_conflicts{tenant=\"$tenant\",hostname=\"$hostname\", datname=~\"$datname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{datname}} conflicts",
@@ -2551,7 +2565,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_database_deadlocks{hostname=\"$hostname\", datname=~\"$datname\"}[5m])",
+          "expr": "irate(pg_stat_database_deadlocks{tenant=\"$tenant\",hostname=\"$hostname\", datname=~\"$datname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{datname}} deadlocks",
@@ -2610,8 +2624,7 @@
             "mode": "absolute",
             "steps": [
               {
-                "color": "green",
+                "color": "green"
-                "value": null
               },
               {
                 "color": "red",
@@ -2653,7 +2666,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_database_temp_bytes{hostname=\"$hostname\", datname=~\"$datname\"}[5m])",
+          "expr": "irate(pg_stat_database_temp_bytes{tenant=\"$tenant\",hostname=\"$hostname\", datname=~\"$datname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{datname}}",
@@ -2710,8 +2723,7 @@
             "mode": "absolute",
             "steps": [
               {
-                "color": "green",
+                "color": "green"
-                "value": null
               },
               {
                 "color": "red",
@@ -2754,7 +2766,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_bgwriter_checkpoint_write_time{hostname=\"$hostname\"}[5m])",
+          "expr": "irate(pg_stat_bgwriter_checkpoint_write_time{tenant=\"$tenant\",hostname=\"$hostname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "write_time - Total amount of time that has been spent in the portion of checkpoint processing where files are written to disk.",
@@ -2765,7 +2777,7 @@
             "type": "prometheus",
             "uid": "mimir"
           },
-          "expr": "irate(pg_stat_bgwriter_checkpoint_sync_time{hostname=\"$hostname\"}[5m])",
+          "expr": "irate(pg_stat_bgwriter_checkpoint_sync_time{tenant=\"$tenant\",hostname=\"$hostname\"}[5m])",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "sync_time - Total amount of time that has been spent in the portion of checkpoint processing where files are synchronized to disk.",
@@ -2866,8 +2878,32 @@
       {
         "current": {
           "selected": false,
-          "text": "bagel-box",
+          "text": "fake",
-          "value": "bagel-box"
+          "value": "fake"
+        },
+        "definition": "label_values(tenant)",
+        "hide": 0,
+        "includeAll": true,
+        "label": "Tenant",
+        "multi": true,
+        "name": "tenant",
+        "options": [],
+        "query": {
+          "qryType": 1,
+          "query": "label_values(tenant)",
+          "refId": "PrometheusVariableQueryEditor-VariableQuery"
+        },
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "sort": 0,
+        "type": "query"
+      },
+      {
+        "current": {
+          "selected": true,
+          "text": "buildbot",
+          "value": "buildbot"
         },
         "datasource": {
           "type": "prometheus",
@@ -2962,7 +2998,6 @@
     "from": "now-6h",
     "to": "now"
   },
-  "timeRangeUpdatedDuringEditOrView": false,
   "timepicker": {
     "refresh_intervals": [
       "5s",

services/monitoring/lgtm/grafana.nix

@@ -17,7 +17,7 @@ in
 
   config = mkIf cfg.enable {
     age.secrets.grafana-oauth-secret = {
-      file = ../../../secrets/grafana-oauth-secret.age;
+      file = ../../../secrets/floral/grafana-oauth-secret.age;
       owner = "grafana";
     };
 

services/monitoring/lgtm/loki.nix

@@ -13,10 +13,10 @@ in
   config = mkIf cfg.enable {
     age.secrets = {
       metrics-push-htpasswd = {
-        file = ../../../secrets/metrics-push-htpasswd.age;
+        file = ../../../secrets/floral/metrics-push-htpasswd.age;
         owner = "nginx";
       };
-      loki-environment.file = ../../../secrets/loki-environment.age;
+      loki-environment.file = ../../../secrets/floral/loki-environment.age;
     };
 
     services.loki = {

services/monitoring/lgtm/mimir.nix

@@ -9,6 +9,15 @@ let
   inherit (lib) mkEnableOption mkIf;
 
   mimirPort = config.services.mimir.configuration.server.http_listen_port;
+
+  alerts = pkgs.runCommand "mimir-alerts-checked" {
+    src = ./alerts;
+    nativeBuildInputs = with pkgs; [ prometheus.cli ];
+  } ''
+    promtool check rules $src/*
+    mkdir $out
+    cp -R $src $out/anonymous/
+  '';
 in
 {
   options.bagel.services.prometheus.enable = mkEnableOption "Prometheus scraper";
@@ -16,11 +25,11 @@ in
   config = mkIf cfg.enable {
     age.secrets = {
       metrics-push-htpasswd = {
-        file = ../../../secrets/metrics-push-htpasswd.age;
+        file = ../../../secrets/floral/metrics-push-htpasswd.age;
         owner = "nginx";
       };
-      mimir-environment.file = ../../../secrets/mimir-environment.age;
+      mimir-environment.file = ../../../secrets/floral/mimir-environment.age;
-      mimir-webhook-url.file = ../../../secrets/mimir-webhook-url.age;
+      mimir-webhook-url.file = ../../../secrets/floral/mimir-webhook-url.age;
     };
 
     services.mimir = {
@@ -60,10 +69,7 @@ in
         blocks_storage.backend = "s3";
         ruler_storage = {
           backend = "local";
-          local.directory = pkgs.runCommand "mimir-rules" {} ''
+          local.directory = alerts;
-            mkdir -p $out
-            ln -s ${./alerts} $out/anonymous
-          '';
         };
 
         alertmanager = {

services/monitoring/lgtm/tempo.nix

@@ -13,10 +13,10 @@ in
   config = mkIf cfg.enable {
     age.secrets = {
       metrics-push-htpasswd = {
-        file = ../../../secrets/metrics-push-htpasswd.age;
+        file = ../../../secrets/floral/metrics-push-htpasswd.age;
         owner = "nginx";
       };
-      tempo-environment.file = ../../../secrets/tempo-environment.age;
+      tempo-environment.file = ../../../secrets/floral/tempo-environment.age;
     };
 
     services.tempo = {

services/netbox/default.nix

@@ -20,7 +20,10 @@ in
   };
 
   config = mkIf cfg.enable {
-    age.secrets.netbox-environment.file = ../../secrets/netbox-environment.age;
+    # FIXME: why
+    nixpkgs.config.permittedInsecurePackages = [ pkgs.netbox_3_7.name ];
+
+    age.secrets.netbox-environment.file = ../../secrets/floral/netbox-environment.age;
     services = {
       netbox = {
         enable = true;

services/ofborg/default.nix

@@ -26,10 +26,12 @@ in {
       webroot = "/var/lib/acme/.challenges";
       group = "rabbitmq";
     };
+
+    services.nginx.enable = true;
     services.nginx.virtualHosts.${amqpHost}.locations."/.well-known/acme-challenge".root =
       "/var/lib/acme/.challenges";
     systemd.services.rabbitmq.requires = ["acme-finished-${amqpHost}.target"];
 
-    networking.firewall.allowedTCPPorts = [ amqpPort ];
+    networking.firewall.allowedTCPPorts = [ 80 443 amqpPort ];
   };
 }

services/s3-revproxy/default.nix

@@ -70,7 +70,7 @@ in
   ];
 
   config = mkIf cfg.enable {
-    age.secrets.s3-revproxy-api-keys.file = ../../secrets/s3-revproxy-api-keys.age;
+    age.secrets.s3-revproxy-api-keys.file = ../../secrets/floral/s3-revproxy-api-keys.age;
     # For each target, generate an entry that passes it to the s3-revproxy.
     services.nginx.virtualHosts = mapAttrs' (subdomain: _: nameValuePair "${subdomain}.${cfg.domain}" (mkProxiedSubdomain subdomain)) cfg.targets;
     # this solves garage supporting neither anonymous access nor automatic

services/uptime-kuma/default.nix

@@ -59,7 +59,7 @@ in
       443
     ];
 
-    age.secrets.stateless-uptime-kuma-password.file = ../../secrets/stateless-uptime-kuma-password.age;
+    age.secrets.stateless-uptime-kuma-password.file = ../../secrets/floral/stateless-uptime-kuma-password.age;
     statelessUptimeKuma = {
       probesConfig = {
         monitors = lib.genAttrs subdomains (name: {
@@ -83,6 +83,9 @@ in
             ];
           };
         };
+        settings = {
+          entryPage = "statusPage-forkos";
+        };
       };
       extraFlags = [ "-s" ];
       host = "http://localhost:${builtins.toString port}/";