Update Terraform libvirt to v0.9.8

improve health checks across all nomad job specs
- traefik: TCP → HTTP check on /ping (enable ping entrypoint) - gitea: check path → /api/healthz - jellyfin: TCP → HTTP check on /health - glance: TCP → HTTP check on / - sonarr/prowlarr: check path / → /ping (×2 checks each) - ntfy/transfer/deluge/openreader/authelia/pgadmin: add name and port to existing checks - postgres: remove invalid TCP check (Connect-enabled service) - unifi: TCP → script check via curl (macvlan host isolation workaround)
2026-07-15 10:26:41 +00:00 · 2026-05-26 20:12:23 +10:00 · 2026-04-19 18:06:17 +10:00
20 changed files with 133 additions and 48 deletions
@@ -52,3 +52,39 @@ jobs:
            echo "==> $f"
            nomad job validate "$f"
          done
+
+  image-pull:
+    name: Docker image pull validation
+    runs-on: ubuntu-latest
+    # Only run on PRs that touch nomad job specs
+    if: github.event_name == 'pull_request'
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Pull changed images
+        run: |
+          git fetch origin ${{ github.base_ref }}
+          IMAGES=$(git diff origin/${{ github.base_ref }}...HEAD -- '*.nomad.hcl' \
+            | grep '^+\s*image\s*=' \
+            | grep -oP '"[^"]+:[^"]+"' \
+            | tr -d '"' \
+            | sort -u || true)
+
+          if [ -z "$IMAGES" ]; then
+            echo "No image changes detected, skipping pull."
+            exit 0
+          fi
+
+          FAILED=0
+          while IFS= read -r image; do
+            echo "==> Pulling $image"
+            if ! docker pull "$image"; then
+              echo "ERROR: Failed to pull $image"
+              FAILED=1
+            fi
+          done <<< "$IMAGES"
+
+          exit $FAILED
@@ -6,7 +6,7 @@ job "csi-smb" {
      driver = "docker"

      config {
-        image = "mcr.microsoft.com/k8s/csi/smb-csi:v1.17.0"
+        image = "mcr.microsoft.com/k8s/csi/smb-csi:v1.7.0"
        args = [
          "--v=5",
          "--nodeid=${attr.unique.hostname}",
@@ -58,8 +58,10 @@ job "pgadmin" {
        ]

        check {
+          name     = "alive"
          type     = "http"
          path     = "/"
+          port     = "http"
          interval = "10s"
          timeout  = "2s"
        }
@@ -7,6 +7,10 @@ job "postgres" {
      connect {
        sidecar_service {}
      }
+
+      # Note: TCP checks are not valid for Connect-enabled services (runs through
+      # Envoy sidecar). Postgres is a single-writer DB that we never canary, so
+      # observable health via Consul is lower priority than other services.
    }

    task "postgres" {
@@ -33,8 +33,10 @@ job "authelia" {
      }

      check {
+        name     = "alive"
        type     = "http"
        path     = "/health"
+        port     = "http"
        interval = "10s"
        timeout  = "2s"
      }
@@ -35,7 +35,8 @@ job "traefik" {

      check {
        name     = "alive"
-        type     = "tcp"
+        type     = "http"
+        path     = "/ping"
        port     = "api"
        interval = "10s"
        timeout  = "2s"
@@ -85,6 +86,9 @@ api:
  dashboard: true
  insecure: true

+ping:
+  entryPoint: traefik
+
 providers:
  file:
    directory: "/etc/traefik/configs/"
@@ -29,7 +29,6 @@ job "act-runner" {

      env = {
        GITEA_INSTANCE_URL = "https://gitea-1ef0bea6b75a4fd3e9393a9f7f7e4b02.othrayte.one"
-        CONFIG_FILE        = "/secrets/runner-config.yml"
      }

      # Required SOPS key:
@@ -43,19 +42,6 @@ EOF
        env         = true
      }

-      # Limit which images/labels the runner will accept so it doesn't pick up
-      # unrelated workloads if more runners are added later.
-      template {
-        data        = <<EOF
-runner:
-  labels:
-    - "ubuntu-latest:docker://node:20-bookworm"
-    - "ubuntu-22.04:docker://node:20-bookworm"
-    - "ubuntu-24.04:docker://node:20-bookworm"
-EOF
-        destination = "secrets/runner-config.yml"
-      }
-
      resources {
        cpu        = 200
        memory     = 256
@@ -54,8 +54,10 @@ EOH
      ]

      check {
+        name     = "alive"
        type     = "http"
        path     = "/"
+        port     = "http"
        interval = "10s"
        timeout  = "2s"
      }
@@ -78,8 +80,10 @@ EOH
      }

      check {
+        name     = "alive"
        type     = "http"
        path     = "/"
+        port     = "http"
        interval = "10s"
        timeout  = "2s"
      }
@@ -32,8 +32,10 @@ job "gitea" {
      ]

      check {
+        name     = "alive"
        type     = "http"
-        path     = "/"
+        path     = "/api/healthz"
+        port     = "http"
        interval = "10s"
        timeout  = "2s"
      }
@@ -12,7 +12,7 @@ job "glance" {
      driver = "docker"

      config {
-        image = "glanceapp/glance:latest"
+        image = "glanceapp/glance:v0.7.8"
        ports = ["http"]
        volumes = [
          "local/glance.yml:/app/config/glance.yml",
@@ -30,7 +30,8 @@ job "glance" {

        check {
          name     = "alive"
-          type     = "tcp"
+          type     = "http"
+          path     = "/"
          port     = "http"
          interval = "10s"
          timeout  = "2s"
@@ -28,10 +28,11 @@ job "jellyfin" {

        check {
          name     = "alive"
-          type     = "tcp"
+          type     = "http"
+          path     = "/health"
          port     = "http"
          interval = "10s"
-          timeout  = "2s"
+          timeout  = "5s"
        }
      }

@@ -33,8 +33,10 @@ job "ntfy" {
      ]

      check {
+        name     = "alive"
        type     = "http"
        path     = "/healthz"
+        port     = "http"
        interval = "10s"
        timeout  = "2s"
      }
@@ -31,8 +31,10 @@ job "openreader" {
      ]

      check {
+        name     = "alive"
        type     = "http"
        path     = "/"
+        port     = "http"
        interval = "10s"
        timeout  = "2s"
      }
@@ -48,8 +50,10 @@ job "openreader" {
      }

      check {
+        name     = "alive"
        type     = "http"
        path     = "/"
+        port     = "http"
        interval = "10s"
        timeout  = "2s"
      }
@@ -34,8 +34,9 @@ job "prowlarr" {
      ]

      check {
+        name     = "alive"
        type     = "http"
-        path     = "/"
+        path     = "/ping"
        interval = "10s"
        timeout  = "2s"
      }
@@ -51,8 +52,9 @@ job "prowlarr" {
      }

      check {
+        name     = "alive"
        type     = "http"
-        path     = "/"
+        path     = "/ping"
        interval = "10s"
        timeout  = "2s"
      }
@@ -37,8 +37,9 @@ job "sonarr" {
      ]

      check {
+        name     = "alive"
        type     = "http"
-        path     = "/"
+        path     = "/ping"
        interval = "10s"
        timeout  = "2s"
      }
@@ -54,8 +55,9 @@ job "sonarr" {
      }

      check {
+        name     = "alive"
        type     = "http"
-        path     = "/"
+        path     = "/ping"
        interval = "10s"
        timeout  = "2s"
      }
@@ -16,8 +16,10 @@ job "transfer" {
      ]

      check {
+        name     = "alive"
        type     = "http"
        path     = "/"
+        port     = "http"
        interval = "10s"
        timeout  = "2s"
      }
@@ -21,6 +21,26 @@ job "unifi-network" {
        UNIFI_STDOUT       = "true"
      }

+      # Register in Consul so Traefik and health checks can find it.
+      # address_mode=driver uses the macvlan IP (192.168.1.50) rather than the host IP.
+      service {
+        name         = "unifi-network"
+        port         = 8443
+        address_mode = "driver"
+
+        # TCP/HTTP checks from the Consul agent can't reach the macvlan IP (host↔macvlan
+        # isolation). Use a script check instead — it runs inside the container via
+        # docker exec and connects to localhost:8443 directly.
+        check {
+          name     = "alive"
+          type     = "script"
+          command  = "/usr/bin/curl"
+          args     = ["-sk", "--max-time", "5", "-o", "/dev/null", "https://localhost:8443"]
+          interval = "30s"
+          timeout  = "10s"
+        }
+      }
+
      volume_mount {
        volume      = "unraid_appdata_unifi_network"
        destination = "/unifi" # Expected root directory (contains data, log, cert subdirs)
@@ -2,23 +2,34 @@
 # Manual edits may be lost in future updates.

 provider "registry.terraform.io/dmacvicar/libvirt" {
-  version     = "0.7.6"
-  constraints = "0.7.6"
+  version     = "0.9.8"
+  constraints = "0.9.8"
  hashes = [
-    "h1:mmbm4vTyC/DCGO4Ed/vbp5AKvy1gmVn/94fzB9VmR08=",
-    "zh:0bde54f6f658b20b620b875daf106b5b25b1bae4d15408d6c5f06d58360e254d",
-    "zh:0c97c6930015918b8a34b6d7a2b0c3d17a649c226fcd1874fcba5bbbc0f35972",
-    "zh:1bdd7aa0011c5f024a09a124836ee9bc8e71b05a6ece810c61824275fd3f695f",
-    "zh:2b0cc7c794e4caf395d84ffff0b380d17e4b3219a4696264271bfe5059450efe",
-    "zh:2f8633f7fe07f76c188836ed6f93321ec5fbf5c004bc7699e1741d9b21ed5f37",
-    "zh:5bf47eed286ce55ed10a5cf657de49a34ab21cc8677c56fef3aab69cdde41a27",
-    "zh:7dca790fc5fd1d42bc4bc7170be003a7093602026d0f95c8aab84ad551fdf2a4",
-    "zh:80476b68bc84e3d661d1390025f83879b88f9cdc836de9751af09bd5716089cb",
-    "zh:82f3e2f3f50176cd6041c8ba36e295cbda1b289ef52ab75b5eceb0f921f64f7b",
-    "zh:a179b165f3b9bb9a67ebbbf9d73157ded33f02d476b2f58906389dca03b653c9",
-    "zh:acae54a5d0616f22b3180ddd8e8aad39af664e604394fdacf1f7b337bca2d5b4",
-    "zh:da4406a2428a9a7e98272c032cb93431c3919253af2fe9934b532d26c0deab09",
-    "zh:f63dbd8e579ab5268d01ffab4503b8a8e736b70d1a04e4f271559ba8dd133dcd",
-    "zh:f85c1d9e51a94ecde137435c9d6b0fb7be590437ea8a725334d1577eebbc550c",
+    "h1:/9TSq9ibeojseTyT6Jx3z/dbvT5uw8ka3/18NKonrQc=",
+    "h1:BN5hy1RaHlpcV0BDJYrSOEklK4YNdZCpiXOOGn0ce9k=",
+    "h1:MNJ6dcFru4DwQM7maIUAADJIHn3aF+L8XsnRJlleNaM=",
+    "h1:P1Cx0VZGTe6cpWpQ4JFOPJJb+Z+N50t4e1VA76T1tAA=",
+    "h1:Pm9du7Rzsg1bhLq+XnW9VaLSjTu0Yytr9AOdP9FLQvM=",
+    "h1:Q/JvNhRskJqDKPJoO9DW3+Ons3mk8kc++zlT4TucyFw=",
+    "h1:Tzk+wRzhboY3F3wB1u0y3ySMMd4ZPtJbOYlTbbkxZc0=",
+    "h1:Uuk8gkDEzmXfOTW/nm8GMG2aen7n/+X5GsTAf7eVRJc=",
+    "h1:cRBlnB/TG4+l0y0i42QLU0JoLDBxxJEwCguLXS9Rv8A=",
+    "h1:jn+hA9lIJzH5T0550IaKNsHxEAbyTGtvYWm02JCxexM=",
+    "h1:pKAwAcCGEwsKvVy5eIxdmb1gLhTTxB0xGVi8/jqj0uI=",
+    "h1:wS5VlGinhpnMCva0tKwLRPRQxmMUl80L05AueWshzNg=",
+    "h1:yqZeKoJ+EZc3687/+ZBqBmtwzvBPLNwaEHW74+bSc6Y=",
+    "zh:061e5187853729e1d8ba20938402ad6e778b4097436925d0bef7741c8aa26ee1",
+    "zh:69a2ac8ee0cb0c1581bdc9a1296d89abcd1808229ff0a2fa20678ba4f7472944",
+    "zh:8b02bf349191b4e7d9529d620da9e9265de5bd01d6983bb079589acdf80dda7a",
+    "zh:9620872ed1da1ff421e85dd4ba2a110c284f3f0d06369c36a9aa75d501155fad",
+    "zh:9ae7c932b7fb6f62ff20b863a15a7cd713415faa4c789472dc403062808366cb",
+    "zh:a369c3e271b49e085940e6181fe6c1086c2126eebf5c7ad2b1db8fc8792dd30c",
+    "zh:a45ad97d7192bea104b32521839dd705a330f13364cf1007dc912b6a0b6be3c8",
+    "zh:b69f2a13ff688ad4b79e14deb6ef6341187864f50960bc0fd9c682f6077b4318",
+    "zh:c20b467ff0ac76431a7bdb99662b9414b922ea603327509518c0179416cdfea3",
+    "zh:c22d45913bd1f00a33d1a4b80547e4a2854409a298a0868c1730124f03a210ad",
+    "zh:cf82bb14884fcbdcd57620cee248994b1633ea246fa49fd668d2f1739abb982d",
+    "zh:ddc1cb4417206dd46eb22c3b81204b3a5edda03c4436e6a5914d541fcfd4c27f",
+    "zh:e6b1983b8f1b9658448d0d09635619cc75dde314e6b4d7fd16d827f9e4bdb767",
  ]
 }
@@ -2,7 +2,7 @@ terraform {
  required_providers {
    libvirt = {
      source = "dmacvicar/libvirt"
-      version = "0.7.6"
+      version = "0.9.8"
    }
  }
 }
@@ -188,8 +188,8 @@ Most jobs already have Consul health checks — these can use `health_check = "c
 | frigate    | ✅            | ✅ `single-node-writer` | ⚠️ same — rolling                                                                 |
 | glance     | ✅            | no                      | ✅ yes                                                                            |
 | transfer   | ✅            | ✅ `single-node-writer` | ⚠️ rolling                                                                        |
-| openreader | ❌            | ✅ `single-node-writer` | ⚠️ add check first, then rolling                                                  |
-| unifi      | ❌            | ✅ `single-node-writer` | ⚠️ add check first, then rolling                                                  |
+| openreader | ✅ `/`        | ✅ `single-node-writer` | ⚠️ rolling                                                                        |
+| unifi      | ✅ script     | ✅ `single-node-writer` | ⚠️ rolling                                                                        |
 | traefik    | (ingress)     | ✅                      | ⚠️ rolling — downtime risk, promote quickly                                       |
 | authelia   | (ingress)     | ✅                      | ✅ stateless config, canary fine                                                  |
 | renovate   | batch job     | n/a                     | n/a — no deployment model                                                         |
@@ -296,10 +296,10 @@ exit 1
 - [x] **Phase 1a**: Create `act-runner.nomad.hcl` + Terraform wrapper, register runner token in Gitea, get a hello-world workflow green
 - [x] **Phase 1b**: Add `terraform fmt` + `terraform validate -backend=false` workflow — no secrets needed
 - [x] **Phase 1c**: Add Nomad validate step — add `NOMAD_ADDR` + read-only `NOMAD_TOKEN` to Gitea secrets
- [ ] **Phase 2**: Add image pull validation step to the workflow
+- [x] **Phase 2**: Add image pull validation step to the workflow
 - [ ] **Phase 3a**: Add `update` stanzas to ntfy and glance (simplest, no volume conflict)
- [ ] **Phase 3b**: Add rolling `update` stanzas to remaining service jobs (jellyfin, sonarr, etc.)
- [ ] **Phase 3c**: Add health checks to openreader and unifi before adding update stanzas
+- [ ] **Phase 3b**: Add rolling `update` stanzas to remaining service jobs (jellyfin, sonarr, prowlarr, deluge, gitea, immich, transfer, frigate, openreader, unifi, authelia, traefik)
+- [x] **Phase 3c**: Add health checks to openreader and unifi before adding update stanzas
 - [ ] **Phase 4a**: Add on-push workflow that runs `terraform apply -auto-approve` using full credential set
 - [ ] **Phase 4b**: Add deployment promotion/revert polling script
 - [ ] **Phase 4c**: Wire ntfy notifications for promote/revert outcomes
Author	SHA1	Message	Date
renovate	3aba16f34d	Update Terraform libvirt to v0.9.8 CI / Terraform fmt + validate (pull_request) Successful in 17s Details CI / Nomad job spec validate (pull_request) Successful in 22s Details CI / Docker image pull validation (pull_request) Successful in 8s Details	2026-07-15 10:26:41 +00:00
othrayte	e695485353	improve health checks across all nomad job specs CI / Terraform fmt + validate (pull_request) Successful in 27s Details CI / Nomad job spec validate (pull_request) Successful in 22s Details CI / Docker image pull validation (pull_request) Successful in 16s Details CI / Nomad job spec validate (push) Successful in 22s Details CI / Docker image pull validation (push) Has been skipped Details CI / Terraform fmt + validate (push) Successful in 23s Details - traefik: TCP → HTTP check on /ping (enable ping entrypoint) - gitea: check path → /api/healthz - jellyfin: TCP → HTTP check on /health - glance: TCP → HTTP check on / - sonarr/prowlarr: check path / → /ping (×2 checks each) - ntfy/transfer/deluge/openreader/authelia/pgadmin: add name and port to existing checks - postgres: remove invalid TCP check (Connect-enabled service) - unifi: TCP → script check via curl (macvlan host isolation workaround)	2026-05-26 20:12:23 +10:00
othrayte	8e32d00d90	ci: add Docker image pull validation job (Phase 2) CI / Docker image pull validation (pull_request) Successful in 14s Details CI / Nomad job spec validate (push) Successful in 30s Details CI / Docker image pull validation (push) Has been skipped Details CI / Terraform fmt + validate (pull_request) Successful in 20s Details CI / Nomad job spec validate (pull_request) Successful in 24s Details CI / Terraform fmt + validate (push) Successful in 21s Details - Add image-pull job to .gitea/workflows/ci.yml that detects image changes in *.nomad.hcl files on PRs and pulls each changed image - Remove act-runner labels config — default runner already uses docker.gitea.com/runner-images:ubuntu-latest which has docker CLI - Remove CONFIG_FILE env var from act-runner (no longer needed) - Mark Phase 2 complete in cicd-plan.md	2026-04-19 18:06:17 +10:00