Update mcr.microsoft.com/k8s/csi/smb-csi Docker tag to v1.17.0

.gitea/workflows/ci.yml

@@ -29,62 +29,3 @@ jobs:
           terraform init -backend=false
           terraform validate
         working-directory: 2-nomad-config
-
-  nomad-validate:
-    name: Nomad job spec validate
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install Nomad CLI
-        run: |
-          curl -fsSL https://apt.releases.hashicorp.com/gpg | gpg --dearmor -o /usr/share/keyrings/hashicorp.gpg
-          . /etc/os-release
-          echo "deb [signed-by=/usr/share/keyrings/hashicorp.gpg] https://apt.releases.hashicorp.com ${VERSION_CODENAME} main" | tee /etc/apt/sources.list.d/hashicorp.list
-          apt-get update && apt-get install -y nomad
-
-      - name: Validate all job specs
-        env:
-          NOMAD_ADDR: http://jaglan-beta-m20.lan:4646
-        run: |
-          find 2-nomad-config -name '*.nomad.hcl' | while read f; do
-            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

2-nomad-config/1-data/csi-smb.nomad.hcl

@@ -6,7 +6,7 @@ job "csi-smb" {
       driver = "docker"
 
       config {
-        image = "mcr.microsoft.com/k8s/csi/smb-csi:v1.7.0"
+        image = "mcr.microsoft.com/k8s/csi/smb-csi:v1.17.0"
         args = [
           "--v=5",
           "--nodeid=${attr.unique.hostname}",

2-nomad-config/1-data/pgadmin.nomad.hcl

@@ -58,10 +58,8 @@ job "pgadmin" {
         ]
 
         check {
-          name     = "alive"
           type     = "http"
           path     = "/"
-          port     = "http"
           interval = "10s"
           timeout  = "2s"
         }

2-nomad-config/1-data/postgres.nomad.hcl

@@ -7,10 +7,6 @@ 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" {

2-nomad-config/2-ingress/authelia.nomad.hcl

@@ -33,10 +33,8 @@ job "authelia" {
       }
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/health"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/2-ingress/traefik.nomad.hcl

@@ -35,8 +35,7 @@ job "traefik" {
 
       check {
         name     = "alive"
-        type     = "http"
-        path     = "/ping"
+        type     = "tcp"
         port     = "api"
         interval = "10s"
         timeout  = "2s"
@@ -86,9 +85,6 @@ api:
   dashboard: true
   insecure: true
 
-ping:
-  entryPoint: traefik
-
 providers:
   file:
     directory: "/etc/traefik/configs/"

2-nomad-config/act-runner.nomad.hcl

@@ -28,7 +28,8 @@ job "act-runner" {
       }
 
       env = {
-        GITEA_INSTANCE_URL = "https://gitea-1ef0bea6b75a4fd3e9393a9f7f7e4b02.othrayte.one"
+        GITEA_INSTANCE_URL = "http://localhost:3000"
+        CONFIG_FILE        = "/secrets/runner-config.yml"
       }
 
       # Required SOPS key:
@@ -42,6 +43,19 @@ 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

2-nomad-config/deluge.nomad.hcl

@@ -54,10 +54,8 @@ EOH
       ]
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }
@@ -80,10 +78,8 @@ EOH
       }
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/gitea.nomad.hcl

@@ -27,15 +27,11 @@ job "gitea" {
       tags = [
         "traefik.enable=true",
         "traefik.http.routers.gitea.middlewares=auth@file",
-        # Token subdomain — no auth middleware — used by act_runner step containers for git checkout
-        "traefik.http.routers.gitea-token.rule=Host(`gitea-1ef0bea6b75a4fd3e9393a9f7f7e4b02.othrayte.one`)",
       ]
 
       check {
-        name     = "alive"
         type     = "http"
-        path     = "/api/healthz"
-        port     = "http"
+        path     = "/"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/glance.nomad.hcl

@@ -12,7 +12,7 @@ job "glance" {
       driver = "docker"
 
       config {
-        image = "glanceapp/glance:v0.7.8"
+        image = "glanceapp/glance:latest"
         ports = ["http"]
         volumes = [
           "local/glance.yml:/app/config/glance.yml",
@@ -30,8 +30,7 @@ job "glance" {
 
         check {
           name     = "alive"
-          type     = "http"
-          path     = "/"
+          type     = "tcp"
           port     = "http"
           interval = "10s"
           timeout  = "2s"

2-nomad-config/jellyfin.nomad.hcl

@@ -28,11 +28,10 @@ job "jellyfin" {
 
         check {
           name     = "alive"
-          type     = "http"
-          path     = "/health"
+          type     = "tcp"
           port     = "http"
           interval = "10s"
-          timeout  = "5s"
+          timeout  = "2s"
         }
       }
 

2-nomad-config/ntfy.nomad.hcl

@@ -33,10 +33,8 @@ job "ntfy" {
       ]
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/healthz"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/openreader.nomad.hcl

@@ -31,10 +31,8 @@ job "openreader" {
       ]
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }
@@ -50,10 +48,8 @@ job "openreader" {
       }
 
       check {
-        name     = "alive"
         type     = "http"
         path     = "/"
-        port     = "http"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/prowlarr.nomad.hcl

@@ -34,9 +34,8 @@ job "prowlarr" {
       ]
 
       check {
-        name     = "alive"
         type     = "http"
-        path     = "/ping"
+        path     = "/"
         interval = "10s"
         timeout  = "2s"
       }
@@ -52,9 +51,8 @@ job "prowlarr" {
       }
 
       check {
-        name     = "alive"
         type     = "http"
-        path     = "/ping"
+        path     = "/"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/sonarr.nomad.hcl

@@ -37,9 +37,8 @@ job "sonarr" {
       ]
 
       check {
-        name     = "alive"
         type     = "http"
-        path     = "/ping"
+        path     = "/"
         interval = "10s"
         timeout  = "2s"
       }
@@ -55,9 +54,8 @@ job "sonarr" {
       }
 
       check {
-        name     = "alive"
         type     = "http"
-        path     = "/ping"
+        path     = "/"
         interval = "10s"
         timeout  = "2s"
       }

2-nomad-config/transfer.nomad.hcl

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

2-nomad-config/unifi.nomad.hcl

@@ -21,26 +21,6 @@ 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)

cicd-plan.md

@@ -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` | ⚠️ rolling                                                                        |
-| unifi      | ✅ script     | ✅ `single-node-writer` | ⚠️ rolling                                                                        |
+| openreader | ❌            | ✅ `single-node-writer` | ⚠️ add check first, then rolling                                                  |
+| unifi      | ❌            | ✅ `single-node-writer` | ⚠️ add check first, then rolling                                                  |
 | traefik    | (ingress)     | ✅                      | ⚠️ rolling — downtime risk, promote quickly                                       |
 | authelia   | (ingress)     | ✅                      | ✅ stateless config, canary fine                                                  |
 | renovate   | batch job     | n/a                     | n/a — no deployment model                                                         |
@@ -293,13 +293,13 @@ exit 1
 
 ## Implementation Order
 
-- [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
-- [x] **Phase 2**: Add image pull validation step to the workflow
+- [ ] **Phase 1a**: Create `act-runner.nomad.hcl` + Terraform wrapper, register runner token in Gitea, get a hello-world workflow green
+- [ ] **Phase 1b**: Add `terraform fmt` + `terraform validate -backend=false` workflow — no secrets needed
+- [ ] **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
 - [ ] **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, 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 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 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