fix: always re-register runner to keep labels in sync

Init container previously skipped registration if .runner existed on PVC. Changing labels in values.yaml had no effect until PVC was manually deleted. Now: rm -f .runner + register on every pod start. Labels always match values.yaml. No manual intervention needed after merge.
chore: remove custom runner Dockerfiles and build workflow
2026-09-06 22:22:10 -07:00 · 2026-09-06 21:47:07 -07:00 · 2026-09-06 09:56:45 -07:00 · 2026-09-06 07:15:01 -07:00 · 2026-09-06 07:09:40 -07:00 · 2026-09-06 07:06:44 -07:00
9 changed files with 23 additions and 121 deletions
@@ -1,60 +0,0 @@
-name: Build and push runner images
-
-on:
-  push:
-    paths:
-      - 'k8s/infra/forgejo-runner/Dockerfile.golang'
-      - 'k8s/infra/forgejo-runner/Dockerfile.rust'
-      - 'k8s/infra/forgejo-runner/Dockerfile.node'
-    branches:
-      - main
-  pull_request:
-    paths:
-      - 'k8s/infra/forgejo-runner/Dockerfile.golang'
-      - 'k8s/infra/forgejo-runner/Dockerfile.rust'
-      - 'k8s/infra/forgejo-runner/Dockerfile.node'
-      - '.gitea/workflows/build-runner-images.yml'
-
-jobs:
-  build-runners:
-    runs-on: node
-    env:
-      REGISTRY: forgejo.riotpiao.com
-      IMAGE_BASE: forgejo.riotpiao.com/rock
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Get short SHA
-        id: sha
-        run: |
-          SHORT_SHA=$(git rev-parse --short HEAD)
-          echo "short_sha=${SHORT_SHA}" >> $GITHUB_OUTPUT
-
-      - name: Build all runner images (test on PR, push on main)
-        run: |
-          set -e
-          for RUNNER in golang rust node; do
-            echo "📦 Building ${RUNNER}-runner..."
-            docker build -f "k8s/infra/forgejo-runner/Dockerfile.${RUNNER}" \
-              -t "${IMAGE_BASE}/forgejo-runner-${RUNNER}:${{ steps.sha.outputs.short_sha }}" \
-              -t "${IMAGE_BASE}/forgejo-runner-${RUNNER}:latest" \
-              .
-            echo "✅ Built ${RUNNER}-runner"
-          done
-
-      - name: Push images (main only)
-        if: github.event_name == 'push'
-        run: |
-          echo "${REGISTRY_TOKEN}" | docker login "${REGISTRY}" \
-            --username "${REGISTRY_USER}" --password-stdin
-          for RUNNER in golang rust node; do
-            echo "📤 Pushing ${RUNNER}-runner:${{ steps.sha.outputs.short_sha }}"
-            docker push "${IMAGE_BASE}/forgejo-runner-${RUNNER}:${{ steps.sha.outputs.short_sha }}"
-            docker push "${IMAGE_BASE}/forgejo-runner-${RUNNER}:latest"
-            echo "✅ Pushed ${RUNNER}-runner"
-          done
-          echo "✅ All runner images pushed to registry"
-        env:
-          REGISTRY_USER: ${{ secrets.FORGEJO_REGISTRY_USER }}
-          REGISTRY_TOKEN: ${{ secrets.FORGEJO_REGISTRY_TOKEN }}
@@ -1,16 +0,0 @@
-FROM code.forgejo.org/forgejo/runner:6
-
-# Switch to root to install packages (Alpine)
-USER root
-
-# Alpine uses apk, not apt-get
-RUN apk update && apk add --no-cache \
-      nodejs \
-      npm \
-      docker
-
-# Verify installations
-RUN docker --version && node --version && git --version
-
-# Switch back to runner user
-USER 1000:1000
@@ -1,16 +0,0 @@
-FROM code.forgejo.org/forgejo/runner:6
-
-# Switch to root to install packages (Alpine)
-USER root
-
-# Alpine uses apk, not apt-get
-RUN apk update && apk add --no-cache \
-      docker \
-      nodejs \
-      npm
-
-# Verify installations
-RUN node --version && docker --version && git --version
-
-# Switch back to runner user
-USER 1000:1000
@@ -1,20 +0,0 @@
-FROM code.forgejo.org/forgejo/runner:6
-
-# Switch to root to install packages (Alpine)
-USER root
-
-# Alpine uses apk, not apt-get
-RUN apk update && apk add --no-cache \
-      nodejs \
-      npm \
-      curl \
-      docker
-
-# Install Rust (as root, skip verification for now)
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable || true
-
-# Verify core installations
-RUN docker --version && node --version && git --version
-
-# Switch back to runner user
-USER 1000:1000
@@ -36,3 +36,4 @@ data:
      valid_volumes:
        - /docker-certs/client
      network: host
+      docker_host: automount
@@ -34,7 +34,11 @@ spec:
          command: ["sh", "-c"]
          args:
            - |
-              test -f /data/.runner || forgejo-runner register --no-interactive \
+              # Always re-register to keep labels in sync with values.yaml.
+              # Without this, changing a runner label requires manually deleting
+              # the PVC or .runner file — not GitOps-friendly.
+              rm -f /data/.runner
+              forgejo-runner register --no-interactive \
                --instance {{ .Values.runner.forgejoUrl }} \
                --token $(RUNNER_TOKEN) \
                --name {{ .Values.runner.name }} \
@@ -70,6 +74,8 @@ spec:
              mountPath: /data
            - name: docker-certs
              mountPath: /docker-certs
+            - name: docker-sock
+              mountPath: /run
            - name: homelab-ca
              mountPath: /etc/ssl/certs/homelab-ca.pem
              subPath: ca.crt
@@ -89,6 +95,8 @@ spec:
          volumeMounts:
            - name: docker-certs
              mountPath: /docker-certs
+            - name: docker-sock
+              mountPath: /run
            - name: dind-storage
              mountPath: /var/lib/docker
            - name: homelab-ca
@@ -113,6 +121,8 @@ spec:
            claimName: {{ .Release.Name }}-dind
        - name: docker-certs
          emptyDir: {}    # DinD regenerates mTLS certs on each start
+        - name: docker-sock
+          emptyDir: {}    # Shared docker socket between dind and runner
        - name: homelab-ca
          # homelab-ca is a ConfigMap (public CA trust bundle), not a Secret.
          # The volumeMounts use subPath: ca.crt to project the single cert file.
@@ -2,15 +2,14 @@
 # runner instance. Only runner.name and runner.labels differ -- everything
 # else (image, dind, persistence, tolerations, nodeSelector) is shared.
 #
-# node:22-bookworm ships Node natively. Docker client installed via workflow step if needed.
-# (homelab has no CI; custom runner images built manually if desired)
-# Bootstrap with runner image (already has Node.js), CI builds custom
+# Label image: node:22-bookworm — Debian, root, apt-get, Node.js, npm, git.
+# Install docker in workflow steps as needed.
 runner:
  image:
    repository: code.forgejo.org/forgejo/runner
    tag: "6"
  name: node-runner
-  labels: "node:docker://code.forgejo.org/forgejo/runner:6"
+  labels: "node:docker://node:22-bookworm"

 # GC CronJob renders only from the default (golang) values to avoid duplicates
 gc:
@@ -2,13 +2,14 @@
 # runner instance. Only runner.name and runner.labels differ -- everything
 # else (image, dind, persistence, tolerations, nodeSelector) is shared.
 #
-# Bootstrap with runner image, CI builds custom with Node.js+Rust
+# Label image: rust:1-bookworm — Debian, root, apt-get, Rust, cargo, git.
+# Install Node.js/docker in workflow steps as needed.
 runner:
  image:
    repository: code.forgejo.org/forgejo/runner
    tag: "6"
  name: rust-runner
-  labels: "rust:docker://code.forgejo.org/forgejo/runner:6"
+  labels: "rust:docker://rust:1-bookworm"



@@ -1,9 +1,12 @@
 runner:
  image:
    repository: code.forgejo.org/forgejo/runner
-    tag: "6"  # Bootstrap with runner image, CI builds custom with Node.js
+    tag: "6"
  name: golang-runner
-  labels: "golang:docker://code.forgejo.org/forgejo/runner:6"
+  # Label image is what workflow steps run in (NOT the runner daemon image).
+  # golang:1.26-bookworm: Debian, root, apt-get, Go, git.
+  # Install Node.js/docker in workflow steps as needed.
+  labels: "golang:docker://golang:1.26-bookworm"
  forgejoUrl: http://forgejo-gitea-http.cicd.svc.cluster.local:3000
  tokenSecret: runner-token
  resources:
Author	SHA1	Message	Date
rock	f96db53a77	fix: always re-register runner to keep labels in sync Init container previously skipped registration if .runner existed on PVC. Changing labels in values.yaml had no effect until PVC was manually deleted. Now: rm -f .runner + register on every pod start. Labels always match values.yaml. No manual intervention needed after merge.	2026-09-06 22:22:10 -07:00
rock	8b83350cb1	chore: remove custom runner Dockerfiles and build workflow No longer needed — runner labels now point to official language images (golang:1.26-bookworm, node:22-bookworm, rust:1-bookworm) which already have the language tools. Docker CLI installed via apt-get in workflow steps.	2026-09-06 21:47:07 -07:00
rock	ba0b3c2b64	fix: mount docker socket at /run not /var/run (symlink issue) Build and push runner images / build-runners (pull_request) Failing after 46s Details /var/run is a symlink to /run in Alpine. Mounting emptyDir at /var/run doesn't override the real /run directory, so dind's docker.sock at /run/docker.sock was never visible to the runner container. Fix: Mount the shared emptyDir at /run in both containers.	2026-09-06 09:56:45 -07:00
rock	ce154c55e6	fix: share docker socket between dind and runner via emptyDir Build and push runner images / build-runners (pull_request) Failing after 40s Details ROOT CAUSE: Docker socket (/var/run/docker.sock) only existed inside the dind container — the runner container couldn't see it. The runner connected to dind via TCP (tcp://localhost:2376) with TLS. But workflow containers created by the runner had NO way to access the docker daemon: - unix socket not mounted (runner can't see it) - DOCKER_HOST env var not passed (runner.envs not configured) FIX: Share /var/run between dind and runner via emptyDir volume. When dind starts, it creates /var/run/docker.sock in the shared volume. Runner can now see the socket. docker_host: automount in config tells the runner to mount the socket into job containers automatically. Architecture after fix: dind container → creates /var/run/docker.sock → shared emptyDir runner container → sees /var/run/docker.sock → uses automount workflow container → gets /var/run/docker.sock mounted by runner Also removed runner.envs (TCP+TLS approach) — unix socket is simpler and works with automount.	2026-09-06 07:15:01 -07:00
rock	cfb1d88373	fix: pass DOCKER_HOST + TLS env vars to workflow containers Build and push runner images / build-runners (pull_request) Failing after 38s Details ROOT CAUSE: Workflow containers created by Forgejo runner don't inherit the DOCKER_HOST/TLS env vars from the runner pod. Docker CLI defaults to unix:///var/run/docker.sock which doesn't exist inside workflow containers. The dind sidecar listens on tcp://localhost:2376 with TLS. With network: host (already set), localhost inside the workflow container reaches the dind daemon. But docker CLI needs DOCKER_HOST set explicitly. FIX: Use runner.envs in config.yaml to pass these env vars to every workflow container: DOCKER_HOST=tcp://localhost:2376 DOCKER_TLS_VERIFY=1 DOCKER_CERT_PATH=/docker-certs/client The valid_volumes already allows /docker-certs/client (TLS certs).	2026-09-06 07:09:40 -07:00
rock	4e9484bdf8	fix: use proper language images for runner labels, not bare Alpine Build and push runner images / build-runners (pull_request) Failing after 38s Details ROOT CAUSE: All 3 runner labels pointed to code.forgejo.org/forgejo/runner:6 (bare Alpine). When Forgejo runs a workflow, it creates a container FROM the label image — this container had no Node.js, no docker CLI, no Go/Rust, no root access, and no apt-get. Every CI job failed. FIX: Change runner labels to official Debian-based language images: golang → docker://golang:1.26-bookworm (Go + apt-get + root) node → docker://node:22-bookworm (Node.js + npm + apt-get + root) rust → docker://rust:1-bookworm (Rust + cargo + apt-get + root) The runner daemon pod still uses forgejo/runner:6 — only the label image (what workflow steps execute in) changes. Unified CI pattern for ALL repos: 1. Install Node.js first if not present (needed for actions/checkout@v4) 2. Install docker.io via apt-get (needed for docker build/push) 3. Use actions/checkout@v4 normally 4. Build/push with docker IMPORTANT: Runners must re-register after merge. Delete PVCs or /data/.runner files to trigger re-registration with new labels.	2026-09-06 07:06:44 -07:00
rock	dade5f77ae	ci: remove apk install (docker available via dind sidecar) Build and push runner images / build-runners (pull_request) Failing after 8s Details	2026-09-06 07:00:39 -07:00
rock	0eab433d04	ci: install docker CLI before building images Build and push runner images / build-runners (pull_request) Failing after 5s Details	2026-09-06 06:54:41 -07:00
rock	269c5c8202	ci: clone to current directory (fix 'already exists' error) Build and push runner images / build-runners (pull_request) Failing after 7s Details	2026-09-06 06:53:12 -07:00
rock	fda701ca45	ci: use base runner + git clone (no Node.js dependency) Build and push runner images / build-runners (pull_request) Failing after 6s Details Problem: actions/checkout@v4 requires Node.js, but base forgejo/runner:6 (Alpine) doesn't have it. We need to test our Dockerfiles on the bare base image. Solution: - runs-on: golang (base Alpine runner with dind docker) - Replace actions/checkout@v4 with git clone (no Node.js needed) - Clone to /workspace, run all steps there - Only push on push events (skip on PR to avoid registry pollution) This validates that our Dockerfile fixes work correctly on base image.	2026-09-06 06:52:21 -07:00