ci: gitea: runners infra

infra/gitea-runners/k8s/cleanup-lifecycle.yaml

@@ -0,0 +1,154 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: gitea-runner-lifecycle
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner-lifecycle
+    app.kubernetes.io/part-of: gitea-actions
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: gitea-runner-lifecycle
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner-lifecycle
+    app.kubernetes.io/part-of: gitea-actions
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - pods
+      - persistentvolumeclaims
+    verbs:
+      - get
+      - list
+  - apiGroups:
+      - apps
+    resources:
+      - statefulsets
+    verbs:
+      - get
+      - list
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: gitea-runner-lifecycle
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner-lifecycle
+    app.kubernetes.io/part-of: gitea-actions
+subjects:
+  - kind: ServiceAccount
+    name: gitea-runner-lifecycle
+    namespace: gitea-runners
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: gitea-runner-lifecycle
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: gitea-runner-lifecycle
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner-lifecycle
+    app.kubernetes.io/part-of: gitea-actions
+data:
+  cleanup-dry-run.sh: |
+    #!/bin/sh
+    set -eu
+
+    namespace="${RUNNER_NAMESPACE:-gitea-runners}"
+    mode="${CLEANUP_MODE:-dry-run}"
+    selector="app.kubernetes.io/name=gitea-runner"
+
+    if [ "$namespace" != "gitea-runners" ]; then
+      printf 'refusing to run outside namespace gitea-runners: %s\n' "$namespace" >&2
+      exit 13
+    fi
+
+    if [ "$mode" != "dry-run" ]; then
+      printf 'refusing destructive mode: set CLEANUP_MODE=dry-run for this CronJob\n' >&2
+      exit 13
+    fi
+
+    printf 'gitea runner lifecycle cleanup dry-run\n'
+    printf 'namespace: %s\n' "$namespace"
+    printf 'mode: %s\n\n' "$mode"
+
+    printf 'StatefulSet:\n'
+    kubectl -n "$namespace" get statefulset gitea-runner -o wide
+
+    printf '\nActive runner pods:\n'
+    kubectl -n "$namespace" get pods -l "$selector" -o wide
+
+    printf '\nRunner /data PVCs:\n'
+    kubectl -n "$namespace" get pvc -l "$selector" -o wide
+
+    printf '\nPVCs whose matching StatefulSet pod is absent (candidates only; no deletion):\n'
+    found_candidate=0
+    for pvc in $(kubectl -n "$namespace" get pvc -l "$selector" -o jsonpath='{range .items[*]}{.metadata.name}{"\n"}{end}'); do
+      pod="${pvc#data-}"
+      if ! kubectl -n "$namespace" get pod "$pod" >/dev/null 2>&1; then
+        found_candidate=1
+        printf 'candidate pvc=%s expected_pod=%s action=investigate-before-delete\n' "$pvc" "$pod"
+      fi
+    done
+
+    if [ "$found_candidate" -eq 0 ]; then
+      printf 'none\n'
+    fi
+
+    printf '\nGitea registration reconciliation:\n'
+    printf 'dry-run only: compare the pod/PVC list above with Gitea org runner registrations.\n'
+    printf 'only deregister a runner after its pod/PVC was intentionally deleted or /data/.runner was intentionally reset.\n'
+---
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  name: gitea-runner-cleanup-dry-run
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner-lifecycle
+    app.kubernetes.io/part-of: gitea-actions
+spec:
+  schedule: "17 3 * * *"
+  concurrencyPolicy: Forbid
+  successfulJobsHistoryLimit: 3
+  failedJobsHistoryLimit: 3
+  jobTemplate:
+    spec:
+      ttlSecondsAfterFinished: 3600
+      template:
+        metadata:
+          labels:
+            app.kubernetes.io/name: gitea-runner-lifecycle
+            app.kubernetes.io/part-of: gitea-actions
+        spec:
+          serviceAccountName: gitea-runner-lifecycle
+          restartPolicy: Never
+          containers:
+            - name: cleanup-dry-run
+              image: bitnami/kubectl:1.30
+              imagePullPolicy: IfNotPresent
+              command:
+                - /bin/sh
+                - /scripts/cleanup-dry-run.sh
+              env:
+                - name: RUNNER_NAMESPACE
+                  value: gitea-runners
+                - name: CLEANUP_MODE
+                  value: dry-run
+              volumeMounts:
+                - name: lifecycle-scripts
+                  mountPath: /scripts
+                  readOnly: true
+          volumes:
+            - name: lifecycle-scripts
+              configMap:
+                name: gitea-runner-lifecycle
+                defaultMode: 0555

infra/gitea-runners/k8s/kustomization.yaml

@@ -0,0 +1,9 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - namespace.yaml
+  - service.yaml
+  - service-account.yaml
+  - runner-config.yaml
+  - statefulset.yaml
+  - cleanup-lifecycle.yaml

infra/gitea-runners/k8s/namespace.yaml

@@ -0,0 +1,7 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner
+    app.kubernetes.io/part-of: gitea-actions

infra/gitea-runners/k8s/runner-config.yaml

@@ -0,0 +1,36 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: gitea-runner-config
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner
+    app.kubernetes.io/part-of: gitea-actions
+data:
+  config.yaml: |
+    log:
+      level: info
+
+    runner:
+      file: /data/.runner
+      capacity: 1
+      envs: {}
+      timeout: 3h
+      insecure: false
+      fetch_timeout: 5s
+      fetch_interval: 2s
+      labels:
+        - ubuntu-latest
+        # The nix label is intentionally disabled until the runner image has a
+        # concrete registry-reported digest; see ../runbook.md before deploy.
+
+    cache:
+      enabled: true
+      dir: /data/cache
+
+    container:
+      network: bridge
+      privileged: false
+      force_pull: true
+      valid_volumes: []
+      docker_host: unix:///runner-docker/docker.sock

infra/gitea-runners/k8s/service-account.yaml

@@ -0,0 +1,36 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: gitea-runner
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner
+    app.kubernetes.io/part-of: gitea-actions
+automountServiceAccountToken: false
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: gitea-runner
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner
+    app.kubernetes.io/part-of: gitea-actions
+rules: []
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: gitea-runner
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner
+    app.kubernetes.io/part-of: gitea-actions
+subjects:
+  - kind: ServiceAccount
+    name: gitea-runner
+    namespace: gitea-runners
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: gitea-runner

infra/gitea-runners/k8s/service.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: gitea-runner
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner
+    app.kubernetes.io/part-of: gitea-actions
+spec:
+  clusterIP: None
+  selector:
+    app.kubernetes.io/name: gitea-runner
+  ports:
+    - name: cache
+      port: 8088
+      targetPort: cache

infra/gitea-runners/k8s/statefulset.yaml

@@ -0,0 +1,156 @@
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: gitea-runner
+  namespace: gitea-runners
+  labels:
+    app.kubernetes.io/name: gitea-runner
+    app.kubernetes.io/part-of: gitea-actions
+spec:
+  serviceName: gitea-runner
+  replicas: 5
+  podManagementPolicy: Parallel
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: gitea-runner
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: gitea-runner
+        app.kubernetes.io/part-of: gitea-actions
+      annotations:
+        hectic-lab.com/security-note: "Privileged rootful DinD is limited to trusted internal Gitea workflows only. Do not enable untrusted fork or PR jobs for this pool."
+    spec:
+      serviceAccountName: gitea-runner
+      automountServiceAccountToken: false
+      terminationGracePeriodSeconds: 60
+      securityContext:
+        fsGroup: 1000
+      containers:
+        - name: runner
+          image: gitea/act_runner:0.2.11
+          imagePullPolicy: IfNotPresent
+          env:
+            - name: GITEA_INSTANCE_URL
+              value: https://gitea.hectic-lab.com
+            - name: GITEA_RUNNER_REGISTRATION_TOKEN_FILE
+              value: /runner-secrets/token
+            - name: CONFIG_FILE
+              value: /runner-config/config.yaml
+            - name: DOCKER_HOST
+              value: unix:///runner-docker/docker.sock
+          ports:
+            - name: cache
+              containerPort: 8088
+          resources:
+            requests:
+              cpu: 250m
+              memory: 256Mi
+            limits:
+              cpu: "1"
+              memory: 1Gi
+          livenessProbe:
+            exec:
+              command:
+                - /bin/sh
+                - -ec
+                - test -s /data/.runner && test -S /runner-docker/docker.sock
+            initialDelaySeconds: 60
+            periodSeconds: 30
+            timeoutSeconds: 5
+            failureThreshold: 6
+          readinessProbe:
+            exec:
+              command:
+                - /bin/sh
+                - -ec
+                - test -S /runner-docker/docker.sock
+            initialDelaySeconds: 15
+            periodSeconds: 10
+            timeoutSeconds: 5
+            failureThreshold: 6
+          volumeMounts:
+            - name: data
+              mountPath: /data
+            - name: config
+              mountPath: /runner-config
+              readOnly: true
+            - name: runner-token
+              mountPath: /runner-secrets
+              readOnly: true
+            - name: docker-socket
+              mountPath: /runner-docker
+        - name: docker
+          image: docker:27-dind
+          imagePullPolicy: IfNotPresent
+          args:
+            - --host=unix:///runner-docker/docker.sock
+            - --storage-driver=overlay2
+            - --tls=false
+          env:
+            - name: DOCKER_TLS_CERTDIR
+              value: ""
+            - name: DOCKER_HOST
+              value: unix:///runner-docker/docker.sock
+          securityContext:
+            # Privileged rootful DinD is intentionally scoped to this trusted
+            # internal runner pool; never expose it to untrusted fork/PR jobs.
+            privileged: true
+          resources:
+            requests:
+              cpu: 500m
+              memory: 1Gi
+            limits:
+              cpu: "2"
+              memory: 4Gi
+          livenessProbe:
+            exec:
+              command:
+                - docker
+                - info
+            initialDelaySeconds: 60
+            periodSeconds: 30
+            timeoutSeconds: 10
+            failureThreshold: 6
+          readinessProbe:
+            exec:
+              command:
+                - docker
+                - info
+            initialDelaySeconds: 20
+            periodSeconds: 10
+            timeoutSeconds: 10
+            failureThreshold: 6
+          volumeMounts:
+            - name: docker-socket
+              mountPath: /runner-docker
+            - name: docker-graph
+              mountPath: /var/lib/docker
+      volumes:
+        - name: config
+          configMap:
+            name: gitea-runner-config
+        - name: runner-token
+          secret:
+            secretName: gitea-runner-token
+            items:
+              - key: token
+                path: token
+            defaultMode: 0400
+        - name: docker-socket
+          emptyDir: {}
+        - name: docker-graph
+          emptyDir: {}
+  volumeClaimTemplates:
+    - metadata:
+        name: data
+        labels:
+          app.kubernetes.io/name: gitea-runner
+          app.kubernetes.io/part-of: gitea-actions
+      spec:
+        accessModes:
+          - ReadWriteOnce
+        storageClassName: hcloud-volumes
+        resources:
+          requests:
+            storage: 20Gi