kured.yaml

# Source: https://github.com/kubereboot/charts/tree/kured-5.2.0/charts/kured (1.14.0)
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: kured
rules:
# Allow kured to read spec.unschedulable
# Allow kubectl to drain/uncordon
#
# NB: These permissions are tightly coupled to the bundled version of kubectl; the ones below
# match https://github.com/kubernetes/kubernetes/blob/v1.19.4/staging/src/k8s.io/kubectl/pkg/cmd/drain/drain.go
#
- apiGroups: [""]
  resources: ["nodes"]
  verbs:     ["get", "patch"]
- apiGroups: [""]
  resources: ["pods"]
  verbs:     ["list","delete","get"]
- apiGroups: ["extensions"]
  resources: ["daemonsets"]
  verbs:     ["get"]
- apiGroups: ["apps"]
  resources: ["daemonsets"]
  verbs:     ["get"]
- apiGroups: [""]
  resources: ["pods/eviction"]
  verbs:     ["create"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: kured
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: kured
subjects:
- kind: ServiceAccount
  name: kured
  namespace: cluster-baseline-settings
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
  namespace: cluster-baseline-settings
  name: kured
rules:
  # Allow kured to lock/unlock itself
  - apiGroups:     ["extensions"]
    resources:     ["daemonsets"]
    resourceNames: ["kured"]
    verbs:         ["update", "patch"]
  - apiGroups:     ["apps"]
    resources:     ["daemonsets"]
    resourceNames: ["kured"]
    verbs:         ["update", "patch"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  namespace: cluster-baseline-settings
  name: kured
subjects:
- kind: ServiceAccount
  namespace: cluster-baseline-settings
  name: kured
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: kured
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: kured
  namespace: cluster-baseline-settings
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: kured                           # Must match `--ds-name`
  namespace: cluster-baseline-settings  # Must match `--ds-namespace`
spec:
  revisionHistoryLimit: 10
  selector:
    matchLabels:
      app.kubernetes.io/name: kured
  updateStrategy:
    type: RollingUpdate
    rollingUpdate:
      maxUnavailable: 1
  template:
    metadata:
      labels:
        app.kubernetes.io/name: kured
      annotations:
        prometheus.io/scrape: "true"
        prometheus.io/path: "/metrics"
        prometheus.io/port: "8080"
    spec:
      serviceAccountName: kured
      tolerations:
        - key: node-role.kubernetes.io/control-plane
          effect: NoSchedule
        - key: node-role.kubernetes.io/master
          effect: NoSchedule
        - key: CriticalAddonsOnly
          effect: NoSchedule
          operator: Equal
          value: "true"
      hostNetwork: true
      hostPID: true # Facilitate entering the host mount namespace via init
      restartPolicy: Always
      nodeSelector:
        kubernetes.io/arch: amd64
        kubernetes.io/os: linux
      containers:
        - name: kured
          # PRODUCTION READINESS CHANGE REQUIRED
          # This image should be sourced from a non-public container registry, such as the
          # one deployed along side of this reference implementation.
          # az acr import --source ghcr.io/kubereboot/kured:1.14.0 -n <your-acr-instance-name>
          # and then set this to
          # image: <your-acr-instance-name>.azurecr.io/kubereboot/kured:1.14.0
          image: ghcr.io/kubereboot/kured:1.14.0
          imagePullPolicy: IfNotPresent
          securityContext:
            privileged: true # Give permission to nsenter /proc/1/ns/mnt
          resources:
            limits:
              cpu: 500m
              memory: 48Mi
            requests:
              cpu: 200m
              memory: 16Mi
          ports:
            - containerPort: 8080
              name: metrics
          env:
            # Pass in the name of the node on which this pod is scheduled
            # for use with drain/uncordon operations and lock acquisition
            - name: KURED_NODE_ID
              valueFrom:
                fieldRef:
                  fieldPath: spec.nodeName
          command:
            - /usr/bin/kured
          args:
            - --ds-namespace=cluster-baseline-settings
#            - --ds-name=kured
#            - --reboot-command=/bin/systemctl reboot
#            - --force-reboot=false
#            - --drain-grace-period=-1
#            - --skip-wait-for-delete-timeout=0
#            - --drain-timeout=0
#            - --period=1h
#            - --ds-name=kured
#            - --lock-annotation=weave.works/kured-node-lock
#            - --lock-ttl=0
#            - --prometheus-url=http://prometheus.monitoring.svc.cluster.local
#            - --alert-filter-regexp=^RebootRequired$
#            - --alert-firing-only=false
#            - --reboot-sentinel=/var/run/reboot-required
#            - --prefer-no-schedule-taint=""
#            - --reboot-sentinel-command=""
#            - --slack-hook-url=https://hooks.slack.com/...
#            - --slack-username=prod
#            - --slack-channel=alerting
#            - --notify-url="" # See also shoutrrr url format
#            - --message-template-drain=Draining node %s
#            - --message-template-reboot=Rebooting node %s
#            - --message-template-uncordon=Node %s rebooted & uncordoned successfully!
#            - --blocking-pod-selector=runtime=long,cost=expensive
#            - --blocking-pod-selector=name=temperamental
#            - --blocking-pod-selector=...
#            - --reboot-days=sun,mon,tue,wed,thu,fri,sat
#            - --reboot-delay=90s
#            - --start-time=0:00
#            - --end-time=23:59:59
#            - --time-zone=UTC
#            - --annotate-nodes=false
#            - --lock-release-delay=30m
#            - --log-format=text