feat(k4.1): Kured automatic node reboot daemon

- Deploy Kured v1.15.1 as DaemonSet
- Maintenance window: 02:00-04:00 Taipei time
- Reboot period: 1 hour between node reboots
- PDB-aware: checks AWOOOI pods before draining
- Prometheus integration for metrics

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
OG T
2026-03-28 22:03:05 +08:00
parent f010f42795
commit c6bef20a97

143
k8s/kured/kured.yaml Normal file
View File

@@ -0,0 +1,143 @@
# =============================================================================
# Kured (KUbernetes REboot Daemon)
# =============================================================================
# K4.1 2026-03-28: Automatic node reboot for OS updates
# Deployed by: Claude Code (首席架構師)
# Maintenance window: 02:00-04:00 (UTC+8 台北時間)
# =============================================================================
---
apiVersion: v1
kind: Namespace
metadata:
name: kured
labels:
app.kubernetes.io/name: kured
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: kured
namespace: kured
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: kured
rules:
- apiGroups: [""]
resources: ["nodes"]
verbs: ["get", "patch"]
- apiGroups: [""]
resources: ["pods"]
verbs: ["list", "delete", "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: kured
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
name: kured
namespace: kured
rules:
- apiGroups: ["apps"]
resources: ["daemonsets"]
verbs: ["update"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
name: kured
namespace: kured
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: kured
subjects:
- kind: ServiceAccount
name: kured
namespace: kured
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kured
namespace: kured
labels:
app.kubernetes.io/name: kured
app.kubernetes.io/version: "1.15.1"
spec:
selector:
matchLabels:
app.kubernetes.io/name: kured
updateStrategy:
type: RollingUpdate
template:
metadata:
labels:
app.kubernetes.io/name: kured
spec:
serviceAccountName: kured
tolerations:
- key: node-role.kubernetes.io/control-plane
operator: Exists
effect: NoSchedule
- key: node-role.kubernetes.io/master
operator: Exists
effect: NoSchedule
hostPID: true
restartPolicy: Always
containers:
- name: kured
image: ghcr.io/kubereboot/kured:1.15.1
imagePullPolicy: IfNotPresent
securityContext:
privileged: true
env:
- name: KURED_NODE_ID
valueFrom:
fieldRef:
fieldPath: spec.nodeName
command:
- /usr/bin/kured
- --reboot-sentinel=/var/run/reboot-required
# 維護窗口: 02:00-04:00 UTC+8 = 18:00-20:00 UTC (前一天)
- --start-time=18:00
- --end-time=20:00
- --time-zone=Asia/Taipei
# 重啟間隔: 1小時
- --period=1h
# PodDisruptionBudget 檢查
- --blocking-pod-selector=app.kubernetes.io/name=awoooi
# Prometheus metrics
- --prometheus-url=http://192.168.0.188:9090
resources:
limits:
cpu: 100m
memory: 64Mi
requests:
cpu: 10m
memory: 32Mi
volumeMounts:
- name: hostrun
mountPath: /var/run
volumes:
- name: hostrun
hostPath:
path: /var/run