stack.basicstack.de/infrastructure/k3s-manifests/coredns.yaml

233 lines
5.2 KiB
YAML
Raw Permalink Normal View History

fix(dns): cap hostNetwork/coredns pod DNS at 3 upstreams (DEV-527) Hetzner OS publishes 4 systemd-resolved upstreams and Kubernetes limits pod resolv.conf to 3 nameservers, so kubelet drops the 4th and fires a DNSConfigForming Warning event on every hostNetwork or dnsPolicy=Default pod restart. Silence the noise by pinning the pods to 3 explicit servers (same 3 kubelet was already picking). - apps/observability/patches/node-exporter-dns-config.yaml — strategic- merge patch adding dnsPolicy=None + dnsConfig to the kube-prometheus-stack node-exporter DaemonSet (Helm-managed, applied by hand) - apps/observability/patches/coredns-dns-config.yaml — companion patch for the k3s built-in CoreDNS Deployment. kubectl patch alone is not durable because the k3s addon controller reverts dnsPolicy; kept as a quick manual re-apply hook - infrastructure/k3s-manifests/coredns.yaml — the authoritative modified k3s addon manifest that must live at /var/lib/rancher/k3s/server/manifests/coredns.yaml on all 3 CP nodes - infrastructure/k3s-manifests/README-DEV-527.md — apply procedure, verification steps, and upgrade caveat Applied and verified on the live cluster: - node-exporter DaemonSet rolled with dnsPolicy=None; no DNSConfigForming events on current pods - coredns Deployment reconciled after pushing the modified manifest to all 3 CPs; new pod runs with dnsPolicy=None and 3-nameserver dnsConfig - internal + external DNS resolution still works Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-08-23 12:05:12 +00:00
apiVersion: v1
kind: ServiceAccount
metadata:
name: coredns
namespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
labels:
kubernetes.io/bootstrapping: rbac-defaults
name: system:coredns
rules:
- apiGroups:
- ""
resources:
- endpoints
- services
- pods
- namespaces
verbs:
- list
- watch
- apiGroups:
- discovery.k8s.io
resources:
- endpointslices
verbs:
- list
- watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
annotations:
rbac.authorization.kubernetes.io/autoupdate: "true"
labels:
kubernetes.io/bootstrapping: rbac-defaults
name: system:coredns
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: system:coredns
subjects:
- kind: ServiceAccount
name: coredns
namespace: kube-system
---
apiVersion: v1
kind: ConfigMap
metadata:
name: coredns
namespace: kube-system
data:
Corefile: |
.:53 {
errors
health
ready
kubernetes cluster.local in-addr.arpa ip6.arpa {
pods insecure
fallthrough in-addr.arpa ip6.arpa
}
hosts /etc/coredns/NodeHosts {
ttl 60
reload 15s
fallthrough
}
prometheus :9153
cache 30
loop
reload
loadbalance
import /etc/coredns/custom/*.override
forward . /etc/resolv.conf
}
import /etc/coredns/custom/*.server
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: coredns
namespace: kube-system
labels:
k8s-app: kube-dns
kubernetes.io/name: "CoreDNS"
spec:
revisionHistoryLimit: 0
strategy:
type: RollingUpdate
rollingUpdate:
maxUnavailable: 1
selector:
matchLabels:
k8s-app: kube-dns
template:
metadata:
labels:
k8s-app: kube-dns
spec:
priorityClassName: "system-cluster-critical"
serviceAccountName: coredns
tolerations:
- key: "CriticalAddonsOnly"
operator: "Exists"
- key: "node-role.kubernetes.io/control-plane"
operator: "Exists"
effect: "NoSchedule"
nodeSelector:
kubernetes.io/os: linux
topologySpreadConstraints:
- maxSkew: 1
topologyKey: kubernetes.io/hostname
whenUnsatisfiable: DoNotSchedule
labelSelector:
matchLabels:
k8s-app: kube-dns
- maxSkew: 1
topologyKey: topology.kubernetes.io/zone
whenUnsatisfiable: ScheduleAnyway
labelSelector:
matchLabels:
k8s-app: kube-dns
containers:
- name: coredns
image: "rancher/mirrored-coredns-coredns:1.14.4"
imagePullPolicy: IfNotPresent
resources:
limits:
memory: 170Mi
requests:
cpu: 100m
memory: 70Mi
args: [ "-conf", "/etc/coredns/Corefile" ]
volumeMounts:
- name: config-volume
mountPath: /etc/coredns
readOnly: true
- name: custom-config-volume
mountPath: /etc/coredns/custom
readOnly: true
ports:
- containerPort: 53
name: dns
protocol: UDP
- containerPort: 53
name: dns-tcp
protocol: TCP
- containerPort: 9153
name: metrics
protocol: TCP
securityContext:
allowPrivilegeEscalation: false
capabilities:
add:
- NET_BIND_SERVICE
drop:
- all
readOnlyRootFilesystem: true
livenessProbe:
httpGet:
path: /health
port: 8080
scheme: HTTP
initialDelaySeconds: 60
periodSeconds: 10
timeoutSeconds: 1
successThreshold: 1
failureThreshold: 3
readinessProbe:
httpGet:
path: /ready
port: 8181
scheme: HTTP
initialDelaySeconds: 0
periodSeconds: 2
timeoutSeconds: 1
successThreshold: 1
failureThreshold: 3
dnsPolicy: None
dnsConfig:
nameservers:
- 2a01:4ff:ff00::add:2
- 2a01:4ff:ff00::add:1
- 185.12.64.1
searches:
- .
options:
- name: edns0
- name: trust-ad
volumes:
- name: config-volume
configMap:
name: coredns
items:
- key: Corefile
path: Corefile
- key: NodeHosts
path: NodeHosts
- name: custom-config-volume
configMap:
name: coredns-custom
optional: true
---
apiVersion: v1
kind: Service
metadata:
name: kube-dns
namespace: kube-system
annotations:
prometheus.io/port: "9153"
prometheus.io/scrape: "true"
labels:
k8s-app: kube-dns
kubernetes.io/cluster-service: "true"
kubernetes.io/name: "CoreDNS"
spec:
selector:
k8s-app: kube-dns
clusterIP: 10.96.0.10
clusterIPs: [10.96.0.10]
ports:
- name: dns
port: 53
protocol: UDP
- name: dns-tcp
port: 53
protocol: TCP
- name: metrics
port: 9153
protocol: TCP
ipFamilyPolicy: SingleStack