[kubernetes]-k8s安装metallb获取tcp source ip

导语：k8s中的pod需要获取tcp请求的source ip。

使用metallb作为LoadBalancer，但是有个缺陷。网络设备不支持BGP的话只能用l2的方式。只能达到高可用，无法实现负载均衡。测试了如下情况。

A 2台node 4个nginx pod，每个node2个pod，请求通过loadBalancerIP访问。请求只会打到某个node的2个节点上。虽然通过ipvsadm -Ln 查看node上的规则确实有对应loadBalancerIP转到pod ip，但是请求就没打到对应的node上

B 2台node 1个nginx pod，pod分配到A情况中没有收到请求的那个node上，pod可以正常接收到请求。

# 修改configmap/kube-proxy  确保 mode: "ipvs"   且  strictARP: true
kubectl edit configmap kube-proxy -n kube-system
#kubectl get configmap kube-proxy -n kube-system -o yaml | \
#sed -e "s/strictARP: false/strictARP: true/" | \
#kubectl apply -f - -n kube-system
# 重启生效
kubectl rollout restart ds kube-proxy -n kube-system

namespace.yaml

# cat namespace.yaml
apiVersion: v1
kind: Namespace
metadata:
  name: metallb-system
  labels:
    app: metallb

metallb.yaml

# cat metallb.yaml
apiVersion: policy/v1beta1
kind: PodSecurityPolicy
metadata:
  labels:
    app: metallb
  name: controller
spec:
  allowPrivilegeEscalation: false
  allowedCapabilities: []
  allowedHostPaths: []
  defaultAddCapabilities: []
  defaultAllowPrivilegeEscalation: false
  fsGroup:
    ranges:
    - max: 65535
      min: 1
    rule: MustRunAs
  hostIPC: false
  hostNetwork: false
  hostPID: false
  privileged: false
  readOnlyRootFilesystem: true
  requiredDropCapabilities:
  - ALL
  runAsUser:
    ranges:
    - max: 65535
      min: 1
    rule: MustRunAs
  seLinux:
    rule: RunAsAny
  supplementalGroups:
    ranges:
    - max: 65535
      min: 1
    rule: MustRunAs
  volumes:
  - configMap
  - secret
  - emptyDir
---
apiVersion: policy/v1beta1
kind: PodSecurityPolicy
metadata:
  labels:
    app: metallb
  name: speaker
spec:
  allowPrivilegeEscalation: false
  allowedCapabilities:
  - NET_RAW
  allowedHostPaths: []
  defaultAddCapabilities: []
  defaultAllowPrivilegeEscalation: false
  fsGroup:
    rule: RunAsAny
  hostIPC: false
  hostNetwork: true
  hostPID: false
  hostPorts:
  - max: 7472
    min: 7472
  - max: 7946
    min: 7946
  privileged: true
  readOnlyRootFilesystem: true
  requiredDropCapabilities:
  - ALL
  runAsUser:
    rule: RunAsAny
  seLinux:
    rule: RunAsAny
  supplementalGroups:
    rule: RunAsAny
  volumes:
  - configMap
  - secret
  - emptyDir
---
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    app: metallb
  name: controller
  namespace: metallb-system
---
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    app: metallb
  name: speaker
  namespace: metallb-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    app: metallb
  name: metallb-system:controller
rules:
- apiGroups:
  - ''
  resources:
  - services
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ''
  resources:
  - services/status
  verbs:
  - update
- apiGroups:
  - ''
  resources:
  - events
  verbs:
  - create
  - patch
- apiGroups:
  - policy
  resourceNames:
  - controller
  resources:
  - podsecuritypolicies
  verbs:
  - use
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  labels:
    app: metallb
  name: metallb-system:speaker
rules:
- apiGroups:
  - ''
  resources:
  - services
  - endpoints
  - nodes
  verbs:
  - get
  - list
  - watch
- apiGroups: ["discovery.k8s.io"]
  resources:
  - endpointslices
  verbs:
  - get
  - list
  - watch
- apiGroups:
  - ''
  resources:
  - events
  verbs:
  - create
  - patch
- apiGroups:
  - policy
  resourceNames:
  - speaker
  resources:
  - podsecuritypolicies
  verbs:
  - use
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
  labels:
    app: metallb
  name: config-watcher
  namespace: metallb-system
rules:
- apiGroups:
  - ''
  resources:
  - configmaps
  verbs:
  - get
  - list
  - watch
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
  labels:
    app: metallb
  name: pod-lister
  namespace: metallb-system
rules:
- apiGroups:
  - ''
  resources:
  - pods
  verbs:
  - list
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
  labels:
    app: metallb
  name: controller
  namespace: metallb-system
rules:
- apiGroups:
  - ''
  resources:
  - secrets
  verbs:
  - create
- apiGroups:
  - ''
  resources:
  - secrets
  resourceNames:
  - memberlist
  verbs:
  - list
- apiGroups:
  - apps
  resources:
  - deployments
  resourceNames:
  - controller
  verbs:
  - get
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    app: metallb
  name: metallb-system:controller
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: metallb-system:controller
subjects:
- kind: ServiceAccount
  name: controller
  namespace: metallb-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    app: metallb
  name: metallb-system:speaker
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: metallb-system:speaker
subjects:
- kind: ServiceAccount
  name: speaker
  namespace: metallb-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  labels:
    app: metallb
  name: config-watcher
  namespace: metallb-system
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: config-watcher
subjects:
- kind: ServiceAccount
  name: controller
- kind: ServiceAccount
  name: speaker
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  labels:
    app: metallb
  name: pod-lister
  namespace: metallb-system
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: pod-lister
subjects:
- kind: ServiceAccount
  name: speaker
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  labels:
    app: metallb
  name: controller
  namespace: metallb-system
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: controller
subjects:
- kind: ServiceAccount
  name: controller
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  labels:
    app: metallb
    component: speaker
  name: speaker
  namespace: metallb-system
spec:
  selector:
    matchLabels:
      app: metallb
      component: speaker
  template:
    metadata:
      annotations:
        prometheus.io/port: '7472'
        prometheus.io/scrape: 'true'
      labels:
        app: metallb
        component: speaker
    spec:
      containers:
      - args:
        - --port=7472
        - --config=config
        - --log-level=info
        env:
        - name: METALLB_NODE_NAME
          valueFrom:
            fieldRef:
              fieldPath: spec.nodeName
        - name: METALLB_HOST
          valueFrom:
            fieldRef:
              fieldPath: status.hostIP
        - name: METALLB_ML_BIND_ADDR
          valueFrom:
            fieldRef:
              fieldPath: status.podIP
        # needed when another software is also using memberlist / port 7946
        # when changing this default you also need to update the container ports definition
        # and the PodSecurityPolicy hostPorts definition
        #- name: METALLB_ML_BIND_PORT
        #  value: "7946"
        - name: METALLB_ML_LABELS
          value: "app=metallb,component=speaker"
        - name: METALLB_ML_SECRET_KEY
          valueFrom:
            secretKeyRef:
              name: memberlist
              key: secretkey
        image: quay.io/metallb/speaker:v0.12.1
        name: speaker
        ports:
        - containerPort: 7472
          name: monitoring
        - containerPort: 7946
          name: memberlist-tcp
        - containerPort: 7946
          name: memberlist-udp
          protocol: UDP
        livenessProbe:
          httpGet:
            path: /metrics
            port: monitoring
          initialDelaySeconds: 10
          periodSeconds: 10
          timeoutSeconds: 1
          successThreshold: 1
          failureThreshold: 3
        readinessProbe:
          httpGet:
            path: /metrics
            port: monitoring
          initialDelaySeconds: 10
          periodSeconds: 10
          timeoutSeconds: 1
          successThreshold: 1
          failureThreshold: 3
        securityContext:
          allowPrivilegeEscalation: false
          capabilities:
            add:
            - NET_RAW
            drop:
            - ALL
          readOnlyRootFilesystem: true
      hostNetwork: true
      nodeSelector:
        kubernetes.io/os: linux
      serviceAccountName: speaker
      terminationGracePeriodSeconds: 2
      tolerations:
      - effect: NoSchedule
        key: node-role.kubernetes.io/master
        operator: Exists
---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: metallb
    component: controller
  name: controller
  namespace: metallb-system
spec:
  revisionHistoryLimit: 3
  selector:
    matchLabels:
      app: metallb
      component: controller
  template:
    metadata:
      annotations:
        prometheus.io/port: '7472'
        prometheus.io/scrape: 'true'
      labels:
        app: metallb
        component: controller
    spec:
      containers:
      - args:
        - --port=7472
        - --config=config
        - --log-level=info
        env:
        - name: METALLB_ML_SECRET_NAME
          value: memberlist
        - name: METALLB_DEPLOYMENT
          value: controller
        image: quay.io/metallb/controller:v0.12.1
        name: controller
        ports:
        - containerPort: 7472
          name: monitoring
        livenessProbe:
          httpGet:
            path: /metrics
            port: monitoring
          initialDelaySeconds: 10
          periodSeconds: 10
          timeoutSeconds: 1
          successThreshold: 1
          failureThreshold: 3
        readinessProbe:
          httpGet:
            path: /metrics
            port: monitoring
          initialDelaySeconds: 10
          periodSeconds: 10
          timeoutSeconds: 1
          successThreshold: 1
          failureThreshold: 3
        securityContext:
          allowPrivilegeEscalation: false
          capabilities:
            drop:
            - all
          readOnlyRootFilesystem: true
      nodeSelector:
        kubernetes.io/os: linux
      securityContext:
        runAsNonRoot: true
        runAsUser: 65534
        fsGroup: 65534
      serviceAccountName: controller
      terminationGracePeriodSeconds: 0

configmap-metallb.yaml

# cat configmap-metallb.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  namespace: metallb-system
  name: config
data:
  config: |
    address-pools:
    - name: default
      protocol: layer2
      addresses:
      # 此处为可以分配的ip
      - 192.168.10.86-192.168.10.87 

nginx-quic-lb.yaml

# cat nginx-quic-lb.yaml
---

apiVersion: apps/v1
kind: Deployment
metadata:
  name: nginx-lb
spec:
  selector:
    matchLabels:
      app: nginx-lb
  replicas: 2
  template:
    metadata:
      labels:
        app: nginx-lb
    spec:
      containers:
      - name: nginx-lb
        image: nginx
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 80

---

apiVersion: v1
kind: Service
metadata:
  name: nginx-lb-service
  annotations:
    metallb.universe.tf/address-pool: default
spec:
  #externalTrafficPolicy: Cluster
  externalTrafficPolicy: Local
  #internalTrafficPolicy: Cluster
  internalTrafficPolicy: Local
  #healthCheckNodePort: 31695
  selector:
    app: nginx-lb
  ports:
  - protocol: TCP
    port: 80 # match for service access port # 对外的
    targetPort: 80 # match for pod access port # ep的容器端口
  type: LoadBalancer
  loadBalancerIP: 192.168.10.86

# 30858为healthCheckNodePort,如果没有配置会自动分配  如果该node上没有节点 会返回500 
curl -i localhost:30858/healthz

https://metallb.universe.tf/installation/