如何使用 Terraform 公开具有公共 IP 地址的 Azure Kubernetes 集群

Question

我无法使用公共 IP 地址公开部署在 AKS 上的 k8s 集群。 我正在使用 GitHub Actions 进行部署。 以下是我的 .tf 和 deployment.yml 文件；

请参阅下面我面临的错误。

主文件

provider "azurerm" {
  features {}
}

provider "azuread" {
  version = "=0.7.0"
}

terraform {
  backend "azurerm" {
    resource_group_name  = "tstate-rg"
    storage_account_name = "tstateidentity11223"
    container_name       = "tstate"
    access_key           = "/qSJCUo..."
    key                  = "terraform.tfstate"
  }
}

# create resource group
resource "azurerm_resource_group" "aks" {
  name     = "${var.name_prefix}-rg"
  location = var.location
  }
}

aks-cluster.tf

resource "azurerm_kubernetes_cluster" "aks" {
  name                = "${var.name_prefix}-aks"
  location            = var.location
  resource_group_name = var.resourcename
  dns_prefix          = "${var.name_prefix}-dns"

  default_node_pool {
    name            = "identitynode"
    node_count      = 3
    vm_size         = "Standard_D2_v2"
    os_disk_size_gb = 30
  }

  service_principal {
    client_id     = var.client_id
    client_secret = var.client_secret
  }

  network_profile {
    network_plugin    = "kubenet"
    load_balancer_sku = "Standard"
  }
}

nginxlb.tf

# Initialize Helm (and install Tiller)
provider "helm" {
  #  install_tiller = true

  kubernetes {
    host                   = azurerm_kubernetes_cluster.aks.kube_config.0.host
    client_certificate     = base64decode(azurerm_kubernetes_cluster.aks.kube_config.0.client_certificate)
    client_key             = base64decode(azurerm_kubernetes_cluster.aks.kube_config.0.client_key)
    cluster_ca_certificate = base64decode(azurerm_kubernetes_cluster.aks.kube_config.0.cluster_ca_certificate)
    load_config_file       = false
  }
}

# Add Kubernetes Stable Helm charts repo
data "helm_repository" "stable" {
  name = "stable"
  url  = "https://kubernetes-charts.storage.googleapis.com"
}

# Create Static Public IP Address to be used by Nginx Ingress
resource "azurerm_public_ip" "nginx_ingress" {
  name                = "nginx-ingress-pip"
  location            = azurerm_kubernetes_cluster.aks.location
  resource_group_name = azurerm_kubernetes_cluster.aks.node_resource_group

  allocation_method = "Static"
  domain_name_label = var.name_prefix
}


# Install Nginx Ingress using Helm Chart
resource "helm_release" "nginx" {
  name       = "nginx-ingress"
  repository = data.helm_repository.stable.url
  #repository = data.helm_repository.stable.metadata.0.name
  chart = "nginx-ingress"
  # namespace  = "kube-system"
  namespace = "default"

  set {
    name  = "rbac.create"
    value = "false"
  }

  set {
    name  = "controller.service.externalTrafficPolicy"
    value = "Local"
  }

  set {
    name  = "controller.service.loadBalancerIP"
    value = azurerm_public_ip.nginx_ingress.ip_address
  }
} 

还有我的 deployment.yml

apiVersion: v1
kind: Namespace
metadata:
  name: 
  namespace: default
---
apiVersion: v1
kind: Service
metadata:
  name: identity-svc
  namespace: default
  labels:
    name: identity-svc
    env: dev
    app: identity-svc
  annotations:
    service.beta.kubernetes.io/azure-load-balancer-resource-group: MC_identity-k8s-rg_identity-k8s-aks_westeurope
    # nginx.ingress.kubernetes.io/rewrite-target: /$1
spec:
  loadBalancerIP: 13.95.67.206
  type: LoadBalancer ## NodePort,ClusterIP,LoadBalancer --> Ingress Controller:nginx,HAProxy
  ports:
  - name: http
    port: 8000
    targetPort: 8000
    nodePort: 30036
    protocol: TCP
  selector:
    app: identity-svc
---
apiVersion: v1
data:
  .dockerconfigjson: eyJhdXRocyI6eyJpZGVudGl0eXNlcnZpY2UuYXp1cmVjVZWcVpYS2o4QTM3RmsvZEZZbTlrbHQiLCJlbWFpbCI6InN1YmplQHN1YmplLmNvbSIsImF1dGgiOiJ
kind: Secret
metadata:
  creationTimestamp: null
  name: acr-secret
  namespace: default
type: kubernetes.io/dockerconfigjson
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: identity-deploy
  namespace: default
  labels:
    name: identity-app
    env: dev
spec:
  replicas: 1
  selector:
    matchLabels:
      app: identity-svc
  template:
    metadata:
      namespace: default
      labels:
        app: identity-svc
    spec:
      #backoffLimit: 1
      imagePullSecrets:
        - name: acr-secret
      containers:
      - name: identitysvc
        image: identitysvc.azurecr.io/identitysvc:${{ github.run_id }}
        env:
          - name: SECRET_KEY
            value: ${SECRET_KEY}
          - name: DOPPLER_TOKEN
            value: ${DOPPLER_TOKEN}
        resources:
          requests:
            cpu: 0.5
            memory: "500Mi" 
          limits:
            cpu: 2
            memory: "1000Mi"
        ports:
        - containerPort: 8000
          name: http
        imagePullPolicy: Always
      restartPolicy: Always

以下是来自 GitHub 操作日志和 Azure 上的 Kubectl 的错误消息。

GitHub 操作日志； 此消息会重复直到超时。

Kubectl 登录 AKS；

kubectl 描述 svc

Name:                     nginx-ingress-controller
Namespace:                default
Labels:                   app=nginx-ingress
                          app.kubernetes.io/managed-by=Helm
                          chart=nginx-ingress-1.41.3
                          component=controller
                          heritage=Helm
                          release=nginx-ingress
Annotations:              meta.helm.sh/release-name: nginx-ingress
                          meta.helm.sh/release-namespace: default
Selector:                 app.kubernetes.io/component=controller,app=nginx-ingress,release=nginx-ingress
Type:                     LoadBalancer
IP:                       10.0.153.66
IP:                       13.95.67.206
Port:                     http  8000/TCP
TargetPort:               http/TCP
NodePort:                 http  30933/TCP
Endpoints:                10.244.1.6:8000
Port:                     https  443/TCP
TargetPort:               https/TCP
NodePort:                 https  32230/TCP
Endpoints:                10.244.1.6:443
Session Affinity:         None
External Traffic Policy:  Local
HealthCheck NodePort:     32755
Events:
  Type     Reason                      Age                     From                  Message
  ----     ------                      ----                    ----                  -------
  Normal   EnsuringLoadBalancer        4m17s (x43 over 3h10m)  service-controller    Ensuring load balancer
  Warning  CreateOrUpdateLoadBalancer  4m16s (x43 over 3h10m)  azure-cloud-provider  Code="PublicIPAndLBSkuDoNotMatch" Message="Standard sku load balancer /subscriptions/e90bd4d0-3b50-4a27-a7e8-bc88cf5f5398/resourceGroups/mc_identity-k8s-rg_identity-k8s-aks_westeurope/providers/Microsoft.Network/loadBalancers/kubernetes cannot reference Basic sku publicIP /subscriptions/e90bd4d0-3b50-4a27-a7e8-bc88cf5f5398/resourceGroups/MC_identity-k8s-rg_identity-k8s-aks_westeurope/providers/Microsoft.Network/publicIPAddresses/nginx-ingress-pip." Details=[]

kubectl 日志

I1108 12:52:52.862797       7 flags.go:205] Watching for Ingress class: nginx
W1108 12:52:52.863034       7 flags.go:250] SSL certificate chain completion is disabled (--enable-ssl-chain-completion=false)
W1108 12:52:52.863078       7 client_config.go:552] Neither --kubeconfig nor --master was specified.  Using the inClusterConfig.  This might not work.
I1108 12:52:52.863272       7 main.go:231] Creating API client for https://10.0.0.1:443
-------------------------------------------------------------------------------
NGINX Ingress controller
  Release:       v0.34.1
  Build:         v20200715-ingress-nginx-2.11.0-8-gda5fa45e2
  Repository:    https://github.com/kubernetes/ingress-nginx
  nginx version: nginx/1.19.1

-------------------------------------------------------------------------------

I1108 12:52:52.892455       7 main.go:275] Running in Kubernetes cluster version v1.17 (v1.17.13) - git (clean) commit 30d651da517185653e34e7ab99a792be6a3d9495 - platform linux/amd64
I1108 12:52:52.897887       7 main.go:87] Validated default/nginx-ingress-default-backend as the default backend.
I1108 12:52:53.229870       7 main.go:105] SSL fake certificate created /etc/ingress-controller/ssl/default-fake-certificate.pem
W1108 12:52:53.252657       7 store.go:659] Unexpected error reading configuration configmap: configmaps "nginx-ingress-controller" not found
I1108 12:52:53.268067       7 nginx.go:263] Starting NGINX Ingress controller
I1108 12:52:54.468656       7 leaderelection.go:242] attempting to acquire leader lease  default/ingress-controller-leader-nginx...
I1108 12:52:54.468691       7 nginx.go:307] Starting NGINX process
W1108 12:52:54.469222       7 controller.go:395] Service "default/nginx-ingress-default-backend" does not have any active Endpoint
I1108 12:52:54.469249       7 controller.go:141] Configuration changes detected, backend reload required.
I1108 12:52:54.473464       7 status.go:86] new leader elected: nginx-ingress-controller-6b45fcd8ff-7mbx4
I1108 12:52:54.543113       7 controller.go:157] Backend successfully reloaded.
I1108 12:52:54.543152       7 controller.go:166] Initial sync, sleeping for 1 second.
W1108 12:52:58.251867       7 controller.go:395] Service "default/nginx-ingress-default-backend" does not have any active Endpoint
I1108 12:53:38.008002       7 leaderelection.go:252] successfully acquired lease default/ingress-controller-leader-nginx
I1108 12:53:38.008203       7 status.go:86] new leader elected: nginx-ingress-controller-6b45fcd8ff-njgjs

帮助我了解我在这里缺少什么？ 这整个过程是我尝试在公共 IP 地址上部署一个简单的 Python 服务。 我只是想在公共 IP 上公开服务，目前使用哪种方法无论是 nginx 还是任何其他负载平衡服务都无关紧要。

同样在我在 Terraform 文件中实现 nginx ingress 之前，我可以看到在运行kubectl get services时身份 svc 正在运行，但现在我什至看不到该服务只有 nginx 入口控制器。 我真的很感激任何帮助。

编辑：在将 sku 标准添加到公共 IP 创建后，@mynko 提到工作流可以成功运行。 现在，当我检查以下内容时；

admin@Azure:~$ kubectl get svc
NAME                            TYPE           CLUSTER-IP     EXTERNAL-IP     PORT(S)                      AGE
identity-svc                    LoadBalancer   10.0.188.32    20.56.242.212   8000:30036/TCP               22m
kubernetes                      ClusterIP      10.0.0.1       <none>          443/TCP                      7h28m
nginx-ingress-controller        LoadBalancer   10.0.230.164   20.50.221.84    8000:31742/TCP,443:31675/TCP   23m
nginx-ingress-default-backend   ClusterIP      10.0.229.217   <none>          8000/TCP                       23m

我明白了，我不确定为什么nginx-ingress-controller正在查看端口 80 而不是 8000。此外，当我尝试访问 `20.56.242.212:8000 时，什么也没有加载。 同样在这种情况下，哪一个应该是我公开的公共 IP？

当我访问20.50.221.84它显示default backend - 404

Answer 1

查看 kubernetes 服务警告消息。

Code="PublicIPAndLBSkuDoNotMatch"

您使用的是基本 SKU 公共 IP，请将其更改为标准。

https://registry.terraform.io/providers/hashicorp/azurerm/latest/docs/resources/public_ip#sku