如何允许Azure中的Kubernetes群集通过Terraform与Azure容器注册表通信？
我想从我的Azure容器注册表中加载自定义图像。不幸的是，在Kubernetes应该从ACR下载图像的时候遇到了权限错误。
在我通过az cli将acr附加到aks之后，一切都完美运行了：
az aks update -n myAKSCluster -g myResourceGroup --attach-acr <acrName>
这是我的地形配置；我已经去除了其他东西。它本身可以工作。
terraform {
backend "azurerm" {
resource_group_name = "tf-state"
storage_account_name = "devopstfstate"
container_name = "tfstatetest"
key = "prod.terraform.tfstatetest"
}
}
provider "azurerm" {
}
provider "azuread" {
}
provider "random" {
}
# define the password
resource "random_string" "password" {
length = 32
special = true
}
# define the resource group
resource "azurerm_resource_group" "rg" {
name = "myrg"
location = "eastus2"
}
# define the app
resource "azuread_application" "tfapp" {
name = "mytfapp"
}
# define the service principal
resource "azuread_service_principal" "tfapp" {
application_id = azuread_application.tfapp.application_id
}
# define the service principal password
resource "azuread_service_principal_password" "tfapp" {
service_principal_id = azuread_service_principal.tfapp.id
end_date = "2020-12-31T09:00:00Z"
value = random_string.password.result
}
# define the container registry
resource "azurerm_container_registry" "acr" {
name = "mycontainerregistry2387987222"
resource_group_name = azurerm_resource_group.rg.name
location = azurerm_resource_group.rg.location
sku = "Basic"
admin_enabled = false
}
# define the kubernetes cluster
resource "azurerm_kubernetes_cluster" "mycluster" {
name = "myaks"
location = azurerm_resource_group.rg.location
resource_group_name = azurerm_resource_group.rg.name
dns_prefix = "mycluster"
network_profile {
network_plugin = "azure"
}
default_node_pool {
name = "default"
node_count = 1
vm_size = "Standard_B2s"
}
# Use the service principal created above
service_principal {
client_id = azuread_service_principal.tfapp.application_id
client_secret = azuread_service_principal_password.tfapp.value
}
tags = {
Environment = "demo"
}
windows_profile {
admin_username = "dingding"
admin_password = random_string.password.result
}
}
# define the windows node pool for kubernetes
resource "azurerm_kubernetes_cluster_node_pool" "winpool" {
name = "winp"
kubernetes_cluster_id = azurerm_kubernetes_cluster.mycluster.id
vm_size = "Standard_B2s"
node_count = 1
os_type = "Windows"
}
# define the kubernetes name space
resource "kubernetes_namespace" "namesp" {
metadata {
name = "namesp"
}
}
# Try to give permissions, to let the AKR access the ACR
resource "azurerm_role_assignment" "acrpull_role" {
scope = azurerm_container_registry.acr.id
role_definition_name = "AcrPull"
principal_id = azuread_service_principal.tfapp.object_id
skip_service_principal_aad_check = true
}
此代码改编自https://github.com/terraform-providers/terraform-provider-azuread/issues/104。
不幸的是，当我在kubernetes集群中启动一个容器时，我收到一条错误消息：
Failed to pull image "mycontainerregistry.azurecr.io/myunittests": [rpc error: code = Unknown desc = Error response from daemon: manifest for mycontainerregistry.azurecr.io/myunittests:latest not found: manifest unknown: manifest unknown, rpc error: code = Unknown desc = Error response from daemon: Get https://mycontainerregistry.azurecr.io/v2/myunittests/manifests/latest: unauthorized: authentication required]
更新/注释：
当我使用上面的代码运行terraform apply时，资源的创建被中断：
azurerm_container_registry.acr: Creation complete after 18s [id=/subscriptions/000/resourceGroups/myrg/providers/Microsoft.ContainerRegistry/registries/mycontainerregistry2387987222]
azurerm_role_assignment.acrpull_role: Creating...
azuread_service_principal_password.tfapp: Still creating... [10s elapsed]
azuread_service_principal_password.tfapp: Creation complete after 12s [id=000/000]
azurerm_kubernetes_cluster.mycluster: Creating...
azurerm_role_assignment.acrpull_role: Creation complete after 8s [id=/subscriptions/000/resourceGroups/myrg/providers/Microsoft.ContainerRegistry/registries/mycontainerregistry2387987222/providers/Microsoft.Authorization/roleAssignments/000]
azurerm_kubernetes_cluster.mycluster: Still creating... [10s elapsed]
Error: Error creating Managed Kubernetes Cluster "myaks" (Resource Group "myrg"): containerservice.ManagedClustersClient#CreateOrUpdate: Failure sending request: StatusCode=400 -- Original Error: Code="ServicePrincipalNotFound" Message="Service principal clientID: 000 not found in Active Directory tenant 000, Please see https://aka.ms/aks-sp-help for more details."
on test.tf line 56, in resource "azurerm_kubernetes_cluster" "mycluster":
56: resource "azurerm_kubernetes_cluster" "mycluster" {
但是，我认为这仅仅是因为创建服务主体需要花费几分钟。几分钟后，当我再次运行terraform apply时，它超出了这一点，没有问题。
答案 0 :(得分：8)
此代码对我有用。
resource "azuread_application" "aks_sp" {
name = "sp-aks-${local.cluster_name}"
}
resource "azuread_service_principal" "aks_sp" {
application_id = azuread_application.aks_sp.application_id
app_role_assignment_required = false
}
resource "azuread_service_principal_password" "aks_sp" {
service_principal_id = azuread_service_principal.aks_sp.id
value = random_string.aks_sp_password.result
end_date_relative = "8760h" # 1 year
lifecycle {
ignore_changes = [
value,
end_date_relative
]
}
}
resource "azuread_application_password" "aks_sp" {
application_object_id = azuread_application.aks_sp.id
value = random_string.aks_sp_secret.result
end_date_relative = "8760h" # 1 year
lifecycle {
ignore_changes = [
value,
end_date_relative
]
}
}
data "azurerm_container_registry" "pyp" {
name = var.container_registry_name
resource_group_name = var.container_registry_resource_group_name
}
resource "azurerm_role_assignment" "aks_sp_container_registry" {
scope = data.azurerm_container_registry.pyp.id
role_definition_name = "AcrPull"
principal_id = azuread_service_principal.aks_sp.object_id
}
# requires Azure Provider 1.37+
resource "azurerm_kubernetes_cluster" "pyp" {
name = local.cluster_name
location = azurerm_resource_group.pyp.location
resource_group_name = azurerm_resource_group.pyp.name
dns_prefix = local.env_name_nosymbols
kubernetes_version = local.kubernetes_version
default_node_pool {
name = "default"
node_count = 1
vm_size = "Standard_D2s_v3"
os_disk_size_gb = 80
}
windows_profile {
admin_username = "winadm"
admin_password = random_string.windows_profile_password.result
}
network_profile {
network_plugin = "azure"
dns_service_ip = cidrhost(local.service_cidr, 10)
docker_bridge_cidr = "172.17.0.1/16"
service_cidr = local.service_cidr
load_balancer_sku = "standard"
}
service_principal {
client_id = azuread_service_principal.aks_sp.application_id
client_secret = random_string.aks_sp_password.result
}
addon_profile {
oms_agent {
enabled = true
log_analytics_workspace_id = azurerm_log_analytics_workspace.pyp.id
}
}
tags = local.tags
}
来源https://github.com/giuliov/pipeline-your-pipelines/tree/master/src/kubernetes/terraform
答案 1 :(得分：4)
（我做了上面的回答）
只需添加一种更简单的方法即可，无需为可能需要此服务的其他人创建服务主体。
resource "azurerm_kubernetes_cluster" "kubweb" {
name = local.cluster_web
location = local.rgloc
resource_group_name = local.rgname
dns_prefix = "${local.cluster_web}-dns"
kubernetes_version = local.kubversion
# used to group all the internal objects of this cluster
node_resource_group = "${local.cluster_web}-rg-node"
# azure will assign the id automatically
identity {
type = "SystemAssigned"
}
default_node_pool {
name = "nodepool1"
node_count = 4
vm_size = local.vm_size
orchestrator_version = local.kubversion
}
role_based_access_control {
enabled = true
}
addon_profile {
kube_dashboard {
enabled = true
}
}
tags = {
environment = local.env
}
}
resource "azurerm_container_registry" "acr" {
name = "acr1"
resource_group_name = local.rgname
location = local.rgloc
sku = "Standard"
admin_enabled = true
tags = {
environment = local.env
}
}
# add the role to the identity the kubernetes cluster was assigned
resource "azurerm_role_assignment" "kubweb_to_acr" {
scope = azurerm_container_registry.acr.id
role_definition_name = "AcrPull"
principal_id = azurerm_kubernetes_cluster.kubweb.kubelet_identity[0].object_id
}