首页 文章

Terraform:如何使用命名空间在Google Cloud(GKE)上创建Kubernetes集群?

提问于
浏览
1

我是在做一个可以做到以下事情的例子:

我不确定的是如何连接新创建的集群和命名空间定义 . 例如,当添加 google_container_node_pool 时,我可以执行类似 cluster = "${google_container_cluster.hosting.name}" 的操作,但我看不到 kubernetes_namespace 的任何类似内容 .

1 回答

  • 4

    从理论上讲,可以像在单个提供程序的上下文中引用资源或数据源一样,从K8S(或任何其他)提供程序中的GCP提供程序引用资源 .

    provider "google" {
      region = "us-west1"
    }
    
    data "google_compute_zones" "available" {}
    
    resource "google_container_cluster" "primary" {
      name = "the-only-marcellus-wallace"
      zone = "${data.google_compute_zones.available.names[0]}"
      initial_node_count = 3
    
      additional_zones = [
        "${data.google_compute_zones.available.names[1]}"
      ]
    
      master_auth {
        username = "mr.yoda"
        password = "adoy.rm"
      }
    
      node_config {
        oauth_scopes = [
          "https://www.googleapis.com/auth/compute",
          "https://www.googleapis.com/auth/devstorage.read_only",
          "https://www.googleapis.com/auth/logging.write",
          "https://www.googleapis.com/auth/monitoring"
        ]
      }
    }
    
    provider "kubernetes" {
      host = "https://${google_container_cluster.primary.endpoint}"
      username = "${google_container_cluster.primary.master_auth.0.username}"
      password = "${google_container_cluster.primary.master_auth.0.password}"
      client_certificate = "${base64decode(google_container_cluster.primary.master_auth.0.client_certificate)}"
      client_key = "${base64decode(google_container_cluster.primary.master_auth.0.client_key)}"
      cluster_ca_certificate = "${base64decode(google_container_cluster.primary.master_auth.0.cluster_ca_certificate)}"
    }
    
    resource "kubernetes_namespace" "n" {
      metadata {
        name = "blablah"
      }
    }
    

    但是在实践中,由于已知的核心错误会破坏跨提供程序依赖性,它可能无法按预期工作,请分别参见https://github.com/hashicorp/terraform/issues/12393https://github.com/hashicorp/terraform/issues/4149 .

    替代解决方案是:

    • 首先使用2阶段申请和target GKE集群,然后使用依赖于它的任何其他东西,即 terraform apply -target=google_container_cluster.primary 然后 terraform apply

    • 从K8S配置中分离出GKE集群配置,为它们提供完全隔离的工作流程并通过remote state连接它们 .

    /terraform-gke/main.tf

    terraform {
      backend "gcs" {
        bucket  = "tf-state-prod"
        prefix  = "terraform/state"
      }
    }
    
    provider "google" {
      region = "us-west1"
    }
    
    data "google_compute_zones" "available" {}
    
    resource "google_container_cluster" "primary" {
      name = "the-only-marcellus-wallace"
      zone = "${data.google_compute_zones.available.names[0]}"
      initial_node_count = 3
    
      additional_zones = [
        "${data.google_compute_zones.available.names[1]}"
      ]
    
      master_auth {
        username = "mr.yoda"
        password = "adoy.rm"
      }
    
      node_config {
        oauth_scopes = [
          "https://www.googleapis.com/auth/compute",
          "https://www.googleapis.com/auth/devstorage.read_only",
          "https://www.googleapis.com/auth/logging.write",
          "https://www.googleapis.com/auth/monitoring"
        ]
      }
    }
    
    output "gke_host" {
      value = "https://${google_container_cluster.primary.endpoint}"
    }
    
    output "gke_username" {
      value = "${google_container_cluster.primary.master_auth.0.username}"
    }
    
    output "gke_password" {
      value = "${google_container_cluster.primary.master_auth.0.password}"
    }
    
    output "gke_client_certificate" {
      value = "${base64decode(google_container_cluster.primary.master_auth.0.client_certificate)}"
    }
    
    output "gke_client_key" {
      value = "${base64decode(google_container_cluster.primary.master_auth.0.client_key)}"
    }
    
    output "gke_cluster_ca_certificate" {
      value = "${base64decode(google_container_cluster.primary.master_auth.0.cluster_ca_certificate)}"
    }
    

    这里我们通过 output 暴露所有必要的配置,并使用后端存储状态,以及这些输出在远程位置,在这种情况下GCS . 这使我们能够在下面的配置中引用它 .

    /terraform-k8s/main.tf

    data "terraform_remote_state" "foo" {
      backend = "gcs"
      config {
        bucket  = "tf-state-prod"
        prefix  = "terraform/state"
      }
    }
    
    provider "kubernetes" {
      host = "https://${data.terraform_remote_state.foo.gke_host}"
      username = "${data.terraform_remote_state.foo.gke_username}"
      password = "${data.terraform_remote_state.foo.gke_password}"
      client_certificate = "${base64decode(data.terraform_remote_state.foo.gke_client_certificate)}"
      client_key = "${base64decode(data.terraform_remote_state.foo.gke_client_key)}"
      cluster_ca_certificate = "${base64decode(data.terraform_remote_state.foo.gke_cluster_ca_certificate)}"
    }
    
    resource "kubernetes_namespace" "n" {
      metadata {
        name = "blablah"
      }
    }
    

    这里可能或不显而易见的是,在创建/更新任何K8S资源之前必须创建/更新集群(如果此类更新依赖于集群的更新) .


    采用第二种方法通常是可取的(即使当/如果错误不是因素并且交叉提供者参考有效),因为它减少了爆炸半径并且定义了更明确的责任 . 这种部署通常是(IMO)让1个人/团队负责管理集群,而另一个人/团队负责管理K8S资源 .

    可能肯定会有重叠 - 例如ops希望在新的GKE集群之上部署日志记录和监控基础架构,因此跨供应商依赖性旨在满足此类用例 . 出于这个原因,我建议订阅上面提到的GH问题 .

相关问题