Compare commits
56 Commits
feature/va
...
b0faaded6a
| Author | SHA1 | Date | |
|---|---|---|---|
| b0faaded6a | |||
|
|
a9dbaf5354 | ||
| 6e175e9e8c | |||
| 396c771f59 | |||
| 7716d16572 | |||
| 0582cd9917 | |||
| c49d03d7f7 | |||
| d47dba2ae5 | |||
| cf9eb47ecf | |||
| 3eca723f05 | |||
| f36996da11 | |||
| 6bf7db21d0 | |||
| 2641d55784 | |||
| 117297effc | |||
| fda90f9e01 | |||
| 1124377d97 | |||
| c0710b89bb | |||
| d7bda18aea | |||
| 2796e1b9d3 | |||
| d7a0c26117 | |||
| 693f2f9168 | |||
| 2509ef062c | |||
| 957757e557 | |||
| 070799da05 | |||
| 1a2817e537 | |||
| b47b0035f5 | |||
| d3fac4d43e | |||
| c37bd3ef04 | |||
| ad661ba3dd | |||
| a9625f96e6 | |||
| cb64edc927 | |||
| ac1c242fb9 | |||
| 4b29c07fd6 | |||
| 52732626e5 | |||
| 8634436dd4 | |||
| a8baa169e9 | |||
| 73ef3a6e12 | |||
| 302705d374 | |||
| f3286ef77e | |||
| 74f4f86770 | |||
| f2c56156bf | |||
| 21fb50ba00 | |||
| b90b630b06 | |||
| 66de9b8a0a | |||
| 716c552be9 | |||
| f048b47a0f | |||
| 66f40427ee | |||
| 332881cbd0 | |||
| f363afa087 | |||
| bc42347cb6 | |||
| 80d7bff4bc | |||
| 3644a3ec87 | |||
| bd478478f1 | |||
| 67b1d95509 | |||
| fff95d98a5 | |||
| 8b743efa43 |
10
.gitignore
vendored
10
.gitignore
vendored
@@ -15,4 +15,12 @@ CLAUDE.md
|
||||
devbox.d/
|
||||
devbox.lock
|
||||
.devbox/
|
||||
bash.exe.stackdump
|
||||
bash.exe.stackdump
|
||||
|
||||
# OpenTofu
|
||||
.tofu/configs/*.env
|
||||
.tofu/scripts/*.config
|
||||
.tofu/platforms/**/.terraform/
|
||||
.tofu/platforms/**/terraform.tfstate*
|
||||
.tofu/platforms/**/tfplan
|
||||
.tofu/platforms/**/.terraform.lock.hcl
|
||||
9
.tofu/configs/aks.env.example
Normal file
9
.tofu/configs/aks.env.example
Normal file
@@ -0,0 +1,9 @@
|
||||
# Azure AKS credentials — copy to aks.env and fill in values
|
||||
# NEVER commit aks.env to git!
|
||||
|
||||
# Required
|
||||
AZURE_TENANT_ID=your-azure-tenant-id
|
||||
AZURE_SUBSCRIPTION_ID=your-azure-subscription-id
|
||||
|
||||
# Optional — defaults to cluster name if not set
|
||||
ARM_RESOURCE_GROUP=
|
||||
10
.tofu/configs/eks.env.example
Normal file
10
.tofu/configs/eks.env.example
Normal file
@@ -0,0 +1,10 @@
|
||||
# AWS EKS credentials — copy to eks.env and fill in values
|
||||
# NEVER commit eks.env to git!
|
||||
|
||||
# Required — AWS CLI profile or access key
|
||||
AWS_PROFILE=default
|
||||
AWS_REGION=eu-west-1
|
||||
|
||||
# Optional — override with explicit keys instead of profile
|
||||
# AWS_ACCESS_KEY_ID=
|
||||
# AWS_SECRET_ACCESS_KEY=
|
||||
9
.tofu/configs/gke.env.example
Normal file
9
.tofu/configs/gke.env.example
Normal file
@@ -0,0 +1,9 @@
|
||||
# GCP GKE credentials — copy to gke.env and fill in values
|
||||
# NEVER commit gke.env to git!
|
||||
|
||||
# Required
|
||||
GCP_PROJECT_ID=your-gcp-project-id
|
||||
GCP_REGION=europe-west4
|
||||
|
||||
# Optional — path to service account JSON key (if not using gcloud auth)
|
||||
# GOOGLE_APPLICATION_CREDENTIALS=/path/to/sa-key.json
|
||||
8
.tofu/configs/upc.env.example
Normal file
8
.tofu/configs/upc.env.example
Normal file
@@ -0,0 +1,8 @@
|
||||
# UpCloud credentials — copy to upc.env and fill in values
|
||||
# NEVER commit upc.env to git!
|
||||
|
||||
# Required
|
||||
UPCLOUD_TOKEN=your-upcloud-api-token
|
||||
|
||||
# Optional — set after cluster creation for kubeconfig retrieval
|
||||
UPCLOUD_CLUSTER_ID=
|
||||
18
.tofu/platforms/aks/dev/main.tf
Normal file
18
.tofu/platforms/aks/dev/main.tf
Normal file
@@ -0,0 +1,18 @@
|
||||
module "cluster" {
|
||||
source = "../modules/cluster"
|
||||
|
||||
prefix = "clst-dev"
|
||||
location = "norwayeast"
|
||||
resource_group_name = "clst-dev-rg"
|
||||
|
||||
# AKS — small dev nodes
|
||||
aks_node_vm_size = "Standard_B2s"
|
||||
aks_node_count = 2
|
||||
|
||||
enable_delete_lock = false
|
||||
|
||||
tags = {
|
||||
Environment = "dev"
|
||||
ManagedBy = "tofu"
|
||||
}
|
||||
}
|
||||
26
.tofu/platforms/aks/dev/outputs.tf
Normal file
26
.tofu/platforms/aks/dev/outputs.tf
Normal file
@@ -0,0 +1,26 @@
|
||||
# ─── Cluster ─────────────────────────────────────────────────────────
|
||||
|
||||
output "cluster_name" {
|
||||
value = module.cluster.cluster_name
|
||||
}
|
||||
|
||||
output "resource_group_name" {
|
||||
value = module.cluster.resource_group_name
|
||||
}
|
||||
|
||||
output "kubernetes_version" {
|
||||
value = module.cluster.kubernetes_version
|
||||
}
|
||||
|
||||
output "location" {
|
||||
value = module.cluster.location
|
||||
}
|
||||
|
||||
output "oidc_issuer_url" {
|
||||
value = module.cluster.oidc_issuer_url
|
||||
}
|
||||
|
||||
output "kubeconfig" {
|
||||
value = module.cluster.kubeconfig
|
||||
sensitive = true
|
||||
}
|
||||
17
.tofu/platforms/aks/dev/providers.tf
Normal file
17
.tofu/platforms/aks/dev/providers.tf
Normal file
@@ -0,0 +1,17 @@
|
||||
terraform {
|
||||
required_version = ">= 1.0"
|
||||
|
||||
required_providers {
|
||||
azurerm = {
|
||||
source = "hashicorp/azurerm"
|
||||
version = "~> 4.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
provider "azurerm" {
|
||||
features {}
|
||||
# Credentials via environment variables:
|
||||
# ARM_SUBSCRIPTION_ID, ARM_TENANT_ID, ARM_CLIENT_ID, ARM_CLIENT_SECRET
|
||||
# Or: az login (uses your Azure CLI session)
|
||||
}
|
||||
72
.tofu/platforms/aks/modules/cluster/main.tf
Normal file
72
.tofu/platforms/aks/modules/cluster/main.tf
Normal file
@@ -0,0 +1,72 @@
|
||||
# Current Azure/Entra ID context — provides tenant_id used in outputs
|
||||
data "azurerm_client_config" "current" {}
|
||||
|
||||
# ─── Resource Group ───────────────────────────────────────────────────
|
||||
|
||||
resource "azurerm_resource_group" "main" {
|
||||
name = var.resource_group_name
|
||||
location = var.location
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
resource "azurerm_management_lock" "main" {
|
||||
count = var.enable_delete_lock ? 1 : 0
|
||||
name = "${var.prefix}-delete-lock"
|
||||
scope = azurerm_resource_group.main.id
|
||||
lock_level = "CanNotDelete"
|
||||
notes = "Prevents accidental deletion of production resources"
|
||||
}
|
||||
|
||||
# ─── Networking ───────────────────────────────────────────────────────
|
||||
|
||||
resource "azurerm_virtual_network" "main" {
|
||||
name = "${var.prefix}-vnet"
|
||||
resource_group_name = azurerm_resource_group.main.name
|
||||
location = azurerm_resource_group.main.location
|
||||
address_space = [var.vnet_address_space]
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
# AKS nodes subnet
|
||||
resource "azurerm_subnet" "aks" {
|
||||
name = "${var.prefix}-aks-subnet"
|
||||
resource_group_name = azurerm_resource_group.main.name
|
||||
virtual_network_name = azurerm_virtual_network.main.name
|
||||
address_prefixes = [var.aks_subnet_cidr]
|
||||
}
|
||||
|
||||
# ─── AKS Cluster ──────────────────────────────────────────────────────
|
||||
|
||||
resource "azurerm_kubernetes_cluster" "main" {
|
||||
name = "${var.prefix}-aks"
|
||||
resource_group_name = azurerm_resource_group.main.name
|
||||
location = azurerm_resource_group.main.location
|
||||
dns_prefix = replace(var.prefix, "-", "")
|
||||
kubernetes_version = var.aks_kubernetes_version
|
||||
tags = var.tags
|
||||
|
||||
default_node_pool {
|
||||
name = "system"
|
||||
node_count = var.aks_node_count
|
||||
vm_size = var.aks_node_vm_size
|
||||
vnet_subnet_id = azurerm_subnet.aks.id
|
||||
node_labels = {
|
||||
prefix = var.prefix
|
||||
role = "worker"
|
||||
env = lookup(var.tags, "Environment", "dev")
|
||||
}
|
||||
}
|
||||
|
||||
identity {
|
||||
type = "SystemAssigned"
|
||||
}
|
||||
|
||||
network_profile {
|
||||
network_plugin = "azure"
|
||||
network_policy = "azure"
|
||||
}
|
||||
|
||||
# Enable Workload Identity for keyless Azure service access (MSI)
|
||||
oidc_issuer_enabled = true
|
||||
workload_identity_enabled = true
|
||||
}
|
||||
32
.tofu/platforms/aks/modules/cluster/outputs.tf
Normal file
32
.tofu/platforms/aks/modules/cluster/outputs.tf
Normal file
@@ -0,0 +1,32 @@
|
||||
# ─── Cluster ─────────────────────────────────────────────────────────
|
||||
|
||||
output "cluster_name" {
|
||||
description = "AKS cluster name"
|
||||
value = azurerm_kubernetes_cluster.main.name
|
||||
}
|
||||
|
||||
output "resource_group_name" {
|
||||
description = "Resource group name"
|
||||
value = azurerm_resource_group.main.name
|
||||
}
|
||||
|
||||
output "kubernetes_version" {
|
||||
description = "Kubernetes version"
|
||||
value = azurerm_kubernetes_cluster.main.kubernetes_version
|
||||
}
|
||||
|
||||
output "location" {
|
||||
description = "Azure region"
|
||||
value = azurerm_resource_group.main.location
|
||||
}
|
||||
|
||||
output "oidc_issuer_url" {
|
||||
description = "AKS OIDC issuer URL (for workload identity federation)"
|
||||
value = azurerm_kubernetes_cluster.main.oidc_issuer_url
|
||||
}
|
||||
|
||||
output "kubeconfig" {
|
||||
description = "Kubeconfig for the AKS cluster"
|
||||
value = azurerm_kubernetes_cluster.main.kube_config_raw
|
||||
sensitive = true
|
||||
}
|
||||
18
.tofu/platforms/aks/modules/cluster/providers.tf
Normal file
18
.tofu/platforms/aks/modules/cluster/providers.tf
Normal file
@@ -0,0 +1,18 @@
|
||||
terraform {
|
||||
required_version = ">= 1.0"
|
||||
|
||||
required_providers {
|
||||
azurerm = {
|
||||
source = "hashicorp/azurerm"
|
||||
version = "~> 4.0"
|
||||
}
|
||||
azuread = {
|
||||
source = "hashicorp/azuread"
|
||||
version = "~> 3.0"
|
||||
}
|
||||
random = {
|
||||
source = "hashicorp/random"
|
||||
version = "~> 3.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
56
.tofu/platforms/aks/modules/cluster/variables.tf
Normal file
56
.tofu/platforms/aks/modules/cluster/variables.tf
Normal file
@@ -0,0 +1,56 @@
|
||||
# ─── Cluster ─────────────────────────────────────────────────────────
|
||||
|
||||
variable "prefix" {
|
||||
description = "Prefix for resource names"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "location" {
|
||||
description = "Azure region (e.g., norwayeast, westeurope, northeurope)"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "resource_group_name" {
|
||||
description = "Name of the Azure Resource Group to create"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "vnet_address_space" {
|
||||
description = "Address space for the virtual network"
|
||||
type = string
|
||||
default = "10.100.0.0/16"
|
||||
}
|
||||
|
||||
variable "aks_subnet_cidr" {
|
||||
description = "CIDR block for the AKS node subnet"
|
||||
type = string
|
||||
default = "10.100.0.0/22"
|
||||
}
|
||||
|
||||
variable "aks_node_vm_size" {
|
||||
description = "VM size for AKS worker nodes (e.g., Standard_B2s, Standard_D4s_v3)"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "aks_node_count" {
|
||||
description = "Number of AKS worker nodes"
|
||||
type = number
|
||||
}
|
||||
|
||||
variable "aks_kubernetes_version" {
|
||||
description = "Kubernetes version for AKS (null = latest stable)"
|
||||
type = string
|
||||
default = null
|
||||
}
|
||||
|
||||
variable "enable_delete_lock" {
|
||||
description = "Protect the resource group from accidental deletion"
|
||||
type = bool
|
||||
default = false
|
||||
}
|
||||
|
||||
variable "tags" {
|
||||
description = "Tags applied to all resources"
|
||||
type = map(string)
|
||||
default = {}
|
||||
}
|
||||
18
.tofu/platforms/aks/prod/main.tf
Normal file
18
.tofu/platforms/aks/prod/main.tf
Normal file
@@ -0,0 +1,18 @@
|
||||
module "cluster" {
|
||||
source = "../modules/cluster"
|
||||
|
||||
prefix = "clst"
|
||||
location = "westeurope"
|
||||
resource_group_name = "clst-prod-rg"
|
||||
|
||||
# AKS — general-purpose nodes for production
|
||||
aks_node_vm_size = "Standard_D4s_v3"
|
||||
aks_node_count = 3
|
||||
|
||||
enable_delete_lock = true
|
||||
|
||||
tags = {
|
||||
Environment = "prod"
|
||||
ManagedBy = "tofu"
|
||||
}
|
||||
}
|
||||
26
.tofu/platforms/aks/prod/outputs.tf
Normal file
26
.tofu/platforms/aks/prod/outputs.tf
Normal file
@@ -0,0 +1,26 @@
|
||||
# ─── Cluster ─────────────────────────────────────────────────────────
|
||||
|
||||
output "cluster_name" {
|
||||
value = module.cluster.cluster_name
|
||||
}
|
||||
|
||||
output "resource_group_name" {
|
||||
value = module.cluster.resource_group_name
|
||||
}
|
||||
|
||||
output "kubernetes_version" {
|
||||
value = module.cluster.kubernetes_version
|
||||
}
|
||||
|
||||
output "location" {
|
||||
value = module.cluster.location
|
||||
}
|
||||
|
||||
output "oidc_issuer_url" {
|
||||
value = module.cluster.oidc_issuer_url
|
||||
}
|
||||
|
||||
output "kubeconfig" {
|
||||
value = module.cluster.kubeconfig
|
||||
sensitive = true
|
||||
}
|
||||
17
.tofu/platforms/aks/prod/providers.tf
Normal file
17
.tofu/platforms/aks/prod/providers.tf
Normal file
@@ -0,0 +1,17 @@
|
||||
terraform {
|
||||
required_version = ">= 1.0"
|
||||
|
||||
required_providers {
|
||||
azurerm = {
|
||||
source = "hashicorp/azurerm"
|
||||
version = "~> 4.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
provider "azurerm" {
|
||||
features {}
|
||||
# Credentials via environment variables:
|
||||
# ARM_SUBSCRIPTION_ID, ARM_TENANT_ID, ARM_CLIENT_ID, ARM_CLIENT_SECRET
|
||||
# Or: az login (uses your Azure CLI session)
|
||||
}
|
||||
173
.tofu/platforms/aks/workload/main.tf
Normal file
173
.tofu/platforms/aks/workload/main.tf
Normal file
@@ -0,0 +1,173 @@
|
||||
# =============================================================================
|
||||
# Azure Workload Cluster
|
||||
# =============================================================================
|
||||
# A lean AKS cluster for running application workloads. No managed data
|
||||
# services — those live on the platform cluster. ArgoCD (on the platform
|
||||
# cluster) deploys apps to this cluster via the app-of-apps pattern.
|
||||
#
|
||||
# Platform components deployed by deploy-workload.sh:
|
||||
# nginx-ingress, cert-manager, external-dns, external-secrets, alloy
|
||||
#
|
||||
# Usage:
|
||||
# tofu init && tofu plan && tofu apply
|
||||
# ./sync-tofu-outputs.sh --env azure-workload
|
||||
# ./deploy-workload.sh --env azure-workload
|
||||
# =============================================================================
|
||||
|
||||
variable "prefix" {
|
||||
description = "Prefix for resource names (e.g., clst-workload)"
|
||||
type = string
|
||||
default = "clst-workload"
|
||||
}
|
||||
|
||||
variable "location" {
|
||||
description = "Azure region"
|
||||
type = string
|
||||
default = "norwayeast"
|
||||
}
|
||||
|
||||
variable "resource_group_name" {
|
||||
description = "Name of the Azure Resource Group to create"
|
||||
type = string
|
||||
default = "clst-workload-rg"
|
||||
}
|
||||
|
||||
variable "vnet_address_space" {
|
||||
description = "Address space for the virtual network"
|
||||
type = string
|
||||
default = "10.110.0.0/16"
|
||||
}
|
||||
|
||||
variable "aks_subnet_cidr" {
|
||||
description = "CIDR block for the AKS node subnet"
|
||||
type = string
|
||||
default = "10.110.0.0/22"
|
||||
}
|
||||
|
||||
variable "aks_node_vm_size" {
|
||||
description = "VM size for AKS worker nodes"
|
||||
type = string
|
||||
default = "Standard_B2s"
|
||||
}
|
||||
|
||||
variable "aks_node_count" {
|
||||
description = "Number of AKS worker nodes"
|
||||
type = number
|
||||
default = 2
|
||||
}
|
||||
|
||||
variable "aks_kubernetes_version" {
|
||||
description = "Kubernetes version for AKS (null = latest stable)"
|
||||
type = string
|
||||
default = null
|
||||
}
|
||||
|
||||
variable "domain" {
|
||||
description = "Public domain name — must have an existing Azure DNS zone"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "dns_zone_resource_group" {
|
||||
description = "Resource group containing the Azure DNS zone (defaults to cluster RG)"
|
||||
type = string
|
||||
default = ""
|
||||
}
|
||||
|
||||
variable "tags" {
|
||||
description = "Tags applied to all resources"
|
||||
type = map(string)
|
||||
default = {
|
||||
Environment = "workload"
|
||||
ManagedBy = "tofu"
|
||||
}
|
||||
}
|
||||
|
||||
# ─── Resource Group ───────────────────────────────────────────────────
|
||||
|
||||
resource "azurerm_resource_group" "main" {
|
||||
name = var.resource_group_name
|
||||
location = var.location
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
# ─── Networking ───────────────────────────────────────────────────────
|
||||
|
||||
resource "azurerm_virtual_network" "main" {
|
||||
name = "${var.prefix}-vnet"
|
||||
resource_group_name = azurerm_resource_group.main.name
|
||||
location = azurerm_resource_group.main.location
|
||||
address_space = [var.vnet_address_space]
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
resource "azurerm_subnet" "aks" {
|
||||
name = "${var.prefix}-aks-subnet"
|
||||
resource_group_name = azurerm_resource_group.main.name
|
||||
virtual_network_name = azurerm_virtual_network.main.name
|
||||
address_prefixes = [var.aks_subnet_cidr]
|
||||
}
|
||||
|
||||
# ─── AKS Cluster ──────────────────────────────────────────────────────
|
||||
|
||||
resource "azurerm_kubernetes_cluster" "main" {
|
||||
name = "${var.prefix}-aks"
|
||||
resource_group_name = azurerm_resource_group.main.name
|
||||
location = azurerm_resource_group.main.location
|
||||
dns_prefix = replace(var.prefix, "-", "")
|
||||
kubernetes_version = var.aks_kubernetes_version
|
||||
tags = var.tags
|
||||
|
||||
default_node_pool {
|
||||
name = "system"
|
||||
node_count = var.aks_node_count
|
||||
vm_size = var.aks_node_vm_size
|
||||
vnet_subnet_id = azurerm_subnet.aks.id
|
||||
node_labels = {
|
||||
prefix = var.prefix
|
||||
role = "worker"
|
||||
env = lookup(var.tags, "Environment", "workload")
|
||||
}
|
||||
}
|
||||
|
||||
identity {
|
||||
type = "SystemAssigned"
|
||||
}
|
||||
|
||||
network_profile {
|
||||
network_plugin = "azure"
|
||||
network_policy = "azure"
|
||||
}
|
||||
|
||||
oidc_issuer_enabled = true
|
||||
workload_identity_enabled = true
|
||||
}
|
||||
|
||||
# ─── External-DNS Workload Identity ──────────────────────────────────
|
||||
# Allows external-dns to manage Azure DNS records for app ingresses.
|
||||
|
||||
data "azurerm_dns_zone" "main" {
|
||||
name = var.domain
|
||||
resource_group_name = var.dns_zone_resource_group != "" ? var.dns_zone_resource_group : azurerm_resource_group.main.name
|
||||
}
|
||||
|
||||
resource "azurerm_user_assigned_identity" "external_dns" {
|
||||
name = "${var.prefix}-external-dns-identity"
|
||||
resource_group_name = azurerm_resource_group.main.name
|
||||
location = azurerm_resource_group.main.location
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
resource "azurerm_role_assignment" "external_dns_dns_contributor" {
|
||||
scope = data.azurerm_dns_zone.main.id
|
||||
role_definition_name = "DNS Zone Contributor"
|
||||
principal_id = azurerm_user_assigned_identity.external_dns.principal_id
|
||||
}
|
||||
|
||||
resource "azurerm_federated_identity_credential" "external_dns" {
|
||||
name = "${var.prefix}-external-dns-fedcred"
|
||||
resource_group_name = azurerm_resource_group.main.name
|
||||
parent_id = azurerm_user_assigned_identity.external_dns.id
|
||||
audience = ["api://AzureADTokenExchange"]
|
||||
issuer = azurerm_kubernetes_cluster.main.oidc_issuer_url
|
||||
subject = "system:serviceaccount:external-dns:external-dns"
|
||||
}
|
||||
4
.tofu/platforms/aks/workload/outputs.tf
Normal file
4
.tofu/platforms/aks/workload/outputs.tf
Normal file
@@ -0,0 +1,4 @@
|
||||
output "cluster_name" { value = azurerm_kubernetes_cluster.main.name }
|
||||
output "resource_group_name" { value = azurerm_resource_group.main.name }
|
||||
output "location" { value = azurerm_resource_group.main.location }
|
||||
output "external_dns_identity_client_id" { value = azurerm_user_assigned_identity.external_dns.client_id }
|
||||
21
.tofu/platforms/aks/workload/providers.tf
Normal file
21
.tofu/platforms/aks/workload/providers.tf
Normal file
@@ -0,0 +1,21 @@
|
||||
terraform {
|
||||
required_version = ">= 1.0"
|
||||
|
||||
required_providers {
|
||||
azurerm = {
|
||||
source = "hashicorp/azurerm"
|
||||
version = "~> 4.0"
|
||||
}
|
||||
random = {
|
||||
source = "hashicorp/random"
|
||||
version = "~> 3.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
provider "azurerm" {
|
||||
features {}
|
||||
# Credentials via environment variables:
|
||||
# ARM_SUBSCRIPTION_ID, ARM_TENANT_ID, ARM_CLIENT_ID, ARM_CLIENT_SECRET
|
||||
# Or: az login (uses your Azure CLI session)
|
||||
}
|
||||
21
.tofu/platforms/eks/dev/main.tf
Normal file
21
.tofu/platforms/eks/dev/main.tf
Normal file
@@ -0,0 +1,21 @@
|
||||
module "cluster" {
|
||||
source = "../modules/cluster"
|
||||
|
||||
region = var.region
|
||||
prefix = "clst-dev"
|
||||
|
||||
# VPC
|
||||
availability_zones = ["${var.region}a", "${var.region}b"]
|
||||
|
||||
# EKS — small dev nodes
|
||||
node_instance_type = "t3.medium"
|
||||
node_count = 2
|
||||
node_min_count = 1
|
||||
node_max_count = 4
|
||||
kubernetes_version = "1.30"
|
||||
|
||||
tags = {
|
||||
Environment = "dev"
|
||||
ManagedBy = "tofu"
|
||||
}
|
||||
}
|
||||
5
.tofu/platforms/eks/dev/outputs.tf
Normal file
5
.tofu/platforms/eks/dev/outputs.tf
Normal file
@@ -0,0 +1,5 @@
|
||||
output "cluster_name" { value = module.cluster.cluster_name }
|
||||
output "aws_region" { value = module.cluster.aws_region }
|
||||
output "oidc_issuer_url" { value = module.cluster.oidc_issuer_url }
|
||||
output "oidc_provider_arn" { value = module.cluster.oidc_provider_arn }
|
||||
output "vpc_id" { value = module.cluster.vpc_id }
|
||||
24
.tofu/platforms/eks/dev/providers.tf
Normal file
24
.tofu/platforms/eks/dev/providers.tf
Normal file
@@ -0,0 +1,24 @@
|
||||
terraform {
|
||||
required_providers {
|
||||
aws = {
|
||||
source = "hashicorp/aws"
|
||||
version = "~> 5.0"
|
||||
}
|
||||
tls = {
|
||||
source = "hashicorp/tls"
|
||||
version = "~> 4.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# Authentication: set AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN
|
||||
# or configure an AWS profile: export AWS_PROFILE=clst
|
||||
provider "aws" {
|
||||
region = var.region
|
||||
}
|
||||
|
||||
variable "region" {
|
||||
description = "AWS region for dev environment"
|
||||
type = string
|
||||
default = "eu-west-1"
|
||||
}
|
||||
207
.tofu/platforms/eks/modules/cluster/main.tf
Normal file
207
.tofu/platforms/eks/modules/cluster/main.tf
Normal file
@@ -0,0 +1,207 @@
|
||||
# ─── VPC ──────────────────────────────────────────────────────────────
|
||||
|
||||
resource "aws_vpc" "main" {
|
||||
cidr_block = var.vpc_cidr
|
||||
enable_dns_hostnames = true
|
||||
enable_dns_support = true
|
||||
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-vpc" })
|
||||
}
|
||||
|
||||
resource "aws_internet_gateway" "main" {
|
||||
vpc_id = aws_vpc.main.id
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-igw" })
|
||||
}
|
||||
|
||||
# Public subnets (one per AZ) — for NAT gateways and load balancers
|
||||
resource "aws_subnet" "public" {
|
||||
count = length(var.availability_zones)
|
||||
vpc_id = aws_vpc.main.id
|
||||
cidr_block = cidrsubnet(var.vpc_cidr, 4, count.index)
|
||||
availability_zone = var.availability_zones[count.index]
|
||||
|
||||
map_public_ip_on_launch = true
|
||||
|
||||
tags = merge(var.tags, {
|
||||
Name = "${var.prefix}-public-${count.index + 1}"
|
||||
"kubernetes.io/cluster/${var.prefix}-eks" = "shared"
|
||||
"kubernetes.io/role/elb" = "1"
|
||||
})
|
||||
}
|
||||
|
||||
# Private subnets (one per AZ) — for EKS nodes
|
||||
resource "aws_subnet" "private" {
|
||||
count = length(var.availability_zones)
|
||||
vpc_id = aws_vpc.main.id
|
||||
cidr_block = cidrsubnet(var.vpc_cidr, 4, count.index + length(var.availability_zones))
|
||||
availability_zone = var.availability_zones[count.index]
|
||||
|
||||
tags = merge(var.tags, {
|
||||
Name = "${var.prefix}-private-${count.index + 1}"
|
||||
"kubernetes.io/cluster/${var.prefix}-eks" = "shared"
|
||||
"kubernetes.io/role/internal-elb" = "1"
|
||||
})
|
||||
}
|
||||
|
||||
# NAT Gateway (single, in first public subnet — use one per AZ for prod HA)
|
||||
resource "aws_eip" "nat" {
|
||||
domain = "vpc"
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-nat-eip" })
|
||||
}
|
||||
|
||||
resource "aws_nat_gateway" "main" {
|
||||
allocation_id = aws_eip.nat.id
|
||||
subnet_id = aws_subnet.public[0].id
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-nat" })
|
||||
|
||||
depends_on = [aws_internet_gateway.main]
|
||||
}
|
||||
|
||||
resource "aws_route_table" "public" {
|
||||
vpc_id = aws_vpc.main.id
|
||||
|
||||
route {
|
||||
cidr_block = "0.0.0.0/0"
|
||||
gateway_id = aws_internet_gateway.main.id
|
||||
}
|
||||
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-public-rt" })
|
||||
}
|
||||
|
||||
resource "aws_route_table_association" "public" {
|
||||
count = length(var.availability_zones)
|
||||
subnet_id = aws_subnet.public[count.index].id
|
||||
route_table_id = aws_route_table.public.id
|
||||
}
|
||||
|
||||
resource "aws_route_table" "private" {
|
||||
vpc_id = aws_vpc.main.id
|
||||
|
||||
route {
|
||||
cidr_block = "0.0.0.0/0"
|
||||
nat_gateway_id = aws_nat_gateway.main.id
|
||||
}
|
||||
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-private-rt" })
|
||||
}
|
||||
|
||||
resource "aws_route_table_association" "private" {
|
||||
count = length(var.availability_zones)
|
||||
subnet_id = aws_subnet.private[count.index].id
|
||||
route_table_id = aws_route_table.private.id
|
||||
}
|
||||
|
||||
# ─── EKS Cluster ──────────────────────────────────────────────────────
|
||||
|
||||
resource "aws_iam_role" "eks_cluster" {
|
||||
name_prefix = "${var.prefix}-eks-cluster-"
|
||||
|
||||
assume_role_policy = jsonencode({
|
||||
Version = "2012-10-17"
|
||||
Statement = [{
|
||||
Action = "sts:AssumeRole"
|
||||
Effect = "Allow"
|
||||
Principal = { Service = "eks.amazonaws.com" }
|
||||
}]
|
||||
})
|
||||
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
resource "aws_iam_role_policy_attachment" "eks_cluster_policy" {
|
||||
policy_arn = "arn:aws:iam::aws:policy/AmazonEKSClusterPolicy"
|
||||
role = aws_iam_role.eks_cluster.name
|
||||
}
|
||||
|
||||
resource "aws_eks_cluster" "main" {
|
||||
name = "${var.prefix}-eks"
|
||||
role_arn = aws_iam_role.eks_cluster.arn
|
||||
version = var.kubernetes_version
|
||||
|
||||
vpc_config {
|
||||
subnet_ids = concat(aws_subnet.private[*].id, aws_subnet.public[*].id)
|
||||
endpoint_private_access = true
|
||||
endpoint_public_access = true
|
||||
}
|
||||
|
||||
# Enable OIDC issuer for IRSA (IAM Roles for Service Accounts)
|
||||
access_config {
|
||||
authentication_mode = "API_AND_CONFIG_MAP"
|
||||
}
|
||||
|
||||
tags = var.tags
|
||||
|
||||
depends_on = [aws_iam_role_policy_attachment.eks_cluster_policy]
|
||||
}
|
||||
|
||||
# OIDC provider — required for IRSA (IAM Roles for Service Accounts)
|
||||
data "tls_certificate" "eks" {
|
||||
url = aws_eks_cluster.main.identity[0].oidc[0].issuer
|
||||
}
|
||||
|
||||
resource "aws_iam_openid_connect_provider" "eks" {
|
||||
client_id_list = ["sts.amazonaws.com"]
|
||||
thumbprint_list = [data.tls_certificate.eks.certificates[0].sha1_fingerprint]
|
||||
url = aws_eks_cluster.main.identity[0].oidc[0].issuer
|
||||
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
# EKS Node Group
|
||||
|
||||
resource "aws_iam_role" "eks_nodes" {
|
||||
name_prefix = "${var.prefix}-eks-nodes-"
|
||||
|
||||
assume_role_policy = jsonencode({
|
||||
Version = "2012-10-17"
|
||||
Statement = [{
|
||||
Action = "sts:AssumeRole"
|
||||
Effect = "Allow"
|
||||
Principal = { Service = "ec2.amazonaws.com" }
|
||||
}]
|
||||
})
|
||||
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
resource "aws_iam_role_policy_attachment" "eks_worker_node_policy" {
|
||||
policy_arn = "arn:aws:iam::aws:policy/AmazonEKSWorkerNodePolicy"
|
||||
role = aws_iam_role.eks_nodes.name
|
||||
}
|
||||
|
||||
resource "aws_iam_role_policy_attachment" "eks_cni_policy" {
|
||||
policy_arn = "arn:aws:iam::aws:policy/AmazonEKS_CNI_Policy"
|
||||
role = aws_iam_role.eks_nodes.name
|
||||
}
|
||||
|
||||
resource "aws_iam_role_policy_attachment" "eks_ecr_readonly" {
|
||||
policy_arn = "arn:aws:iam::aws:policy/AmazonEC2ContainerRegistryReadOnly"
|
||||
role = aws_iam_role.eks_nodes.name
|
||||
}
|
||||
|
||||
resource "aws_eks_node_group" "main" {
|
||||
cluster_name = aws_eks_cluster.main.name
|
||||
node_group_name = "${var.prefix}-nodes"
|
||||
node_role_arn = aws_iam_role.eks_nodes.arn
|
||||
subnet_ids = aws_subnet.private[*].id
|
||||
|
||||
instance_types = [var.node_instance_type]
|
||||
|
||||
scaling_config {
|
||||
desired_size = var.node_count
|
||||
max_size = var.node_max_count
|
||||
min_size = var.node_min_count
|
||||
}
|
||||
|
||||
update_config {
|
||||
max_unavailable = 1
|
||||
}
|
||||
|
||||
tags = var.tags
|
||||
|
||||
depends_on = [
|
||||
aws_iam_role_policy_attachment.eks_worker_node_policy,
|
||||
aws_iam_role_policy_attachment.eks_cni_policy,
|
||||
aws_iam_role_policy_attachment.eks_ecr_readonly,
|
||||
]
|
||||
}
|
||||
26
.tofu/platforms/eks/modules/cluster/outputs.tf
Normal file
26
.tofu/platforms/eks/modules/cluster/outputs.tf
Normal file
@@ -0,0 +1,26 @@
|
||||
# ─── Cluster ─────────────────────────────────────────────────────────
|
||||
|
||||
output "cluster_name" {
|
||||
description = "EKS cluster name"
|
||||
value = aws_eks_cluster.main.name
|
||||
}
|
||||
|
||||
output "aws_region" {
|
||||
description = "AWS region"
|
||||
value = var.region
|
||||
}
|
||||
|
||||
output "oidc_issuer_url" {
|
||||
description = "EKS OIDC issuer URL (for IRSA)"
|
||||
value = aws_eks_cluster.main.identity[0].oidc[0].issuer
|
||||
}
|
||||
|
||||
output "oidc_provider_arn" {
|
||||
description = "IAM OIDC provider ARN (for IRSA trust policies)"
|
||||
value = aws_iam_openid_connect_provider.eks.arn
|
||||
}
|
||||
|
||||
output "vpc_id" {
|
||||
description = "VPC ID"
|
||||
value = aws_vpc.main.id
|
||||
}
|
||||
12
.tofu/platforms/eks/modules/cluster/providers.tf
Normal file
12
.tofu/platforms/eks/modules/cluster/providers.tf
Normal file
@@ -0,0 +1,12 @@
|
||||
terraform {
|
||||
required_providers {
|
||||
aws = {
|
||||
source = "hashicorp/aws"
|
||||
version = "~> 5.0"
|
||||
}
|
||||
tls = {
|
||||
source = "hashicorp/tls"
|
||||
version = "~> 4.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
61
.tofu/platforms/eks/modules/cluster/variables.tf
Normal file
61
.tofu/platforms/eks/modules/cluster/variables.tf
Normal file
@@ -0,0 +1,61 @@
|
||||
# ─── Region ──────────────────────────────────────────────────────────
|
||||
|
||||
variable "region" {
|
||||
description = "AWS region (e.g., eu-west-1, us-east-1)"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "prefix" {
|
||||
description = "Prefix for resource names (e.g., clst-dev)"
|
||||
type = string
|
||||
}
|
||||
|
||||
# ─── Networking ───────────────────────────────────────────────────────
|
||||
|
||||
variable "vpc_cidr" {
|
||||
description = "VPC CIDR block"
|
||||
type = string
|
||||
default = "10.100.0.0/16"
|
||||
}
|
||||
|
||||
variable "availability_zones" {
|
||||
description = "List of AZs for subnets (2–3 recommended)"
|
||||
type = list(string)
|
||||
}
|
||||
|
||||
# ─── EKS Cluster ─────────────────────────────────────────────────────
|
||||
|
||||
variable "node_instance_type" {
|
||||
description = "EKS node instance type (e.g., t3.medium, m5.xlarge)"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "node_count" {
|
||||
description = "Desired number of EKS worker nodes"
|
||||
type = number
|
||||
}
|
||||
|
||||
variable "node_min_count" {
|
||||
description = "Minimum number of EKS worker nodes"
|
||||
type = number
|
||||
default = 1
|
||||
}
|
||||
|
||||
variable "node_max_count" {
|
||||
description = "Maximum number of EKS worker nodes"
|
||||
type = number
|
||||
}
|
||||
|
||||
variable "kubernetes_version" {
|
||||
description = "Kubernetes version for EKS (e.g., \"1.30\")"
|
||||
type = string
|
||||
default = "1.30"
|
||||
}
|
||||
|
||||
# ─── Tags ─────────────────────────────────────────────────────────────
|
||||
|
||||
variable "tags" {
|
||||
description = "Tags applied to all resources"
|
||||
type = map(string)
|
||||
default = {}
|
||||
}
|
||||
21
.tofu/platforms/eks/prod/main.tf
Normal file
21
.tofu/platforms/eks/prod/main.tf
Normal file
@@ -0,0 +1,21 @@
|
||||
module "cluster" {
|
||||
source = "../modules/cluster"
|
||||
|
||||
region = var.region
|
||||
prefix = "clst"
|
||||
|
||||
# VPC
|
||||
availability_zones = ["${var.region}a", "${var.region}b", "${var.region}c"]
|
||||
|
||||
# EKS — general-purpose nodes for production
|
||||
node_instance_type = "m5.xlarge"
|
||||
node_count = 3
|
||||
node_min_count = 3
|
||||
node_max_count = 6
|
||||
kubernetes_version = "1.30"
|
||||
|
||||
tags = {
|
||||
Environment = "prod"
|
||||
ManagedBy = "tofu"
|
||||
}
|
||||
}
|
||||
5
.tofu/platforms/eks/prod/outputs.tf
Normal file
5
.tofu/platforms/eks/prod/outputs.tf
Normal file
@@ -0,0 +1,5 @@
|
||||
output "cluster_name" { value = module.cluster.cluster_name }
|
||||
output "aws_region" { value = module.cluster.aws_region }
|
||||
output "oidc_issuer_url" { value = module.cluster.oidc_issuer_url }
|
||||
output "oidc_provider_arn" { value = module.cluster.oidc_provider_arn }
|
||||
output "vpc_id" { value = module.cluster.vpc_id }
|
||||
22
.tofu/platforms/eks/prod/providers.tf
Normal file
22
.tofu/platforms/eks/prod/providers.tf
Normal file
@@ -0,0 +1,22 @@
|
||||
terraform {
|
||||
required_providers {
|
||||
aws = {
|
||||
source = "hashicorp/aws"
|
||||
version = "~> 5.0"
|
||||
}
|
||||
tls = {
|
||||
source = "hashicorp/tls"
|
||||
version = "~> 4.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
provider "aws" {
|
||||
region = var.region
|
||||
}
|
||||
|
||||
variable "region" {
|
||||
description = "AWS region for prod environment"
|
||||
type = string
|
||||
default = "eu-west-1"
|
||||
}
|
||||
339
.tofu/platforms/eks/workload/main.tf
Normal file
339
.tofu/platforms/eks/workload/main.tf
Normal file
@@ -0,0 +1,339 @@
|
||||
# =============================================================================
|
||||
# AWS Workload Cluster
|
||||
# =============================================================================
|
||||
# A lean EKS cluster for running application workloads. No managed data
|
||||
# services — those live on the platform cluster. ArgoCD (on the platform
|
||||
# cluster) deploys apps to this cluster via the app-of-apps pattern.
|
||||
#
|
||||
# Platform components deployed by deploy-workload.sh:
|
||||
# nginx-ingress, cert-manager, external-dns, external-secrets, alloy
|
||||
#
|
||||
# Usage:
|
||||
# tofu init && tofu plan && tofu apply
|
||||
# ./sync-tofu-outputs.sh --env aws-workload
|
||||
# ./deploy-workload.sh --env aws-workload
|
||||
# =============================================================================
|
||||
|
||||
variable "prefix" {
|
||||
description = "Prefix for resource names (e.g., clst-workload)"
|
||||
type = string
|
||||
default = "clst-workload"
|
||||
}
|
||||
|
||||
variable "availability_zones" {
|
||||
description = "List of AZs for subnets"
|
||||
type = list(string)
|
||||
default = ["eu-west-1a", "eu-west-1b"]
|
||||
}
|
||||
|
||||
variable "vpc_cidr" {
|
||||
description = "VPC CIDR block"
|
||||
type = string
|
||||
default = "10.110.0.0/16"
|
||||
}
|
||||
|
||||
variable "node_instance_type" {
|
||||
description = "EKS node instance type"
|
||||
type = string
|
||||
default = "t3.medium"
|
||||
}
|
||||
|
||||
variable "node_count" {
|
||||
description = "Desired number of EKS worker nodes"
|
||||
type = number
|
||||
default = 2
|
||||
}
|
||||
|
||||
variable "node_min_count" {
|
||||
description = "Minimum number of EKS worker nodes"
|
||||
type = number
|
||||
default = 1
|
||||
}
|
||||
|
||||
variable "node_max_count" {
|
||||
description = "Maximum number of EKS worker nodes"
|
||||
type = number
|
||||
default = 4
|
||||
}
|
||||
|
||||
variable "kubernetes_version" {
|
||||
description = "Kubernetes version for EKS"
|
||||
type = string
|
||||
default = "1.30"
|
||||
}
|
||||
|
||||
variable "domain" {
|
||||
description = "Public domain name — must have an existing Route53 hosted zone"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "tags" {
|
||||
description = "Tags applied to all resources"
|
||||
type = map(string)
|
||||
default = {
|
||||
Environment = "workload"
|
||||
ManagedBy = "tofu"
|
||||
}
|
||||
}
|
||||
|
||||
# ─── VPC ──────────────────────────────────────────────────────────────
|
||||
|
||||
resource "aws_vpc" "main" {
|
||||
cidr_block = var.vpc_cidr
|
||||
enable_dns_hostnames = true
|
||||
enable_dns_support = true
|
||||
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-vpc" })
|
||||
}
|
||||
|
||||
resource "aws_internet_gateway" "main" {
|
||||
vpc_id = aws_vpc.main.id
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-igw" })
|
||||
}
|
||||
|
||||
resource "aws_subnet" "public" {
|
||||
count = length(var.availability_zones)
|
||||
vpc_id = aws_vpc.main.id
|
||||
cidr_block = cidrsubnet(var.vpc_cidr, 4, count.index)
|
||||
availability_zone = var.availability_zones[count.index]
|
||||
|
||||
map_public_ip_on_launch = true
|
||||
|
||||
tags = merge(var.tags, {
|
||||
Name = "${var.prefix}-public-${count.index + 1}"
|
||||
"kubernetes.io/cluster/${var.prefix}-eks" = "shared"
|
||||
"kubernetes.io/role/elb" = "1"
|
||||
})
|
||||
}
|
||||
|
||||
resource "aws_subnet" "private" {
|
||||
count = length(var.availability_zones)
|
||||
vpc_id = aws_vpc.main.id
|
||||
cidr_block = cidrsubnet(var.vpc_cidr, 4, count.index + length(var.availability_zones))
|
||||
availability_zone = var.availability_zones[count.index]
|
||||
|
||||
tags = merge(var.tags, {
|
||||
Name = "${var.prefix}-private-${count.index + 1}"
|
||||
"kubernetes.io/cluster/${var.prefix}-eks" = "shared"
|
||||
"kubernetes.io/role/internal-elb" = "1"
|
||||
})
|
||||
}
|
||||
|
||||
resource "aws_eip" "nat" {
|
||||
domain = "vpc"
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-nat-eip" })
|
||||
}
|
||||
|
||||
resource "aws_nat_gateway" "main" {
|
||||
allocation_id = aws_eip.nat.id
|
||||
subnet_id = aws_subnet.public[0].id
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-nat" })
|
||||
|
||||
depends_on = [aws_internet_gateway.main]
|
||||
}
|
||||
|
||||
resource "aws_route_table" "public" {
|
||||
vpc_id = aws_vpc.main.id
|
||||
|
||||
route {
|
||||
cidr_block = "0.0.0.0/0"
|
||||
gateway_id = aws_internet_gateway.main.id
|
||||
}
|
||||
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-public-rt" })
|
||||
}
|
||||
|
||||
resource "aws_route_table_association" "public" {
|
||||
count = length(var.availability_zones)
|
||||
subnet_id = aws_subnet.public[count.index].id
|
||||
route_table_id = aws_route_table.public.id
|
||||
}
|
||||
|
||||
resource "aws_route_table" "private" {
|
||||
vpc_id = aws_vpc.main.id
|
||||
|
||||
route {
|
||||
cidr_block = "0.0.0.0/0"
|
||||
nat_gateway_id = aws_nat_gateway.main.id
|
||||
}
|
||||
|
||||
tags = merge(var.tags, { Name = "${var.prefix}-private-rt" })
|
||||
}
|
||||
|
||||
resource "aws_route_table_association" "private" {
|
||||
count = length(var.availability_zones)
|
||||
subnet_id = aws_subnet.private[count.index].id
|
||||
route_table_id = aws_route_table.private.id
|
||||
}
|
||||
|
||||
# ─── EKS Cluster ──────────────────────────────────────────────────────
|
||||
|
||||
resource "aws_iam_role" "eks_cluster" {
|
||||
name_prefix = "${var.prefix}-eks-cluster-"
|
||||
|
||||
assume_role_policy = jsonencode({
|
||||
Version = "2012-10-17"
|
||||
Statement = [{
|
||||
Action = "sts:AssumeRole"
|
||||
Effect = "Allow"
|
||||
Principal = { Service = "eks.amazonaws.com" }
|
||||
}]
|
||||
})
|
||||
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
resource "aws_iam_role_policy_attachment" "eks_cluster_policy" {
|
||||
policy_arn = "arn:aws:iam::aws:policy/AmazonEKSClusterPolicy"
|
||||
role = aws_iam_role.eks_cluster.name
|
||||
}
|
||||
|
||||
resource "aws_eks_cluster" "main" {
|
||||
name = "${var.prefix}-eks"
|
||||
role_arn = aws_iam_role.eks_cluster.arn
|
||||
version = var.kubernetes_version
|
||||
|
||||
vpc_config {
|
||||
subnet_ids = concat(aws_subnet.private[*].id, aws_subnet.public[*].id)
|
||||
endpoint_private_access = true
|
||||
endpoint_public_access = true
|
||||
}
|
||||
|
||||
access_config {
|
||||
authentication_mode = "API_AND_CONFIG_MAP"
|
||||
}
|
||||
|
||||
tags = var.tags
|
||||
|
||||
depends_on = [aws_iam_role_policy_attachment.eks_cluster_policy]
|
||||
}
|
||||
|
||||
# OIDC provider — required for IRSA
|
||||
data "tls_certificate" "eks" {
|
||||
url = aws_eks_cluster.main.identity[0].oidc[0].issuer
|
||||
}
|
||||
|
||||
resource "aws_iam_openid_connect_provider" "eks" {
|
||||
client_id_list = ["sts.amazonaws.com"]
|
||||
thumbprint_list = [data.tls_certificate.eks.certificates[0].sha1_fingerprint]
|
||||
url = aws_eks_cluster.main.identity[0].oidc[0].issuer
|
||||
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
resource "aws_iam_role" "eks_nodes" {
|
||||
name_prefix = "${var.prefix}-eks-nodes-"
|
||||
|
||||
assume_role_policy = jsonencode({
|
||||
Version = "2012-10-17"
|
||||
Statement = [{
|
||||
Action = "sts:AssumeRole"
|
||||
Effect = "Allow"
|
||||
Principal = { Service = "ec2.amazonaws.com" }
|
||||
}]
|
||||
})
|
||||
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
resource "aws_iam_role_policy_attachment" "eks_worker_node_policy" {
|
||||
policy_arn = "arn:aws:iam::aws:policy/AmazonEKSWorkerNodePolicy"
|
||||
role = aws_iam_role.eks_nodes.name
|
||||
}
|
||||
|
||||
resource "aws_iam_role_policy_attachment" "eks_cni_policy" {
|
||||
policy_arn = "arn:aws:iam::aws:policy/AmazonEKS_CNI_Policy"
|
||||
role = aws_iam_role.eks_nodes.name
|
||||
}
|
||||
|
||||
resource "aws_iam_role_policy_attachment" "eks_ecr_readonly" {
|
||||
policy_arn = "arn:aws:iam::aws:policy/AmazonEC2ContainerRegistryReadOnly"
|
||||
role = aws_iam_role.eks_nodes.name
|
||||
}
|
||||
|
||||
resource "aws_eks_node_group" "main" {
|
||||
cluster_name = aws_eks_cluster.main.name
|
||||
node_group_name = "${var.prefix}-nodes"
|
||||
node_role_arn = aws_iam_role.eks_nodes.arn
|
||||
subnet_ids = aws_subnet.private[*].id
|
||||
|
||||
instance_types = [var.node_instance_type]
|
||||
|
||||
scaling_config {
|
||||
desired_size = var.node_count
|
||||
max_size = var.node_max_count
|
||||
min_size = var.node_min_count
|
||||
}
|
||||
|
||||
update_config {
|
||||
max_unavailable = 1
|
||||
}
|
||||
|
||||
tags = var.tags
|
||||
|
||||
depends_on = [
|
||||
aws_iam_role_policy_attachment.eks_worker_node_policy,
|
||||
aws_iam_role_policy_attachment.eks_cni_policy,
|
||||
aws_iam_role_policy_attachment.eks_ecr_readonly,
|
||||
]
|
||||
}
|
||||
|
||||
# ─── External-DNS IRSA ───────────────────────────────────────────────
|
||||
# Allows external-dns to manage Route53 records for app ingresses.
|
||||
|
||||
data "aws_route53_zone" "main" {
|
||||
name = var.domain
|
||||
private_zone = false
|
||||
}
|
||||
|
||||
data "aws_iam_policy_document" "external_dns_assume_role" {
|
||||
statement {
|
||||
effect = "Allow"
|
||||
|
||||
principals {
|
||||
type = "Federated"
|
||||
identifiers = [aws_iam_openid_connect_provider.eks.arn]
|
||||
}
|
||||
|
||||
actions = ["sts:AssumeRoleWithWebIdentity"]
|
||||
|
||||
condition {
|
||||
test = "StringEquals"
|
||||
variable = "${replace(aws_iam_openid_connect_provider.eks.url, "https://", "")}:sub"
|
||||
values = ["system:serviceaccount:external-dns:external-dns"]
|
||||
}
|
||||
|
||||
condition {
|
||||
test = "StringEquals"
|
||||
variable = "${replace(aws_iam_openid_connect_provider.eks.url, "https://", "")}:aud"
|
||||
values = ["sts.amazonaws.com"]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
resource "aws_iam_role" "external_dns_irsa" {
|
||||
name_prefix = "${var.prefix}-external-dns-irsa-"
|
||||
assume_role_policy = data.aws_iam_policy_document.external_dns_assume_role.json
|
||||
|
||||
tags = var.tags
|
||||
}
|
||||
|
||||
data "aws_iam_policy_document" "external_dns_route53" {
|
||||
statement {
|
||||
effect = "Allow"
|
||||
actions = ["route53:ChangeResourceRecordSets"]
|
||||
resources = ["arn:aws:route53:::hostedzone/${data.aws_route53_zone.main.zone_id}"]
|
||||
}
|
||||
|
||||
statement {
|
||||
effect = "Allow"
|
||||
actions = ["route53:ListHostedZones", "route53:ListResourceRecordSets", "route53:ListTagsForResource"]
|
||||
resources = ["*"]
|
||||
}
|
||||
}
|
||||
|
||||
resource "aws_iam_role_policy" "external_dns_route53" {
|
||||
name_prefix = "${var.prefix}-external-dns-route53-"
|
||||
role = aws_iam_role.external_dns_irsa.id
|
||||
policy = data.aws_iam_policy_document.external_dns_route53.json
|
||||
}
|
||||
3
.tofu/platforms/eks/workload/outputs.tf
Normal file
3
.tofu/platforms/eks/workload/outputs.tf
Normal file
@@ -0,0 +1,3 @@
|
||||
output "cluster_name" { value = aws_eks_cluster.main.name }
|
||||
output "aws_region" { value = var.region }
|
||||
output "external_dns_irsa_role_arn" { value = aws_iam_role.external_dns_irsa.arn }
|
||||
24
.tofu/platforms/eks/workload/providers.tf
Normal file
24
.tofu/platforms/eks/workload/providers.tf
Normal file
@@ -0,0 +1,24 @@
|
||||
terraform {
|
||||
required_providers {
|
||||
aws = {
|
||||
source = "hashicorp/aws"
|
||||
version = "~> 5.0"
|
||||
}
|
||||
tls = {
|
||||
source = "hashicorp/tls"
|
||||
version = "~> 4.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# Authentication: set AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN
|
||||
# or configure an AWS profile: export AWS_PROFILE=clst
|
||||
provider "aws" {
|
||||
region = var.region
|
||||
}
|
||||
|
||||
variable "region" {
|
||||
description = "AWS region for the workload environment"
|
||||
type = string
|
||||
default = "eu-west-1"
|
||||
}
|
||||
17
.tofu/platforms/gke/dev/main.tf
Normal file
17
.tofu/platforms/gke/dev/main.tf
Normal file
@@ -0,0 +1,17 @@
|
||||
module "cluster" {
|
||||
source = "../modules/cluster"
|
||||
|
||||
project_id = var.project_id
|
||||
region = var.region
|
||||
prefix = "clst-dev"
|
||||
|
||||
# GKE — small dev nodes
|
||||
node_machine_type = "e2-standard-2"
|
||||
node_count = 2
|
||||
deletion_protection = false
|
||||
|
||||
labels = {
|
||||
environment = "dev"
|
||||
managed-by = "tofu"
|
||||
}
|
||||
}
|
||||
3
.tofu/platforms/gke/dev/outputs.tf
Normal file
3
.tofu/platforms/gke/dev/outputs.tf
Normal file
@@ -0,0 +1,3 @@
|
||||
output "cluster_name" { value = module.cluster.cluster_name }
|
||||
output "project_id" { value = module.cluster.project_id }
|
||||
output "region" { value = module.cluster.region }
|
||||
26
.tofu/platforms/gke/dev/providers.tf
Normal file
26
.tofu/platforms/gke/dev/providers.tf
Normal file
@@ -0,0 +1,26 @@
|
||||
terraform {
|
||||
required_providers {
|
||||
google = {
|
||||
source = "hashicorp/google"
|
||||
version = "~> 6.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# Authentication: use Application Default Credentials (gcloud auth application-default login)
|
||||
# or set GOOGLE_APPLICATION_CREDENTIALS to a service account key file.
|
||||
provider "google" {
|
||||
project = var.project_id
|
||||
region = var.region
|
||||
}
|
||||
|
||||
variable "project_id" {
|
||||
description = "GCP project ID for the dev environment"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "region" {
|
||||
description = "GCP region"
|
||||
type = string
|
||||
default = "europe-west4"
|
||||
}
|
||||
115
.tofu/platforms/gke/modules/cluster/main.tf
Normal file
115
.tofu/platforms/gke/modules/cluster/main.tf
Normal file
@@ -0,0 +1,115 @@
|
||||
# ─── Required APIs ────────────────────────────────────────────────────
|
||||
|
||||
resource "google_project_service" "compute" {
|
||||
project = var.project_id
|
||||
service = "compute.googleapis.com"
|
||||
disable_on_destroy = false
|
||||
}
|
||||
|
||||
resource "google_project_service" "container" {
|
||||
project = var.project_id
|
||||
service = "container.googleapis.com"
|
||||
disable_on_destroy = false
|
||||
}
|
||||
|
||||
# ─── Networking ───────────────────────────────────────────────────────
|
||||
|
||||
resource "google_compute_network" "main" {
|
||||
project = var.project_id
|
||||
name = "${var.prefix}-vpc"
|
||||
auto_create_subnetworks = false
|
||||
|
||||
depends_on = [google_project_service.compute]
|
||||
}
|
||||
|
||||
resource "google_compute_subnetwork" "main" {
|
||||
project = var.project_id
|
||||
name = "${var.prefix}-subnet"
|
||||
ip_cidr_range = "10.100.0.0/22"
|
||||
region = var.region
|
||||
network = google_compute_network.main.id
|
||||
|
||||
# Secondary ranges required for GKE VPC-native cluster
|
||||
secondary_ip_range {
|
||||
range_name = "pods"
|
||||
ip_cidr_range = "10.200.0.0/14" # /14 = ~262k pod IPs
|
||||
}
|
||||
|
||||
secondary_ip_range {
|
||||
range_name = "services"
|
||||
ip_cidr_range = "10.204.0.0/20" # /20 = ~4k service IPs
|
||||
}
|
||||
}
|
||||
|
||||
# ─── GKE Cluster ──────────────────────────────────────────────────────
|
||||
#
|
||||
# Regional cluster (3 control-plane replicas) for HA.
|
||||
# Workload Identity enabled — allows K8s service accounts to impersonate
|
||||
# Google Service Accounts for keyless access to GCP services.
|
||||
|
||||
resource "google_container_cluster" "main" {
|
||||
project = var.project_id
|
||||
name = "${var.prefix}-gke"
|
||||
location = var.region # regional cluster
|
||||
|
||||
network = google_compute_network.main.id
|
||||
subnetwork = google_compute_subnetwork.main.id
|
||||
|
||||
# VPC-native cluster with alias IP ranges
|
||||
ip_allocation_policy {
|
||||
cluster_secondary_range_name = "pods"
|
||||
services_secondary_range_name = "services"
|
||||
}
|
||||
|
||||
# Workload Identity pool — enables OIDC token projection for pods
|
||||
workload_identity_config {
|
||||
workload_pool = "${var.project_id}.svc.id.goog"
|
||||
}
|
||||
|
||||
# Remove default node pool — we manage our own below
|
||||
remove_default_node_pool = true
|
||||
initial_node_count = 1
|
||||
|
||||
deletion_protection = var.deletion_protection
|
||||
|
||||
dynamic "release_channel" {
|
||||
for_each = var.kubernetes_version == null ? [1] : []
|
||||
content {
|
||||
channel = "STABLE"
|
||||
}
|
||||
}
|
||||
|
||||
resource_labels = var.labels
|
||||
|
||||
depends_on = [google_project_service.container]
|
||||
}
|
||||
|
||||
resource "google_container_node_pool" "main" {
|
||||
project = var.project_id
|
||||
name = "${var.prefix}-nodes"
|
||||
location = var.region
|
||||
cluster = google_container_cluster.main.name
|
||||
node_count = var.node_count
|
||||
|
||||
node_config {
|
||||
machine_type = var.node_machine_type
|
||||
|
||||
# GKE_METADATA mode is required for Workload Identity
|
||||
workload_metadata_config {
|
||||
mode = "GKE_METADATA"
|
||||
}
|
||||
|
||||
oauth_scopes = [
|
||||
"https://www.googleapis.com/auth/cloud-platform",
|
||||
]
|
||||
|
||||
labels = merge(var.labels, {
|
||||
role = "worker"
|
||||
})
|
||||
}
|
||||
|
||||
management {
|
||||
auto_repair = true
|
||||
auto_upgrade = true
|
||||
}
|
||||
}
|
||||
16
.tofu/platforms/gke/modules/cluster/outputs.tf
Normal file
16
.tofu/platforms/gke/modules/cluster/outputs.tf
Normal file
@@ -0,0 +1,16 @@
|
||||
# ─── Cluster ─────────────────────────────────────────────────────────
|
||||
|
||||
output "cluster_name" {
|
||||
description = "GKE cluster name"
|
||||
value = google_container_cluster.main.name
|
||||
}
|
||||
|
||||
output "project_id" {
|
||||
description = "GCP project ID"
|
||||
value = var.project_id
|
||||
}
|
||||
|
||||
output "region" {
|
||||
description = "GCP region"
|
||||
value = var.region
|
||||
}
|
||||
8
.tofu/platforms/gke/modules/cluster/providers.tf
Normal file
8
.tofu/platforms/gke/modules/cluster/providers.tf
Normal file
@@ -0,0 +1,8 @@
|
||||
terraform {
|
||||
required_providers {
|
||||
google = {
|
||||
source = "hashicorp/google"
|
||||
version = "~> 6.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
48
.tofu/platforms/gke/modules/cluster/variables.tf
Normal file
48
.tofu/platforms/gke/modules/cluster/variables.tf
Normal file
@@ -0,0 +1,48 @@
|
||||
# ─── Project / Region ────────────────────────────────────────────────
|
||||
|
||||
variable "project_id" {
|
||||
description = "GCP project ID"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "region" {
|
||||
description = "GCP region (e.g., europe-west4, europe-west1)"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "prefix" {
|
||||
description = "Prefix for resource names (e.g., clst-dev)"
|
||||
type = string
|
||||
}
|
||||
|
||||
# ─── GKE Cluster ─────────────────────────────────────────────────────
|
||||
|
||||
variable "node_machine_type" {
|
||||
description = "GKE node machine type (e.g., e2-standard-2, e2-standard-4)"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "node_count" {
|
||||
description = "Number of nodes per zone (regional cluster spawns nodes in each zone)"
|
||||
type = number
|
||||
}
|
||||
|
||||
variable "kubernetes_version" {
|
||||
description = "GKE Kubernetes version channel (null = STABLE release channel)"
|
||||
type = string
|
||||
default = null
|
||||
}
|
||||
|
||||
variable "deletion_protection" {
|
||||
description = "Prevent cluster deletion (set true for production)"
|
||||
type = bool
|
||||
default = false
|
||||
}
|
||||
|
||||
# ─── Labels ──────────────────────────────────────────────────────────
|
||||
|
||||
variable "labels" {
|
||||
description = "Labels applied to all resources"
|
||||
type = map(string)
|
||||
default = {}
|
||||
}
|
||||
17
.tofu/platforms/gke/prod/main.tf
Normal file
17
.tofu/platforms/gke/prod/main.tf
Normal file
@@ -0,0 +1,17 @@
|
||||
module "cluster" {
|
||||
source = "../modules/cluster"
|
||||
|
||||
project_id = var.project_id
|
||||
region = var.region
|
||||
prefix = "clst"
|
||||
|
||||
# GKE — general-purpose nodes for production
|
||||
node_machine_type = "e2-standard-4"
|
||||
node_count = 3
|
||||
deletion_protection = true
|
||||
|
||||
labels = {
|
||||
environment = "prod"
|
||||
managed-by = "tofu"
|
||||
}
|
||||
}
|
||||
3
.tofu/platforms/gke/prod/outputs.tf
Normal file
3
.tofu/platforms/gke/prod/outputs.tf
Normal file
@@ -0,0 +1,3 @@
|
||||
output "cluster_name" { value = module.cluster.cluster_name }
|
||||
output "project_id" { value = module.cluster.project_id }
|
||||
output "region" { value = module.cluster.region }
|
||||
24
.tofu/platforms/gke/prod/providers.tf
Normal file
24
.tofu/platforms/gke/prod/providers.tf
Normal file
@@ -0,0 +1,24 @@
|
||||
terraform {
|
||||
required_providers {
|
||||
google = {
|
||||
source = "hashicorp/google"
|
||||
version = "~> 6.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
provider "google" {
|
||||
project = var.project_id
|
||||
region = var.region
|
||||
}
|
||||
|
||||
variable "project_id" {
|
||||
description = "GCP project ID for the prod environment"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "region" {
|
||||
description = "GCP region"
|
||||
type = string
|
||||
default = "europe-west1"
|
||||
}
|
||||
194
.tofu/platforms/gke/workload/main.tf
Normal file
194
.tofu/platforms/gke/workload/main.tf
Normal file
@@ -0,0 +1,194 @@
|
||||
# =============================================================================
|
||||
# GCP Workload Cluster
|
||||
# =============================================================================
|
||||
# A lean GKE cluster for running application workloads. No managed data
|
||||
# services — those live on the platform cluster. ArgoCD (on the platform
|
||||
# cluster) deploys apps to this cluster via the app-of-apps pattern.
|
||||
#
|
||||
# Platform components deployed by deploy-workload.sh:
|
||||
# nginx-ingress, cert-manager, external-dns, external-secrets, alloy
|
||||
#
|
||||
# Usage:
|
||||
# tofu init && tofu plan && tofu apply
|
||||
# ./sync-tofu-outputs.sh --env gcp-workload
|
||||
# ./deploy-workload.sh --env gcp-workload
|
||||
# =============================================================================
|
||||
|
||||
variable "prefix" {
|
||||
description = "Prefix for resource names (e.g., clst-workload)"
|
||||
type = string
|
||||
default = "clst-workload"
|
||||
}
|
||||
|
||||
variable "node_machine_type" {
|
||||
description = "GKE node machine type"
|
||||
type = string
|
||||
default = "e2-standard-2"
|
||||
}
|
||||
|
||||
variable "node_count" {
|
||||
description = "Number of nodes per zone"
|
||||
type = number
|
||||
default = 1
|
||||
}
|
||||
|
||||
variable "kubernetes_version" {
|
||||
description = "GKE Kubernetes version (null = STABLE release channel)"
|
||||
type = string
|
||||
default = null
|
||||
}
|
||||
|
||||
variable "deletion_protection" {
|
||||
description = "Prevent cluster deletion"
|
||||
type = bool
|
||||
default = false
|
||||
}
|
||||
|
||||
variable "labels" {
|
||||
description = "Labels applied to all resources"
|
||||
type = map(string)
|
||||
default = {
|
||||
environment = "workload"
|
||||
managed-by = "tofu"
|
||||
}
|
||||
}
|
||||
|
||||
# ─── Required APIs ────────────────────────────────────────────────────
|
||||
|
||||
resource "google_project_service" "compute" {
|
||||
project = var.project_id
|
||||
service = "compute.googleapis.com"
|
||||
disable_on_destroy = false
|
||||
}
|
||||
|
||||
resource "google_project_service" "container" {
|
||||
project = var.project_id
|
||||
service = "container.googleapis.com"
|
||||
disable_on_destroy = false
|
||||
}
|
||||
|
||||
resource "google_project_service" "iam" {
|
||||
project = var.project_id
|
||||
service = "iam.googleapis.com"
|
||||
disable_on_destroy = false
|
||||
}
|
||||
|
||||
resource "google_project_service" "dns" {
|
||||
project = var.project_id
|
||||
service = "dns.googleapis.com"
|
||||
disable_on_destroy = false
|
||||
}
|
||||
|
||||
# ─── Networking ───────────────────────────────────────────────────────
|
||||
|
||||
resource "google_compute_network" "main" {
|
||||
project = var.project_id
|
||||
name = "${var.prefix}-vpc"
|
||||
auto_create_subnetworks = false
|
||||
|
||||
depends_on = [google_project_service.compute]
|
||||
}
|
||||
|
||||
resource "google_compute_subnetwork" "main" {
|
||||
project = var.project_id
|
||||
name = "${var.prefix}-subnet"
|
||||
ip_cidr_range = "10.110.0.0/22"
|
||||
region = var.region
|
||||
network = google_compute_network.main.id
|
||||
|
||||
secondary_ip_range {
|
||||
range_name = "pods"
|
||||
ip_cidr_range = "10.210.0.0/14"
|
||||
}
|
||||
|
||||
secondary_ip_range {
|
||||
range_name = "services"
|
||||
ip_cidr_range = "10.214.0.0/20"
|
||||
}
|
||||
}
|
||||
|
||||
# ─── GKE Cluster ──────────────────────────────────────────────────────
|
||||
|
||||
resource "google_container_cluster" "main" {
|
||||
project = var.project_id
|
||||
name = "${var.prefix}-gke"
|
||||
location = var.region
|
||||
|
||||
network = google_compute_network.main.id
|
||||
subnetwork = google_compute_subnetwork.main.id
|
||||
|
||||
ip_allocation_policy {
|
||||
cluster_secondary_range_name = "pods"
|
||||
services_secondary_range_name = "services"
|
||||
}
|
||||
|
||||
workload_identity_config {
|
||||
workload_pool = "${var.project_id}.svc.id.goog"
|
||||
}
|
||||
|
||||
remove_default_node_pool = true
|
||||
initial_node_count = 1
|
||||
|
||||
deletion_protection = var.deletion_protection
|
||||
|
||||
dynamic "release_channel" {
|
||||
for_each = var.kubernetes_version == null ? [1] : []
|
||||
content {
|
||||
channel = "STABLE"
|
||||
}
|
||||
}
|
||||
|
||||
resource_labels = var.labels
|
||||
|
||||
depends_on = [google_project_service.container]
|
||||
}
|
||||
|
||||
resource "google_container_node_pool" "main" {
|
||||
project = var.project_id
|
||||
name = "${var.prefix}-nodes"
|
||||
location = var.region
|
||||
cluster = google_container_cluster.main.name
|
||||
node_count = var.node_count
|
||||
|
||||
node_config {
|
||||
machine_type = var.node_machine_type
|
||||
|
||||
workload_metadata_config {
|
||||
mode = "GKE_METADATA"
|
||||
}
|
||||
|
||||
oauth_scopes = [
|
||||
"https://www.googleapis.com/auth/cloud-platform",
|
||||
]
|
||||
|
||||
labels = merge(var.labels, { role = "worker" })
|
||||
}
|
||||
|
||||
management {
|
||||
auto_repair = true
|
||||
auto_upgrade = true
|
||||
}
|
||||
}
|
||||
|
||||
# ─── External-DNS Workload Identity ──────────────────────────────────
|
||||
# Allows external-dns to manage Cloud DNS records for app ingresses.
|
||||
|
||||
resource "google_service_account" "external_dns" {
|
||||
project = var.project_id
|
||||
account_id = "${var.prefix}-external-dns"
|
||||
display_name = "External-DNS Service Account (Workload Identity)"
|
||||
|
||||
depends_on = [google_project_service.iam]
|
||||
}
|
||||
|
||||
resource "google_project_iam_member" "external_dns_dns_admin" {
|
||||
project = var.project_id
|
||||
role = "roles/dns.admin"
|
||||
member = "serviceAccount:${google_service_account.external_dns.email}"
|
||||
}
|
||||
|
||||
resource "google_service_account_iam_member" "external_dns_workload_identity" {
|
||||
service_account_id = google_service_account.external_dns.name
|
||||
role = "roles/iam.workloadIdentityUser"
|
||||
member = "serviceAccount:${var.project_id}.svc.id.goog[external-dns/external-dns]"
|
||||
}
|
||||
4
.tofu/platforms/gke/workload/outputs.tf
Normal file
4
.tofu/platforms/gke/workload/outputs.tf
Normal file
@@ -0,0 +1,4 @@
|
||||
output "cluster_name" { value = google_container_cluster.main.name }
|
||||
output "project_id" { value = var.project_id }
|
||||
output "region" { value = var.region }
|
||||
output "external_dns_gsa_email" { value = google_service_account.external_dns.email }
|
||||
26
.tofu/platforms/gke/workload/providers.tf
Normal file
26
.tofu/platforms/gke/workload/providers.tf
Normal file
@@ -0,0 +1,26 @@
|
||||
terraform {
|
||||
required_providers {
|
||||
google = {
|
||||
source = "hashicorp/google"
|
||||
version = "~> 6.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# Authentication: use Application Default Credentials (gcloud auth application-default login)
|
||||
# or set GOOGLE_APPLICATION_CREDENTIALS to a service account key file.
|
||||
provider "google" {
|
||||
project = var.project_id
|
||||
region = var.region
|
||||
}
|
||||
|
||||
variable "project_id" {
|
||||
description = "GCP project ID for the workload environment"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "region" {
|
||||
description = "GCP region"
|
||||
type = string
|
||||
default = "europe-west4"
|
||||
}
|
||||
14
.tofu/platforms/upc/dev/main.tf
Normal file
14
.tofu/platforms/upc/dev/main.tf
Normal file
@@ -0,0 +1,14 @@
|
||||
module "cluster" {
|
||||
source = "../modules/cluster"
|
||||
|
||||
prefix = "clst-dev"
|
||||
zone = "no-svg1"
|
||||
node_plan = "DEV-1xCPU-2GB"
|
||||
node_count = 2
|
||||
network_cidr = "10.100.0.0/24"
|
||||
|
||||
tags = {
|
||||
Environment = "dev"
|
||||
ManagedBy = "tofu"
|
||||
}
|
||||
}
|
||||
13
.tofu/platforms/upc/dev/outputs.tf
Normal file
13
.tofu/platforms/upc/dev/outputs.tf
Normal file
@@ -0,0 +1,13 @@
|
||||
# ─── Cluster ─────────────────────────────────────────────────────────
|
||||
|
||||
output "cluster_id" {
|
||||
value = module.cluster.cluster_id
|
||||
}
|
||||
|
||||
output "cluster_name" {
|
||||
value = module.cluster.cluster_name
|
||||
}
|
||||
|
||||
output "zone" {
|
||||
value = module.cluster.zone
|
||||
}
|
||||
14
.tofu/platforms/upc/dev/providers.tf
Normal file
14
.tofu/platforms/upc/dev/providers.tf
Normal file
@@ -0,0 +1,14 @@
|
||||
terraform {
|
||||
required_version = ">= 1.0"
|
||||
|
||||
required_providers {
|
||||
upcloud = {
|
||||
source = "UpCloudLtd/upcloud"
|
||||
version = "~> 5.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
provider "upcloud" {
|
||||
# Set via environment variables: UPCLOUD_USERNAME, UPCLOUD_PASSWORD
|
||||
}
|
||||
56
.tofu/platforms/upc/modules/cluster/main.tf
Normal file
56
.tofu/platforms/upc/modules/cluster/main.tf
Normal file
@@ -0,0 +1,56 @@
|
||||
# Router for the private network
|
||||
resource "upcloud_router" "kubernetes" {
|
||||
name = "${var.prefix}-${var.cluster_name}-router"
|
||||
}
|
||||
|
||||
# Gateway for internet connectivity
|
||||
resource "upcloud_gateway" "kubernetes" {
|
||||
name = "${var.prefix}-${var.cluster_name}-gateway"
|
||||
zone = var.zone
|
||||
features = ["nat"]
|
||||
router {
|
||||
id = upcloud_router.kubernetes.id
|
||||
}
|
||||
}
|
||||
|
||||
# Private network for the Kubernetes cluster
|
||||
resource "upcloud_network" "kubernetes" {
|
||||
name = "${var.prefix}-${var.cluster_name}-network"
|
||||
zone = var.zone
|
||||
router = upcloud_router.kubernetes.id
|
||||
|
||||
ip_network {
|
||||
address = var.network_cidr
|
||||
dhcp = true
|
||||
dhcp_default_route = true
|
||||
family = "IPv4"
|
||||
gateway = cidrhost(var.network_cidr, 1)
|
||||
}
|
||||
|
||||
depends_on = [upcloud_gateway.kubernetes]
|
||||
}
|
||||
|
||||
# Kubernetes cluster
|
||||
resource "upcloud_kubernetes_cluster" "main" {
|
||||
name = "${var.prefix}-${var.cluster_name}"
|
||||
zone = var.zone
|
||||
network = upcloud_network.kubernetes.id
|
||||
control_plane_ip_filter = var.control_plane_ip_filter
|
||||
|
||||
private_node_groups = true
|
||||
}
|
||||
|
||||
# Node group for worker nodes
|
||||
resource "upcloud_kubernetes_node_group" "workers" {
|
||||
cluster = upcloud_kubernetes_cluster.main.id
|
||||
name = "${var.prefix}-${var.cluster_name}-workers"
|
||||
node_count = var.node_count
|
||||
plan = var.node_plan
|
||||
anti_affinity = var.node_count > 1
|
||||
labels = {
|
||||
prefix = var.prefix
|
||||
cluster = var.cluster_name
|
||||
role = "worker"
|
||||
env = lookup(var.tags, "Environment", "dev")
|
||||
}
|
||||
}
|
||||
31
.tofu/platforms/upc/modules/cluster/outputs.tf
Normal file
31
.tofu/platforms/upc/modules/cluster/outputs.tf
Normal file
@@ -0,0 +1,31 @@
|
||||
# ─── Cluster ─────────────────────────────────────────────────────────
|
||||
|
||||
output "cluster_id" {
|
||||
description = "The ID of the Kubernetes cluster"
|
||||
value = upcloud_kubernetes_cluster.main.id
|
||||
}
|
||||
|
||||
output "cluster_name" {
|
||||
description = "The name of the Kubernetes cluster"
|
||||
value = upcloud_kubernetes_cluster.main.name
|
||||
}
|
||||
|
||||
output "network_id" {
|
||||
description = "The ID of the private network"
|
||||
value = upcloud_network.kubernetes.id
|
||||
}
|
||||
|
||||
output "network_cidr" {
|
||||
description = "The CIDR block of the private network"
|
||||
value = var.network_cidr
|
||||
}
|
||||
|
||||
output "kubernetes_version" {
|
||||
description = "The Kubernetes version of the cluster"
|
||||
value = upcloud_kubernetes_cluster.main.version
|
||||
}
|
||||
|
||||
output "zone" {
|
||||
description = "The zone where the cluster is deployed"
|
||||
value = var.zone
|
||||
}
|
||||
8
.tofu/platforms/upc/modules/cluster/providers.tf
Normal file
8
.tofu/platforms/upc/modules/cluster/providers.tf
Normal file
@@ -0,0 +1,8 @@
|
||||
terraform {
|
||||
required_providers {
|
||||
upcloud = {
|
||||
source = "UpCloudLtd/upcloud"
|
||||
version = "~> 5.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
44
.tofu/platforms/upc/modules/cluster/variables.tf
Normal file
44
.tofu/platforms/upc/modules/cluster/variables.tf
Normal file
@@ -0,0 +1,44 @@
|
||||
# ─── Cluster ─────────────────────────────────────────────────────────
|
||||
|
||||
variable "prefix" {
|
||||
description = "Prefix for resource names"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "cluster_name" {
|
||||
description = "Name of the Kubernetes cluster"
|
||||
type = string
|
||||
default = "main"
|
||||
}
|
||||
|
||||
variable "zone" {
|
||||
description = "UpCloud zone"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "node_plan" {
|
||||
description = "UpCloud server plan for worker nodes"
|
||||
type = string
|
||||
}
|
||||
|
||||
variable "node_count" {
|
||||
description = "Number of worker nodes"
|
||||
type = number
|
||||
}
|
||||
|
||||
variable "network_cidr" {
|
||||
description = "CIDR block for the private network"
|
||||
type = string
|
||||
default = "10.100.0.0/24"
|
||||
}
|
||||
|
||||
variable "control_plane_ip_filter" {
|
||||
description = "CIDRs allowed to access the K8s API"
|
||||
type = list(string)
|
||||
default = ["0.0.0.0/0"]
|
||||
}
|
||||
|
||||
variable "tags" {
|
||||
description = "Labels to apply to resources"
|
||||
type = map(string)
|
||||
}
|
||||
16
.tofu/platforms/upc/prod/main.tf
Normal file
16
.tofu/platforms/upc/prod/main.tf
Normal file
@@ -0,0 +1,16 @@
|
||||
module "cluster" {
|
||||
source = "../modules/cluster"
|
||||
|
||||
prefix = "clst"
|
||||
zone = "de-fra1"
|
||||
node_plan = "4xCPU-8GB"
|
||||
node_count = 3
|
||||
network_cidr = "10.100.0.0/24"
|
||||
|
||||
control_plane_ip_filter = ["0.0.0.0/0"] # TODO: restrict to known CIDRs
|
||||
|
||||
tags = {
|
||||
Environment = "prod"
|
||||
ManagedBy = "tofu"
|
||||
}
|
||||
}
|
||||
13
.tofu/platforms/upc/prod/outputs.tf
Normal file
13
.tofu/platforms/upc/prod/outputs.tf
Normal file
@@ -0,0 +1,13 @@
|
||||
# ─── Cluster ─────────────────────────────────────────────────────────
|
||||
|
||||
output "cluster_id" {
|
||||
value = module.cluster.cluster_id
|
||||
}
|
||||
|
||||
output "cluster_name" {
|
||||
value = module.cluster.cluster_name
|
||||
}
|
||||
|
||||
output "zone" {
|
||||
value = module.cluster.zone
|
||||
}
|
||||
14
.tofu/platforms/upc/prod/providers.tf
Normal file
14
.tofu/platforms/upc/prod/providers.tf
Normal file
@@ -0,0 +1,14 @@
|
||||
terraform {
|
||||
required_version = ">= 1.0"
|
||||
|
||||
required_providers {
|
||||
upcloud = {
|
||||
source = "UpCloudLtd/upcloud"
|
||||
version = "~> 5.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
provider "upcloud" {
|
||||
# Set via environment variables: UPCLOUD_USERNAME, UPCLOUD_PASSWORD
|
||||
}
|
||||
116
.tofu/platforms/upc/workload/main.tf
Normal file
116
.tofu/platforms/upc/workload/main.tf
Normal file
@@ -0,0 +1,116 @@
|
||||
# =============================================================================
|
||||
# UpCloud Workload Cluster
|
||||
# =============================================================================
|
||||
# A lean UCS cluster for running application workloads. No managed data
|
||||
# services — those live on the platform cluster. ArgoCD (on the platform
|
||||
# cluster) deploys apps to this cluster via the app-of-apps pattern.
|
||||
#
|
||||
# Platform components deployed by deploy-workload.sh:
|
||||
# nginx-ingress, cert-manager, external-dns, external-secrets, alloy
|
||||
#
|
||||
# Usage:
|
||||
# tofu init && tofu plan && tofu apply
|
||||
# ./sync-tofu-outputs.sh --env upcloud-workload
|
||||
# ./deploy-workload.sh --env upcloud-workload
|
||||
# =============================================================================
|
||||
|
||||
variable "prefix" {
|
||||
description = "Prefix for resource names"
|
||||
type = string
|
||||
default = "clst-workload"
|
||||
}
|
||||
|
||||
variable "zone" {
|
||||
description = "UpCloud zone"
|
||||
type = string
|
||||
default = "fi-hel1"
|
||||
}
|
||||
|
||||
variable "node_plan" {
|
||||
description = "UpCloud server plan for worker nodes"
|
||||
type = string
|
||||
default = "2xCPU-4GB"
|
||||
}
|
||||
|
||||
variable "node_count" {
|
||||
description = "Number of worker nodes"
|
||||
type = number
|
||||
default = 2
|
||||
}
|
||||
|
||||
variable "network_cidr" {
|
||||
description = "CIDR block for the private network"
|
||||
type = string
|
||||
default = "10.110.0.0/24"
|
||||
}
|
||||
|
||||
variable "control_plane_ip_filter" {
|
||||
description = "CIDRs allowed to access the K8s API"
|
||||
type = list(string)
|
||||
default = ["0.0.0.0/0"]
|
||||
}
|
||||
|
||||
variable "tags" {
|
||||
description = "Labels to apply to resources"
|
||||
type = map(string)
|
||||
default = {
|
||||
Environment = "workload"
|
||||
ManagedBy = "tofu"
|
||||
}
|
||||
}
|
||||
|
||||
# ─── Networking ───────────────────────────────────────────────────────
|
||||
|
||||
resource "upcloud_router" "kubernetes" {
|
||||
name = "${var.prefix}-workload-router"
|
||||
}
|
||||
|
||||
resource "upcloud_gateway" "kubernetes" {
|
||||
name = "${var.prefix}-workload-gateway"
|
||||
zone = var.zone
|
||||
features = ["nat"]
|
||||
router {
|
||||
id = upcloud_router.kubernetes.id
|
||||
}
|
||||
}
|
||||
|
||||
resource "upcloud_network" "kubernetes" {
|
||||
name = "${var.prefix}-workload-network"
|
||||
zone = var.zone
|
||||
router = upcloud_router.kubernetes.id
|
||||
|
||||
ip_network {
|
||||
address = var.network_cidr
|
||||
dhcp = true
|
||||
dhcp_default_route = true
|
||||
family = "IPv4"
|
||||
gateway = cidrhost(var.network_cidr, 1)
|
||||
}
|
||||
|
||||
depends_on = [upcloud_gateway.kubernetes]
|
||||
}
|
||||
|
||||
# ─── Kubernetes Cluster ───────────────────────────────────────────────
|
||||
|
||||
resource "upcloud_kubernetes_cluster" "main" {
|
||||
name = "${var.prefix}-workload"
|
||||
zone = var.zone
|
||||
network = upcloud_network.kubernetes.id
|
||||
control_plane_ip_filter = var.control_plane_ip_filter
|
||||
|
||||
private_node_groups = true
|
||||
}
|
||||
|
||||
resource "upcloud_kubernetes_node_group" "workers" {
|
||||
cluster = upcloud_kubernetes_cluster.main.id
|
||||
name = "${var.prefix}-workload-workers"
|
||||
node_count = var.node_count
|
||||
plan = var.node_plan
|
||||
anti_affinity = var.node_count > 1
|
||||
labels = {
|
||||
prefix = var.prefix
|
||||
cluster = "workload"
|
||||
role = "worker"
|
||||
env = lookup(var.tags, "Environment", "workload")
|
||||
}
|
||||
}
|
||||
3
.tofu/platforms/upc/workload/outputs.tf
Normal file
3
.tofu/platforms/upc/workload/outputs.tf
Normal file
@@ -0,0 +1,3 @@
|
||||
output "cluster_name" { value = upcloud_kubernetes_cluster.main.name }
|
||||
output "cluster_id" { value = upcloud_kubernetes_cluster.main.id }
|
||||
output "zone" { value = var.zone }
|
||||
14
.tofu/platforms/upc/workload/providers.tf
Normal file
14
.tofu/platforms/upc/workload/providers.tf
Normal file
@@ -0,0 +1,14 @@
|
||||
terraform {
|
||||
required_version = ">= 1.0"
|
||||
|
||||
required_providers {
|
||||
upcloud = {
|
||||
source = "UpCloudLtd/upcloud"
|
||||
version = "~> 5.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
provider "upcloud" {
|
||||
# Set via environment variables: UPCLOUD_USERNAME, UPCLOUD_PASSWORD
|
||||
}
|
||||
66
.tofu/scripts/get-kubeconfig.sh
Normal file
66
.tofu/scripts/get-kubeconfig.sh
Normal file
@@ -0,0 +1,66 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
TOFU_ROOT="$(dirname "$SCRIPT_DIR")"
|
||||
PROJECT_ROOT="$(dirname "$TOFU_ROOT")"
|
||||
|
||||
CLUSTER="${1:?Usage: $0 <cluster> (e.g., aks-dev, eks-prod)}"
|
||||
PLATFORM="${CLUSTER%%-*}"
|
||||
ENV="${CLUSTER#*-}"
|
||||
|
||||
KUBECONFIG_FILE="$PROJECT_ROOT/private/$CLUSTER/kubeconfig"
|
||||
|
||||
if [[ -f "$KUBECONFIG_FILE" ]]; then
|
||||
echo "Kubeconfig already exists: $KUBECONFIG_FILE"
|
||||
echo ""
|
||||
echo " export KUBECONFIG=$KUBECONFIG_FILE"
|
||||
else
|
||||
echo "No cached kubeconfig. Fetching from platform..."
|
||||
|
||||
# Load platform credentials
|
||||
ENV_FILE="$TOFU_ROOT/configs/$PLATFORM.env"
|
||||
if [[ -f "$ENV_FILE" ]]; then
|
||||
set -a; source "$ENV_FILE"; set +a
|
||||
fi
|
||||
|
||||
TOFU_DIR="$TOFU_ROOT/platforms/$PLATFORM/$ENV"
|
||||
mkdir -p "$(dirname "$KUBECONFIG_FILE")"
|
||||
|
||||
case "$PLATFORM" in
|
||||
aks)
|
||||
cd "$TOFU_DIR"
|
||||
RG=$(tofu output -raw resource_group_name 2>/dev/null || echo "$CLUSTER-rg")
|
||||
NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "$CLUSTER")
|
||||
az aks get-credentials --resource-group "$RG" --name "$NAME" --file "$KUBECONFIG_FILE" --overwrite-existing
|
||||
;;
|
||||
eks)
|
||||
cd "$TOFU_DIR"
|
||||
NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "$CLUSTER")
|
||||
REGION=$(tofu output -raw aws_region 2>/dev/null || echo "${AWS_REGION:-eu-west-1}")
|
||||
aws eks update-kubeconfig --name "$NAME" --region "$REGION" --kubeconfig "$KUBECONFIG_FILE"
|
||||
;;
|
||||
gke)
|
||||
cd "$TOFU_DIR"
|
||||
NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "$CLUSTER")
|
||||
REGION=$(tofu output -raw region 2>/dev/null || echo "${GCP_REGION:-europe-west4}")
|
||||
PROJECT=$(tofu output -raw project_id 2>/dev/null || echo "${GCP_PROJECT_ID:-}")
|
||||
gcloud container clusters get-credentials "$NAME" --region "$REGION" --project "$PROJECT"
|
||||
cp ~/.kube/config "$KUBECONFIG_FILE"
|
||||
;;
|
||||
upc)
|
||||
cd "$TOFU_DIR"
|
||||
CLUSTER_ID=$(tofu output -raw cluster_id 2>/dev/null || echo "${UPCLOUD_CLUSTER_ID:-}")
|
||||
upctl kubernetes config "$CLUSTER_ID" > "$KUBECONFIG_FILE"
|
||||
;;
|
||||
*)
|
||||
echo "Error: unknown platform '$PLATFORM'"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
chmod 600 "$KUBECONFIG_FILE"
|
||||
echo "Kubeconfig saved: $KUBECONFIG_FILE"
|
||||
echo ""
|
||||
echo " export KUBECONFIG=$KUBECONFIG_FILE"
|
||||
fi
|
||||
246
.tofu/scripts/setup-cluster.sh
Normal file
246
.tofu/scripts/setup-cluster.sh
Normal file
@@ -0,0 +1,246 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
TOFU_ROOT="$(dirname "$SCRIPT_DIR")"
|
||||
PROJECT_ROOT="$(dirname "$TOFU_ROOT")"
|
||||
|
||||
# ─── Usage ────────────────────────────────────────────────────────────
|
||||
usage() {
|
||||
cat <<EOF
|
||||
Usage: $0 <cluster> [options]
|
||||
|
||||
Provision a Kubernetes cluster using OpenTofu.
|
||||
Mirrors bootstrap.sh convention: cluster = <platform>-<env>
|
||||
|
||||
Clusters: aks-dev | aks-prod | eks-dev | eks-prod
|
||||
gke-dev | gke-prod | upc-dev | upc-prod
|
||||
<platform>-workload (for workload clusters)
|
||||
|
||||
Options:
|
||||
--plan Plan only, don't apply
|
||||
--destroy Destroy the cluster (use teardown-cluster.sh instead)
|
||||
--auto Skip confirmation prompts
|
||||
-h, --help Show this help
|
||||
|
||||
Examples:
|
||||
$0 aks-dev
|
||||
$0 eks-prod --plan
|
||||
$0 upc-dev --auto
|
||||
|
||||
Prerequisites:
|
||||
- tofu, kubectl, helm installed
|
||||
- Platform credentials in .tofu/configs/<platform>.env
|
||||
- Cluster config in clusters/<cluster>.yaml
|
||||
|
||||
After provisioning, run:
|
||||
./bootstrap.sh <cluster>
|
||||
EOF
|
||||
exit "${1:-0}"
|
||||
}
|
||||
|
||||
# ─── Parse arguments ──────────────────────────────────────────────────
|
||||
CLUSTER=""
|
||||
PLAN_ONLY=false
|
||||
DESTROY=false
|
||||
AUTO_APPROVE=false
|
||||
|
||||
while [[ $# -gt 0 ]]; do
|
||||
case "$1" in
|
||||
--plan) PLAN_ONLY=true; shift ;;
|
||||
--destroy) DESTROY=true; shift ;;
|
||||
--auto) AUTO_APPROVE=true; shift ;;
|
||||
-h|--help) usage 0 ;;
|
||||
-*) echo "Unknown option: $1"; usage 1 ;;
|
||||
*)
|
||||
if [[ -z "$CLUSTER" ]]; then
|
||||
CLUSTER="$1"
|
||||
else
|
||||
echo "Error: unexpected argument '$1'"
|
||||
usage 1
|
||||
fi
|
||||
shift
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
[[ -z "$CLUSTER" ]] && { echo "Error: <cluster> argument required"; usage 1; }
|
||||
|
||||
# ─── Map cluster → platform + env ────────────────────────────────────
|
||||
PLATFORM="${CLUSTER%%-*}" # aks-dev → aks
|
||||
ENV="${CLUSTER#*-}" # aks-dev → dev
|
||||
|
||||
case "$PLATFORM" in
|
||||
aks|eks|gke|upc) ;;
|
||||
*) echo "Error: unknown platform '$PLATFORM'. Expected: aks, eks, gke, upc"; exit 1 ;;
|
||||
esac
|
||||
|
||||
TOFU_DIR="$TOFU_ROOT/platforms/$PLATFORM/$ENV"
|
||||
if [[ ! -d "$TOFU_DIR" ]]; then
|
||||
echo "Error: tofu directory not found: $TOFU_DIR"
|
||||
echo "Available environments for $PLATFORM:"
|
||||
ls -1 "$TOFU_ROOT/platforms/$PLATFORM/" 2>/dev/null | grep -v modules || echo " (none)"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "========================================="
|
||||
echo " Kubernetes Cluster Setup"
|
||||
echo "========================================="
|
||||
echo ""
|
||||
echo " Cluster: $CLUSTER"
|
||||
echo " Platform: $PLATFORM"
|
||||
echo " Env: $ENV"
|
||||
echo " Tofu dir: $TOFU_DIR"
|
||||
echo ""
|
||||
|
||||
# ─── Prerequisites ────────────────────────────────────────────────────
|
||||
echo "=== Checking Prerequisites ==="
|
||||
command -v tofu >/dev/null 2>&1 || { echo "Error: tofu is not installed."; exit 1; }
|
||||
command -v kubectl >/dev/null 2>&1 || { echo "Error: kubectl is not installed."; exit 1; }
|
||||
command -v helm >/dev/null 2>&1 || { echo "Error: helm is not installed."; exit 1; }
|
||||
echo " tofu, kubectl, helm: OK"
|
||||
|
||||
# ─── Load platform credentials ────────────────────────────────────────
|
||||
ENV_FILE="$TOFU_ROOT/configs/$PLATFORM.env"
|
||||
if [[ -f "$ENV_FILE" ]]; then
|
||||
echo " Loading credentials from configs/$PLATFORM.env"
|
||||
set -a
|
||||
# shellcheck disable=SC1090
|
||||
source "$ENV_FILE"
|
||||
set +a
|
||||
else
|
||||
echo " Warning: $ENV_FILE not found — using existing environment/CLI auth"
|
||||
echo " Copy configs/$PLATFORM.env.example → configs/$PLATFORM.env to configure"
|
||||
fi
|
||||
|
||||
# ─── Load cluster config (if exists) ──────────────────────────────────
|
||||
CLUSTER_CONFIG="$PROJECT_ROOT/clusters/$CLUSTER.yaml"
|
||||
if [[ -f "$CLUSTER_CONFIG" ]]; then
|
||||
echo " Loading cluster config from clusters/$CLUSTER.yaml"
|
||||
if command -v yq >/dev/null 2>&1; then
|
||||
eval "$(yq -r 'to_entries[] | "export CLUSTER_\(.key)=\"\(.value)\""' "$CLUSTER_CONFIG")"
|
||||
echo " Cluster name: ${CLUSTER_clusterName:-$CLUSTER}"
|
||||
else
|
||||
echo " Warning: yq not installed — cluster config not loaded"
|
||||
fi
|
||||
else
|
||||
echo " Warning: $CLUSTER_CONFIG not found — using defaults"
|
||||
fi
|
||||
echo ""
|
||||
|
||||
# ─── Run OpenTofu ─────────────────────────────────────────────────────
|
||||
cd "$TOFU_DIR"
|
||||
|
||||
echo "=== Initializing OpenTofu ==="
|
||||
tofu init
|
||||
|
||||
echo ""
|
||||
if $DESTROY; then
|
||||
echo "=== Planning Destruction ==="
|
||||
tofu plan -destroy -out=tfplan
|
||||
|
||||
if ! $AUTO_APPROVE; then
|
||||
echo ""
|
||||
read -rp "DESTROY cluster $CLUSTER? This is irreversible. (yes/no) " REPLY
|
||||
[[ "$REPLY" == "yes" ]] || { echo "Cancelled."; exit 1; }
|
||||
fi
|
||||
|
||||
echo "Destroying infrastructure..."
|
||||
tofu apply tfplan
|
||||
echo ""
|
||||
echo "=== Cluster $CLUSTER Destroyed ==="
|
||||
|
||||
elif $PLAN_ONLY; then
|
||||
echo "=== Planning Infrastructure ==="
|
||||
tofu plan
|
||||
echo ""
|
||||
echo "=== Plan complete (--plan mode, no changes applied) ==="
|
||||
|
||||
else
|
||||
echo "=== Planning Infrastructure ==="
|
||||
tofu plan -out=tfplan
|
||||
|
||||
if ! $AUTO_APPROVE; then
|
||||
echo ""
|
||||
read -rp "Apply this plan for $CLUSTER? (y/n) " -n 1 REPLY
|
||||
echo
|
||||
[[ "$REPLY" =~ ^[Yy]$ ]] || { echo "Cancelled."; exit 1; }
|
||||
fi
|
||||
|
||||
echo "Applying infrastructure..."
|
||||
tofu apply tfplan
|
||||
|
||||
# ─── Save kubeconfig ──────────────────────────────────────────────
|
||||
KUBECONFIG_DIR="$PROJECT_ROOT/private/$CLUSTER"
|
||||
mkdir -p "$KUBECONFIG_DIR"
|
||||
KUBECONFIG_FILE="$KUBECONFIG_DIR/kubeconfig"
|
||||
|
||||
echo ""
|
||||
echo "=== Saving Kubeconfig ==="
|
||||
|
||||
case "$PLATFORM" in
|
||||
aks)
|
||||
if tofu output -raw kubeconfig > "$KUBECONFIG_FILE" 2>/dev/null; then
|
||||
echo " Saved from tofu output"
|
||||
else
|
||||
echo " Fetching from Azure CLI..."
|
||||
RG=$(tofu output -raw resource_group_name 2>/dev/null || echo "${CLUSTER_clusterName:-$CLUSTER}-rg")
|
||||
NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "${CLUSTER_clusterName:-$CLUSTER}")
|
||||
az aks get-credentials --resource-group "$RG" --name "$NAME" --file "$KUBECONFIG_FILE" --overwrite-existing
|
||||
fi
|
||||
;;
|
||||
eks)
|
||||
NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "${CLUSTER_clusterName:-$CLUSTER}")
|
||||
REGION=$(tofu output -raw aws_region 2>/dev/null || echo "${AWS_REGION:-eu-west-1}")
|
||||
aws eks update-kubeconfig --name "$NAME" --region "$REGION" --kubeconfig "$KUBECONFIG_FILE"
|
||||
;;
|
||||
gke)
|
||||
NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "${CLUSTER_clusterName:-$CLUSTER}")
|
||||
REGION=$(tofu output -raw region 2>/dev/null || echo "${GCP_REGION:-europe-west4}")
|
||||
PROJECT=$(tofu output -raw project_id 2>/dev/null || echo "${GCP_PROJECT_ID:-}")
|
||||
gcloud container clusters get-credentials "$NAME" --region "$REGION" --project "$PROJECT" 2>/dev/null \
|
||||
&& cp ~/.kube/config "$KUBECONFIG_FILE" \
|
||||
|| echo " Warning: could not fetch kubeconfig via gcloud"
|
||||
;;
|
||||
upc)
|
||||
if tofu output -raw kubeconfig > "$KUBECONFIG_FILE" 2>/dev/null; then
|
||||
echo " Saved from tofu output"
|
||||
else
|
||||
CLUSTER_ID=$(tofu output -raw cluster_id 2>/dev/null || echo "${UPCLOUD_CLUSTER_ID:-}")
|
||||
if [[ -n "$CLUSTER_ID" ]]; then
|
||||
upctl kubernetes config "$CLUSTER_ID" > "$KUBECONFIG_FILE"
|
||||
else
|
||||
echo " Warning: could not determine cluster ID for kubeconfig"
|
||||
fi
|
||||
fi
|
||||
;;
|
||||
esac
|
||||
|
||||
if [[ -f "$KUBECONFIG_FILE" ]]; then
|
||||
chmod 600 "$KUBECONFIG_FILE"
|
||||
echo " Kubeconfig: $KUBECONFIG_FILE"
|
||||
fi
|
||||
|
||||
# ─── Wait for nodes ──────────────────────────────────────────────
|
||||
echo ""
|
||||
echo "=== Waiting for Cluster Nodes ==="
|
||||
export KUBECONFIG="$KUBECONFIG_FILE"
|
||||
if kubectl wait --for=condition=Ready nodes --all --timeout=300s 2>/dev/null; then
|
||||
echo " All nodes ready"
|
||||
else
|
||||
echo " Warning: nodes not ready within timeout — check cluster status"
|
||||
fi
|
||||
|
||||
# ─── Summary ─────────────────────────────────────────────────────
|
||||
echo ""
|
||||
echo "========================================="
|
||||
echo " Cluster $CLUSTER Provisioned"
|
||||
echo "========================================="
|
||||
echo ""
|
||||
echo " Kubeconfig: $KUBECONFIG_FILE"
|
||||
echo ""
|
||||
echo " Next steps:"
|
||||
echo " export KUBECONFIG=$KUBECONFIG_FILE"
|
||||
echo " ./bootstrap.sh $CLUSTER"
|
||||
echo ""
|
||||
fi
|
||||
7
.tofu/scripts/teardown-cluster.sh
Normal file
7
.tofu/scripts/teardown-cluster.sh
Normal file
@@ -0,0 +1,7 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
|
||||
# Delegate to setup-cluster.sh with --destroy flag
|
||||
exec "$SCRIPT_DIR/setup-cluster.sh" "$@" --destroy
|
||||
55
README.md
55
README.md
@@ -57,11 +57,11 @@ This repository contains the complete GitOps configuration for our Kubernetes cl
|
||||
|
||||
### What's Inside
|
||||
|
||||
- **Infrastructure Applications**: Traefik, Cert-Manager, Kyverno, Prometheus, Grafana, Loki, Tempo, Vault, Vault Secrets Operator, Homepage (platform dashboard)
|
||||
- **Infrastructure Applications**: Traefik, Cert-Manager, Kyverno, Prometheus, Grafana, Loki, Tempo, Sealed Secrets, Homepage (platform dashboard)
|
||||
- **Business Applications**: MCP10X, MusicMan, Dot-AI Stack, ArgoCD MCP
|
||||
- **Policies**: Kyverno security policies for secret management, namespace controls, pod verification
|
||||
- **Monitoring**: Full observability stack with metrics, logs, traces, and alerting
|
||||
- **Secrets**: Vault Secrets Operator (VSO) syncs secrets from HashiCorp Vault to K8s
|
||||
- **Secrets**: Sealed Secrets for secure Git storage
|
||||
|
||||
### Key Features
|
||||
|
||||
@@ -80,8 +80,23 @@ This repository contains the complete GitOps configuration for our Kubernetes cl
|
||||
|
||||
```
|
||||
.
|
||||
├── bootstrap.sh # Cluster initialization script
|
||||
├── _app-of-apps.yaml # Root ArgoCD Application (App-of-Apps pattern)
|
||||
├── bootstrap.sh # Cluster initialization (ArgoCD + GitOps)
|
||||
├── _app-of-apps-{cluster}.yaml # Root ArgoCD Application (per cluster)
|
||||
│
|
||||
├── .tofu/ # Infrastructure provisioning (OpenTofu)
|
||||
│ ├── platforms/ # Per-platform IaC (one dir per cloud)
|
||||
│ │ ├── aks/ # Azure AKS (modules/ + dev/ + prod/ + workload/)
|
||||
│ │ ├── eks/ # AWS EKS
|
||||
│ │ ├── gke/ # GCP GKE
|
||||
│ │ └── upc/ # UpCloud
|
||||
│ ├── configs/ # Platform credentials (git-ignored)
|
||||
│ │ └── *.env.example # Template for each platform
|
||||
│ └── scripts/ # Cluster lifecycle scripts
|
||||
│ ├── setup-cluster.sh # Create cluster: ./setup-cluster.sh aks-dev
|
||||
│ ├── teardown-cluster.sh
|
||||
│ └── get-kubeconfig.sh
|
||||
│
|
||||
├── clusters/ # Cluster metadata (domain, trustedIPs, etc.)
|
||||
│
|
||||
├── infra/ # Infrastructure ArgoCD Applications (Kustomize multi-cluster)
|
||||
│ ├── base/ # Base ArgoCD Application manifests (one dir per component)
|
||||
@@ -187,7 +202,7 @@ Developer commits code → CI/CD builds image → Updates helm-prod-values → A
|
||||
**Quick version**:
|
||||
1. Create `apps/myapp.yaml` (ArgoCD Application manifest)
|
||||
2. Create `helm-prod-values/myapp/values.yaml` (configuration)
|
||||
3. Write secrets to Vault and create VaultStaticSecret CRD if needed
|
||||
3. Create sealed secrets if needed
|
||||
4. Commit and push - ArgoCD auto-syncs!
|
||||
|
||||
### Update an Existing Application
|
||||
@@ -200,18 +215,22 @@ Developer commits code → CI/CD builds image → Updates helm-prod-values → A
|
||||
|
||||
### Manage Secrets
|
||||
|
||||
**See detailed guide**: [Vault Secrets Operator Reference](docs/vault-secrets-operator.md)
|
||||
**See detailed guide**: [Developer Guide - Working with Secrets](docs/DEVELOPER-GUIDE.md#working-with-secrets)
|
||||
|
||||
```bash
|
||||
# 1. Write secret to Vault
|
||||
vault kv put kv/myapp/myapp-creds KEY=value
|
||||
# Create plain secret
|
||||
kubectl create secret generic myapp-creds \
|
||||
--from-literal=KEY=value \
|
||||
--dry-run=client -o yaml > private/myapp-creds.yaml
|
||||
|
||||
# 2. Create VaultStaticSecret CRD (one-time, commit to git)
|
||||
# See docs/vault-secrets-operator.md for CRD template
|
||||
# Seal it
|
||||
kubeseal --format=yaml --cert=pub-cert.pem \
|
||||
< private/myapp-creds.yaml > secrets/myapp-creds-sealed.yaml
|
||||
|
||||
# 3. Rotate secrets — no git commit needed!
|
||||
vault kv put kv/myapp/myapp-creds KEY=new-value
|
||||
# VSO picks up changes within 30 seconds
|
||||
# Commit sealed version
|
||||
git add secrets/myapp-creds-sealed.yaml
|
||||
git commit -m "Add myapp credentials"
|
||||
git push
|
||||
```
|
||||
|
||||
### Enable Authentication
|
||||
@@ -324,7 +343,7 @@ kubectl patch application myapp -n argocd \
|
||||
## 🔐 Security
|
||||
|
||||
### Secret Management
|
||||
- ✅ Vault Secrets Operator (VSO) for secret management
|
||||
- ✅ Sealed Secrets for Git storage
|
||||
- ✅ Kyverno auto-clones secrets to namespaces
|
||||
- ❌ Never commit plain secrets
|
||||
|
||||
@@ -351,8 +370,7 @@ kubectl patch application myapp -n argocd \
|
||||
| **Traefik** | Ingress controller | `traefik` | 2 |
|
||||
| **Cert-Manager** | TLS certificates | `cert-manager` | 1 |
|
||||
| **Kyverno** | Policy engine | `kyverno` | 1 |
|
||||
| **Vault** | Secret storage | `vault` | 1 |
|
||||
| **Vault Secrets Operator** | Secret sync (Vault → K8s) | `vault-secrets-operator-system` | 1 |
|
||||
| **Sealed Secrets** | Secret encryption | `kube-system` | 1 |
|
||||
| **Prometheus** | Metrics | `monitoring` | 1 |
|
||||
| **Grafana** | Dashboards | `monitoring` | 1 |
|
||||
| **Loki** | Logs | `monitoring` | 1 |
|
||||
@@ -452,7 +470,7 @@ Applications deploy in order using `argocd.argoproj.io/sync-wave`:
|
||||
1. Read [Developer Guide - Deploying Your First Application](docs/DEVELOPER-GUIDE.md#deploying-your-first-application)
|
||||
2. Create ArgoCD Application manifest in `apps/`
|
||||
3. Create Helm values in `helm-prod-values/`
|
||||
4. Write secrets to Vault and create VaultStaticSecret CRD if needed
|
||||
4. Create sealed secrets if needed
|
||||
5. Commit and push - ArgoCD handles the rest!
|
||||
|
||||
### Modifying Infrastructure
|
||||
@@ -496,8 +514,7 @@ Documentation lives in `docs/`. To update:
|
||||
- [Traefik Documentation](https://doc.traefik.io/traefik/)
|
||||
- [Cert-Manager Documentation](https://cert-manager.io/docs/)
|
||||
- [Grafana Tempo Documentation](https://grafana.com/docs/tempo/)
|
||||
- [Vault Secrets Operator](https://developer.hashicorp.com/vault/docs/platform/k8s/vso)
|
||||
- [HashiCorp Vault](https://developer.hashicorp.com/vault/docs)
|
||||
- [Sealed Secrets](https://github.com/bitnami-labs/sealed-secrets)
|
||||
|
||||
### Related Repositories
|
||||
- [forte-helm](https://git.forteapps.net/Forte/forte-helm) - Helm chart templates
|
||||
|
||||
@@ -1,14 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: argocd-mcp-credentials
|
||||
namespace: argocd-mcp
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: argocd-mcp/argocd-mcp-credentials
|
||||
destination:
|
||||
name: argocd-mcp-credentials
|
||||
create: true
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -1,14 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: auth-oidc
|
||||
namespace: argocd-mcp
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: argocd-mcp/auth-oidc
|
||||
destination:
|
||||
name: auth-oidc
|
||||
create: true
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -2,7 +2,5 @@ apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
resources:
|
||||
- argo-mcp.yaml
|
||||
- vault-auth.yaml
|
||||
- auth-oidc-vault.yaml
|
||||
- argocd-mcp-credentials-vault.yaml
|
||||
# Removed: argocdmcp-auth-oidc-sealed.yaml, argocd-mcp-credentials.yaml (migrated to VSO)
|
||||
- argocdmcp-auth-oidc-sealed.yaml
|
||||
- argocd-mcp-credentials.yaml
|
||||
|
||||
@@ -1,20 +0,0 @@
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: vault-auth-argocd-mcp
|
||||
namespace: argocd-mcp
|
||||
---
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultAuth
|
||||
metadata:
|
||||
name: vault-auth
|
||||
namespace: argocd-mcp
|
||||
spec:
|
||||
method: kubernetes
|
||||
mount: kubernetes
|
||||
kubernetes:
|
||||
role: ns-argocd-mcp
|
||||
serviceAccount: vault-auth-argocd-mcp
|
||||
audiences:
|
||||
- vault
|
||||
@@ -1,14 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: dot-ai-secrets
|
||||
namespace: dot-ai
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: dot-ai/dot-ai-secrets
|
||||
destination:
|
||||
name: dot-ai-secrets
|
||||
create: true
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -2,6 +2,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
resources:
|
||||
- dot-ai-stack.yaml
|
||||
- vault-auth.yaml
|
||||
- dot-ai-secrets-vault.yaml
|
||||
# Removed: dot-ai-secrets.yaml (migrated to VSO)
|
||||
- dot-ai-secrets.yaml
|
||||
|
||||
@@ -1,20 +0,0 @@
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: vault-auth-dot-ai
|
||||
namespace: dot-ai
|
||||
---
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultAuth
|
||||
metadata:
|
||||
name: vault-auth
|
||||
namespace: dot-ai
|
||||
spec:
|
||||
method: kubernetes
|
||||
mount: kubernetes
|
||||
kubernetes:
|
||||
role: ns-dot-ai
|
||||
serviceAccount: vault-auth-dot-ai
|
||||
audiences:
|
||||
- vault
|
||||
@@ -1,15 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: app-credentials
|
||||
namespace: mcp10x
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: mcp10x/app-credentials
|
||||
destination:
|
||||
name: app-credentials
|
||||
create: true
|
||||
type: Opaque
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -2,6 +2,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
resources:
|
||||
- mcp10x.yaml
|
||||
- vault-auth.yaml
|
||||
- app-credentials-vault.yaml
|
||||
# Removed: forte10x-app-credentials-sealed.yaml (migrated to VSO)
|
||||
- forte10x-app-credentials-sealed.yaml
|
||||
|
||||
@@ -1,20 +0,0 @@
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: vault-auth-mcp10x
|
||||
namespace: mcp10x
|
||||
---
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultAuth
|
||||
metadata:
|
||||
name: vault-auth
|
||||
namespace: mcp10x
|
||||
spec:
|
||||
method: kubernetes
|
||||
mount: kubernetes
|
||||
kubernetes:
|
||||
role: ns-mcp10x
|
||||
serviceAccount: vault-auth-mcp10x
|
||||
audiences:
|
||||
- vault
|
||||
@@ -2,6 +2,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
resources:
|
||||
- musicman.yaml
|
||||
- vault-auth.yaml
|
||||
- musicman-credentials-vault.yaml
|
||||
# Removed: musicman-credentials.yaml (migrated to VSO)
|
||||
- musicman-credentials.yaml
|
||||
|
||||
@@ -1,15 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: musicman-credentials
|
||||
namespace: music-man
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: music-man/musicman-credentials
|
||||
destination:
|
||||
name: musicman-credentials
|
||||
create: true
|
||||
type: Opaque
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -1,20 +0,0 @@
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: vault-auth-music-man
|
||||
namespace: music-man
|
||||
---
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultAuth
|
||||
metadata:
|
||||
name: vault-auth
|
||||
namespace: music-man
|
||||
spec:
|
||||
method: kubernetes
|
||||
mount: kubernetes
|
||||
kubernetes:
|
||||
role: ns-music-man
|
||||
serviceAccount: vault-auth-music-man
|
||||
audiences:
|
||||
- vault
|
||||
@@ -2,6 +2,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
resources:
|
||||
- ts-mcp.yaml
|
||||
- vault-auth.yaml
|
||||
- ts-mcp-secrets-vault.yaml
|
||||
# Removed: ts-mcp-secrets-sealed.yaml (migrated to VSO)
|
||||
- ts-mcp-secrets-sealed.yaml
|
||||
|
||||
@@ -1,14 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: ts-mcp-secrets
|
||||
namespace: ts-mcp
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: ts-mcp/ts-mcp-secrets
|
||||
destination:
|
||||
name: ts-mcp-secrets
|
||||
create: true
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -1,20 +0,0 @@
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: vault-auth-ts-mcp
|
||||
namespace: ts-mcp
|
||||
---
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultAuth
|
||||
metadata:
|
||||
name: vault-auth
|
||||
namespace: ts-mcp
|
||||
spec:
|
||||
method: kubernetes
|
||||
mount: kubernetes
|
||||
kubernetes:
|
||||
role: ns-ts-mcp
|
||||
serviceAccount: vault-auth-ts-mcp
|
||||
audiences:
|
||||
- vault
|
||||
@@ -3,7 +3,6 @@ kind: Kustomization
|
||||
resources:
|
||||
- ../../base
|
||||
- dbunk-demo
|
||||
- feedback
|
||||
|
||||
# No patches needed — base already has "upc-dev" paths
|
||||
# upc-dev is the default/base cluster
|
||||
|
||||
@@ -1,15 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: argocd-notifications-secret
|
||||
namespace: argocd
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: argocd/argocd-notifications-secret
|
||||
destination:
|
||||
name: argocd-notifications-secret
|
||||
create: true
|
||||
type: Opaque
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -1,16 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: forte-helm-repo
|
||||
namespace: argocd
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: argocd/forte-helm-repo
|
||||
destination:
|
||||
name: forte-helm-repo
|
||||
create: true
|
||||
labels:
|
||||
argocd.argoproj.io/secret-type: repository
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -1,17 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: forte10x-repo-creds
|
||||
namespace: argocd
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: argocd/forte10x-repo-creds
|
||||
destination:
|
||||
name: forte10x-repo-creds
|
||||
create: true
|
||||
type: Opaque
|
||||
labels:
|
||||
argocd.argoproj.io/secret-type: repository
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -12,6 +12,18 @@ spec:
|
||||
privateKeySecretRef:
|
||||
name: letsencrypt-staging-key
|
||||
solvers:
|
||||
# DNS-01 solver for wildcard certificates (*.example.com)
|
||||
- dns01:
|
||||
cloudflare:
|
||||
email: danijels@gmail.com
|
||||
apiTokenSecretRef:
|
||||
name: cloudflare-api-token-secret
|
||||
key: api-token
|
||||
selector:
|
||||
dnsNames:
|
||||
- '*.example.com'
|
||||
- 'example.com'
|
||||
# HTTP-01 fallback for non-wildcard certificates
|
||||
- http01:
|
||||
ingress:
|
||||
class: traefik
|
||||
@@ -30,6 +42,116 @@ spec:
|
||||
privateKeySecretRef:
|
||||
name: letsencrypt-prod-key
|
||||
solvers:
|
||||
# DNS-01 solver for wildcard certificates (*.example.com)
|
||||
- dns01:
|
||||
cloudflare:
|
||||
email: danijels@gmail.com
|
||||
apiTokenSecretRef:
|
||||
name: cloudflare-api-token-secret
|
||||
key: api-token
|
||||
selector:
|
||||
dnsNames:
|
||||
- '*.example.com'
|
||||
- 'example.com'
|
||||
# HTTP-01 fallback for non-wildcard certificates
|
||||
- http01:
|
||||
ingress:
|
||||
class: traefik
|
||||
|
||||
# =============================================================================
|
||||
# DNS PROVIDER EXAMPLES - Uncomment and configure based on your provider:
|
||||
# =============================================================================
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
# Option 1: Cloudflare (recommended - supports API tokens with limited scope)
|
||||
# -----------------------------------------------------------------------------
|
||||
# Create secret with: kubectl create secret generic cloudflare-api-token-secret \
|
||||
# --from-literal=api-token=YOUR_CLOUDFLARE_API_TOKEN -n cert-manager
|
||||
#
|
||||
# dns01:
|
||||
# cloudflare:
|
||||
# email: your-cloudflare-email@example.com
|
||||
# apiTokenSecretRef:
|
||||
# name: cloudflare-api-token-secret
|
||||
# key: api-token
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
# Option 2: AWS Route53
|
||||
# -----------------------------------------------------------------------------
|
||||
# Create secret with: kubectl create secret generic route53-credentials \
|
||||
# --from-literal=secret-access-key=YOUR_SECRET_KEY -n cert-manager
|
||||
#
|
||||
# dns01:
|
||||
# route53:
|
||||
# region: us-east-1
|
||||
# hostedZoneID: ZXXXXXXXXXXXXX # Optional: auto-detected if not specified
|
||||
# accessKeyID: YOUR_ACCESS_KEY_ID
|
||||
# secretAccessKeySecretRef:
|
||||
# name: route53-credentials
|
||||
# key: secret-access-key
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
# Option 3: Azure DNS
|
||||
# -----------------------------------------------------------------------------
|
||||
# Create secret with: kubectl create secret generic azuredns-config \
|
||||
# --from-literal=client-secret=YOUR_CLIENT_SECRET -n cert-manager
|
||||
#
|
||||
# dns01:
|
||||
# azureDNS:
|
||||
# subscriptionID: YOUR_SUBSCRIPTION_ID
|
||||
# resourceGroupName: YOUR_RESOURCE_GROUP
|
||||
# hostedZoneName: example.com
|
||||
# environment: AzurePublicCloud
|
||||
# managedIdentity:
|
||||
# clientID: YOUR_MANAGED_IDENTITY_CLIENT_ID # For AKS with pod identity
|
||||
# # OR use service principal:
|
||||
# # clientID: YOUR_SERVICE_PRINCIPAL_CLIENT_ID
|
||||
# # clientSecretSecretRef:
|
||||
# # name: azuredns-config
|
||||
# # key: client-secret
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
# Option 4: Google Cloud DNS
|
||||
# -----------------------------------------------------------------------------
|
||||
# Create secret with service account JSON key:
|
||||
# kubectl create secret generic clouddns-service-account \
|
||||
# --from-file=service-account.json=path/to/key.json -n cert-manager
|
||||
#
|
||||
# dns01:
|
||||
# cloudDNS:
|
||||
# project: YOUR_GCP_PROJECT_ID
|
||||
# hostedZoneName: example-com # Managed zone name in Cloud DNS
|
||||
# serviceAccountSecretRef:
|
||||
# name: clouddns-service-account
|
||||
# key: service-account.json
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
# Option 5: GoDaddy
|
||||
# -----------------------------------------------------------------------------
|
||||
# Requires external webhook: https://github.com/snowdrop/godaddy-webhook
|
||||
#
|
||||
# dns01:
|
||||
# webhook:
|
||||
# groupName: acme.yourcompany.com
|
||||
# solverName: godaddy
|
||||
# config:
|
||||
# apiKeySecretRef:
|
||||
# name: godaddy-api-credentials
|
||||
# key: api-key
|
||||
# apiSecretSecretRef:
|
||||
# name: godaddy-api-credentials
|
||||
# key: api-secret
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
# Option 6: Manual/Dynamic DNS (for homelab)
|
||||
# -----------------------------------------------------------------------------
|
||||
# Requires RFC2136 provider or external webhook
|
||||
#
|
||||
# dns01:
|
||||
# rfc2136:
|
||||
# nameserver: your-dns-server.example.com
|
||||
# tsigKeyName: cert-manager-key
|
||||
# tsigAlgorithm: HMACSHA256
|
||||
# tsigSecretSecretRef:
|
||||
# name: tsig-secret
|
||||
# key: secret
|
||||
@@ -1,17 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: mcp10x-repo-creds
|
||||
namespace: argocd
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: argocd/mcp10x-repo-creds
|
||||
destination:
|
||||
name: mcp10x-repo-creds
|
||||
create: true
|
||||
type: Opaque
|
||||
labels:
|
||||
argocd.argoproj.io/secret-type: repository
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -245,12 +245,6 @@ spec:
|
||||
secretKeyRef:
|
||||
name: "{{ request.object.metadata.annotations.\"policies.forteapps.io/auth-oidc-credentials-secret\" || 'auth-oidc' }}"
|
||||
key: "{{ request.object.metadata.annotations.\"policies.forteapps.io/auth-oidc-credentials-secret-key\" || 'client-secret' }}"
|
||||
- name: AUTH_OIDC_IDP_HINT
|
||||
value: "{{ request.object.metadata.annotations.\"policies.forteapps.io/auth-oidc-idp-hint\" || '' }}"
|
||||
- name: AUTH_OIDC_BROKER_ALIAS
|
||||
value: "{{ request.object.metadata.annotations.\"policies.forteapps.io/auth-oidc-broker-alias\" || '' }}"
|
||||
- name: AUTH_OIDC_BROKER_TOKEN_HEADER
|
||||
value: "{{ request.object.metadata.annotations.\"policies.forteapps.io/auth-oidc-broker-token-header\" || '' }}"
|
||||
resources:
|
||||
limits:
|
||||
cpu: 50m
|
||||
@@ -330,8 +324,6 @@ spec:
|
||||
value: "{{ request.object.metadata.annotations.\"policies.forteapps.io/auth-public-paths\" || '/healthz' }}"
|
||||
- name: AUTH_MCP_SCOPES_SUPPORTED
|
||||
value: "{{ request.object.metadata.annotations.\"policies.forteapps.io/auth-mcp-scopes\" || 'profile' }}"
|
||||
- name: AUTH_MCP_IDP_HINT
|
||||
value: "{{ request.object.metadata.annotations.\"policies.forteapps.io/auth-mcp-idp-hint\" || '' }}"
|
||||
resources:
|
||||
limits:
|
||||
cpu: 50m
|
||||
|
||||
@@ -1,40 +0,0 @@
|
||||
apiVersion: kyverno.io/v1
|
||||
kind: ClusterPolicy
|
||||
metadata:
|
||||
name: require-labels
|
||||
annotations:
|
||||
policies.kyverno.io/title: Require Labels
|
||||
policies.kyverno.io/category: Best Practices
|
||||
policies.kyverno.io/minversion: 1.6.0
|
||||
policies.kyverno.io/severity: medium
|
||||
policies.kyverno.io/subject: Pod, Label
|
||||
policies.kyverno.io/description: Define and use labels that identify semantic attributes of your application or Deployment. A common set of labels allows tools to work collaboratively, describing objects in a common manner that all tools can understand. The recommended labels describe applications in a way that can be queried. This policy validates that the label `app.kubernetes.io/name` is specified with some value.
|
||||
spec:
|
||||
validationFailureAction: Audit
|
||||
background: true
|
||||
rules:
|
||||
- name: check-for-labels
|
||||
skipBackgroundRequests: true
|
||||
exclude:
|
||||
any:
|
||||
- resources:
|
||||
namespaces:
|
||||
- kube-system
|
||||
- istio-system
|
||||
- argocd
|
||||
- cert-manager
|
||||
- monitoring
|
||||
- secrets
|
||||
- kyverno
|
||||
match:
|
||||
any:
|
||||
- resources:
|
||||
kinds:
|
||||
- Pod
|
||||
validate:
|
||||
message: The label `app.kubernetes.io/name` is required.
|
||||
allowExistingViolations: true
|
||||
pattern:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: "?*"
|
||||
@@ -1,20 +0,0 @@
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: vault-auth-argocd
|
||||
namespace: argocd
|
||||
---
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultAuth
|
||||
metadata:
|
||||
name: vault-auth
|
||||
namespace: argocd
|
||||
spec:
|
||||
method: kubernetes
|
||||
mount: kubernetes
|
||||
kubernetes:
|
||||
role: ns-argocd
|
||||
serviceAccount: vault-auth-argocd
|
||||
audiences:
|
||||
- vault
|
||||
92
cluster-resources/wildcard-certificate-example.yaml
Normal file
92
cluster-resources/wildcard-certificate-example.yaml
Normal file
@@ -0,0 +1,92 @@
|
||||
---
|
||||
# Example: Wildcard Certificate for *.example.com
|
||||
# This creates a certificate that covers ALL subdomains of example.com
|
||||
apiVersion: cert-manager.io/v1
|
||||
kind: Certificate
|
||||
metadata:
|
||||
name: wildcard-example-com
|
||||
namespace: default # Change to your application's namespace
|
||||
spec:
|
||||
# The secret where the TLS certificate will be stored
|
||||
secretName: wildcard-example-com-tls
|
||||
|
||||
# Use the production issuer (use letsencrypt-staging for testing)
|
||||
issuerRef:
|
||||
name: letsencrypt-prod
|
||||
kind: ClusterIssuer
|
||||
|
||||
# DNS names this certificate will cover
|
||||
# Both wildcard AND apex domain are recommended
|
||||
dnsNames:
|
||||
- '*.example.com' # Covers: app.example.com, api.example.com, etc.
|
||||
- 'example.com' # Also include apex domain explicitly
|
||||
|
||||
# Optional: Configure certificate duration and renewal
|
||||
duration: 2160h0m0s # 90 days (Let's Encrypt default)
|
||||
renewBefore: 720h0m0s # Renew 30 days before expiry
|
||||
|
||||
# Optional: Private key settings
|
||||
privateKey:
|
||||
algorithm: RSA
|
||||
encoding: PKCS1
|
||||
size: 4096
|
||||
|
||||
---
|
||||
# Example: Using the wildcard certificate with a Traefik IngressRoute
|
||||
apiVersion: traefik.containo.us/v1alpha1
|
||||
kind: IngressRoute
|
||||
metadata:
|
||||
name: app-ingress
|
||||
namespace: default
|
||||
spec:
|
||||
entryPoints:
|
||||
- websecure
|
||||
routes:
|
||||
# Match any subdomain - the wildcard cert covers all of them
|
||||
- match: Host(`app.example.com`) || Host(`api.example.com`) || Host(`www.example.com`)
|
||||
kind: Rule
|
||||
services:
|
||||
- name: my-service
|
||||
port: 80
|
||||
tls:
|
||||
# Reference the secret created by the Certificate
|
||||
secretName: wildcard-example-com-tls
|
||||
|
||||
---
|
||||
# Example: Using wildcard certificate with standard Kubernetes Ingress
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: wildcard-ingress
|
||||
namespace: default
|
||||
annotations:
|
||||
cert-manager.io/cluster-issuer: "letsencrypt-prod"
|
||||
traefik.ingress.kubernetes.io/router.entrypoints: websecure
|
||||
traefik.ingress.kubernetes.io/router.tls: "true"
|
||||
spec:
|
||||
tls:
|
||||
- hosts:
|
||||
- '*.example.com'
|
||||
- 'example.com'
|
||||
secretName: wildcard-example-com-tls
|
||||
rules:
|
||||
- host: app.example.com
|
||||
http:
|
||||
paths:
|
||||
- path: /
|
||||
pathType: Prefix
|
||||
backend:
|
||||
service:
|
||||
name: app-service
|
||||
port:
|
||||
number: 80
|
||||
- host: api.example.com
|
||||
http:
|
||||
paths:
|
||||
- path: /
|
||||
pathType: Prefix
|
||||
backend:
|
||||
service:
|
||||
name: api-service
|
||||
port:
|
||||
number: 80
|
||||
@@ -17,7 +17,9 @@
|
||||
"claude-code@latest",
|
||||
"go@latest",
|
||||
"dotnet-sdk@latest",
|
||||
"opentofu@1.11.6"
|
||||
"opentofu@1.11.6",
|
||||
"_1password@latest",
|
||||
"github-cli@latest"
|
||||
],
|
||||
"shell": {
|
||||
"init_hook": [
|
||||
|
||||
@@ -60,16 +60,18 @@ If you do need cluster access, install:
|
||||
curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl"
|
||||
```
|
||||
|
||||
2. **vault** CLI - For managing secrets in HashiCorp Vault
|
||||
2. **kubeseal** - For sealing secrets
|
||||
```bash
|
||||
# macOS
|
||||
brew install hashicorp/tap/vault
|
||||
brew install kubeseal
|
||||
|
||||
# Windows
|
||||
choco install vault
|
||||
choco install kubeseal
|
||||
|
||||
# Linux
|
||||
# See https://developer.hashicorp.com/vault/install
|
||||
wget https://github.com/bitnami-labs/sealed-secrets/releases/download/v0.24.0/kubeseal-0.24.0-linux-amd64.tar.gz
|
||||
tar -xvzf kubeseal-0.24.0-linux-amd64.tar.gz
|
||||
sudo mv kubeseal /usr/local/bin/
|
||||
```
|
||||
|
||||
3. **Git** - Version control
|
||||
@@ -632,100 +634,115 @@ git push
|
||||
|
||||
### Understanding Secret Management
|
||||
|
||||
Secrets are managed via **HashiCorp Vault** and synced to Kubernetes by the **Vault Secrets Operator (VSO)**. See [Vault Secrets Operator Reference](vault-secrets-operator.md) for full details.
|
||||
|
||||
**NEVER commit plain secret values to Git.** Only VaultStaticSecret CRD manifests are committed.
|
||||
**NEVER commit plain secrets to Git.** We use **Sealed Secrets** to encrypt secrets before committing.
|
||||
|
||||
### Creating a New Secret
|
||||
|
||||
#### Step 1: Write Secret to Vault
|
||||
#### Step 1: Create Plain Secret Locally
|
||||
|
||||
```bash
|
||||
vault kv put kv/myapp/myapp-credentials \
|
||||
API_KEY=your-secret-key-here \
|
||||
DB_PASSWORD=super-secret-password
|
||||
cd ~/dev/k8s/launchpad
|
||||
|
||||
# Create secret in private/ folder (Git-ignored)
|
||||
kubectl create secret generic myapp-credentials \
|
||||
--from-literal=API_KEY=your-secret-key-here \
|
||||
--from-literal=DB_PASSWORD=super-secret-password \
|
||||
--dry-run=client -o yaml > private/myapp-credentials.yaml
|
||||
```
|
||||
|
||||
#### Step 2: Create VaultStaticSecret CRD
|
||||
**DO NOT commit this file!** It's in `private/` which is Git-ignored.
|
||||
|
||||
Create a YAML file (e.g., `apps/base/myapp/myapp-credentials-vault.yaml`):
|
||||
#### Step 2: Seal the Secret
|
||||
|
||||
```yaml
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: myapp-credentials
|
||||
namespace: myapp
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: myapp/myapp-credentials
|
||||
destination:
|
||||
name: myapp-credentials
|
||||
create: true
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
```
|
||||
|
||||
#### Step 3: Add VaultAuth (if new namespace)
|
||||
|
||||
If this is a new namespace, also create a `vault-auth.yaml` with a ServiceAccount and VaultAuth CRD. See [VSO Reference](vault-secrets-operator.md#vaultauth) for template.
|
||||
|
||||
#### Step 4: Commit and Push
|
||||
Seal your secret:
|
||||
|
||||
```bash
|
||||
git add apps/base/myapp/myapp-credentials-vault.yaml
|
||||
git commit -m "Add myapp credentials (VSO)"
|
||||
kubeseal --format=yaml \
|
||||
--namespace=myapp \
|
||||
< private/myapp-credentials.yaml \
|
||||
> secrets/myapp-credentials-sealed.yaml
|
||||
```
|
||||
|
||||
#### Step 3: Commit Sealed Secret
|
||||
|
||||
```bash
|
||||
git add secrets/myapp-credentials-sealed.yaml
|
||||
git commit -m "Add myapp credentials (sealed)"
|
||||
git push
|
||||
```
|
||||
|
||||
ArgoCD syncs the CRD, VSO creates the K8s Secret.
|
||||
|
||||
#### Step 5: Reference Secret in Application
|
||||
#### Step 4: Reference Secret in Application
|
||||
|
||||
Update your `helm-prod-values/myapp/values.yaml`:
|
||||
|
||||
```yaml
|
||||
app:
|
||||
envSecretName: "myapp-credentials" # VSO creates this K8s Secret
|
||||
envSecretName: "myapp-credentials" # References the SealedSecret
|
||||
```
|
||||
|
||||
### Updating / Rotating a Secret
|
||||
|
||||
**No git commit needed** — just update in Vault:
|
||||
|
||||
Commit and push:
|
||||
```bash
|
||||
vault kv put kv/myapp/myapp-credentials \
|
||||
API_KEY=new-key-here \
|
||||
DB_PASSWORD=new-password
|
||||
cd ~/dev/k8s/helm-prod-values
|
||||
git add myapp/values.yaml
|
||||
git commit -m "Reference myapp credentials"
|
||||
git push
|
||||
```
|
||||
|
||||
VSO picks up changes within 30 seconds. Restart pods if they don't watch for secret updates:
|
||||
### Updating a Secret
|
||||
|
||||
To update an existing secret:
|
||||
|
||||
```bash
|
||||
# 1. Create new version of secret
|
||||
kubectl create secret generic myapp-credentials \
|
||||
--from-literal=API_KEY=new-key-here \
|
||||
--from-literal=DB_PASSWORD=new-password \
|
||||
--dry-run=client -o yaml > private/myapp-credentials.yaml
|
||||
|
||||
# 2. Seal it
|
||||
kubeseal --format=yaml \
|
||||
--namespace=myapp \
|
||||
< private/myapp-credentials.yaml \
|
||||
> secrets/myapp-credentials-sealed.yaml
|
||||
|
||||
# 3. Commit sealed version
|
||||
git add secrets/myapp-credentials-sealed.yaml
|
||||
git commit -m "Update myapp credentials"
|
||||
git push
|
||||
|
||||
# 4. Restart pods to pick up new secret
|
||||
kubectl rollout restart deployment myapp -n myapp
|
||||
```
|
||||
|
||||
### Secret Best Practices
|
||||
|
||||
- Write secrets to Vault via UI or CLI — never commit values to Git
|
||||
- Use meaningful secret names matching the KV path convention: `kv/{namespace}/{secret-name}`
|
||||
✅ **DO**:
|
||||
- Store secrets in `private/` folder locally
|
||||
- Always seal secrets before committing
|
||||
- Delete plain secrets after sealing
|
||||
- Use meaningful secret names
|
||||
- Document what each secret contains
|
||||
- Use Vault's versioning for audit trail
|
||||
|
||||
❌ **DON'T**:
|
||||
- Commit plain secrets to Git
|
||||
- Share secrets via Slack/email
|
||||
- Hard-code secrets in code
|
||||
- Use the same secret across multiple environments
|
||||
- Store secrets in Docker images
|
||||
|
||||
### Where Secrets Are Stored
|
||||
|
||||
```
|
||||
┌──────────────────────────────────────────────────────────────────┐
|
||||
│ Location │ Content │ In Git? │
|
||||
├────────────────────────────┼─────────────────────────┼──────────┤
|
||||
│ Vault KV (kv/{ns}/{name}) │ Secret values │ ❌ NO │
|
||||
│ VaultStaticSecret CRD │ Sync config (no values)│ ✅ YES │
|
||||
│ Kubernetes cluster │ K8s Secret (synced) │ N/A │
|
||||
└──────────────────────────────────────────────────────────────────┘
|
||||
┌─────────────────────────────────────────────────────────────┐
|
||||
│ Location │ Content │ Committed?│
|
||||
├──────────────────────────┼────────────────────┼────────────┤
|
||||
│ private/ │ Plain secrets │ ❌ NO │
|
||||
│ secrets/ │ Sealed secrets │ ✅ YES │
|
||||
│ Kubernetes cluster │ Unsealed secrets │ N/A │
|
||||
└─────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
**Vault Secrets Operator** syncs secrets from Vault to K8s automatically (30s refresh).
|
||||
**Sealed Secrets Controller** in the cluster decrypts sealed secrets automatically.
|
||||
|
||||
---
|
||||
|
||||
@@ -859,13 +876,28 @@ In your identity provider (e.g., Keycloak):
|
||||
#### Step 2: Create OIDC Secret
|
||||
|
||||
```bash
|
||||
# Write OIDC secret to Vault
|
||||
vault kv put kv/myapp/auth-oidc \
|
||||
client-secret=your-oidc-client-secret \
|
||||
cookie-secret=$(openssl rand -hex 32)
|
||||
# Create plain secret
|
||||
kubectl create secret generic auth-oidc \
|
||||
--from-literal=client-secret=your-oidc-client-secret \
|
||||
--from-literal=cookie-secret=$(openssl rand -hex 32) \
|
||||
--namespace=myapp \
|
||||
--dry-run=client -o yaml > private/myapp-auth-oidc.yaml
|
||||
|
||||
# Create VaultStaticSecret CRD (see docs/vault-secrets-operator.md for template)
|
||||
# Add to apps/base/myapp/auth-oidc-vault.yaml and commit
|
||||
# Seal it
|
||||
kubeseal --format=yaml \
|
||||
--cert=pub-cert.pem \
|
||||
--namespace=myapp \
|
||||
< private/myapp-auth-oidc.yaml \
|
||||
> secrets/myapp-auth-oidc-sealed.yaml
|
||||
|
||||
# Commit sealed secret
|
||||
cd ~/dev/k8s/launchpad
|
||||
git add secrets/myapp-auth-oidc-sealed.yaml
|
||||
git commit -m "Add OIDC secrets for myapp"
|
||||
git push
|
||||
|
||||
# Clean up
|
||||
rm private/myapp-auth-oidc.yaml
|
||||
```
|
||||
|
||||
#### Step 3: Configure Helm Values
|
||||
@@ -1095,13 +1127,16 @@ ingress:
|
||||
host: web-app.forteapps.net
|
||||
```
|
||||
|
||||
**With Vault OIDC secret**:
|
||||
**With sealed OIDC secret**:
|
||||
```bash
|
||||
# Write OIDC secret to Vault
|
||||
vault kv put kv/web-app/auth-oidc \
|
||||
client-secret=super-secret-value \
|
||||
cookie-secret=$(openssl rand -hex 32)
|
||||
# Then create VaultStaticSecret CRD — see docs/vault-secrets-operator.md
|
||||
# Create and seal secret
|
||||
kubectl create secret generic auth-oidc \
|
||||
--from-literal=client-secret=super-secret-value \
|
||||
--from-literal=cookie-secret=$(openssl rand -hex 32) \
|
||||
--namespace=web-app \
|
||||
--dry-run=client -o yaml | \
|
||||
kubeseal --format=yaml --cert=pub-cert.pem --namespace=web-app \
|
||||
> secrets/web-app-auth-oidc-sealed.yaml
|
||||
```
|
||||
|
||||
#### Example 3: MCP Server with OAuth 2.0
|
||||
@@ -1229,7 +1264,7 @@ kubectl logs -n myapp <pod-name> -c authn
|
||||
- Use token auth for service-to-service communication
|
||||
- Rotate tokens and secrets regularly
|
||||
- Use strong random tokens (32+ bytes)
|
||||
- Store client secrets in Vault
|
||||
- Store client secrets in SealedSecrets
|
||||
- Test authentication before deploying to production
|
||||
- Document which tokens/users have access
|
||||
|
||||
@@ -1301,16 +1336,34 @@ stringData:
|
||||
|
||||
| Field | Required | Description |
|
||||
|-------|----------|-------------|
|
||||
| `clientId` | Yes | Keycloak client ID |
|
||||
| `name` | Yes | Display name in Keycloak |
|
||||
| `redirectUris` | Yes | Allowed redirect URIs |
|
||||
| `webOrigins` | Yes | Allowed web origins (CORS) |
|
||||
| `defaultClientScopes` | No | Scopes (default: `["openid", "email", "profile"]`) |
|
||||
| `protocolMappers` | No | Custom claim mappers (default: `[]`) |
|
||||
| `secret.namespace` | No | Namespace for the credential Secret (default: source namespace) |
|
||||
| `secret.name` | No | Name of the credential Secret (default: `<clientId>-oidc-credentials`) |
|
||||
| `secret.keys.clientId` | No | Key name for client ID in credential Secret (default: `client-id`) |
|
||||
| `secret.keys.clientSecret` | No | Key name for client secret in credential Secret (default: `client-secret`) |
|
||||
| `clientId` | Yes | Keycloak client ID (must be unique in realm) |
|
||||
| `name` | Yes | Display name in Keycloak UI |
|
||||
| `redirectUris` | Yes | Allowed OAuth redirect URLs (supports wildcards like `/*`) |
|
||||
| `webOrigins` | Yes | Allowed CORS origins |
|
||||
| `defaultClientScopes` | No | OIDC scopes (default: `["openid", "email", "profile"]`) |
|
||||
| `protocolMappers` | No | Custom claim mappers for tokens (see examples below) |
|
||||
| `secret.namespace` | No | Target namespace for credentials (default: `source-namespace` annotation value) |
|
||||
| `secret.name` | No | Credential Secret name (default: `<clientId>-oidc-credentials`) |
|
||||
| `secret.keys.clientId` | No | Key name for client ID (default: `client-id`) |
|
||||
| `secret.keys.clientSecret` | No | Key name for client secret (default: `client-secret`) |
|
||||
|
||||
**Protocol Mappers Example**:
|
||||
```json
|
||||
"protocolMappers": [
|
||||
{
|
||||
"name": "groups",
|
||||
"protocol": "openid-connect",
|
||||
"protocolMapper": "oidc-group-membership-mapper",
|
||||
"config": {
|
||||
"claim.name": "groups",
|
||||
"full.path": "false",
|
||||
"id.token.claim": "true",
|
||||
"access.token.claim": "true",
|
||||
"userinfo.token.claim": "true"
|
||||
}
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
#### Step 2: Reference the Credential Secret
|
||||
|
||||
@@ -1533,22 +1586,22 @@ curl http://localhost:8080
|
||||
|
||||
#### Problem: Secret not found
|
||||
|
||||
**Check VSO sync status:**
|
||||
**Check if SealedSecret exists:**
|
||||
```bash
|
||||
kubectl get vaultstaticsecret -n myapp
|
||||
kubectl get sealedsecret -n myapp
|
||||
kubectl get secret -n myapp
|
||||
```
|
||||
|
||||
**Solutions:**
|
||||
```bash
|
||||
# Check VaultAuth is authenticated
|
||||
kubectl get vaultauth -n myapp
|
||||
# Check if secret is in Git
|
||||
ls -l secrets/myapp-credentials-sealed.yaml
|
||||
|
||||
# Check VaultStaticSecret events
|
||||
kubectl describe vaultstaticsecret myapp-credentials -n myapp
|
||||
# Re-apply sealed secret
|
||||
kubectl apply -f secrets/myapp-credentials-sealed.yaml
|
||||
|
||||
# Verify secret exists in Vault
|
||||
vault kv get kv/myapp/myapp-credentials
|
||||
# Check sealed-secrets-controller logs
|
||||
kubectl logs -n kube-system deployment/sealed-secrets-controller
|
||||
```
|
||||
|
||||
#### Problem: Secret exists but pods can't access it
|
||||
@@ -1659,7 +1712,7 @@ If you're stuck:
|
||||
### Secret Management
|
||||
|
||||
✅ **DO**:
|
||||
- Use Vault for all secrets (see docs/vault-secrets-operator.md)
|
||||
- Use kubeseal for all secrets
|
||||
- Store plain secrets in password manager
|
||||
- Rotate secrets regularly
|
||||
- Use different secrets per environment
|
||||
@@ -1711,9 +1764,16 @@ kubectl rollout restart deployment myapp -n myapp
|
||||
# Port-forward to service
|
||||
kubectl port-forward -n myapp service/myapp 8080:3000
|
||||
|
||||
# Write secret to Vault
|
||||
vault kv put kv/myapp/myapp-credentials KEY=value
|
||||
# Create VaultStaticSecret CRD — see docs/vault-secrets-operator.md
|
||||
# Create secret
|
||||
kubectl create secret generic myapp-credentials \
|
||||
--from-literal=KEY=value \
|
||||
--dry-run=client -o yaml > private/myapp-credentials.yaml
|
||||
|
||||
# Seal secret
|
||||
kubeseal --format=yaml \
|
||||
--cert=pub-cert.pem \
|
||||
< private/myapp-credentials.yaml \
|
||||
> secrets/myapp-credentials-sealed.yaml
|
||||
```
|
||||
|
||||
### Repository Locations
|
||||
|
||||
@@ -115,9 +115,30 @@ This Kubernetes cluster uses a **GitOps approach** powered by **ArgoCD**, where
|
||||
|
||||
```
|
||||
launchpad/
|
||||
├── bootstrap.sh # Cluster initialization script
|
||||
├── _app-of-apps-upc-dev.yaml # Root ArgoCD Application (upc-dev cluster)
|
||||
├── _app-of-apps-upc-prod.yaml # Root ArgoCD Application (upc-prod cluster)
|
||||
├── bootstrap.sh # Cluster initialization (ArgoCD + GitOps)
|
||||
├── _app-of-apps-{cluster}.yaml # Root ArgoCD Application (per cluster)
|
||||
│
|
||||
├── .tofu/ # Infrastructure provisioning (OpenTofu)
|
||||
│ ├── platforms/ # Per-platform IaC
|
||||
│ │ ├── aks/ # Azure AKS
|
||||
│ │ │ ├── modules/cluster/ # Reusable AKS module
|
||||
│ │ │ ├── dev/ # tofu root for aks-dev
|
||||
│ │ │ ├── prod/ # tofu root for aks-prod
|
||||
│ │ │ └── workload/ # workload cluster (no data services)
|
||||
│ │ ├── eks/ # AWS EKS (same structure)
|
||||
│ │ ├── gke/ # GCP GKE
|
||||
│ │ └── upc/ # UpCloud
|
||||
│ ├── configs/ # Platform credentials (git-ignored)
|
||||
│ │ └── {platform}.env.example # Template per platform
|
||||
│ └── scripts/
|
||||
│ ├── setup-cluster.sh # ./setup-cluster.sh <cluster> [--plan|--auto]
|
||||
│ ├── teardown-cluster.sh # ./teardown-cluster.sh <cluster>
|
||||
│ └── get-kubeconfig.sh # ./get-kubeconfig.sh <cluster>
|
||||
│
|
||||
├── clusters/ # Cluster metadata YAML (domain, IPs, etc.)
|
||||
│ ├── aks-dev.yaml
|
||||
│ ├── upc-dev.yaml
|
||||
│ └── ...
|
||||
│
|
||||
├── infra/ # Infrastructure ArgoCD Applications (Kustomize)
|
||||
│ ├── base/ # Base Application manifests (one dir per component)
|
||||
|
||||
@@ -188,15 +188,13 @@ Save the following file in private/ (gitignored) folder as secret.yaml
|
||||
<paste your private key here>
|
||||
project: default
|
||||
```
|
||||
Write the secret to Vault:
|
||||
Seal the secret using `kubeseal` command
|
||||
```bash
|
||||
vault kv put kv/argocd/forte-helm-repo \
|
||||
type=git \
|
||||
url=ssh://git@git.forteapps.net:2222/Forte/forte-helm.git \
|
||||
sshPrivateKey="$(cat private/ssh-key)" \
|
||||
project=default
|
||||
kubeseal --format=yaml \
|
||||
--namespace=argocd \
|
||||
< private/secret.yaml \
|
||||
> secrets/forte-helm-repo-secret-sealed.yaml
|
||||
```
|
||||
Then create a VaultStaticSecret CRD with `argocd.argoproj.io/secret-type: repository` label.
|
||||
|
||||
**Step 4: Register Repository in ArgoCD**
|
||||
|
||||
@@ -501,7 +499,7 @@ See [Developer Guide](DEVELOPER-GUIDE.md#deploying-your-first-application) for d
|
||||
**Quick checklist:**
|
||||
- [ ] Create `helm-prod-values/myapp/values.yaml`
|
||||
- [ ] Create `apps/myapp.yaml` in config repo
|
||||
- [ ] Write secrets to Vault and create VaultStaticSecret CRD if needed
|
||||
- [ ] Create SealedSecret if needed
|
||||
- [ ] Commit and push changes
|
||||
- [ ] Verify sync in Slack/ArgoCD
|
||||
- [ ] Configure DNS for domain
|
||||
@@ -672,61 +670,92 @@ db:
|
||||
|
||||
## Secret Management
|
||||
|
||||
Secrets are managed via **HashiCorp Vault** and synced to Kubernetes by the **Vault Secrets Operator (VSO)**. See [Vault Secrets Operator Reference](vault-secrets-operator.md) for full details.
|
||||
|
||||
### Creating Secrets
|
||||
|
||||
#### Step 1: Write to Vault
|
||||
#### Step 1: Get Public Certificate
|
||||
|
||||
```bash
|
||||
# From literal values
|
||||
vault kv put kv/myapp/myapp-credentials \
|
||||
API_KEY=secret123 \
|
||||
DB_PASSWORD=pass456
|
||||
# Fetch sealed-secrets public cert (one-time)
|
||||
kubeseal --fetch-cert \
|
||||
--controller-name=sealed-secrets-controller \
|
||||
--controller-namespace=kube-system \
|
||||
> pub-cert.pem
|
||||
|
||||
# Save this certificate for future use
|
||||
```
|
||||
|
||||
#### Step 2: Create VaultStaticSecret CRD
|
||||
|
||||
```yaml
|
||||
# apps/base/myapp/myapp-credentials-vault.yaml
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: myapp-credentials
|
||||
namespace: myapp
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: myapp/myapp-credentials
|
||||
destination:
|
||||
name: myapp-credentials
|
||||
create: true
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
```
|
||||
|
||||
#### Step 3: Commit CRD
|
||||
#### Step 2: Create Plain Secret
|
||||
|
||||
```bash
|
||||
git add apps/base/myapp/myapp-credentials-vault.yaml
|
||||
git commit -m "Add myapp credentials (VSO)"
|
||||
# Method 1: From literal values
|
||||
kubectl create secret generic myapp-credentials \
|
||||
--from-literal=API_KEY=secret123 \
|
||||
--from-literal=DB_PASSWORD=pass456 \
|
||||
--namespace=myapp \
|
||||
--dry-run=client -o yaml > private/myapp-credentials.yaml
|
||||
|
||||
# Method 2: From file
|
||||
kubectl create secret generic myapp-credentials \
|
||||
--from-file=.env \
|
||||
--namespace=myapp \
|
||||
--dry-run=client -o yaml > private/myapp-credentials.yaml
|
||||
|
||||
# Method 3: From multiple files
|
||||
kubectl create secret generic myapp-credentials \
|
||||
--from-file=api-key.txt \
|
||||
--from-file=db-password.txt \
|
||||
--namespace=myapp \
|
||||
--dry-run=client -o yaml > private/myapp-credentials.yaml
|
||||
```
|
||||
|
||||
#### Step 3: Seal Secret
|
||||
|
||||
```bash
|
||||
kubeseal --format=yaml \
|
||||
--cert=pub-cert.pem \
|
||||
--namespace=myapp \
|
||||
< private/myapp-credentials.yaml \
|
||||
> secrets/myapp-credentials-sealed.yaml
|
||||
```
|
||||
|
||||
#### Step 4: Commit Sealed Secret
|
||||
|
||||
```bash
|
||||
git add secrets/myapp-credentials-sealed.yaml
|
||||
git commit -m "Add myapp credentials"
|
||||
git push
|
||||
|
||||
# Delete plain secret
|
||||
rm private/myapp-credentials.yaml
|
||||
```
|
||||
|
||||
ArgoCD syncs the CRD, VSO creates the K8s Secret automatically.
|
||||
|
||||
### Updating / Rotating Secrets
|
||||
|
||||
**No git commit needed** — just update in Vault:
|
||||
### Updating Secrets
|
||||
|
||||
```bash
|
||||
vault kv put kv/myapp/myapp-credentials \
|
||||
API_KEY=new-secret-key \
|
||||
DB_PASSWORD=new-password
|
||||
# 1. Create new version
|
||||
kubectl create secret generic myapp-credentials \
|
||||
--from-literal=API_KEY=new-secret-key \
|
||||
--from-literal=DB_PASSWORD=new-password \
|
||||
--namespace=myapp \
|
||||
--dry-run=client -o yaml > private/myapp-credentials.yaml
|
||||
|
||||
# VSO picks up changes within 30 seconds
|
||||
# Restart pods if needed
|
||||
# 2. Seal it
|
||||
kubeseal --format=yaml \
|
||||
--cert=pub-cert.pem \
|
||||
--namespace=myapp \
|
||||
< private/myapp-credentials.yaml \
|
||||
> secrets/myapp-credentials-sealed.yaml
|
||||
|
||||
# 3. Commit
|
||||
git add secrets/myapp-credentials-sealed.yaml
|
||||
git commit -m "Update myapp credentials"
|
||||
git push
|
||||
|
||||
# 4. Restart pods to pick up new secret
|
||||
kubectl rollout restart deployment myapp -n myapp
|
||||
|
||||
# 5. Delete plain secret
|
||||
rm private/myapp-credentials.yaml
|
||||
```
|
||||
|
||||
### Viewing Secrets (Unsealed)
|
||||
@@ -803,13 +832,30 @@ OIDC auth requires an `auth-oidc` Secret with two keys:
|
||||
CLIENT_SECRET="your-oidc-client-secret-from-provider"
|
||||
COOKIE_SECRET=$(openssl rand -hex 32)
|
||||
|
||||
# Write to Vault
|
||||
vault kv put kv/myapp/auth-oidc \
|
||||
client-secret=$CLIENT_SECRET \
|
||||
cookie-secret=$COOKIE_SECRET
|
||||
# Create plain secret
|
||||
kubectl create secret generic auth-oidc \
|
||||
--from-literal=client-secret=$CLIENT_SECRET \
|
||||
--from-literal=cookie-secret=$COOKIE_SECRET \
|
||||
--namespace=myapp \
|
||||
--dry-run=client -o yaml > private/myapp-auth-oidc.yaml
|
||||
|
||||
# Create VaultStaticSecret CRD (one-time) and commit
|
||||
# See docs/vault-secrets-operator.md for CRD template
|
||||
# Seal it
|
||||
kubeseal --format=yaml \
|
||||
--cert=pub-cert.pem \
|
||||
--namespace=myapp \
|
||||
< private/myapp-auth-oidc.yaml \
|
||||
> secrets/myapp-auth-oidc-sealed.yaml
|
||||
|
||||
# Apply sealed secret
|
||||
kubectl apply -f secrets/myapp-auth-oidc-sealed.yaml
|
||||
|
||||
# Commit to Git
|
||||
git add secrets/myapp-auth-oidc-sealed.yaml
|
||||
git commit -m "Add OIDC secrets for myapp"
|
||||
git push
|
||||
|
||||
# Clean up
|
||||
rm private/myapp-auth-oidc.yaml
|
||||
```
|
||||
|
||||
#### Rotating Authentication Secrets
|
||||
@@ -836,12 +882,16 @@ kubectl rollout restart deployment myapp -n myapp
|
||||
# Rotate cookie secret (safe - invalidates existing sessions)
|
||||
NEW_COOKIE_SECRET=$(openssl rand -hex 32)
|
||||
|
||||
# Update in Vault — no git commit needed
|
||||
vault kv put kv/myapp/auth-oidc \
|
||||
client-secret=$CLIENT_SECRET \
|
||||
cookie-secret=$NEW_COOKIE_SECRET
|
||||
# Recreate secret
|
||||
kubectl create secret generic auth-oidc \
|
||||
--from-literal=client-secret=$CLIENT_SECRET \
|
||||
--from-literal=cookie-secret=$NEW_COOKIE_SECRET \
|
||||
--namespace=myapp \
|
||||
--dry-run=client -o yaml | \
|
||||
kubeseal --format=yaml --cert=pub-cert.pem --namespace=myapp | \
|
||||
kubectl apply -f -
|
||||
|
||||
# VSO picks up within 30s. Restart pods to use new secret:
|
||||
# Restart to pick up new secret
|
||||
kubectl rollout restart deployment myapp -n myapp
|
||||
```
|
||||
|
||||
@@ -1292,11 +1342,13 @@ kubectl get applications -n argocd -w
|
||||
- pg_dump -U $DB_USER -d $DB_NAME > /backup/dump-$(date +%Y%m%d).sql
|
||||
```
|
||||
|
||||
3. **Vault backup**
|
||||
3. **Sealed Secrets private key backup**
|
||||
```bash
|
||||
# Vault data is stored on PVC — ensure PVC snapshots are configured
|
||||
# For disaster recovery, maintain Vault unseal keys in a secure location
|
||||
# All secrets can be re-seeded from source if needed
|
||||
# Backup sealed-secrets controller private key
|
||||
kubectl get secret -n kube-system sealed-secrets-key \
|
||||
-o yaml > sealed-secrets-key-backup.yaml
|
||||
|
||||
# Store in secure location (password manager, vault)
|
||||
```
|
||||
|
||||
---
|
||||
@@ -1616,7 +1668,7 @@ echo "Remember to delete: $SECRET_FILE"
|
||||
- [ ] Gitea Actions workflow configured
|
||||
- [ ] Helm values created in `helm-prod-values/`
|
||||
- [ ] ArgoCD application manifest created in `apps/`
|
||||
- [ ] Secrets written to Vault and VaultStaticSecret CRD created
|
||||
- [ ] Secrets created and sealed
|
||||
- [ ] DNS record added for domain
|
||||
- [ ] Application synced successfully
|
||||
- [ ] Health check passed
|
||||
|
||||
@@ -72,9 +72,22 @@ Internet
|
||||
|
||||
```
|
||||
launchpad/
|
||||
├── bootstrap.sh # Cluster initialization script
|
||||
├── _app-of-apps-upc-dev.yaml # Root ArgoCD Application (upc-dev)
|
||||
├── _app-of-apps-upc-prod.yaml # Root ArgoCD Application (upc-prod)
|
||||
├── bootstrap.sh # Cluster initialization (ArgoCD + GitOps)
|
||||
├── _app-of-apps-{cluster}.yaml # Root ArgoCD Application (per cluster)
|
||||
│
|
||||
├── .tofu/ # Infrastructure provisioning (OpenTofu)
|
||||
│ ├── platforms/ # Per-platform IaC
|
||||
│ │ ├── aks/ # Azure: modules/cluster/, dev/, prod/, workload/
|
||||
│ │ ├── eks/ # AWS: same structure
|
||||
│ │ ├── gke/ # GCP
|
||||
│ │ └── upc/ # UpCloud
|
||||
│ ├── configs/ # Platform credentials (git-ignored)
|
||||
│ └── scripts/ # setup-cluster.sh, teardown-cluster.sh, get-kubeconfig.sh
|
||||
│
|
||||
├── clusters/ # Cluster metadata YAML
|
||||
│ ├── aks-dev.yaml
|
||||
│ ├── upc-dev.yaml
|
||||
│ └── ...
|
||||
│
|
||||
├── infra/ # Infrastructure applications (Kustomize)
|
||||
│ ├── base/ # One subdirectory per component
|
||||
@@ -1063,6 +1076,52 @@ dind:
|
||||
- Gitea admin panel (`/admin/runners`) — runners show as Online
|
||||
- Create test workflow in `.gitea/workflows/test.yml` — job executes
|
||||
|
||||
### Vaultwarden
|
||||
|
||||
**Chart**: `guerzon/vaultwarden`
|
||||
**Version**: 0.36.4 (app v1.36.0-alpine)
|
||||
**Namespace**: `vaultwarden`
|
||||
|
||||
**Purpose**: Self-hosted Bitwarden-compatible password manager.
|
||||
|
||||
**Configuration**:
|
||||
```yaml
|
||||
# infra/overlays/upc-dev/vaultwarden/ + infra/values/
|
||||
domain: "https://bitwarden.forteapps.net"
|
||||
|
||||
ingress:
|
||||
enabled: true
|
||||
class: "traefik"
|
||||
tls: true
|
||||
tlsSecret: vaultwarden-tls
|
||||
hostname: bitwarden.forteapps.net
|
||||
additionalAnnotations:
|
||||
cert-manager.io/cluster-issuer: letsencrypt-prod
|
||||
|
||||
database:
|
||||
type: postgresql
|
||||
host: vaultwarden-postgresql # StatefulSet in overlay
|
||||
existingSecret: prod-db-creds
|
||||
|
||||
storage:
|
||||
data: 5Gi (ReadWriteOnce)
|
||||
attachments: 5Gi (ReadWriteOnce)
|
||||
```
|
||||
|
||||
**TLS**: cert-manager auto-provisions Let's Encrypt certificate via `letsencrypt-prod` ClusterIssuer (same pattern as Gitea, Grafana, etc).
|
||||
|
||||
**SSO**: Keycloak OIDC via `forte` realm (client ID: `vaultwarden`). Self-service client config Secret (`keycloak-client-vaultwarden`) triggers registrar to create KC client and sync credentials to `vaultwarden-oidc-credentials`. PKCE enabled.
|
||||
|
||||
**Endpoints**:
|
||||
- Web UI: `https://bitwarden.forteapps.net`
|
||||
|
||||
**Database**: Separate ArgoCD Application `vaultwarden-postgresql` (sync-wave `"0"`) deploys PostgreSQL 16 StatefulSet + SealedSecret before Vaultwarden (wave `"1"`). 2Gi PVC. Chart does NOT include a PostgreSQL subchart — must be provisioned separately.
|
||||
|
||||
**Secrets**:
|
||||
- `prod-db-creds` (SealedSecret) — PostgreSQL credentials (`pgusername`, `pgpassword`) + SMTP credentials
|
||||
- `vaultwarden-oidc-credentials` (registrar-managed) — OIDC client ID + secret
|
||||
- `vaultwarden-tls` — auto-managed by cert-manager
|
||||
|
||||
### AI Code Review (ai-review)
|
||||
|
||||
**Type**: Gitea Actions workflow (`.gitea/workflows/ai-review.yaml`)
|
||||
@@ -1141,6 +1200,30 @@ ignore:
|
||||
- Check Gitea Actions tab for workflow run status and logs
|
||||
- Monitor Anthropic usage dashboard for token consumption
|
||||
|
||||
### Keycloak Browser Flow (IdP Auto-Redirect)
|
||||
|
||||
**File**: `infra/values/base/keycloak-values.yaml` (inside `forte-realm.json`)
|
||||
|
||||
The realm uses a custom browser authentication flow (`browser-auto-idp`) that skips the Keycloak login page and redirects directly to the Entra ID identity provider.
|
||||
|
||||
**Flow executions**:
|
||||
|
||||
| Priority | Authenticator | Requirement | Purpose |
|
||||
|----------|--------------|-------------|---------|
|
||||
| 10 | `auth-cookie` | ALTERNATIVE | Reuse existing session (no redirect) |
|
||||
| 20 | `identity-provider-redirector` | ALTERNATIVE | Auto-redirect to `forte-entra` IdP |
|
||||
|
||||
**Key fields in realm JSON**:
|
||||
- `"browserFlow": "browser-auto-idp"` — overrides the default `browser` flow at realm level
|
||||
- `"authenticationFlows"` — defines the custom flow with its executions
|
||||
- `"authenticatorConfig"` — sets `defaultProvider: "forte-entra"` on the redirector
|
||||
|
||||
**Why custom flow**: The default KC browser flow shows a username/password form with an IdP button. Since all authentication is via Entra ID, the custom flow eliminates this step. The `auth-cookie` execution preserves session reuse so returning users aren't redirected again.
|
||||
|
||||
**Important**: The `forte-entra` identity provider must exist in Keycloak (currently configured manually in the KC admin console). If the IdP alias changes, update the `defaultProvider` value in the realm JSON.
|
||||
|
||||
---
|
||||
|
||||
### Keycloak Client Registrar
|
||||
|
||||
**Type**: CronJob (deployed via Keycloak Helm chart `extraDeploy`)
|
||||
@@ -1172,9 +1255,18 @@ ignore:
|
||||
|
||||
**Resources**:
|
||||
- `ServiceAccount`: `keycloak-client-registrar` (namespace: `keycloak`)
|
||||
- `ClusterRole`: `keycloak-client-registrar` (secrets: get/list/create/update/patch; namespaces: get/list)
|
||||
- `ClusterRole`: `keycloak-client-registrar`
|
||||
- Secrets: `get`, `list`, `create`, `update`, `patch`
|
||||
- Namespaces: `get`, `list`
|
||||
- `ClusterRoleBinding`: `keycloak-client-registrar`
|
||||
- `CronJob`: `keycloak-client-registrar`
|
||||
- **Schedule**: `*/2 * * * *` (every 2 minutes)
|
||||
- **Concurrency Policy**: `Forbid` (prevents concurrent runs)
|
||||
- **Backoff Limit**: 3 retries per job
|
||||
- **History**: 1 successful job, 3 failed jobs retained
|
||||
- **Resources**: 50m CPU / 64Mi memory (requests), 200m CPU / 128Mi memory (limits)
|
||||
|
||||
**Container**: Alpine 3.20 with `curl` and `jq` installed
|
||||
|
||||
**Kyverno Policy**: `keycloak-client-config-cloner` — clones labeled Secrets from app namespaces to `keycloak` namespace (see [Kyverno Policies](#kyverno-policies))
|
||||
|
||||
@@ -1384,46 +1476,6 @@ spec:
|
||||
- Adds source tracking annotations (`keycloak.forteapps.net/source-namespace`, `keycloak.forteapps.net/source-name`)
|
||||
- `synchronize: true` — changes to the source Secret are reflected in the clone
|
||||
|
||||
### Keycloak Microsoft/Entra Identity Provider
|
||||
|
||||
**File**: `infra/values/upc-dev/keycloak-values.yaml`
|
||||
**Namespace**: `keycloak`
|
||||
|
||||
**Purpose**: Configures Microsoft Entra (Azure AD) as an external identity provider for the Forte realm, enabling SSO via Microsoft accounts with token storage for downstream API access (e.g., Microsoft Graph).
|
||||
|
||||
**Configuration via keycloakConfigCli**:
|
||||
- IdP alias: `forte-entra`, provider: `microsoft`
|
||||
- Client secret injected from `microsoft-idp-credentials` Secret via `$(env:MS_IDP_CLIENT_SECRET)` syntax
|
||||
- `extraEnvVarsSecret: microsoft-idp-credentials` makes the Secret available as env vars to config-cli
|
||||
|
||||
**Key Configuration Notes**:
|
||||
|
||||
| Field | Location | Notes |
|
||||
|-------|----------|-------|
|
||||
| `tenant` | `config.tenant` | **Must be `tenant`, NOT `tenantId`** — wrong key silently falls back to `common` (multi-tenant) |
|
||||
| `storeToken` | Top-level IdP field | **NOT inside `config`** — enables broker token storage for KC broker API |
|
||||
| `defaultScope` | `config.defaultScope` | Space-separated: `openid email profile User.Read Mail.Send` |
|
||||
| `syncMode` | `config.syncMode` | `IMPORT` — imports user on first login |
|
||||
|
||||
**Token Storage & Broker Access**:
|
||||
- `storeToken: true` persists the Entra access token in Keycloak
|
||||
- Realm role `default-roles-forte` includes composite `broker.read-token` — grants all realm users access to broker token API
|
||||
- Broker token retrievable via: `GET /realms/forte/broker/forte-entra/token`
|
||||
|
||||
**Identity Provider Mappers**:
|
||||
- `forte-entra-email`: Hardcodes `emailVerified=true` for Entra-authenticated users (Entra guarantees email verification)
|
||||
|
||||
**Required Secret** (`microsoft-idp-credentials`):
|
||||
```yaml
|
||||
apiVersion: v1
|
||||
kind: Secret
|
||||
metadata:
|
||||
name: microsoft-idp-credentials
|
||||
namespace: keycloak
|
||||
stringData:
|
||||
MS_IDP_CLIENT_SECRET: "<entra-app-client-secret>"
|
||||
```
|
||||
|
||||
### Default Namespace Blocker
|
||||
|
||||
**File**: `cluster-resources/policies/default-ns-blocker.yaml`
|
||||
|
||||
@@ -1,206 +0,0 @@
|
||||
# Vault Secrets Operator (VSO) Reference
|
||||
|
||||
## Overview
|
||||
|
||||
The platform uses HashiCorp Vault Secrets Operator (VSO) to sync secrets from Vault KV v2 to native Kubernetes Secrets. This replaces the previous SealedSecrets workflow.
|
||||
|
||||
**Key benefit**: Secret values can be rotated via Vault UI/CLI without a git commit. Only new VaultStaticSecret CRDs need to be committed.
|
||||
|
||||
## Architecture
|
||||
|
||||
```
|
||||
Vault (KV v2) VSO K8s Secret
|
||||
kv/{namespace}/{name} --> VaultStaticSecret CRD --> Secret in namespace
|
||||
(polls every 30s)
|
||||
```
|
||||
|
||||
- **Vault**: Standalone instance in `vault` namespace, KV v2 at `kv/`
|
||||
- **VSO**: Deployed in `vault-secrets-operator-system` namespace via ArgoCD
|
||||
- **Auth**: Kubernetes auth method — each namespace has its own ServiceAccount + VaultAuth CRD
|
||||
|
||||
## KV Path Convention
|
||||
|
||||
```
|
||||
kv/{namespace}/{secret-name}
|
||||
```
|
||||
|
||||
Examples:
|
||||
- `kv/homepage/homepage-widget-credentials`
|
||||
- `kv/argocd/forte-helm-repo`
|
||||
- `kv/gitea/gitea-smtp-secret`
|
||||
- `kv/keycloak/keycloak-credentials`
|
||||
|
||||
## Vault Policy Structure
|
||||
|
||||
Each namespace gets a read-only policy:
|
||||
|
||||
```hcl
|
||||
# Policy: ns-{namespace}
|
||||
path "kv/data/{namespace}/*" {
|
||||
capabilities = ["read"]
|
||||
}
|
||||
path "kv/metadata/{namespace}/*" {
|
||||
capabilities = ["read", "list"]
|
||||
}
|
||||
```
|
||||
|
||||
## Kubernetes Auth Roles
|
||||
|
||||
Each namespace has a bound ServiceAccount:
|
||||
|
||||
```
|
||||
Role: ns-{namespace}
|
||||
bound_service_account_names: vault-auth-{namespace}
|
||||
bound_service_account_namespaces: {namespace}
|
||||
policies: ns-{namespace}
|
||||
audience: vault
|
||||
ttl: 1h
|
||||
```
|
||||
|
||||
## CRD Reference
|
||||
|
||||
### VaultAuth
|
||||
|
||||
Per-namespace auth binding. One per namespace.
|
||||
|
||||
```yaml
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultAuth
|
||||
metadata:
|
||||
name: vault-auth
|
||||
namespace: {namespace}
|
||||
spec:
|
||||
method: kubernetes
|
||||
mount: kubernetes
|
||||
kubernetes:
|
||||
role: ns-{namespace}
|
||||
serviceAccount: vault-auth-{namespace}
|
||||
audiences:
|
||||
- vault
|
||||
```
|
||||
|
||||
Each VaultAuth requires a corresponding ServiceAccount:
|
||||
|
||||
```yaml
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: vault-auth-{namespace}
|
||||
namespace: {namespace}
|
||||
```
|
||||
|
||||
### VaultStaticSecret
|
||||
|
||||
One per secret. Syncs a Vault KV path to a K8s Secret.
|
||||
|
||||
```yaml
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: {secret-name}
|
||||
namespace: {namespace}
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: {namespace}/{secret-name}
|
||||
destination:
|
||||
name: {secret-name} # K8s Secret name (must match what apps expect)
|
||||
create: true
|
||||
type: Opaque # Optional, defaults to Opaque
|
||||
labels: # Optional, for secrets that need labels
|
||||
some-label: "value"
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
```
|
||||
|
||||
## Special Labels
|
||||
|
||||
Some secrets require specific labels for correct operation:
|
||||
|
||||
| Secret | Label | Purpose |
|
||||
|--------|-------|---------|
|
||||
| `renovate-env` | `allowedToBeCloned: "true"` | Kyverno secret-cloner policy |
|
||||
| `gitea-smtp-secret` | `allowedToBeCloned: "true"` | Kyverno secret-cloner policy |
|
||||
| `forte-helm-repo` | `argocd.argoproj.io/secret-type: repository` | ArgoCD repository recognition |
|
||||
| `forte10x-repo-creds` | `argocd.argoproj.io/secret-type: repository` | ArgoCD repository recognition |
|
||||
| `mcp10x-repo-creds` | `argocd.argoproj.io/secret-type: repository` | ArgoCD repository recognition |
|
||||
|
||||
These are set in `destination.labels` of the VaultStaticSecret CRD.
|
||||
|
||||
## Namespaces & Secrets Map
|
||||
|
||||
| Namespace | Secrets |
|
||||
|-----------|---------|
|
||||
| `homepage` | homepage-widget-credentials |
|
||||
| `renovate` | renovate-env |
|
||||
| `gitea` | gitea-credentials, gitea-backup-s3, gitea-smtp-secret, gitea-runner-token |
|
||||
| `keycloak` | keycloak-credentials, microsoft-idp-credentials (overlay) |
|
||||
| `argocd` | forte-helm-repo, forte10x-repo-creds, mcp10x-repo-creds, argocd-notifications-secret |
|
||||
| `mcp10x` | app-credentials |
|
||||
| `ts-mcp` | ts-mcp-secrets |
|
||||
| `argocd-mcp` | auth-oidc, argocd-mcp-credentials |
|
||||
| `dot-ai` | dot-ai-secrets |
|
||||
| `music-man` | musicman-credentials |
|
||||
|
||||
## Common Operations
|
||||
|
||||
### Add a new secret
|
||||
|
||||
1. Write to Vault:
|
||||
```bash
|
||||
vault kv put kv/{namespace}/{secret-name} key1=val1 key2=val2
|
||||
```
|
||||
|
||||
2. Create VaultStaticSecret YAML (see template above)
|
||||
|
||||
3. Add to kustomization.yaml in the appropriate directory
|
||||
|
||||
4. Commit and push — ArgoCD syncs the CRD, VSO creates the K8s Secret
|
||||
|
||||
### Rotate a secret value
|
||||
|
||||
No git commit needed:
|
||||
```bash
|
||||
vault kv put kv/{namespace}/{secret-name} key1=new-val1 key2=new-val2
|
||||
```
|
||||
VSO picks up changes within 30 seconds.
|
||||
|
||||
### Check sync status
|
||||
|
||||
```bash
|
||||
# VaultAuth status
|
||||
kubectl get vaultauth -n {namespace}
|
||||
|
||||
# VaultStaticSecret status
|
||||
kubectl get vaultstaticsecret -n {namespace}
|
||||
|
||||
# Verify K8s Secret exists with correct keys
|
||||
kubectl get secret {name} -n {namespace} -o jsonpath='{.data}' | jq
|
||||
```
|
||||
|
||||
### Troubleshooting
|
||||
|
||||
1. **VaultAuth not authenticating**: Check ServiceAccount exists, Vault role matches SA name/namespace
|
||||
2. **VaultStaticSecret not syncing**: Check `kubectl describe vaultstaticsecret {name} -n {ns}` for events
|
||||
3. **Secret missing keys**: Verify Vault KV path has all expected keys: `vault kv get kv/{ns}/{name}`
|
||||
4. **Permission denied**: Verify Vault policy allows read on `kv/data/{ns}/*`
|
||||
|
||||
## File Locations
|
||||
|
||||
| Type | Location |
|
||||
|------|----------|
|
||||
| VSO ArgoCD Application | `infra/base/vault-secrets-operator/` |
|
||||
| VSO Helm values | `infra/values/base/vault-secrets-operator-values.yaml` |
|
||||
| Vault policies script | `scripts/vault-setup-policies.sh` |
|
||||
| Seed script | `scripts/seed-vault-from-cluster.sh` |
|
||||
| VaultAuth + VaultStaticSecret | Alongside ArgoCD Application in each component directory |
|
||||
|
||||
## Setup Scripts
|
||||
|
||||
```bash
|
||||
# Create all Vault policies and auth roles
|
||||
./scripts/vault-setup-policies.sh
|
||||
|
||||
# Seed Vault KV from existing K8s Secrets
|
||||
./scripts/seed-vault-from-cluster.sh
|
||||
```
|
||||
@@ -1,15 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: gitea-backup-s3
|
||||
namespace: gitea
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: gitea/gitea-backup-s3
|
||||
destination:
|
||||
name: gitea-backup-s3
|
||||
create: true
|
||||
type: Opaque
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -1,14 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: gitea-credentials
|
||||
namespace: gitea
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: gitea/gitea-credentials
|
||||
destination:
|
||||
name: gitea-credentials
|
||||
create: true
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -1,14 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: gitea-runner-token
|
||||
namespace: gitea
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: gitea/gitea-runner-token
|
||||
destination:
|
||||
name: gitea-runner-token
|
||||
create: true
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -1,17 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: gitea-smtp-secret
|
||||
namespace: gitea
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: gitea/gitea-smtp-secret
|
||||
destination:
|
||||
name: gitea-smtp-secret
|
||||
create: true
|
||||
type: Opaque
|
||||
labels:
|
||||
allowedToBeCloned: "true"
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
@@ -2,9 +2,7 @@ apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
resources:
|
||||
- gitea.yaml
|
||||
- vault-auth.yaml
|
||||
- gitea-credentials-vault.yaml
|
||||
- gitea-backup-s3-vault.yaml
|
||||
- gitea-smtp-secret-vault.yaml
|
||||
- gitea-runner-token-vault.yaml
|
||||
# Removed: gitea-*-sealed.yaml (migrated to VSO)
|
||||
- gitea-backup-s3-sealed.yaml
|
||||
- gitea-credentials-sealed.yaml
|
||||
- gitea-runner-token-sealed.yaml
|
||||
- gitea-smtp-secret-sealed.yaml
|
||||
|
||||
@@ -1,20 +0,0 @@
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: vault-auth-gitea
|
||||
namespace: gitea
|
||||
---
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultAuth
|
||||
metadata:
|
||||
name: vault-auth
|
||||
namespace: gitea
|
||||
spec:
|
||||
method: kubernetes
|
||||
mount: kubernetes
|
||||
kubernetes:
|
||||
role: ns-gitea
|
||||
serviceAccount: vault-auth-gitea
|
||||
audiences:
|
||||
- vault
|
||||
@@ -1,14 +0,0 @@
|
||||
apiVersion: secrets.hashicorp.com/v1beta1
|
||||
kind: VaultStaticSecret
|
||||
metadata:
|
||||
name: homepage-widget-credentials
|
||||
namespace: homepage
|
||||
spec:
|
||||
type: kv-v2
|
||||
mount: kv
|
||||
path: homepage/homepage-widget-credentials
|
||||
destination:
|
||||
name: homepage-widget-credentials
|
||||
create: true
|
||||
refreshAfter: 30s
|
||||
vaultAuthRef: vault-auth
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user