Add comprehensive EKS Cluster Template roadmap and configuration files

ROADMAP.md

@@ -0,0 +1,59 @@
+# EKS Cluster Template Roadmap
+
+## Current Architecture
+- Template repository (`template-eks-cluster`) serves as the base for creating new EKS cluster configurations
+- Uses Terraform GitHub repo module to create new repositories from the template
+- Implements managed and non-managed extra files functionality
+- Supports configuration through `config.json`
+
+## Planned Enhancements
+
+### 1. Automated Cluster Setup (High Priority)
+- [ ] Add GitHub Actions workflows with workflow_dispatch triggers
+- [ ] Implement automated terragrunt command execution for cluster building
+- [ ] Configure workflows to run on specific runners for credential management
+- [ ] Create templatized GitHub Actions workflow files
+- [ ] Enable direct cluster creation without manual repository cloning
+
+### 2. File Management System (Medium Priority)
+- [ ] Implement wrapper module for repo module
+- [ ] Add support for crafting and injecting various configuration files
+- [ ] Define file lifecycle management strategy
+  - [ ] Managed files (controlled by workspace)
+  - [ ] Non-managed files (user-modifiable)
+
+### 3. Version Management (Medium Priority)
+- [ ] Implement version control strategy for `default-versions.hcl`
+- [ ] Create system for managing platform release versions
+- [ ] Set up version override mechanism
+  - [ ] Default versions in template repo
+  - [ ] Override capability in workspace creating repos
+
+### 4. Configuration Management (Low Priority)
+- [ ] Enhance Makefile and Ansible playbook integration
+- [ ] Improve configuration file templating
+- [ ] Add validation for configuration files
+
+## Technical Considerations
+1. File Lifecycle Management:
+   - Managed files: Controlled by workspace
+   - Non-managed files: User-modifiable post-creation
+   - Version-specific files: Platform release coordination
+
+2. Automation Requirements:
+   - GitHub Actions runner configuration
+   - Credential management
+   - Workflow templating
+   - Terragrunt integration
+
+3. Version Control Strategy:
+   - Module version collections
+   - Platform release versions
+   - Override mechanisms
+
+## Success Criteria
+- Fully automated cluster creation process
+- Minimal manual intervention required
+- Proper version management system
+- Clear file lifecycle management
+- Secure credential handling

locals.tf

@@ -0,0 +1,144 @@
+locals {
+  common_vars = merge({
+    organization = "census:ocio:csvd"
+    project_name = "csvd_platformbaseline"
+    project_number = "fs0000000078"
+    project_role = "csvd_platformbaseline_app"
+    state_bucket_prefix = "inf-tfstate"
+    state_table_name = "tf_remote_state"
+    route53_endpoints = {}
+  }, var.common_variables)
+
+  all_namespaces = merge({
+    grafana = local.namespaces.telemetry_namespace
+    k8s-dashboard = local.namespaces.telemetry_namespace
+    loki = local.namespaces.telemetry_namespace
+    otel = local.namespaces.telemetry_namespace
+    prometheus = local.namespaces.telemetry_namespace
+    tempo = local.namespaces.telemetry_namespace
+  }, var.namespaces.custom_namespaces)
+
+  namespaces = {
+    operator_namespace = var.namespaces.operator_namespace
+    telemetry_namespace = var.namespaces.telemetry_namespace
+    namespaces = local.all_namespaces
+  }
+
+  default_versions = {
+    cluster_version = var.versions.cluster_version
+    custom_service_eks_account = var.versions.release_version
+    eks_module_version = var.versions.eks_module_version
+    istio_ingress_version = var.versions.release_version
+    release_version = var.versions.release_version
+
+    # Provider versions
+    aws_version = var.versions.aws_version
+    helm_version = var.versions.helm_version
+    kubernetes_version = var.versions.kubernetes_version
+    null_version = var.versions.null_version
+    random_version = var.versions.random_version
+    template_version = var.versions.template_version
+    tf_version = var.versions.tf_version
+
+    # Component versions
+    cert_manager_version = var.versions.cert_manager.version
+    cert_manager_helm_chart = var.versions.cert_manager.chart_version
+    cluster_issuer_name = var.versions.cert_manager.cluster_issuer_name
+
+    gogatekeeper_tag = var.versions.gogatekeeper.tag
+    gogatekeeper_chart_version = var.versions.gogatekeeper.chart_version
+
+    grafana_hostname = var.versions.grafana.hostname
+    grafana_operator_chart_version = var.versions.grafana.operator_chart_version
+    grafana_operator_tag = var.versions.grafana.operator_tag
+    grafana_tag = var.versions.grafana.tag
+    os_shell_image_tag = var.versions.grafana.os_shell_image_tag
+
+    istio_version = var.versions.istio.version
+    istio_namespace = var.versions.istio.namespace
+
+    dashboard_hostname = var.versions.k8s_dashboard.hostname
+    k8s_dashboard_metrics_scraper = var.versions.k8s_dashboard.metrics_scraper
+    k8s_dashboard_version = var.versions.k8s_dashboard.version
+
+    karpenter_helm_chart = var.versions.karpenter.helm_chart
+    karpenter_tag = var.versions.karpenter.tag
+
+    keycloak_chart_version = var.versions.keycloak.chart_version
+    keycloak_tag = var.versions.keycloak.tag
+    keycloak_hostname = var.versions.keycloak.hostname
+    keycloak_database = var.versions.keycloak.database
+    keycloak_username = var.versions.keycloak.username
+    keycloak_password = var.versions.keycloak.password
+    postgresql_tag = var.versions.keycloak.postgresql_tag
+
+    kiali_operator_version = var.versions.kiali.operator_version
+    kiali_application_version = "v${var.versions.kiali.operator_version}"
+
+    loki_chart_version = var.versions.loki.chart_version
+    loki_tag = var.versions.loki.tag
+    enterprise_logs_provisioner_tag = var.versions.loki.enterprise_logs_provisioner_tag
+    gateway_tag = var.versions.loki.gateway_tag
+    memcached_tag = var.versions.loki.memcached_tag
+    exporter_tag = var.versions.loki.exporter_tag
+    sidecar_tag = var.versions.loki.sidecar_tag
+
+    metrics_server_helm_chart = var.versions.metrics_server.helm_chart
+    metrics_server_tag = var.versions.metrics_server.tag
+
+    prometheus_chart_version = var.versions.prometheus.chart_version
+    prometheus_server_tag = var.versions.prometheus.server_tag
+    prometheus_config_reloader_tag = var.versions.prometheus.config_reloader_tag
+    alertmanager_tag = var.versions.prometheus.alertmanager_tag
+    kube_state_metrics_tag = var.versions.prometheus.kube_state_metrics_tag
+    node_exporter_tag = var.versions.prometheus.node_exporter_tag
+    pushgateway_tag = var.versions.prometheus.pushgateway_tag
+
+    tempo_chart_version = var.versions.tempo.chart_version
+    tempo_tag = var.versions.tempo.tag
+  }
+
+  config_json = jsonencode({
+    environment = var.environment
+    region = var.region
+    cluster_dir = "platform-cluster"
+    enable_all_modules = false
+    account = {
+      account_name = var.cluster_config.account_name
+      aws_account_id = var.cluster_config.aws_account_id
+      aws_profile = var.cluster_config.aws_profile
+      environment_abbr = var.cluster_config.environment_abbr
+    }
+    vpc = {
+      vpc_name = var.cluster_config.vpc_name
+      vpc_domain_name = var.cluster_config.vpc_domain_name
+    }
+    cluster = {
+      cluster_name = var.cluster_config.cluster_name
+      cluster_mailing_list = var.cluster_config.cluster_mailing_list
+      eks_instance_disk_size = var.cluster_config.eks_instance_disk_size
+      eks_ng_desired_size = var.cluster_config.eks_ng_desired_size
+      eks_ng_max_size = var.cluster_config.eks_ng_max_size
+      eks_ng_min_size = var.cluster_config.eks_ng_min_size
+      enable_cluster_creator_admin_permissions = var.cluster_config.enable_cluster_creator_admin_permissions
+      tags = var.cluster_config.tags
+    }
+    modules = var.enable_modules
+  })
+
+  managed_extra_files = concat([
+    {
+      path = "config.json"
+      content = local.config_json
+    },
+    {
+      path = "_envcommon/default-versions.hcl"
+      content = templatefile("${path.module}/templates/default-versions.hcl", local.default_versions)
+    },
+    {
+      path = "_envcommon/common-variables.hcl"
+      content = templatefile("${path.module}/templates/common-variables.hcl", local.common_vars)
+    }
+  ],
+  var.github_actions_workflows)
+}

main.tf

@@ -0,0 +1,28 @@
+module "github_repo" {
+  source = "HappyPathway/repo/github"
+
+  name = var.name
+  repo_org = var.organization
+  github_repo_description = "EKS Cluster Configuration for ${var.cluster_config.cluster_name}"
+  github_repo_topics = ["eks", "kubernetes", "terraform", "infrastructure"]
+
+  template_repo = "template-eks-cluster"
+  template_repo_org = var.template_repo_org
+
+  github_is_private = true
+  github_has_issues = true
+  github_has_wiki = true
+  github_has_projects = true
+
+  managed_extra_files = local.managed_extra_files
+}
+
+output "repository_url" {
+  description = "URL of the created repository"
+  value = module.github_repo.html_url
+}
+
+output "ssh_clone_url" {
+  description = "SSH clone URL of the repository"
+  value = module.github_repo.ssh_clone_url
+}

templates/common-variables.hcl

@@ -0,0 +1,10 @@
+locals {
+  organization        = "${organization}"
+  project_name        = "${project_name}"
+  project_number      = "${project_number}"
+  project_role        = "${project_role}"
+  state_bucket_prefix = "${state_bucket_prefix}"
+  state_table_name    = "${state_table_name}"
+
+  route53_endpoints   = ${jsonencode(route53_endpoints)}
+}

templates/default-versions.hcl

@@ -0,0 +1,124 @@
+locals {
+  #####################
+  # Module Versions
+  #####################
+  cluster_version            = "${cluster_version}"
+  custom_service_eks_account = "${custom_service_eks_account}"
+  eks_module_version         = "${eks_module_version}"
+  istio_ingress_version     = "${istio_ingress_version}"
+  release_version           = "${release_version}"
+
+  #####################
+  # TF Providers
+  #####################
+  aws_version        = "${aws_version}"
+  helm_version       = "${helm_version}"
+  kubernetes_version = "${kubernetes_version}"
+  null_version       = "${null_version}"
+  random_version     = "${random_version}"
+  template_version   = "${template_version}"
+  tf_version         = "${tf_version}"
+
+  #####################
+  # Component Versions
+  #####################
+
+  ################
+  # Cert-Manager
+  ################
+  cluster_issuer_name              = "${cluster_issuer_name}"
+  cert_manager_version             = "${cert_manager_version}"
+  cert_manager_helm_chart          = "${cert_manager_helm_chart}"
+
+  ################
+  # GoGatekeeper
+  ################
+  gogatekeeper_tag           = "${gogatekeeper_tag}"
+  gogatekeeper_chart_version = "${gogatekeeper_chart_version}"
+
+  ################
+  # Grafana
+  ################
+  grafana_hostname               = "${grafana_hostname}"
+  grafana_operator_chart_version = "${grafana_operator_chart_version}"
+  grafana_operator_tag           = "${grafana_operator_tag}"
+  grafana_tag                    = "${grafana_tag}"
+  os_shell_image_tag             = "${os_shell_image_tag}"
+
+  ################
+  # Istio
+  ################
+  istio_namespace = "${istio_namespace}"
+  istio_version   = "${istio_version}"
+
+  ################
+  # k8s-dashboard
+  ################
+  dashboard_hostname            = "${dashboard_hostname}"
+  k8s_dashboard_metrics_scraper = "${k8s_dashboard_metrics_scraper}"
+  k8s_dashboard_version         = "${k8s_dashboard_version}"
+
+  ################
+  # Karpenter
+  ################
+  karpenter_helm_chart = "${karpenter_helm_chart}"
+  karpenter_tag        = "${karpenter_tag}"
+
+  ################
+  # Keycloak
+  ################
+  keycloak_chart_version = "${keycloak_chart_version}"
+  keycloak_tag           = "${keycloak_tag}"
+  keycloak_hostname      = "${keycloak_hostname}"
+  keycloak_database      = "${keycloak_database}"
+  keycloak_username      = "${keycloak_username}"
+  keycloak_password      = "${keycloak_password}"
+  postgresql_tag         = "${postgresql_tag}"
+
+  ################
+  # Kiali
+  ################
+  kiali_operator_version    = "${kiali_operator_version}"
+  kiali_application_version = "${kiali_application_version}"
+
+  ################
+  # Loki
+  ################
+  loki_chart_version              = "${loki_chart_version}"
+  loki_tag                        = "${loki_tag}"
+  enterprise_logs_provisioner_tag = "${enterprise_logs_provisioner_tag}"
+  gateway_tag                     = "${gateway_tag}"
+  memcached_tag                    = "${memcached_tag}"
+  exporter_tag                     = "${exporter_tag}"
+  sidecar_tag                      = "${sidecar_tag}"
+
+  ################
+  # Metrics Server
+  ################
+  metrics_server_helm_chart = "${metrics_server_helm_chart}"
+  metrics_server_tag        = "${metrics_server_tag}"
+
+  ################
+  # Prometheus
+  ################
+  prometheus_chart_version       = "${prometheus_chart_version}"
+  prometheus_server_tag          = "${prometheus_server_tag}"
+  prometheus_config_reloader_tag = "${prometheus_config_reloader_tag}"
+  alertmanager_tag               = "${alertmanager_tag}"
+  kube_state_metrics_tag         = "${kube_state_metrics_tag}"
+  node_exporter_tag              = "${node_exporter_tag}"
+  pushgateway_tag                = "${pushgateway_tag}"
+
+  ################
+  # Tempo
+  ################
+  tempo_chart_version = "${tempo_chart_version}"
+  tempo_tag           = "${tempo_tag}"
+
+  #####################
+  # Namespaces Config
+  #####################
+  operator_namespace  = "${operator_namespace}"
+  telemetry_namespace = "${telemetry_namespace}"
+  namespaces = ${jsonencode(namespaces)}
+}