add promethus

lab/us-gov-east-1/vpc/_mcmCluster/eks-promethus/README.md

@@ -0,0 +1,55 @@
+## eks-prometheus
+This module deploys EKS kubeenetes prometheus inside existing EKS cluster. Prometheus is an open-source systems monitoring and alerting tool.
+This module consisits of 4 components. It creates prometheus namespace and  copies image repositories for the following components from quay.io into local account ECR repository. It deploys these components using helm charts using the configured ECR repositories.
+    1. prometheus-alert-manager
+    2. prometheus-node-exporter
+    3. prometheus-pushgateway
+    4. prometheus-server
+
+### Dependencies
+This module is dependent on EKS module (eks). The cluster should exist already for this module to work.
+
+### Inputs
+    cluster_name
+    profile
+    prometheus_chart_version
+    prometheus_server_tag
+    prometheus_config_reloader_tag
+    alertmanager_tag
+    kube_state_metrics_tag
+    node_exporter_tag
+    pushgateway_tag
+    rwo_storage_class
+
+### Outputs
+    alertmanager_internal_endpoint
+    alertmanager_headless_internal_endpoint
+    pushgateway_internal_endpoint
+    prometheus_server_internal_endpoint
+
+### Issues observed/fixed
+1. The rwo_storage_class value had to be updated from "gp3" to "gp3-encrypted"
+2. The node_exporter_tag value had to be updated from "1.6.1" to "v1.8.1"
+3. The kube_state_metrics_tag value had to be updated from "2.10.0" to "v2.6.0"
+4. The alertmanager_tag value had to be updated from
+5. The helm chart set config for the ecr image had to be split into 2 components, one for registry and other for repository as an example mentioned below:
+    ```
+    set {
+    name = "kube-state-metrics.image.registry"
+    value = module.images.images[local.ksm_key].dest_registry
+  }
+  set {
+    name = "kube-state-metrics.image.repository"
+    value = module.images.images[local.ksm_key].dest_repository
+      }
+    ```
+6. In some other cases the image ecr repository had to be split by the colon separatory (:)
+    ```
+    set {
+    name = "alertmanager.configmapReload.image.repository"
+    value = split(":", module.images.images[local.prom_config_reload_key].dest_full_path)[0]
+        }
+    ```
+
+
+

lab/us-gov-east-1/vpc/_mcmCluster/eks-promethus/terragrunt.hcl

@@ -0,0 +1,47 @@
+terraform {
+  source      = "git@github.e.it.census.gov:SCT-Engineering/tfmod-prometheus.git?ref=platform-changes"
+  extra_arguments "retry_lock" {
+    commands  = get_terraform_commands_that_need_locking()
+    arguments = ["-lock-timeout=20m"]
+  }
+}
+
+dependency "eks" {
+  config_path = "../eks"
+}
+
+inputs = {
+  profile                                         = dependency.eks.inputs.profile
+  cluster_name                                    = dependency.eks.inputs.cluster_name
+  region                                          = dependency.eks.inputs.region
+}
+
+generate "provider-eks" {
+  path      = "provider.tf"
+  if_exists = "overwrite_terragrunt"
+  contents  = <<EOF
+data "aws_eks_cluster" "cluster" {
+  name = "${dependency.eks.inputs.cluster_name}"
+}
+
+data "aws_eks_cluster_auth" "cluster" {
+  name = "${dependency.eks.inputs.cluster_name}"
+}
+
+provider "kubernetes" {
+  host = data.aws_eks_cluster.cluster.endpoint
+
+  cluster_ca_certificate = base64decode(data.aws_eks_cluster.cluster.certificate_authority[0].data)
+  token                  = data.aws_eks_cluster_auth.cluster.token
+}
+
+provider "helm" {
+  kubernetes {
+    host = data.aws_eks_cluster.cluster.endpoint
+
+    cluster_ca_certificate = base64decode(data.aws_eks_cluster.cluster.certificate_authority[0].data)
+    token                  = data.aws_eks_cluster_auth.cluster.token
+  }
+}
+EOF
+}

lab/us-gov-east-1/vpc/_mcmCluster/eks-slim/terragrunt.hcl

@@ -0,0 +1,85 @@
+include "root" {
+  path   = find_in_parent_folders()
+  expose = true
+}
+
+locals {
+  # In which AWS region are operations being performed
+  vpc_name               = "vpc3-lab-dev"
+  cluster_name           = "eks-slim-cluster"
+  cluster_version        = 1.29
+  domain                 = "dev.lab.csp2.census.gov"
+  eks_instance_disk_size = 40
+  eks_vpc_name           = "vpc3-lab-dev"
+  eks_ng_desired_size    = 1
+  eks_ng_max_size        = 4
+  eks_ng_min_size        = 1
+  operators_ns           = "operators"
+  enable_cluster_creator_admin_permissions = true
+  cluster_endpoint_public_access  = true
+  profile                = "224384469011-lab-dev-gov"
+
+  # Tags applied to AWS objects created
+  tags = {
+      "Environment"           = "dev"
+      "slim:schedule"         = "8:00-17:00"
+      "cluster:size"          = "min:${local.eks_ng_min_size}-max:${local.eks_ng_max_size}-desired:${local.eks_ng_desired_size}"
+  }
+
+  aws_auth_roles = [
+    {
+      rolearn : "arn:aws-us-gov:iam::224384469011:role/AWSReservedSSO_inf-admin-t3_b200ae7af469cdc8"
+      aws_rolename : ""
+      username : "admin"
+      groups = ["system:masters"]
+    },
+    {
+      rolearn : "arn:aws-us-gov:iam::224384469011:role/AWSReservedSSO_inf-admin-t2_f3912d726991bbfa"
+      aws_rolename : ""
+      username : "admin"
+      groups = ["system:masters"]
+    }
+  ]
+}
+
+terraform {
+  source      = "git@github.e.it.census.gov:SCT-Engineering/tfmod-eks.git"
+  extra_arguments "retry_lock" {
+    commands  = get_terraform_commands_that_need_locking()
+    arguments = ["-lock-timeout=20m"]
+  }
+}
+
+remote_state {
+  backend     = "s3"
+  generate = {
+    path      = "backend.tf"
+    if_exists = "overwrite_terragrunt"
+  }
+  config = {
+    bucket         = "tg-infrastructure-tf-state-lab-dev-ew-us-gov-east-1"
+    key            = "eks-slim-cluster/terraform.tfstate"
+    region         = "us-gov-east-1"
+    encrypt        = true
+    #dynamodb_table = "my-lock-table"
+  }
+}
+
+inputs = {
+  profile                = local.profile
+  vpc_name               = local.eks_vpc_name               
+  cluster_name           = local.cluster_name
+  cluster_version        = local.cluster_version
+  eks_instance_disk_size = local.eks_instance_disk_size
+  eks_vpc_name           = local.eks_vpc_name
+  #eks_instance_types     = local.eks_instance_types
+  eks_ng_desired_size    = local.eks_ng_desired_size
+  eks_ng_max_size        = local.eks_ng_max_size
+  eks_ng_min_size        = local.eks_ng_min_size
+  operators_ns           = local.operators_ns
+  enable_cluster_creator_admin_permissions = local.enable_cluster_creator_admin_permissions
+  cluster_endpoint_public_access  = local.cluster_endpoint_public_access 
+  tags                   = local.tags
+  aws_auth_roles         = local.aws_auth_roles
+  domain                 = local.domain
+}