adding more eks addons and fixes

Author: marcincuber

README.md

@@ -10,7 +10,7 @@ Module creates:
 * VPC Endpoints- S3, ECR, STS, APS, GuardDuty
 * EKS Cluster
 * EKS Node Group to run cluster critical services
-* EKS Addons- coredns, kube-proxy, guardduty, aws-ebs-csi-driver, adot (requires cert-manger to be installed), kubecost, cloudwatch observability, snapshot-controller and identity agent
+* EKS Addons- coredns, kube-proxy, guardduty, aws-ebs-csi-driver, adot (requires cert-manger to be installed), kubecost, cloudwatch observability, snapshot-controller, identity agent, metrics server and kube-state-metrics
 * IAM Roles for worker nodes and Karpenter nodes
 * Additional IAM Roles for operators- load-balancer-controller, external-dns, cert-manager, adot-collector
 * SQS queue configuration to be used with Karpeneter while utlising Spot Instances.

terraform/configs/amazon-cloudwatch-observability.json

@@ -0,0 +1,16 @@
+{
+  "agent": {
+    "config": {
+      "logs": {
+        "metrics_collected": {
+          "kubernetes": {
+            "enhanced_container_insights": true
+          }
+        }
+      }
+    }
+  },
+  "containerLogs": {
+    "enabled": false 
+  }
+}

terraform/configs/kube-state-metrics.json

@@ -0,0 +1,16 @@
+{
+  "replicas": 3,
+  "resources": {
+    "limits": {
+      "cpu": "256m",
+      "memory": "512Mi"
+    },
+    "requests": {
+      "cpu": "256m",
+      "memory": "512Mi"
+    }
+  },
+  "nodeSelector": {
+    "kubernetes.io/os": "linux"
+  }
+}

terraform/configs/metrics-server.json

@@ -0,0 +1,3 @@
+{
+    "replicas": 3
+}

terraform/eks-addons.tf

@@ -1,5 +1,8 @@
 locals {
-  core_dns_config = file("${path.module}/configs/core-dns.json")
+  core_dns_config                        = trimspace(file("${path.module}/configs/core-dns.json"))
+  amazon_cloudwatch_observability_config = trimspace(file("${path.module}/configs/amazon-cloudwatch-observability.json"))
+  metrics_server_config                  = trimspace(file("${path.module}/configs/metrics-server.json"))
+  kube_state_metrics_config              = trimspace(file("${path.module}/configs/kube-state-metrics.json"))
 }
 
 resource "aws_eks_addon" "kube_proxy" {
@@ -173,3 +176,64 @@ resource "aws_eks_addon" "identity_agent" {
     "eks_addon" = "eks-pod-identity-agent"
   }
 }
+
+resource "aws_eks_addon" "amazon_cloudwatch_observability" {
+  count = var.eks_addon_version_amazon_cloudwatch_observability != null ? 1 : 0
+
+  cluster_name  = aws_eks_cluster.cluster.name
+  addon_name    = "amazon-cloudwatch-observability"
+  addon_version = var.eks_addon_version_amazon_cloudwatch_observability
+
+  resolve_conflicts_on_create = "OVERWRITE"
+  resolve_conflicts_on_update = "OVERWRITE"
+
+  configuration_values = local.amazon_cloudwatch_observability_config
+
+  preserve = true
+
+  tags = {
+    "eks_addon" = "amazon-cloudwatch-observability"
+  }
+
+  depends_on = [
+    aws_cloudwatch_log_group.cluster_performance
+  ]
+}
+
+resource "aws_eks_addon" "metrics_server" {
+  count = var.eks_addon_version_metrics_server != null ? 1 : 0
+
+  cluster_name  = aws_eks_cluster.cluster.name
+  addon_name    = "metrics-server"
+  addon_version = var.eks_addon_version_metrics_server
+
+  configuration_values = local.metrics_server_config
+
+  resolve_conflicts_on_create = "OVERWRITE"
+  resolve_conflicts_on_update = "OVERWRITE"
+
+  preserve = true
+
+  tags = {
+    "eks_addon" = "metrics-server"
+  }
+}
+
+resource "aws_eks_addon" "kube_state_metrics" {
+  count = var.eks_addon_version_kube_state_metrics != null ? 1 : 0
+
+  cluster_name  = aws_eks_cluster.cluster.name
+  addon_name    = "kube-state-metrics"
+  addon_version = var.eks_addon_version_kube_state_metrics
+
+  configuration_values = local.kube_state_metrics_config
+
+  resolve_conflicts_on_create = "OVERWRITE"
+  resolve_conflicts_on_update = "OVERWRITE"
+
+  preserve = true
+
+  tags = {
+    "eks_addon" = "kube-state-metrics"
+  }
+}

terraform/locals.tf

@@ -1,4 +1,6 @@
 locals {
+  eks_cluster_name = var.name_prefix
+
   events = {
     health_event = {
       name        = "HealthEvent"

terraform/terraform.tfvars

@@ -22,4 +22,6 @@ eks_addon_version_ebs_csi_driver                  = "v1.38.1-eksbuild.2"
 eks_addon_version_guardduty                       = "v1.8.1-eksbuild.2"
 eks_addon_version_snapshot_controller             = "v8.1.0-eksbuild.2"
 eks_addon_version_identity_agent                  = "v1.3.4-eksbuild.1"
-eks_addon_version_amazon_cloudwatch_observability = "v3.0.0-eksbuild.1"
+eks_addon_version_amazon_cloudwatch_observability = "v3.6.0-eksbuild.2"
+eks_addon_version_metrics_server                  = "v0.7.2-eksbuild.3"
+eks_addon_version_kube_state_metrics              = "v2.15.0-eksbuild.3"

terraform/variables.tf

@@ -134,6 +134,24 @@ variable "eks_addon_version_identity_agent" {
   default     = null
 }
 
+variable "eks_addon_version_amazon_cloudwatch_observability" {
+  type        = string
+  description = "Amazon cloudwatch observability addon version."
+  default     = null
+}
+
+variable "eks_addon_version_metrics_server" {
+  type        = string
+  description = "Metrics server addon version."
+  default     = null
+}
+
+variable "eks_addon_version_kube_state_metrics" {
+  type        = string
+  description = "Kube State Metrics addon version."
+  default     = null
+}
+
 #####
 # EKS Default Managed Node Group 
 #####

terraform/vpc.tf

@@ -87,7 +87,7 @@ resource "aws_vpc_endpoint" "eks_vpc_s3_gateway" {
   vpc_endpoint_type = "Gateway"
 
   tags = {
-    Name = "${local.name_prefix_platform_vpc}-s3-gateway"
+    Name = "${var.name_prefix}-gateway"
   }
 }