☕️ Port java collector

examples/variables.tf

@@ -14,3 +14,15 @@ variable "aws_region" {
   description = "AWS Region"
   type        = string
 }
+variable "managed_prometheus_id" {
+  type    = string
+  default = ""
+}
+variable "managed_prometheus_endpoint" {
+  type    = string
+  default = ""
+}
+variable "managed_prometheus_region" {
+  type    = string
+  default = ""
+}

examples/workloads.tf

@@ -8,17 +8,25 @@ module "eks_observability_accelerator" {
   eks_cluster_id = var.eks_cluster_id
 
   # deploys AWS Distro for OpenTelemetry operator into the cluster
-  enable_amazon_eks_adot = true
+  enable_amazon_eks_adot = false
 
   # reusing existing certificate manager? defaults to true
   enable_cert_manager = false
 
   # # -- or enable opentelemetry operator
-  # enable_open_telemetry_operator = true
+  enable_opentelemetry_operator = false #-- true doesn't work for me, needs fix
   # open_telemetry_operator_config = map() // custom config
 
   # creates a new AMP workspace, defaults to true
-  create_managed_prometheus_workspace = true
+  create_managed_prometheus_workspace = false
+
+  # reusing existing AMP -- needs data source for alerting rules
+  managed_prometheus_id       = var.managed_prometheus_id
+  managed_prometheus_endpoint = var.managed_prometheus_endpoint
+  managed_prometheus_region   = var.managed_prometheus_region
+
+
+  enable_java = true
 
   # enable_haproxy = true
   # haproxy_config = {
@@ -26,7 +34,7 @@ module "eks_observability_accelerator" {
   #   grafana_endpoint = module.grafana.endpoint
   # }
 
-  # enable_java = true
+
   # java_config = {
   #   amp_endpoint     = ""
   #   grafana_endpoint = ""

main.tf

@@ -26,16 +26,27 @@ module "operator" {
   addon_context      = local.context
 }
 
-module "java" {
-  source = "./modules/workloads/java"
-
-  amp_endpoint = var.create_managed_prometheus_workspace ? aws_prometheus_workspace.this[0].prometheus_endpoint : var.managed_prometheus_endpoint
-  amp_id       = var.create_managed_prometheus_workspace ? aws_prometheus_workspace.this[0].id : var.managed_prometheus_id
-}
-
 resource "aws_prometheus_workspace" "this" {
   count = var.create_managed_prometheus_workspace ? 1 : 0
 
   alias = local.name
   tags  = var.tags
 }
+
+
+module "java" {
+  count  = var.enable_java ? 1 : 0
+  source = "./modules/workloads/java"
+
+  addon_context = local.context
+
+  amp_endpoint = var.create_managed_prometheus_workspace ? aws_prometheus_workspace.this[0].prometheus_endpoint : var.managed_prometheus_endpoint
+  amp_id       = var.create_managed_prometheus_workspace ? aws_prometheus_workspace.this[0].id : var.managed_prometheus_id
+
+  # if region is not passed, we assume the current one
+  amp_region = try(var.managed_prometheus_region, local.context.aws_region_name)
+
+  depends_on = [
+    module.operator
+  ]
+}

modules/workloads/java/main.tf

@@ -1 +1,65 @@
 
+locals {
+  name      = "adot-collector-java"
+  namespace = try(var.helm_config.namespace, local.name)
+}
+
+data "aws_partition" "current" {}
+
+
+module "helm_addon" {
+  source = "github.com/aws-ia/terraform-aws-eks-blueprints/modules/kubernetes-addons/helm-addon"
+
+
+  helm_config = merge(
+    {
+      name        = local.name
+      chart       = "${path.module}/otel-config"
+      version     = "0.2.0"
+      namespace   = local.namespace
+      description = "ADOT helm Chart deployment configuration"
+    },
+    var.helm_config
+  )
+
+  set_values = [
+    {
+      name  = "ampurl"
+      value = "${var.amp_endpoint}api/v1/remote_write"
+    },
+    {
+      name  = "region"
+      value = var.amp_region
+    },
+    {
+      name  = "prometheusMetricsEndpoint"
+      value = "metrics"
+    },
+    {
+      name  = "prometheusMetricsPort"
+      value = 8888
+    },
+    {
+      name  = "scrapeInterval"
+      value = "15s"
+    },
+    {
+      name  = "scrapeTimeout"
+      value = "10s"
+    },
+    {
+      name  = "scrapeSampleLimit"
+      value = 1000
+    }
+  ]
+
+  irsa_config = {
+    create_kubernetes_namespace       = try(var.helm_config["create_namespace"], true)
+    kubernetes_namespace              = local.namespace
+    create_kubernetes_service_account = true
+    kubernetes_service_account        = try(var.helm_config.service_account, local.name)
+    irsa_iam_policies                 = ["arn:${data.aws_partition.current.partition}:iam::aws:policy/AmazonPrometheusRemoteWriteAccess"]
+  }
+
+  addon_context = var.addon_context
+}

modules/workloads/java/otel-config/Chart.yaml

@@ -0,0 +1,6 @@
+apiVersion: v2
+name: opentelemetry
+description: A Helm chart to install otel operator
+type: application
+version: 0.2.0
+appVersion: v0.1.0

modules/workloads/java/otel-config/templates/clusterrole.yaml

@@ -0,0 +1,29 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: otel-prometheus-role
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - nodes
+      - nodes/proxy
+      - services
+      - endpoints
+      - pods
+    verbs:
+      - get
+      - list
+      - watch
+  - apiGroups:
+      - extensions
+    resources:
+      - ingresses
+    verbs:
+      - get
+      - list
+      - watch
+  - nonResourceURLs:
+      - /metrics
+    verbs:
+      - get

modules/workloads/java/otel-config/templates/clusterrolebinding.yaml

@@ -0,0 +1,12 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: otel-prometheus-role-binding
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: otel-prometheus-role
+subjects:
+  - kind: ServiceAccount
+    name: adot-collector-java
+    namespace: adot-collector-java

modules/workloads/java/otel-config/templates/opentelemetrycollector.yaml

@@ -0,0 +1,67 @@
+apiVersion: opentelemetry.io/v1alpha1
+kind: OpenTelemetryCollector
+metadata:
+  name: adot
+spec:
+  image: public.ecr.aws/aws-observability/aws-otel-collector:latest
+  mode: deployment
+  serviceAccount: adot-collector-java
+  config: |
+    receivers:
+      prometheus:
+        config:
+          global:
+            scrape_interval: {{ .Values.scrapeInterval }}
+            scrape_timeout: {{ .Values.scrapeTimeout }}
+
+          scrape_configs:
+            - job_name: 'kubernetes-pod-jmx'
+              sample_limit: {{ .Values.scrapeSampleLimit }}
+              metrics_path: /{{ .Values.prometheusMetricsEndpoint }}
+              kubernetes_sd_configs:
+                - role: pod
+              relabel_configs:
+                - source_labels: [ __address__ ]
+                  action: keep
+                  regex: '.*:9404$'
+                - action: labelmap
+                  regex: __meta_kubernetes_pod_label_(.+)
+                - action: replace
+                  source_labels: [ __meta_kubernetes_namespace ]
+                  target_label: Namespace
+                - source_labels: [ __meta_kubernetes_pod_name ]
+                  action: replace
+                  target_label: pod_name
+                - action: replace
+                  source_labels: [ __meta_kubernetes_pod_container_name ]
+                  target_label: container_name
+                - action: replace
+                  source_labels: [ __meta_kubernetes_pod_controller_kind ]
+                  target_label: pod_controller_kind
+                - action: replace
+                  source_labels: [ __meta_kubernetes_pod_phase ]
+                  target_label: pod_controller_phase
+              metric_relabel_configs:
+                - source_labels: [ __name__ ]
+                  regex: 'jvm_gc_collection_seconds.*'
+                  action: drop
+    exporters:
+      awsprometheusremotewrite:
+        endpoint: {{ .Values.ampurl }}
+        aws_auth:
+          region: {{ .Values.region }}
+          service: "aps"
+      logging:
+        loglevel: info
+    extensions:
+      health_check:
+      pprof:
+        endpoint: :1888
+      zpages:
+        endpoint: :55679
+    service:
+      extensions: [pprof, zpages, health_check]
+      pipelines:
+        metrics:
+          receivers: [prometheus]
+          exporters: [logging, awsprometheusremotewrite]

modules/workloads/java/otel-config/values.yaml

@@ -0,0 +1,7 @@
+ampurl: ${amp_url}
+region: ${region}
+prometheusMetricsEndpoint: ${prometheus_metrics_endpoint}
+prometheusMetricsPort: ${prometheus_metrics_port}
+scrapeInterval: ${scrape_interval}
+scrapeTimeout: ${scrape_timeout}
+scrapeSampleLimit: ${scrape_sample_limit}

modules/workloads/java/variables.tf

@@ -6,7 +6,7 @@ variable "java" {
 }
 
 variable "amp_endpoint" {
-  description = "Managed Prometheus endpoint"
+  description = "Amazon Managed Prometheus endpoint"
   type        = string
 }
 
@@ -14,3 +14,32 @@ variable "amp_id" {
   description = "Managed Prometheus workspace id"
   type        = string
 }
+
+variable "helm_config" {
+  description = "Helm Config for Prometheus"
+  type        = any
+  default     = {}
+}
+
+variable "amp_region" {
+  description = "Amazon Managed Prometheus Workspace's Region"
+  type        = string
+  default     = null
+}
+
+variable "addon_context" {
+  description = "Input configuration for the addon"
+  type = object({
+    aws_caller_identity_account_id = string
+    aws_caller_identity_arn        = string
+    aws_eks_cluster_endpoint       = string
+    aws_partition_id               = string
+    aws_region_name                = string
+    eks_cluster_id                 = string
+    eks_oidc_issuer_url            = string
+    eks_oidc_provider_arn          = string
+    irsa_iam_permissions_boundary  = string
+    irsa_iam_role_path             = string
+    tags                           = map(string)
+  })
+}

variables.tf

@@ -49,7 +49,6 @@ variable "create_managed_prometheus_workspace" {
   default = true
 }
 
-
 variable "managed_prometheus_id" {
   description = "AWS Managed Prometheus Workspace ID"
   type        = string
@@ -61,6 +60,17 @@ variable "managed_prometheus_endpoint" {
   type        = string
   default     = ""
 }
+variable "managed_prometheus_region" {
+  description = "AWS Managed Prometheus Workspace Region"
+  type        = string
+  default     = null
+}
+
+variable "enable_java" {
+  description = "Deploys a collector for JAVA/JMX based workloads, dashboards and alerting rules"
+  type        = bool
+  default     = false
+}
 
 variable "tags" {
   description = "Additional tags (e.g. `map('BusinessUnit`,`XYZ`)"