Compose EKS monitoring modules (#115)

* Move modules around

* Update amp billing source

* Merge Java monitoring to EKS

* Update docs

* Merge nginx pattern

* Pre-commit

* Add save and test URL output

* Move EKS dependencies to EKS monitoring module

* update docs

* Update examples and docs

* Add java doc

* Add NGINX doc

* Update nginx doc

* Fix amp monitoring example path

* Fix pre-commit

* Todo: move to main after merge

* Update docs, fix tags

modules/eks-monitoring/README.md

@@ -33,6 +33,9 @@ This module is inspired from the open source [kube-prometheus-stack](https://git
 | Name | Source | Version |
 |------|--------|---------|
 | <a name="module_helm_addon"></a> [helm\_addon](#module\_helm\_addon) | github.com/aws-ia/terraform-aws-eks-blueprints//modules/kubernetes-addons/helm-addon | v4.13.1 |
+| <a name="module_java_monitoring"></a> [java\_monitoring](#module\_java\_monitoring) | ./patterns/java | n/a |
+| <a name="module_nginx_monitoring"></a> [nginx\_monitoring](#module\_nginx\_monitoring) | ./patterns/nginx | n/a |
+| <a name="module_operator"></a> [operator](#module\_operator) | ./add-ons/adot-operator | n/a |
 
 ## Resources
 
@@ -61,20 +64,25 @@ This module is inspired from the open source [kube-prometheus-stack](https://git
 | <a name="input_dashboards_folder_id"></a> [dashboards\_folder\_id](#input\_dashboards\_folder\_id) | Grafana folder ID for automatic dashboards | `string` | n/a | yes |
 | <a name="input_eks_cluster_id"></a> [eks\_cluster\_id](#input\_eks\_cluster\_id) | EKS Cluster Id | `string` | n/a | yes |
 | <a name="input_enable_alerting_rules"></a> [enable\_alerting\_rules](#input\_enable\_alerting\_rules) | Enables or disables Managed Prometheus alerting rules | `bool` | `true` | no |
+| <a name="input_enable_amazon_eks_adot"></a> [enable\_amazon\_eks\_adot](#input\_enable\_amazon\_eks\_adot) | Enables the ADOT Operator on the EKS Cluster | `bool` | `true` | no |
+| <a name="input_enable_cert_manager"></a> [enable\_cert\_manager](#input\_enable\_cert\_manager) | Allow reusing an existing installation of cert-manager | `bool` | `true` | no |
 | <a name="input_enable_custom_metrics"></a> [enable\_custom\_metrics](#input\_enable\_custom\_metrics) | Allows additional metrics collection for config elements in the `custom_metrics_config` config object. Automatic dashboards are not included | `bool` | `false` | no |
 | <a name="input_enable_dashboards"></a> [enable\_dashboards](#input\_enable\_dashboards) | Enables or disables curated dashboards | `bool` | `true` | no |
+| <a name="input_enable_java"></a> [enable\_java](#input\_enable\_java) | Enable Java workloads monitoring, alerting and default dashboards | `bool` | `false` | no |
 | <a name="input_enable_kube_state_metrics"></a> [enable\_kube\_state\_metrics](#input\_enable\_kube\_state\_metrics) | Enables or disables Kube State metrics exporter. Disabling this might affect some data in the dashboards | `bool` | `true` | no |
+| <a name="input_enable_nginx"></a> [enable\_nginx](#input\_enable\_nginx) | Enable NGINX workloads monitoring, alerting and default dashboards | `bool` | `false` | no |
 | <a name="input_enable_node_exporter"></a> [enable\_node\_exporter](#input\_enable\_node\_exporter) | Enables or disables Node exporter. Disabling this might affect some data in the dashboards | `bool` | `true` | no |
-| <a name="input_enable_recording_rules"></a> [enable\_recording\_rules](#input\_enable\_recording\_rules) | Enables or disables Managed Prometheus recording rules. Disabling this might affect some data in the dashboards | `bool` | `true` | no |
 | <a name="input_enable_tracing"></a> [enable\_tracing](#input\_enable\_tracing) | (Experimental) Enables tracing with AWS X-Ray. This changes the deploy mode of the collector to daemon set. Requirement: adot add-on <= 0.58-build.0 | `bool` | `false` | no |
 | <a name="input_helm_config"></a> [helm\_config](#input\_helm\_config) | Helm Config for Prometheus | `any` | `{}` | no |
 | <a name="input_irsa_iam_permissions_boundary"></a> [irsa\_iam\_permissions\_boundary](#input\_irsa\_iam\_permissions\_boundary) | IAM permissions boundary for IRSA roles | `string` | `null` | no |
 | <a name="input_irsa_iam_role_path"></a> [irsa\_iam\_role\_path](#input\_irsa\_iam\_role\_path) | IAM role path for IRSA roles | `string` | `"/"` | no |
+| <a name="input_java_config"></a> [java\_config](#input\_java\_config) | Configuration object for Java/JMX monitoring | <pre>object({<br>    enable_alerting_rules = bool<br>    scrape_sample_limit   = number<br>  })</pre> | <pre>{<br>  "enable_alerting_rules": true,<br>  "scrape_sample_limit": 1000<br>}</pre> | no |
 | <a name="input_ksm_config"></a> [ksm\_config](#input\_ksm\_config) | Kube State metrics configuration | <pre>object({<br>    create_namespace   = bool<br>    k8s_namespace      = string<br>    helm_chart_name    = string<br>    helm_chart_version = string<br>    helm_release_name  = string<br>    helm_repo_url      = string<br>    helm_settings      = map(string)<br>    helm_values        = map(any)<br><br>    scrape_interval = string<br>    scrape_timeout  = string<br>  })</pre> | <pre>{<br>  "create_namespace": true,<br>  "helm_chart_name": "kube-state-metrics",<br>  "helm_chart_version": "4.24.0",<br>  "helm_release_name": "kube-state-metrics",<br>  "helm_repo_url": "https://prometheus-community.github.io/helm-charts",<br>  "helm_settings": {},<br>  "helm_values": {},<br>  "k8s_namespace": "kube-system",<br>  "scrape_interval": "60s",<br>  "scrape_timeout": "15s"<br>}</pre> | no |
 | <a name="input_managed_prometheus_workspace_endpoint"></a> [managed\_prometheus\_workspace\_endpoint](#input\_managed\_prometheus\_workspace\_endpoint) | Amazon Managed Prometheus Workspace Endpoint | `string` | `""` | no |
 | <a name="input_managed_prometheus_workspace_id"></a> [managed\_prometheus\_workspace\_id](#input\_managed\_prometheus\_workspace\_id) | Amazon Managed Prometheus Workspace ID | `string` | `null` | no |
 | <a name="input_managed_prometheus_workspace_region"></a> [managed\_prometheus\_workspace\_region](#input\_managed\_prometheus\_workspace\_region) | Amazon Managed Prometheus Workspace's Region | `string` | `null` | no |
 | <a name="input_ne_config"></a> [ne\_config](#input\_ne\_config) | Node exporter configuration | <pre>object({<br>    create_namespace   = bool<br>    k8s_namespace      = string<br>    helm_chart_name    = string<br>    helm_chart_version = string<br>    helm_release_name  = string<br>    helm_repo_url      = string<br>    helm_settings      = map(string)<br>    helm_values        = map(any)<br><br>    scrape_interval = string<br>    scrape_timeout  = string<br>  })</pre> | <pre>{<br>  "create_namespace": true,<br>  "helm_chart_name": "prometheus-node-exporter",<br>  "helm_chart_version": "2.0.3",<br>  "helm_release_name": "prometheus-node-exporter",<br>  "helm_repo_url": "https://prometheus-community.github.io/helm-charts",<br>  "helm_settings": {},<br>  "helm_values": {},<br>  "k8s_namespace": "prometheus-node-exporter",<br>  "scrape_interval": "60s",<br>  "scrape_timeout": "60s"<br>}</pre> | no |
+| <a name="input_nginx_config"></a> [nginx\_config](#input\_nginx\_config) | Configuration object for NGINX monitoring | <pre>object({<br>    enable_alerting_rules       = bool<br>    scrape_sample_limit         = number<br>    prometheus_metrics_endpoint = string<br>  })</pre> | <pre>{<br>  "enable_alerting_rules": true,<br>  "prometheus_metrics_endpoint": "metrics",<br>  "scrape_sample_limit": 1000<br>}</pre> | no |
 | <a name="input_prometheus_config"></a> [prometheus\_config](#input\_prometheus\_config) | Controls default values such as scrape interval, timeouts and ports globally | <pre>object({<br>    global_scrape_interval = string<br>    global_scrape_timeout  = string<br>  })</pre> | <pre>{<br>  "global_scrape_interval": "60s",<br>  "global_scrape_timeout": "15s"<br>}</pre> | no |
 | <a name="input_tags"></a> [tags](#input\_tags) | Additional tags (e.g. `map('BusinessUnit`,`XYZ`) | `map(string)` | `{}` | no |
 | <a name="input_tracing_config"></a> [tracing\_config](#input\_tracing\_config) | Configuration object for traces collection to AWS X-Ray | <pre>object({<br>    otlp_grpc_endpoint = string<br>    otlp_http_endpoint = string<br>    send_batch_size    = number<br>    timeout            = string<br>  })</pre> | <pre>{<br>  "otlp_grpc_endpoint": "0.0.0.0:4317",<br>  "otlp_http_endpoint": "0.0.0.0:4318",<br>  "send_batch_size": 50,<br>  "timeout": "30s"<br>}</pre> | no |
@@ -83,5 +91,7 @@ This module is inspired from the open source [kube-prometheus-stack](https://git
 
 | Name | Description |
 |------|-------------|
+| <a name="output_eks_cluster_id"></a> [eks\_cluster\_id](#output\_eks\_cluster\_id) | EKS Cluster Id |
+| <a name="output_eks_cluster_version"></a> [eks\_cluster\_version](#output\_eks\_cluster\_version) | EKS Cluster version |
 | <a name="output_grafana_dashboard_urls"></a> [grafana\_dashboard\_urls](#output\_grafana\_dashboard\_urls) | URLs for dashboards created |
 <!-- END OF PRE-COMMIT-TERRAFORM DOCS HOOK -->

modules/eks-monitoring/locals.tf

@@ -14,6 +14,7 @@ locals {
 
   eks_oidc_issuer_url  = replace(data.aws_eks_cluster.eks_cluster.identity[0].oidc[0].issuer, "https://", "")
   eks_cluster_endpoint = data.aws_eks_cluster.eks_cluster.endpoint
+  eks_cluster_version  = data.aws_eks_cluster.eks_cluster.version
 
   context = {
     aws_caller_identity_account_id = data.aws_caller_identity.current.account_id

modules/eks-monitoring/main.tf

@@ -1,3 +1,12 @@
+module "operator" {
+  source = "./add-ons/adot-operator"
+  count  = var.enable_amazon_eks_adot ? 1 : 0
+
+  enable_cert_manager = var.enable_cert_manager
+  kubernetes_version  = local.eks_cluster_version
+  addon_context       = local.context
+}
+
 resource "helm_release" "kube_state_metrics" {
   count            = var.enable_kube_state_metrics ? 1 : 0
   chart            = var.ksm_config.helm_chart_name
@@ -104,6 +113,26 @@ module "helm_addon" {
     {
       name  = "customMetricsDroppedSeriesPrefixes"
       value = format("(%s.*)$", join(".*|", var.custom_metrics_config.dropped_series_prefixes))
+    },
+    {
+      name  = "enable_java"
+      value = var.enable_java
+    },
+    {
+      name  = "javaScrapeSampleLimit"
+      value = var.java_config.scrape_sample_limit
+    },
+    {
+      name  = "enable_nginx"
+      value = var.enable_nginx
+    },
+    {
+      name  = "nginxScrapeSampleLimit"
+      value = var.nginx_config.scrape_sample_limit
+    },
+    {
+      name  = "nginxPrometheusMetricsEndpoint"
+      value = var.nginx_config.prometheus_metrics_endpoint
     }
   ]
 
@@ -119,4 +148,24 @@ module "helm_addon" {
   }
 
   addon_context = local.context
+
+  depends_on = [module.operator]
+}
+
+module "java_monitoring" {
+  source = "./patterns/java"
+  count  = var.enable_java ? 1 : 0
+
+  managed_prometheus_workspace_id = var.managed_prometheus_workspace_id
+  enable_alerting_rules           = var.java_config.enable_alerting_rules
+  dashboards_folder_id            = var.dashboards_folder_id
+}
+
+module "nginx_monitoring" {
+  source = "./patterns/nginx"
+  count  = var.enable_nginx ? 1 : 0
+
+  managed_prometheus_workspace_id = var.managed_prometheus_workspace_id
+  enable_alerting_rules           = var.nginx_config.enable_alerting_rules
+  dashboards_folder_id            = var.dashboards_folder_id
 }

modules/eks-monitoring/otel-config/templates/opentelemetrycollector.yaml

@@ -1703,6 +1703,72 @@ spec:
                 - source_labels: [ __name__ ]
                   regex: '{{ .Values.customMetricsDroppedSeriesPrefixes }}'
                   action: drop
+
+            {{ if .Values.enableJava }}
+            - job_name: 'kubernetes-java-jmx'
+              sample_limit: {{ .Values.javaScrapeSampleLimit }}
+              kubernetes_sd_configs:
+                - role: pod
+              relabel_configs:
+                - source_labels: [ __address__ ]
+                  action: keep
+                  regex: '.*:9404$'
+                - action: labelmap
+                  regex: __meta_kubernetes_pod_label_(.+)
+                - action: replace
+                  source_labels: [ __meta_kubernetes_namespace ]
+                  target_label: Namespace
+                - source_labels: [ __meta_kubernetes_pod_name ]
+                  action: replace
+                  target_label: pod_name
+                - action: replace
+                  source_labels: [ __meta_kubernetes_pod_container_name ]
+                  target_label: container_name
+                - action: replace
+                  source_labels: [ __meta_kubernetes_pod_controller_kind ]
+                  target_label: pod_controller_kind
+                - action: replace
+                  source_labels: [ __meta_kubernetes_pod_phase ]
+                  target_label: pod_controller_phase
+              metric_relabel_configs:
+                - source_labels: [ __name__ ]
+                  regex: 'jvm_gc_collection_seconds.*'
+                  action: drop
+            {{ end }}
+
+            {{ if .Values.enableNginx }}
+            - job_name: 'kubernetes-nginx'
+              sample_limit: {{ .Values.nginxScrapeSampleLimit }}
+              metrics_path: /{{ .Values.nginxPrometheusMetricsEndpoint }}
+              kubernetes_sd_configs:
+                - role: pod
+              relabel_configs:
+                - source_labels: [ __address__ ]
+                  action: keep
+                  regex: '.*:10254$'
+                - source_labels: [__meta_kubernetes_pod_container_name]
+                  target_label: container
+                  action: replace
+                - source_labels: [__meta_kubernetes_pod_node_name]
+                  target_label: host
+                  action: replace
+                - source_labels: [__meta_kubernetes_namespace]
+                  target_label: namespace
+                  action: replace
+              metric_relabel_configs:
+                - source_labels: [__name__]
+                  regex: 'go_memstats.*'
+                  action: drop
+                - source_labels: [__name__]
+                  regex: 'go_gc.*'
+                  action: drop
+                - source_labels: [__name__]
+                  regex: 'go_threads'
+                  action: drop
+                - regex: exported_host
+                  action: labeldrop
+            {{ end }}
+
     exporters:
       {{ if .Values.enableTracing }}
       awsxray:

modules/eks-monitoring/otel-config/values.yaml

@@ -14,3 +14,10 @@ tracingSendBatchSize: ${tracing_send_batch_size}
 enableCustomMetrics: ${enable_custom_metrics}
 customMetricsPorts: ${custom_metrics_ports}
 customMetricsDroppedSeriesPrefixes: ${custom_metrics_dropped_series_prefixes}
+
+enableJava: ${enable_java}
+javaScrapeSampleLimit: ${java_scrape_sample_limit}
+
+enableNginx: ${enable_nginx}
+nginxScrapeSampleLimit: ${nginx_scrape_sample_limit}
+nginxPrometheusMetricsEndpoint: ${nginx_prometheus_metrics_endpoint}

modules/eks-monitoring/outputs.tf

@@ -0,0 +1,21 @@
+output "grafana_dashboard_urls" {
+  value = [concat(
+    grafana_dashboard.workloads[*].url,
+    grafana_dashboard.nodes[*].url,
+    grafana_dashboard.nsworkload[*].url,
+    grafana_dashboard.kubelet[*].url,
+    grafana_dashboard.cluster[*].url,
+    flatten(module.java_monitoring[*].grafana_dashboard_urls),
+    flatten(module.nginx_monitoring[*].grafana_dashboard_urls),
+  )]
+  description = "URLs for dashboards created"
+}
+output "eks_cluster_version" {
+  description = "EKS Cluster version"
+  value       = data.aws_eks_cluster.eks_cluster.version
+}
+
+output "eks_cluster_id" {
+  description = "EKS Cluster Id"
+  value       = var.eks_cluster_id
+}

modules/eks-monitoring/patterns/java/README.md

@@ -0,0 +1,52 @@
+# Java patterns module
+
+Provides monitoring for Java based workloads with the following resources:
+
+- AWS Managed Grafana Dashboard and data source
+- Alerts and recording rules with AWS Managed Service for Prometheus
+
+<!-- BEGINNING OF PRE-COMMIT-TERRAFORM DOCS HOOK -->
+## Requirements
+
+| Name | Version |
+|------|---------|
+| <a name="requirement_terraform"></a> [terraform](#requirement\_terraform) | >= 1.1.0 |
+| <a name="requirement_aws"></a> [aws](#requirement\_aws) | >= 4.0.0 |
+| <a name="requirement_grafana"></a> [grafana](#requirement\_grafana) | >= 1.25.0 |
+| <a name="requirement_helm"></a> [helm](#requirement\_helm) | >= 2.4.1 |
+| <a name="requirement_kubectl"></a> [kubectl](#requirement\_kubectl) | >= 1.14 |
+| <a name="requirement_kubernetes"></a> [kubernetes](#requirement\_kubernetes) | >= 2.10 |
+
+## Providers
+
+| Name | Version |
+|------|---------|
+| <a name="provider_aws"></a> [aws](#provider\_aws) | >= 4.0.0 |
+| <a name="provider_grafana"></a> [grafana](#provider\_grafana) | >= 1.25.0 |
+
+## Modules
+
+No modules.
+
+## Resources
+
+| Name | Type |
+|------|------|
+| [aws_prometheus_rule_group_namespace.alerting_rules](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/prometheus_rule_group_namespace) | resource |
+| [aws_prometheus_rule_group_namespace.recording_rules](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/prometheus_rule_group_namespace) | resource |
+| [grafana_dashboard.this](https://registry.terraform.io/providers/grafana/grafana/latest/docs/resources/dashboard) | resource |
+
+## Inputs
+
+| Name | Description | Type | Default | Required |
+|------|-------------|------|---------|:--------:|
+| <a name="input_dashboards_folder_id"></a> [dashboards\_folder\_id](#input\_dashboards\_folder\_id) | Grafana folder ID for automatic dashboards | `string` | n/a | yes |
+| <a name="input_enable_alerting_rules"></a> [enable\_alerting\_rules](#input\_enable\_alerting\_rules) | Enables or disables Managed Prometheus alerting rules | `bool` | `true` | no |
+| <a name="input_managed_prometheus_workspace_id"></a> [managed\_prometheus\_workspace\_id](#input\_managed\_prometheus\_workspace\_id) | Amazon Managed Prometheus Workspace ID | `string` | `null` | no |
+
+## Outputs
+
+| Name | Description |
+|------|-------------|
+| <a name="output_grafana_dashboard_urls"></a> [grafana\_dashboard\_urls](#output\_grafana\_dashboard\_urls) | URLs for dashboards created |
+<!-- END OF PRE-COMMIT-TERRAFORM DOCS HOOK -->

modules/eks-monitoring/patterns/java/dashboards/default.json

@@ -1837,4 +1837,4 @@
   "uid": "m9mHfAy7ks",
   "version": 4,
   "weekStart": ""
-}
+}

modules/eks-monitoring/patterns/java/main.tf

@@ -0,0 +1,36 @@
+resource "aws_prometheus_rule_group_namespace" "recording_rules" {
+  name         = "accelerator-java-rules"
+  workspace_id = var.managed_prometheus_workspace_id
+  data         = <<EOF
+groups:
+  - name: default-metric
+    rules:
+      - record: metric:recording_rule
+        expr: avg(rate(container_cpu_usage_seconds_total[5m]))
+EOF
+}
+
+resource "aws_prometheus_rule_group_namespace" "alerting_rules" {
+  count = var.enable_alerting_rules ? 1 : 0
+
+  name         = "accelerator-java-alerting"
+  workspace_id = var.managed_prometheus_workspace_id
+  data         = <<EOF
+groups:
+  - name: default-alert
+    rules:
+      - alert: metric:alerting_rule
+        expr: jvm_memory_bytes_used{job="java", area="heap"} / jvm_memory_bytes_max * 100 > 80
+        for: 1m
+        labels:
+            severity: warning
+        annotations:
+            summary: "JVM heap warning"
+            description: "JVM heap of instance `{{$labels.instance}}` from application `{{$labels.application}}` is above 80% for one minute. (current=`{{$value}}%`)"
+EOF
+}
+
+resource "grafana_dashboard" "this" {
+  folder      = var.dashboards_folder_id
+  config_json = file("${path.module}/dashboards/default.json")
+}

modules/eks-monitoring/patterns/java/variables.tf

@@ -0,0 +1,16 @@
+variable "enable_alerting_rules" {
+  description = "Enables or disables Managed Prometheus alerting rules"
+  type        = bool
+  default     = true
+}
+
+variable "managed_prometheus_workspace_id" {
+  description = "Amazon Managed Prometheus Workspace ID"
+  type        = string
+  default     = null
+}
+
+variable "dashboards_folder_id" {
+  description = "Grafana folder ID for automatic dashboards"
+  type        = string
+}

modules/eks-monitoring/patterns/nginx/README.md

@@ -26,9 +26,7 @@ It provides the following resources:
 
 ## Modules
 
-| Name | Source | Version |
-|------|--------|---------|
-| <a name="module_helm_addon"></a> [helm\_addon](#module\_helm\_addon) | github.com/aws-ia/terraform-aws-eks-blueprints//modules/kubernetes-addons/helm-addon | v4.13.1 |
+No modules.
 
 ## Resources
 
@@ -36,27 +34,14 @@ It provides the following resources:
 |------|------|
 | [aws_prometheus_rule_group_namespace.alerting_rules](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/prometheus_rule_group_namespace) | resource |
 | [grafana_dashboard.workloads](https://registry.terraform.io/providers/grafana/grafana/latest/docs/resources/dashboard) | resource |
-| [aws_caller_identity.current](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/caller_identity) | data source |
-| [aws_eks_cluster.eks_cluster](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/eks_cluster) | data source |
-| [aws_partition.current](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/partition) | data source |
-| [aws_region.current](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/region) | data source |
 
 ## Inputs
 
 | Name | Description | Type | Default | Required |
 |------|-------------|------|---------|:--------:|
-| <a name="input_config"></a> [config](#input\_config) | Helm Config for Prometheus | `any` | `{}` | no |
 | <a name="input_dashboards_folder_id"></a> [dashboards\_folder\_id](#input\_dashboards\_folder\_id) | Grafana folder ID for automatic dashboards | `string` | n/a | yes |
-| <a name="input_eks_cluster_id"></a> [eks\_cluster\_id](#input\_eks\_cluster\_id) | EKS Cluster Id | `string` | n/a | yes |
 | <a name="input_enable_alerting_rules"></a> [enable\_alerting\_rules](#input\_enable\_alerting\_rules) | Enables or disables Managed Prometheus alerting rules | `bool` | `true` | no |
-| <a name="input_enable_dashboards"></a> [enable\_dashboards](#input\_enable\_dashboards) | Enables or disables curated dashboards | `bool` | `true` | no |
-| <a name="input_helm_config"></a> [helm\_config](#input\_helm\_config) | Helm Config for Prometheus | `any` | `{}` | no |
-| <a name="input_irsa_iam_permissions_boundary"></a> [irsa\_iam\_permissions\_boundary](#input\_irsa\_iam\_permissions\_boundary) | IAM permissions boundary for IRSA roles | `string` | `null` | no |
-| <a name="input_irsa_iam_role_path"></a> [irsa\_iam\_role\_path](#input\_irsa\_iam\_role\_path) | IAM role path for IRSA roles | `string` | `"/"` | no |
-| <a name="input_managed_prometheus_workspace_endpoint"></a> [managed\_prometheus\_workspace\_endpoint](#input\_managed\_prometheus\_workspace\_endpoint) | Amazon Managed Prometheus Workspace Endpoint | `string` | `""` | no |
 | <a name="input_managed_prometheus_workspace_id"></a> [managed\_prometheus\_workspace\_id](#input\_managed\_prometheus\_workspace\_id) | Amazon Managed Prometheus Workspace ID | `string` | `null` | no |
-| <a name="input_managed_prometheus_workspace_region"></a> [managed\_prometheus\_workspace\_region](#input\_managed\_prometheus\_workspace\_region) | Amazon Managed Prometheus Workspace's Region | `string` | `null` | no |
-| <a name="input_tags"></a> [tags](#input\_tags) | Additional tags (e.g. `map('BusinessUnit`,`XYZ`) | `map(string)` | `{}` | no |
 
 ## Outputs
 

modules/eks-monitoring/patterns/nginx/main.tf

@@ -1,7 +1,3 @@
-################################################################################################################################################
-# Alerting rules ###############################################################################################################################
-################################################################################################################################################
-
 resource "aws_prometheus_rule_group_namespace" "alerting_rules" {
   count = var.enable_alerting_rules ? 1 : 0
 
@@ -41,3 +37,8 @@ groups:
          description: "Nginx p99 latency is higher than 3 seconds\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 EOF
 }
+resource "grafana_dashboard" "workloads" {
+  folder      = var.dashboards_folder_id
+  config_json = file("${path.module}/dashboards/nginx.json")
+
+}

modules/eks-monitoring/patterns/nginx/variables.tf

@@ -0,0 +1,16 @@
+variable "managed_prometheus_workspace_id" {
+  description = "Amazon Managed Prometheus Workspace ID"
+  type        = string
+  default     = null
+}
+
+variable "dashboards_folder_id" {
+  type        = string
+  description = "Grafana folder ID for automatic dashboards"
+}
+
+variable "enable_alerting_rules" {
+  type        = bool
+  default     = true
+  description = "Enables or disables Managed Prometheus alerting rules"
+}

modules/eks-monitoring/rules.tf

@@ -5,7 +5,6 @@
 ################################################################################################################################################
 
 resource "aws_prometheus_rule_group_namespace" "recording_rules" {
-  count        = var.enable_recording_rules ? 1 : 0
   name         = "accelerator-infra-rules"
   workspace_id = var.managed_prometheus_workspace_id
   data         = <<EOF

modules/eks-monitoring/variables.tf

@@ -3,6 +3,18 @@ variable "eks_cluster_id" {
   type        = string
 }
 
+variable "enable_amazon_eks_adot" {
+  description = "Enables the ADOT Operator on the EKS Cluster"
+  type        = bool
+  default     = true
+}
+
+variable "enable_cert_manager" {
+  description = "Allow reusing an existing installation of cert-manager"
+  type        = bool
+  default     = true
+}
+
 variable "helm_config" {
   description = "Helm Config for Prometheus"
   type        = any
@@ -44,12 +56,6 @@ variable "dashboards_folder_id" {
   type        = string
 }
 
-variable "enable_recording_rules" {
-  description = "Enables or disables Managed Prometheus recording rules. Disabling this might affect some data in the dashboards"
-  type        = bool
-  default     = true
-}
-
 variable "enable_alerting_rules" {
   description = "Enables or disables Managed Prometheus alerting rules"
   type        = bool
@@ -201,3 +207,43 @@ variable "custom_metrics_config" {
     dropped_series_prefixes = ["unspecified"]
   }
 }
+
+variable "enable_java" {
+  description = "Enable Java workloads monitoring, alerting and default dashboards"
+  type        = bool
+  default     = false
+}
+
+variable "java_config" {
+  description = "Configuration object for Java/JMX monitoring"
+  type = object({
+    enable_alerting_rules = bool
+    scrape_sample_limit   = number
+  })
+
+  default = {
+    enable_alerting_rules = true
+    scrape_sample_limit   = 1000
+  }
+}
+
+variable "enable_nginx" {
+  description = "Enable NGINX workloads monitoring, alerting and default dashboards"
+  type        = bool
+  default     = false
+}
+
+variable "nginx_config" {
+  description = "Configuration object for NGINX monitoring"
+  type = object({
+    enable_alerting_rules       = bool
+    scrape_sample_limit         = number
+    prometheus_metrics_endpoint = string
+  })
+
+  default = {
+    enable_alerting_rules       = true
+    scrape_sample_limit         = 1000
+    prometheus_metrics_endpoint = "metrics"
+  }
+}

modules/managed-prometheus-monitoring/main.tf

@@ -9,9 +9,11 @@ locals {
 }
 
 resource "grafana_data_source" "cloudwatch" {
-  type       = "cloudwatch"
-  name       = local.name
-  is_default = true
+  type = "cloudwatch"
+  name = local.name
+
+  # Giving priority to Managed Prometheus datasources
+  is_default = false
   json_data {
     default_region  = var.aws_region
     sigv4_auth      = true
@@ -26,7 +28,7 @@ resource "grafana_dashboard" "this" {
 }
 
 module "billing" {
-  source = "../../workloads/managed-prometheus-monitoring/billing"
+  source = "./billing"
   providers = {
     aws = aws.billing_region
   }

modules/workloads/infra/outputs.tf

@@ -1,10 +0,0 @@
-output "grafana_dashboard_urls" {
-  value = [concat(
-    grafana_dashboard.workloads[*].url,
-    grafana_dashboard.nodes[*].url,
-    grafana_dashboard.nsworkload[*].url,
-    grafana_dashboard.kubelet[*].url,
-    grafana_dashboard.cluster[*].url,
-  )]
-  description = "URLs for dashboards created"
-}

modules/workloads/java/README.md

@@ -1,68 +0,0 @@
-# Java based workloads monitoring
-
-This module provides monitoring for Java based workloads with the following resources:
-
-- AWS Distro For OpenTelemetry Operator and Collector
-- AWS Managed Grafana Dashboard and data source
-- Alerts and recording rules with AWS Managed Service for Prometheus
-
-<!-- BEGINNING OF PRE-COMMIT-TERRAFORM DOCS HOOK -->
-## Requirements
-
-| Name | Version |
-|------|---------|
-| <a name="requirement_terraform"></a> [terraform](#requirement\_terraform) | >= 1.1.0 |
-| <a name="requirement_aws"></a> [aws](#requirement\_aws) | >= 4.0.0 |
-| <a name="requirement_grafana"></a> [grafana](#requirement\_grafana) | >= 1.25.0 |
-| <a name="requirement_helm"></a> [helm](#requirement\_helm) | >= 2.4.1 |
-| <a name="requirement_kubectl"></a> [kubectl](#requirement\_kubectl) | >= 1.14 |
-| <a name="requirement_kubernetes"></a> [kubernetes](#requirement\_kubernetes) | >= 2.10 |
-
-## Providers
-
-| Name | Version |
-|------|---------|
-| <a name="provider_aws"></a> [aws](#provider\_aws) | >= 4.0.0 |
-| <a name="provider_grafana"></a> [grafana](#provider\_grafana) | >= 1.25.0 |
-
-## Modules
-
-| Name | Source | Version |
-|------|--------|---------|
-| <a name="module_helm_addon"></a> [helm\_addon](#module\_helm\_addon) | github.com/aws-ia/terraform-aws-eks-blueprints//modules/kubernetes-addons/helm-addon | v4.13.1 |
-
-## Resources
-
-| Name | Type |
-|------|------|
-| [aws_prometheus_rule_group_namespace.alerting_rules](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/prometheus_rule_group_namespace) | resource |
-| [aws_prometheus_rule_group_namespace.recording_rules](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/prometheus_rule_group_namespace) | resource |
-| [grafana_dashboard.this](https://registry.terraform.io/providers/grafana/grafana/latest/docs/resources/dashboard) | resource |
-| [aws_caller_identity.current](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/caller_identity) | data source |
-| [aws_eks_cluster.eks_cluster](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/eks_cluster) | data source |
-| [aws_partition.current](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/partition) | data source |
-| [aws_region.current](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/data-sources/region) | data source |
-
-## Inputs
-
-| Name | Description | Type | Default | Required |
-|------|-------------|------|---------|:--------:|
-| <a name="input_dashboards_folder_id"></a> [dashboards\_folder\_id](#input\_dashboards\_folder\_id) | Grafana folder ID for automatic dashboards | `string` | n/a | yes |
-| <a name="input_eks_cluster_id"></a> [eks\_cluster\_id](#input\_eks\_cluster\_id) | EKS Cluster Id | `string` | n/a | yes |
-| <a name="input_enable_alerting_rules"></a> [enable\_alerting\_rules](#input\_enable\_alerting\_rules) | Enables or disables Managed Prometheus alerting rules | `bool` | `true` | no |
-| <a name="input_enable_recording_rules"></a> [enable\_recording\_rules](#input\_enable\_recording\_rules) | Enables or disables Managed Prometheus recording rules. Disabling this might affect some data in the dashboards | `bool` | `true` | no |
-| <a name="input_helm_config"></a> [helm\_config](#input\_helm\_config) | Helm Config for Prometheus | `any` | `{}` | no |
-| <a name="input_irsa_iam_permissions_boundary"></a> [irsa\_iam\_permissions\_boundary](#input\_irsa\_iam\_permissions\_boundary) | IAM permissions boundary for IRSA roles | `string` | `null` | no |
-| <a name="input_irsa_iam_role_path"></a> [irsa\_iam\_role\_path](#input\_irsa\_iam\_role\_path) | IAM role path for IRSA roles | `string` | `"/"` | no |
-| <a name="input_managed_prometheus_workspace_endpoint"></a> [managed\_prometheus\_workspace\_endpoint](#input\_managed\_prometheus\_workspace\_endpoint) | Amazon Managed Prometheus Workspace Endpoint | `string` | `""` | no |
-| <a name="input_managed_prometheus_workspace_id"></a> [managed\_prometheus\_workspace\_id](#input\_managed\_prometheus\_workspace\_id) | Amazon Managed Prometheus Workspace ID | `string` | `null` | no |
-| <a name="input_managed_prometheus_workspace_region"></a> [managed\_prometheus\_workspace\_region](#input\_managed\_prometheus\_workspace\_region) | Amazon Managed Prometheus Workspace's Region | `string` | `null` | no |
-| <a name="input_prometheus_config"></a> [prometheus\_config](#input\_prometheus\_config) | Controls default values such as scrape interval, timeouts and ports globally | <pre>object({<br>    global_scrape_interval = string<br>    global_scrape_timeout  = string<br>    scrape_sample_limit    = number<br>  })</pre> | <pre>{<br>  "global_scrape_interval": "60s",<br>  "global_scrape_timeout": "15s",<br>  "scrape_sample_limit": 1000<br>}</pre> | no |
-| <a name="input_tags"></a> [tags](#input\_tags) | Additional tags (e.g. `map('BusinessUnit`,`XYZ`) | `map(string)` | `{}` | no |
-
-## Outputs
-
-| Name | Description |
-|------|-------------|
-| <a name="output_grafana_dashboard_urls"></a> [grafana\_dashboard\_urls](#output\_grafana\_dashboard\_urls) | URLs for dashboards created |
-<!-- END OF PRE-COMMIT-TERRAFORM DOCS HOOK -->

modules/workloads/java/locals.tf

@@ -1,31 +0,0 @@
-data "aws_partition" "current" {}
-
-data "aws_caller_identity" "current" {}
-
-data "aws_region" "current" {}
-
-data "aws_eks_cluster" "eks_cluster" {
-  name = var.eks_cluster_id
-}
-
-locals {
-  name      = "adot-collector-java"
-  namespace = try(var.helm_config.namespace, local.name)
-
-  eks_oidc_issuer_url  = replace(data.aws_eks_cluster.eks_cluster.identity[0].oidc[0].issuer, "https://", "")
-  eks_cluster_endpoint = data.aws_eks_cluster.eks_cluster.endpoint
-
-  context = {
-    aws_caller_identity_account_id = data.aws_caller_identity.current.account_id
-    aws_caller_identity_arn        = data.aws_caller_identity.current.arn
-    aws_eks_cluster_endpoint       = local.eks_cluster_endpoint
-    aws_partition_id               = data.aws_partition.current.partition
-    aws_region_name                = data.aws_region.current.name
-    eks_cluster_id                 = var.eks_cluster_id
-    eks_oidc_issuer_url            = local.eks_oidc_issuer_url
-    eks_oidc_provider_arn          = "arn:${data.aws_partition.current.partition}:iam::${data.aws_caller_identity.current.account_id}:oidc-provider/${local.eks_oidc_issuer_url}"
-    tags                           = var.tags
-    irsa_iam_role_path             = var.irsa_iam_role_path
-    irsa_iam_permissions_boundary  = var.irsa_iam_permissions_boundary
-  }
-}

modules/workloads/java/main.tf

@@ -1,95 +0,0 @@
-# deploys collector
-module "helm_addon" {
-  source = "github.com/aws-ia/terraform-aws-eks-blueprints//modules/kubernetes-addons/helm-addon?ref=v4.13.1"
-
-  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.managed_prometheus_workspace_endpoint}api/v1/remote_write"
-    },
-    {
-      name  = "region"
-      value = var.managed_prometheus_workspace_region
-    },
-    {
-      name  = "ekscluster"
-      value = local.context.eks_cluster_id
-    },
-    {
-      name  = "accountId"
-      value = local.context.aws_caller_identity_account_id
-    },
-    {
-      name  = "globalScrapeInterval"
-      value = var.prometheus_config.global_scrape_interval
-    },
-    {
-      name  = "globalScrapeTimeout"
-      value = var.prometheus_config.global_scrape_timeout
-    },
-    {
-      name  = "scrapeSampleLimit"
-      value = var.prometheus_config.scrape_sample_limit
-    }
-  ]
-
-  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:${data.aws_partition.current.partition}:iam::aws:policy/AmazonPrometheusRemoteWriteAccess"]
-  }
-
-  addon_context = local.context
-}
-
-resource "aws_prometheus_rule_group_namespace" "recording_rules" {
-  count = var.enable_recording_rules ? 1 : 0
-
-  name         = "accelerator-java-rules"
-  workspace_id = var.managed_prometheus_workspace_id
-  data         = <<EOF
-groups:
-  - name: default-metric
-    rules:
-      - record: metric:recording_rule
-        expr: avg(rate(container_cpu_usage_seconds_total[5m]))
-EOF
-}
-
-resource "aws_prometheus_rule_group_namespace" "alerting_rules" {
-  count = var.enable_alerting_rules ? 1 : 0
-
-  name         = "accelerator-java-alerting"
-  workspace_id = var.managed_prometheus_workspace_id
-  data         = <<EOF
-groups:
-  - name: default-alert
-    rules:
-      - alert: metric:alerting_rule
-        expr: jvm_memory_bytes_used{job="java", area="heap"} / jvm_memory_bytes_max * 100 > 80
-        for: 1m
-        labels:
-            severity: warning
-        annotations:
-            summary: "JVM heap warning"
-            description: "JVM heap of instance `{{$labels.instance}}` from application `{{$labels.application}}` is above 80% for one minute. (current=`{{$value}}%`)"
-EOF
-}
-
-resource "grafana_dashboard" "this" {
-  folder      = var.dashboards_folder_id
-  config_json = file("${path.module}/dashboards/default.json")
-}

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

@@ -1,6 +0,0 @@
-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

@@ -1,29 +0,0 @@
-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

@@ -1,12 +0,0 @@
-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

@@ -1,71 +0,0 @@
-apiVersion: opentelemetry.io/v1alpha1
-kind: OpenTelemetryCollector
-metadata:
-  name: adot
-spec:
-  image: public.ecr.aws/aws-observability/aws-otel-collector:v0.22.0
-  mode: deployment
-  serviceAccount: adot-collector-java
-  config: |
-    receivers:
-      prometheus:
-        config:
-          global:
-            scrape_interval: {{ .Values.globalScrapeInterval }}
-            scrape_timeout: {{ .Values.globalScrapeTimeout }}
-            external_labels:
-              cluster: {{ .Values.ekscluster }}
-              account_id: {{ .Values.accountId }}
-              region: {{ .Values.region }}
-          scrape_configs:
-            - job_name: 'kubernetes-pod-jmx'
-              sample_limit: {{ .Values.scrapeSampleLimit }}
-              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:
-      prometheusremotewrite:
-        endpoint: {{ .Values.ampurl }}
-        auth:
-          authenticator: sigv4auth
-      logging:
-          loglevel: info
-    extensions:
-      sigv4auth:
-        region: {{ .Values.region }}
-        service: "aps"
-      health_check:
-      pprof:
-        endpoint: :1888
-      zpages:
-        endpoint: :55679
-    service:
-      extensions: [pprof, zpages, health_check, sigv4auth]
-      pipelines:
-        metrics:
-          receivers: [prometheus]
-          exporters: [logging, prometheusremotewrite]

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

@@ -1,6 +0,0 @@
-ampurl: ${amp_url}
-region: ${region}
-prometheusMetricsEndpoint: ${prometheus_metrics_endpoint}
-globalScrapeInterval: ${scrape_interval}
-globalScrapeTimeout: ${scrape_timeout}
-scrapeSampleLimit: ${scrape_sample_limit}

modules/workloads/java/variables.tf

@@ -1,79 +0,0 @@
-variable "eks_cluster_id" {
-  description = "EKS Cluster Id"
-  type        = string
-}
-
-variable "irsa_iam_role_path" {
-  description = "IAM role path for IRSA roles"
-  type        = string
-  default     = "/"
-}
-
-variable "irsa_iam_permissions_boundary" {
-  description = "IAM permissions boundary for IRSA roles"
-  type        = string
-  default     = null
-}
-
-variable "enable_recording_rules" {
-  description = "Enables or disables Managed Prometheus recording rules. Disabling this might affect some data in the dashboards"
-  type        = bool
-  default     = true
-}
-
-variable "enable_alerting_rules" {
-  description = "Enables or disables Managed Prometheus alerting rules"
-  type        = bool
-  default     = true
-}
-
-variable "managed_prometheus_workspace_endpoint" {
-  description = "Amazon Managed Prometheus Workspace Endpoint"
-  type        = string
-  default     = ""
-}
-
-variable "managed_prometheus_workspace_id" {
-  description = "Amazon Managed Prometheus Workspace ID"
-  type        = string
-  default     = null
-}
-
-variable "managed_prometheus_workspace_region" {
-  description = "Amazon Managed Prometheus Workspace's Region"
-  type        = string
-  default     = null
-}
-
-variable "helm_config" {
-  description = "Helm Config for Prometheus"
-  type        = any
-  default     = {}
-}
-
-variable "dashboards_folder_id" {
-  description = "Grafana folder ID for automatic dashboards"
-  type        = string
-}
-
-variable "prometheus_config" {
-  description = "Controls default values such as scrape interval, timeouts and ports globally"
-  type = object({
-    global_scrape_interval = string
-    global_scrape_timeout  = string
-    scrape_sample_limit    = number
-  })
-
-  default = {
-    global_scrape_interval = "60s"
-    global_scrape_timeout  = "15s"
-    scrape_sample_limit    = 1000
-  }
-  nullable = false
-}
-
-variable "tags" {
-  description = "Additional tags (e.g. `map('BusinessUnit`,`XYZ`)"
-  type        = map(string)
-  default     = {}
-}

modules/workloads/nginx/dashboards.tf

@@ -1,6 +0,0 @@
-resource "grafana_dashboard" "workloads" {
-  count = var.enable_dashboards ? 1 : 0
-
-  folder      = var.dashboards_folder_id
-  config_json = file("${path.module}/dashboards/nginx.json")
-}

modules/workloads/nginx/locals.tf

@@ -1,31 +0,0 @@
-data "aws_partition" "current" {}
-
-data "aws_caller_identity" "current" {}
-
-data "aws_region" "current" {}
-
-data "aws_eks_cluster" "eks_cluster" {
-  name = var.eks_cluster_id
-}
-
-locals {
-  name      = "adot-collector-nginx"
-  namespace = try(var.config.helm_config.namespace, local.name)
-
-  eks_oidc_issuer_url  = replace(data.aws_eks_cluster.eks_cluster.identity[0].oidc[0].issuer, "https://", "")
-  eks_cluster_endpoint = data.aws_eks_cluster.eks_cluster.endpoint
-
-  context = {
-    aws_caller_identity_account_id = data.aws_caller_identity.current.account_id
-    aws_caller_identity_arn        = data.aws_caller_identity.current.arn
-    aws_eks_cluster_endpoint       = local.eks_cluster_endpoint
-    aws_partition_id               = data.aws_partition.current.partition
-    aws_region_name                = data.aws_region.current.name
-    eks_cluster_id                 = var.eks_cluster_id
-    eks_oidc_issuer_url            = local.eks_oidc_issuer_url
-    eks_oidc_provider_arn          = "arn:${data.aws_partition.current.partition}:iam::${data.aws_caller_identity.current.account_id}:oidc-provider/${local.eks_oidc_issuer_url}"
-    tags                           = var.tags
-    irsa_iam_role_path             = var.irsa_iam_role_path
-    irsa_iam_permissions_boundary  = var.irsa_iam_permissions_boundary
-  }
-}

modules/workloads/nginx/main.tf

@@ -1,55 +0,0 @@
-module "helm_addon" {
-  source = "github.com/aws-ia/terraform-aws-eks-blueprints//modules/kubernetes-addons/helm-addon?ref=v4.13.1"
-
-  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.managed_prometheus_workspace_endpoint}api/v1/remote_write"
-    },
-    {
-      name  = "region"
-      value = var.managed_prometheus_workspace_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 = local.context
-}

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

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

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

@@ -1,29 +0,0 @@
-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/nginx/otel-config/templates/clusterrolebinding.yaml

@@ -1,12 +0,0 @@
-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-nginx
-    namespace: adot-collector-nginx

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

@@ -1,68 +0,0 @@
-apiVersion: opentelemetry.io/v1alpha1
-kind: OpenTelemetryCollector
-metadata:
-  name: adot
-spec:
-  image: public.ecr.aws/aws-observability/aws-otel-collector:v0.21.1
-  mode: deployment
-  serviceAccount: adot-collector-nginx
-  config: |
-    receivers:
-      prometheus:
-        config:
-          global:
-            scrape_interval: {{ .Values.scrapeInterval }}
-            scrape_timeout: {{ .Values.scrapeTimeout }}
-          scrape_configs:
-          - job_name: 'kubernetes-pod-nginx'
-            sample_limit: {{ .Values.scrapeSampleLimit }}
-            metrics_path: /{{ .Values.prometheusMetricsEndpoint }}
-            kubernetes_sd_configs:
-              - role: pod
-            relabel_configs:
-              - source_labels: [ __address__ ]
-                action: keep
-                regex: '.*:10254$'
-              - source_labels: [__meta_kubernetes_pod_container_name]
-                target_label: container
-                action: replace
-              - source_labels: [__meta_kubernetes_pod_node_name]
-                target_label: host
-                action: replace
-              - source_labels: [__meta_kubernetes_namespace]
-                target_label: namespace
-                action: replace
-            metric_relabel_configs:
-              - source_labels: [__name__]
-                regex: 'go_memstats.*'
-                action: drop
-              - source_labels: [__name__]
-                regex: 'go_gc.*'
-                action: drop
-              - source_labels: [__name__]
-                regex: 'go_threads'
-                action: drop
-              - regex: exported_host
-                action: labeldrop
-    exporters:
-      prometheusremotewrite:
-        endpoint: {{ .Values.ampurl }}
-        auth:
-          authenticator: sigv4auth
-      logging:
-          loglevel: info
-    extensions:
-      sigv4auth:
-        region: {{ .Values.region }}
-        service: "aps"
-      health_check:
-      pprof:
-        endpoint: :1888
-      zpages:
-        endpoint: :55679
-    service:
-      extensions: [pprof, zpages, health_check, sigv4auth]
-      pipelines:
-        metrics:
-          receivers: [prometheus]
-          exporters: [logging, prometheusremotewrite]

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

@@ -1,7 +0,0 @@
-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/nginx/variables.tf

@@ -1,69 +0,0 @@
-
-variable "eks_cluster_id" {
-  description = "EKS Cluster Id"
-  type        = string
-}
-
-variable "helm_config" {
-  description = "Helm Config for Prometheus"
-  type        = any
-  default     = {}
-}
-
-variable "irsa_iam_role_path" {
-  description = "IAM role path for IRSA roles"
-  type        = string
-  default     = "/"
-}
-
-variable "irsa_iam_permissions_boundary" {
-  description = "IAM permissions boundary for IRSA roles"
-  type        = string
-  default     = null
-}
-
-variable "managed_prometheus_workspace_endpoint" {
-  description = "Amazon Managed Prometheus Workspace Endpoint"
-  type        = string
-  default     = ""
-}
-variable "managed_prometheus_workspace_id" {
-  description = "Amazon Managed Prometheus Workspace ID"
-  type        = string
-  default     = null
-}
-
-variable "managed_prometheus_workspace_region" {
-  description = "Amazon Managed Prometheus Workspace's Region"
-  type        = string
-  default     = null
-}
-
-variable "dashboards_folder_id" {
-  type        = string
-  description = "Grafana folder ID for automatic dashboards"
-}
-
-variable "enable_alerting_rules" {
-  type        = bool
-  default     = true
-  description = "Enables or disables Managed Prometheus alerting rules"
-}
-
-variable "enable_dashboards" {
-  type        = bool
-  description = "Enables or disables curated dashboards"
-  default     = true
-}
-
-variable "config" {
-  description = "Helm Config for Prometheus"
-  type        = any
-  default     = {}
-}
-
-variable "tags" {
-  description = "Additional tags (e.g. `map('BusinessUnit`,`XYZ`)"
-  type        = map(string)
-  default     = {}
-}