Node exporter dashboards (#43)

* Added dashboards for node exporter
* Drop use cluster and node
* Add nodename to ne metrics
* Add account ID and region

Co-authored-by: Venkataraman <vikrvenk@88665a367666.ant.amazon.com>
Co-authored-by: Rodrigue Koffi <bonclay7@users.noreply.github.com>

.github/workflows/plan-examples.yml

@@ -8,7 +8,7 @@ on:
   workflow_dispatch:
 
 concurrency:
-  group: '${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}'
+  group: "${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}"
   cancel-in-progress: true
 
 jobs:

.github/workflows/pre-commit.yaml

@@ -137,4 +137,4 @@ jobs:
         with:
           terraform-version: ${{ steps.minMax.outputs.maxVersion }}
           terraform-docs-version: ${{ env.TERRAFORM_DOCS_VERSION }}
-          tflint-version: ${{ env.TFLINT_VERSION }}
+          tflint-version: ${{ env.TFLINT_VERSION }}

.github/workflows/stale_issue_pr.yaml

@@ -30,4 +30,4 @@ jobs:
             with no activity. Remove stale label or comment or this issue will be closed in 10 days
           stale-pr-message: |
             This PR has been automatically marked as stale because it has been open 30 days
-            with no activity. Remove stale label or comment or this PR will be closed in 10 days
+            with no activity. Remove stale label or comment or this PR will be closed in 10 days

modules/workloads/infra/README.md

@@ -42,6 +42,7 @@ This module is inspired from the open source [kube-prometheus-stack](https://git
 | [aws_prometheus_rule_group_namespace.recording_rules](https://registry.terraform.io/providers/hashicorp/aws/latest/docs/resources/prometheus_rule_group_namespace) | resource |
 | [grafana_dashboard.cluster](https://registry.terraform.io/providers/grafana/grafana/latest/docs/resources/dashboard) | resource |
 | [grafana_dashboard.kubelet](https://registry.terraform.io/providers/grafana/grafana/latest/docs/resources/dashboard) | resource |
+| [grafana_dashboard.nodeexp_nodes](https://registry.terraform.io/providers/grafana/grafana/latest/docs/resources/dashboard) | resource |
 | [grafana_dashboard.nodes](https://registry.terraform.io/providers/grafana/grafana/latest/docs/resources/dashboard) | resource |
 | [grafana_dashboard.nsworkload](https://registry.terraform.io/providers/grafana/grafana/latest/docs/resources/dashboard) | resource |
 | [grafana_dashboard.workloads](https://registry.terraform.io/providers/grafana/grafana/latest/docs/resources/dashboard) | resource |

modules/workloads/infra/dashboards.tf

@@ -28,3 +28,9 @@ resource "grafana_dashboard" "cluster" {
   folder      = var.dashboards_folder_id
   config_json = file("${path.module}/dashboards/cluster.json")
 }
+
+resource "grafana_dashboard" "nodeexp_nodes" {
+  count       = var.enable_dashboards ? 1 : 0
+  folder      = var.dashboards_folder_id
+  config_json = file("${path.module}/dashboards/nodeexporter-nodes.json")
+}

modules/workloads/infra/main.tf

@@ -41,7 +41,7 @@ module "helm_addon" {
     {
       name        = local.name
       chart       = "${path.module}/otel-config"
-      version     = "0.3.0"
+      version     = "0.3.1"
       namespace   = local.namespace
       description = "ADOT helm Chart deployment configuration"
     },
@@ -69,6 +69,10 @@ module "helm_addon" {
       name  = "globalScrapeTimeout"
       value = var.prometheus_config.global_scrape_timeout
     },
+    {
+      name  = "accountId"
+      value = local.context.aws_caller_identity_account_id
+    },
   ]
 
   irsa_config = {

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

@@ -15,6 +15,8 @@ spec:
             scrape_timeout: {{ .Values.globalScrapeTimeout }}
             external_labels:
               cluster: {{ .Values.ekscluster }}
+              account_id: {{ .Values.accountId }}
+              region: {{ .Values.region }}
           scrape_configs:
             - job_name: 'kubernetes-kubelet'
               scrape_interval: {{ .Values.globalScrapeInterval }}
@@ -1552,6 +1554,14 @@ spec:
             - job_name: 'node-exporter'
               kubernetes_sd_configs:
                 - role: endpoints
+              ec2_sd_configs:
+              relabel_configs:
+                - source_labels: [ __address__ ]
+                  action: keep
+                  regex: '.*:9100$'
+                - action: replace
+                  source_labels: [__meta_kubernetes_endpoint_node_name]
+                  target_label: nodename
     exporters:
       prometheusremotewrite:
         endpoint: {{ .Values.ampurl }}