Add Traefik Dashboard (#797)

nebari-dev · Sep 13, 2021 · 8d1ae18 · 8d1ae18
1 parent a0b3d90
commit 8d1ae18
Show file tree

Hide file tree

Showing 4 changed files with 1,407 additions and 0 deletions.
diff --git a/.github/workflows/kubernetes_test.yaml b/.github/workflows/kubernetes_test.yaml
@@ -122,6 +122,9 @@ jobs:
 
       - name: Get qhub-config.yaml full path
         run: echo "QHUB_CONFIG_PATH=`realpath ./local-deployment/qhub-config.yaml`" >> $GITHUB_ENV
+
+      - name: Sleep to see if it fixes flaky Kubernetes Tests 
+        run: sleep 60
 
       - name: Cypress run
         uses: cypress-io/github-action@v2

diff --git a/...plate/{{ cookiecutter.repo_directory }}/infrastructure/modules/kubernetes/ingress/main.tf b/...plate/{{ cookiecutter.repo_directory }}/infrastructure/modules/kubernetes/ingress/main.tf
@@ -107,6 +107,38 @@ resource "kubernetes_service" "main" {
   }
 }
 
+resource "kubernetes_service" "traefik_internal" {
+  wait_for_load_balancer = true
+
+  metadata {
+    name      = "${var.name}-traefik-internal"
+    namespace = var.namespace
+    annotations = {
+      "prometheus.io/scrape" = "true"
+      "prometheus.io/path"   = "/metrics"
+      "prometheus.io/port"   = 9000
+    }
+    labels = {
+      "app.kubernetes.io/component" = "traefik-internal-service"
+      "app.kubernetes.io/part-of"   = "traefik-ingress"
+    }
+  }
+
+  spec {
+    selector = {
+      "app.kubernetes.io/component" = "traefik-ingress"
+    }
+
+    port {
+      name        = "http"
+      protocol    = "TCP"
+      port        = 9000
+      target_port = 9000
+    }
+
+    type = "ClusterIP"
+  }
+}
 
 resource "kubernetes_deployment" "main" {
   metadata {
@@ -189,6 +221,8 @@ resource "kubernetes_deployment" "main" {
             "--entryPoints.traefik.address=:9000",
             "--entrypoints.web.http.redirections.entryPoint.to=websecure",
             "--entrypoints.web.http.redirections.entryPoint.scheme=https",
+            # Enable Prometheus Monitoring of Traefik
+            "--metrics.prometheus=true",
             # Enable debug logging. Useful to work out why something might not be
             # working. Fetch logs of the pod.
             "--log.level=${var.loglevel}",

diff --git a/...kiecutter.repo_directory }}/infrastructure/modules/kubernetes/services/monitoring/main.tf b/...kiecutter.repo_directory }}/infrastructure/modules/kubernetes/services/monitoring/main.tf
@@ -5,6 +5,34 @@ resource "helm_release" "kube-prometheus-stack-helm-deployment" {
   chart      = "kube-prometheus-stack"
   version    = "16.12.0"
 
+  values = [<<EOT
+prometheus:    
+  prometheusSpec:    
+    additionalScrapeConfigs:    
+    
+    # This job will scrape from any service with the label app.kubernetes.io/component=traefik-internal-service
+    # and the annotation app.kubernetes.io/scrape=true 
+    - job_name: 'traefik'    
+    
+      kubernetes_sd_configs:    
+        - role: service    
+          
+      relabel_configs:    
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]    
+        action: keep    
+        regex: true    
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]    
+        action: replace    
+        target_label: __metrics_path__    
+        regex: (.+)    
+      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
+        action: replace    
+        regex: ([^:]+)(?::\d+)?;(\d+)    
+        replacement: $1:$2    
+        target_label: __address__
+EOT
+  ]
+
   set {
     name  = "grafana.grafana\\.ini.server.domain"
     value = var.external-url
@@ -19,7 +47,26 @@ resource "helm_release" "kube-prometheus-stack-helm-deployment" {
     name  = "grafana.grafana\\.ini.server.server_from_sub_path"
     value = "true"
   }
+}
+
+resource "kubernetes_manifest" "traefik_dashboard_configmap" {
+  provider = kubernetes-alpha
 
+  manifest = {
+    apiVersion = "v1"
+    kind       = "ConfigMap"
+    metadata = {
+      name      = "grafana-traefik-dashboard"
+      namespace = var.namespace
+      labels = {
+        # grafana_dashboard label needed for grafana to pick it up automatically
+        grafana_dashboard = "1"
+      }
+    }
+    data = {
+      "traefik-dashboard.json" = file("${path.module}/traefik.json")
+    }
+  }
 }
 
 resource "kubernetes_manifest" "grafana-strip-prefix-middleware" {