Feat: Introducing Grafana(7.0.2) and Prometheus(25.4.0) Addon

.github/workflows/readme.yml

@@ -5,8 +5,6 @@ on:
   push:
     branches:
       - master
-    paths:
-      - '_examples/**' 
   workflow_dispatch:
 
 jobs:
@@ -26,7 +24,7 @@ jobs:
         uses: actions/checkout@master
         with:
           fetch-depth: 0
-          ref: master
+          ref: ${{ github.head_ref }}
           token: ${{ env.GH_TOKEN }}
 
       - name: 'Set up Python 3.7'
@@ -84,13 +82,13 @@ jobs:
         uses: actions/checkout@master
         with:
           fetch-depth: 0
-          ref: master
+          ref: ${{ github.head_ref }}
           token: ${{ env.GH_TOKEN }}
 
       - name: Generate TF Docs
         uses: terraform-docs/gh-actions@v1.0.0
         with:
-          working-dir: addons/aws-ebs-csi-driver,addons/aws-efs-csi-driver,addons/aws-load-balancer-controller,addons/aws-node-termination-handler,addons/calico-tigera,addons/cluster-autoscaler,addons/external-secrets,addons/fluent-bit,addons/helm,addons/ingress-nginx,addons/istio-ingress,addons/karpenter,addons/kiali-server,addons/kubeclarity,addons/metrics-server,addons/nri-bundle,addons/velero,addons/kube-state-metrics,addons/keda,addons/cert-manager,addons/filebeat,addons/reloader,addons/external-dns,addons/redis,addons/actions-runner-controller
+          working-dir: addons/aws-ebs-csi-driver,addons/aws-efs-csi-driver,addons/aws-load-balancer-controller,addons/aws-node-termination-handler,addons/calico-tigera,addons/cluster-autoscaler,addons/external-secrets,addons/fluent-bit,addons/helm,addons/ingress-nginx,addons/istio-ingress,addons/karpenter,addons/kiali-server,addons/kubeclarity,addons/metrics-server,addons/nri-bundle,addons/velero,addons/kube-state-metrics,addons/keda,addons/cert-manager,addons/filebeat,addons/reloader,addons/external-dns,addons/redis,addons/prometheus,addons/jaeger,addons/grafana,addons/actions-runner-controller
           git-push: true
           template: |-
             <!-- BEGINNING OF PRE-COMMIT-TERRAFORM DOCS HOOK -->

_examples/complete/config/jaeger/override-cassandra.yaml

@@ -0,0 +1,16 @@
+affinity:
+  nodeAffinity:
+    requiredDuringSchedulingIgnoredDuringExecution:
+      nodeSelectorTerms:
+      - matchExpressions:
+        - key: "eks.amazonaws.com/nodegroup"
+          operator: In
+          values:
+          - "test-clouddrove-eks-test-cluster-critical-nodes"
+resources:
+  limits:
+    cpu: 300m
+    memory: 250Mi
+  requests:
+    cpu: 50m
+    memory: 150Mi

_examples/complete/config/jaeger/override-jaeger.yaml

@@ -0,0 +1,64 @@
+provisionDataStore:
+  cassandra: false
+agent:
+  affinity:
+    nodeAffinity:
+      requiredDuringSchedulingIgnoredDuringExecution:
+        nodeSelectorTerms:
+        - matchExpressions:
+          - key: "eks.amazonaws.com/nodegroup"
+            operator: In
+            values:
+            - "test-clouddrove-eks-test-cluster-critical-nodes"
+  resources:
+    limits:
+      cpu: 300m
+      memory: 250Mi
+    requests:
+      cpu: 50m
+      memory: 150Mi
+
+collector:
+  affinity:
+    nodeAffinity:
+      requiredDuringSchedulingIgnoredDuringExecution:
+        nodeSelectorTerms:
+        - matchExpressions:
+          - key: "eks.amazonaws.com/nodegroup"
+            operator: In
+            values:
+            - "test-clouddrove-eks-test-cluster-critical-nodes"
+  resources:
+    limits:
+      cpu: 300m
+      memory: 250Mi
+    requests:
+      cpu: 50m
+      memory: 150Mi
+
+query:
+  affinity:
+    nodeAffinity:
+      requiredDuringSchedulingIgnoredDuringExecution:
+        nodeSelectorTerms:
+        - matchExpressions:
+          - key: "eks.amazonaws.com/nodegroup"
+            operator: In
+            values:
+            - "test-clouddrove-eks-test-cluster-critical-nodes"
+  resources:
+    limits:
+      cpu: 300m
+      memory: 250Mi
+    requests:
+      cpu: 50m
+      memory: 150Mi
+
+schema:
+  resources:
+    limits:
+      cpu: 300m
+      memory: 250Mi
+    requests:
+      cpu: 50m
+      memory: 150Mi

_examples/complete/config/override-grafana.yaml

@@ -0,0 +1,16 @@
+affinity:
+  nodeAffinity:
+    requiredDuringSchedulingIgnoredDuringExecution:
+      nodeSelectorTerms:
+      - matchExpressions:
+        - key: "eks.amazonaws.com/nodegroup"
+          operator: In
+          values:
+          - "critical"
+resources:
+  limits:
+    cpu: 300m
+    memory: 250Mi
+  requests:
+    cpu: 50m
+    memory: 150Mi

_examples/complete/config/override-prometheus.yaml

@@ -0,0 +1,47 @@
+server:
+  service:
+    ## If false, no Service will be created for the Prometheus server
+    ##
+    enabled: true
+    annotations: 
+      service.beta.kubernetes.io/aws-load-balancer-scheme: "internet-facing"
+      service.beta.kubernetes.io/aws-load-balancer-name: "prometheus"
+    labels: {}
+    clusterIP: ""
+
+  ## Node affinity for particular node in which labels key is "Infra-Services" and value is "true"
+  affinity:
+    nodeAffinity:
+      requiredDuringSchedulingIgnoredDuringExecution:
+        nodeSelectorTerms:
+        - matchExpressions:
+          - key: "eks.amazonaws.com/nodegroup"
+            operator: In
+            values:
+            - "critical"
+
+    ## List of IP addresses at which the Prometheus server service is available
+    ## Ref: https://kubernetes.io/docs/concepts/services-networking/service/#external-ips
+    ##
+    externalIPs: []
+    loadBalancerIP: ""
+    loadBalancerSourceRanges: []
+    servicePort: 80
+    sessionAffinity: None
+    type: LoadBalancer
+
+  persistentVolume:
+    accessModes:
+      - ReadWriteOnce
+    enabled: true
+    mountPath: /data
+    size: 20Gi
+    storageClass: gp2
+
+  resources: 
+    limits:
+      cpu: 300m
+      memory: 250Mi
+    requests:
+      cpu: 50m
+      memory: 150Mi

_examples/complete/main.tf

@@ -173,8 +173,13 @@ module "addons" {
   external_dns                 = true
   redis                        = true
   actions_runner_controller    = true
+  prometheus                   = true
+  grafana                      = true
 
-
+  # Jaeger deployment
+  jaeger                 = true
+  jaeger_extra_configs   = var.jaeger_extra_configs
+  jaeger_extra_manifests = var.jaeger_extra_manifests
 
   # -- Addons with mandatory variable
   istio_ingress    = true
@@ -208,6 +213,8 @@ module "addons" {
   external_dns_helm_config                 = { values = [file("./config/override-external-dns.yaml")] }
   redis_helm_config                        = { values = [file("./config/override-redis.yaml")] }
   actions_runner_controller_helm_config    = { values = [file("./config/override-actions-runner-controller.yaml")] }
+  prometheus_helm_config                   = { values = [file("./config/override-prometheus.yaml")] }
+  grafana_helm_config                      = { values = [file("./config/override-grafana.yaml")] }
 
   # -- Override Helm Release attributes
   metrics_server_extra_configs               = var.metrics_server_extra_configs
@@ -234,6 +241,8 @@ module "addons" {
   external_dns_extra_configs                 = var.external_dns_extra_configs
   redis_extra_configs                        = var.redis_extra_configs
   actions_runner_controller_extra_configs    = var.actions_runner_controller_extra_configs
+  prometheus_extra_configs                   = var.prometheus_extra_configs
+  grafana_extra_configs                      = var.grafana_extra_configs
 
   # -- Custom IAM Policy Json for Addon's ServiceAccount
   cluster_autoscaler_iampolicy_json_content = file("./custom-iam-policies/cluster-autoscaler.json")

_examples/complete/variables.tf

@@ -208,3 +208,44 @@ variable "actions_runner_controller_extra_configs" {
   type    = any
   default = {}
 }
+
+# ------------------ PROMETHEUS --------------------------------------------------
+variable "prometheus_extra_configs" {
+  type = any
+  default = {
+    atomic    = true
+    namespace = "istio-system"
+  }
+}
+
+# ------------------ JAEGER --------------------------------------------------
+variable "jaeger_extra_configs" {
+  type = any
+  default = {
+    manifest_deployment = true
+    enable_cassandra    = false
+    enable_kafka        = false
+  }
+}
+
+variable "jaeger_extra_manifests" {
+  type = object({
+    jaeger_cassandra_file_path = list(any)
+    jaeger_kafka_file_path     = list(any)
+    jaeger_manifest            = list(any)
+  })
+  default = {
+    jaeger_cassandra_file_path = [""]
+    jaeger_kafka_file_path     = [""]
+    jaeger_manifest            = ["./config/jaeger/jaeger.yaml"]
+  }
+  description = "Path of override files to create customized depedency helm charts for jaeger"
+}
+
+# ------------------------------- GRAFANA ------------------------------------------
+variable "grafana_extra_configs" {
+  type = any
+  default = {
+    atomic = true
+  }
+}

_examples/external-eks/config/jaeger/jaeger.yaml

@@ -0,0 +1,117 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: jaeger
+  namespace: istio-system
+  labels:
+    app: jaeger
+spec:
+  selector:
+    matchLabels:
+      app: jaeger
+  template:
+    metadata:
+      labels:
+        app: jaeger
+      annotations:
+        sidecar.istio.io/inject: "false"
+        prometheus.io/scrape: "true"
+        prometheus.io/port: "14269"
+    spec:
+      containers:
+        - name: jaeger
+          image: "docker.io/jaegertracing/all-in-one:1.35"
+          env:
+            - name: BADGER_EPHEMERAL
+              value: "false"
+            - name: SPAN_STORAGE_TYPE
+              value: "badger"
+            - name: BADGER_DIRECTORY_VALUE
+              value: "/badger/data"
+            - name: BADGER_DIRECTORY_KEY
+              value: "/badger/key"
+            - name: COLLECTOR_ZIPKIN_HOST_PORT
+              value: ":9411"
+            - name: MEMORY_MAX_TRACES
+              value: "50000"
+            - name: QUERY_BASE_PATH
+              value: /jaeger
+          livenessProbe:
+            httpGet:
+              path: /
+              port: 14269
+          readinessProbe:
+            httpGet:
+              path: /
+              port: 14269
+          volumeMounts:
+            - name: data
+              mountPath: /badger
+          resources:
+            requests:
+              cpu: 10m
+      volumes:
+        - name: data
+          emptyDir: {}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: tracing
+  namespace: istio-system
+  labels:
+    app: jaeger
+spec:
+  type: ClusterIP
+  ports:
+    - name: http-query
+      port: 80
+      protocol: TCP
+      targetPort: 16686
+    # Note: Change port name if you add '--query.grpc.tls.enabled=true'
+    - name: grpc-query
+      port: 16685
+      protocol: TCP
+      targetPort: 16685
+  selector:
+    app: jaeger
+---
+# Jaeger implements the Zipkin API. To support swapping out the tracing backend, we use a Service named Zipkin.
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    name: zipkin
+  name: zipkin
+  namespace: istio-system
+spec:
+  ports:
+    - port: 9411
+      targetPort: 9411
+      name: http-query
+  selector:
+    app: jaeger
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: jaeger-collector
+  namespace: istio-system
+  labels:
+    app: jaeger
+spec:
+  type: ClusterIP
+  ports:
+  - name: jaeger-collector-http
+    port: 14268
+    targetPort: 14268
+    protocol: TCP
+  - name: jaeger-collector-grpc
+    port: 14250
+    targetPort: 14250
+    protocol: TCP
+  - port: 9411
+    targetPort: 9411
+    name: http-zipkin
+  selector:
+    app: jaeger

_examples/external-eks/config/jaeger/override-cassandra.yaml

@@ -0,0 +1,16 @@
+affinity:
+  nodeAffinity:
+    requiredDuringSchedulingIgnoredDuringExecution:
+      nodeSelectorTerms:
+      - matchExpressions:
+        - key: "eks.amazonaws.com/nodegroup"
+          operator: In
+          values:
+          - "test-clouddrove-eks-test-cluster-critical-nodes"
+resources:
+  limits:
+    cpu: 300m
+    memory: 250Mi
+  requests:
+    cpu: 50m
+    memory: 150Mi