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

.github/workflows/readme.yml

@@ -5,8 +5,8 @@ on:
   push:
     branches:
       - master
-    paths:
-      - '_examples/**' 
+    paths-ignore:
+      - '**/*README.md'
   workflow_dispatch:
 
 jobs:
@@ -26,7 +26,7 @@ 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 +84,13 @@ 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/grafana,addons/actions-runner-controller
           git-push: true
           template: |-
             <!-- BEGINNING OF PRE-COMMIT-TERRAFORM DOCS HOOK -->

_examples/complete/config/grafana/grafana-vs.yaml

@@ -0,0 +1,16 @@
+apiVersion: networking.istio.io/v1alpha3
+kind: VirtualService
+metadata:
+  name: grafana
+  namespace: monitoring
+spec:
+  hosts:
+    - dash.test.clouddrove.com
+  gateways:
+  - istio-system/istio-gateway
+  http:
+  - route:
+    - destination:
+        host: grafana
+        port:
+          number: 80

_examples/complete/config/grafana/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 +1,36 @@
+server:    
+  ## 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"
+
+  persistentVolume:     # Persistent volume will not be deployed for prometheus server pod - Enable if EBS or EFS CSI Driver is installed
+    enabled: false
+
+  resources: 
+    limits:
+      cpu: 300m
+      memory: 250Mi
+    requests:
+      cpu: 50m
+      memory: 150Mi
+
+alertmanager:                 # Dependency for prometheus server
+  enabled: true
+  persistence:                # Persistent volume will not be deployed for alertmanager - Enable if EBS or EFS CSI Driver is installed
+    enabled: false
+
+kube-state-metrics:           # Dependency for prometheus server
+  enabled: true
+
+prometheus-node-exporter:     # Dependency for prometheus server
+  enabled: true
+
+prometheus-pushgateway:       # Dependency for prometheus server
+  enabled: true

_examples/complete/main.tf

@@ -173,8 +173,13 @@ module "addons" {
   external_dns                 = true
   redis                        = true
   actions_runner_controller    = true
+  prometheus                   = true
 
-
+  # Grafaa Deployment
+  grafana               = true
+  grafana_helm_config   = { values = [file("./config/grafana/override-grafana.yaml")] }
+  grafana_manifests     = var.grafana_manifests
+  grafana_extra_configs = var.grafana_extra_configs
 
   # -- Addons with mandatory variable
   istio_ingress    = true
@@ -208,6 +213,7 @@ 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")] }
 
   # -- Override Helm Release attributes
   metrics_server_extra_configs               = var.metrics_server_extra_configs
@@ -234,6 +240,7 @@ 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
 
   # -- Custom IAM Policy Json for Addon's ServiceAccount
   cluster_autoscaler_iampolicy_json_content = file("./custom-iam-policies/cluster-autoscaler.json")

_examples/complete/providers.tf

@@ -8,22 +8,31 @@ provider "aws" {
 
 provider "kubernetes" {
   host                   = module.eks.cluster_endpoint
-  cluster_ca_certificate = base64decode(module.eks.cluster_certificate_authority_data)
-  token                  = data.aws_eks_cluster_auth.eks_cluster.token
+  cluster_ca_certificate = base64decode(data.aws_eks_cluster.eks_cluster.certificate_authority[0].data)
+  exec {
+    api_version = "client.authentication.k8s.io/v1beta1"
+    args        = ["eks", "get-token", "--cluster-name", data.aws_eks_cluster.eks_cluster.name]
+    command     = "aws"
+  }
 }
 
 provider "helm" {
   kubernetes {
     host                   = module.eks.cluster_endpoint
     cluster_ca_certificate = base64decode(module.eks.cluster_certificate_authority_data)
-    token                  = data.aws_eks_cluster_auth.eks_cluster.token
+    exec {
+      api_version = "client.authentication.k8s.io/v1beta1"
+      args        = ["eks", "get-token", "--cluster-name", data.aws_eks_cluster.eks_cluster.name]
+      command     = "aws"
+    }
   }
 }
 
 provider "kubectl" {
   host                   = module.eks.cluster_endpoint
   cluster_ca_certificate = base64decode(module.eks.cluster_certificate_authority_data)
   token                  = data.aws_eks_cluster_auth.eks_cluster.token
+  load_config_file       = false
 }
 
 # ------------------------------------------------------------------------------

_examples/complete/variables.tf

@@ -208,3 +208,29 @@ variable "actions_runner_controller_extra_configs" {
   type    = any
   default = {}
 }
+
+# ------------------ PROMETHEUS --------------------------------------------------
+variable "prometheus_extra_configs" {
+  type = any
+  default = {
+    atomic    = true
+    namespace = "istio-system"
+  }
+}
+
+# ------------------------------- GRAFANA ------------------------------------------
+variable "grafana_extra_configs" {
+  type = any
+  default = {
+    atomic = true
+  }
+}
+
+variable "grafana_manifests" {
+  type = object({
+    grafana_virtualservice_file_path = string
+  })
+  default = {
+    grafana_virtualservice_file_path = "./config/grafana/grafana-vs.yaml"
+  }
+}

_examples/complete/versions.tf

@@ -15,7 +15,7 @@ terraform {
     }
     kubectl = {
       source  = "gavinbunney/kubectl"
-      version = ">= 1.7.0"
+      version = ">= 1.14.0"
     }
   }
 }

_examples/external-eks/config/grafana/grafana-vs.yaml

@@ -0,0 +1,16 @@
+apiVersion: networking.istio.io/v1alpha3
+kind: VirtualService
+metadata:
+  name: grafana
+  namespace: istio-system
+spec:
+  hosts:
+    - dash.test.clouddrove.com
+  gateways:
+  - istio-system/istio-gateway
+  http:
+  - route:
+    - destination:
+        host: grafana
+        port:
+          number: 80

_examples/external-eks/config/grafana/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/external-eks/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/external-eks/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/external-eks/main.tf

@@ -32,7 +32,13 @@ module "addons" {
   filebeat                     = true
   reloader                     = true
   redis                        = true
+  prometheus                   = true
 
+  # Grafana Deployment
+  grafana               = true
+  grafana_helm_config   = { values = [file("./config/grafana/override-grafana.yaml")] }
+  grafana_manifests     = var.grafana_manifests
+  grafana_extra_configs = var.grafana_extra_configs
 
   # -- Addons with mandatory variable
   istio_ingress    = true
@@ -64,6 +70,7 @@ module "addons" {
   filebeat_helm_config                     = { values = [file("./config/override-filebeat.yaml")] }
   reloader_helm_config                     = { values = [file("./config/reloader/override-reloader.yaml")] }
   redis_helm_config                        = { values = [file("./config/override-redis.yaml")] }
+  prometheus_helm_config                   = { values = [file("./config/override-prometheus.yaml")] }
 
   # -- Override Helm Release attributes
   metrics_server_extra_configs               = var.metrics_server_extra_configs
@@ -88,7 +95,7 @@ module "addons" {
   filebeat_extra_configs                     = var.filebeat_extra_configs
   reloader_extra_configs                     = var.reloader_extra_configs
   redis_extra_configs                        = var.redis_extra_configs
-
+  prometheus_extra_configs                   = var.prometheus_extra_configs
 
   # -- Custom IAM Policy Json for Addon's ServiceAccount
   external_secrets_iampolicy_json_content = file("./custom-iam-policies/external-secrets.json")

_examples/external-eks/providers.tf

@@ -8,21 +8,30 @@ provider "aws" {
 provider "kubernetes" {
   host                   = data.aws_eks_cluster.eks_cluster.endpoint
   cluster_ca_certificate = base64decode(data.aws_eks_cluster.eks_cluster.certificate_authority[0].data)
-  token                  = join("", data.aws_eks_cluster_auth.eks_cluster[*].token)
+  exec {
+    api_version = "client.authentication.k8s.io/v1beta1"
+    args        = ["eks", "get-token", "--cluster-name", data.aws_eks_cluster.eks_cluster.name]
+    command     = "aws"
+  }
 }
 
 provider "helm" {
   kubernetes {
     host                   = data.aws_eks_cluster.eks_cluster.endpoint
     cluster_ca_certificate = base64decode(data.aws_eks_cluster.eks_cluster.certificate_authority[0].data)
-    token                  = join("", data.aws_eks_cluster_auth.eks_cluster[*].token)
+    exec {
+      api_version = "client.authentication.k8s.io/v1beta1"
+      args        = ["eks", "get-token", "--cluster-name", data.aws_eks_cluster.eks_cluster.name]
+      command     = "aws"
+    }
   }
 }
 
 provider "kubectl" {
   host                   = data.aws_eks_cluster.eks_cluster.endpoint
   cluster_ca_certificate = base64decode(data.aws_eks_cluster.eks_cluster.certificate_authority[0].data)
-  token                  = join("", data.aws_eks_cluster_auth.eks_cluster[*].token)
+  token                  = data.aws_eks_cluster_auth.eks_cluster.token
+  load_config_file       = false
 }
 
 data "aws_eks_cluster_auth" "eks_cluster" {