Setup prometheus for monitoring

.github/workflows/charts.yml

@@ -21,6 +21,10 @@ jobs:
  - name: Setup chart-testing
  uses: helm/chart-testing-action@v2.6.1
 
+ - name: Install chart dependencies
+ run: |
+ helm repo add prometheus https://prometheus-community.github.io/helm-charts
+
  - name: Lint
  run: >
  ct

charts/data-gateway/Chart.lock

@@ -0,0 +1,6 @@
+dependencies:
+- name: prometheus
+ repository: https://prometheus-community.github.io/helm-charts
+ version: 25.17.0
+digest: sha256:1567645f0c8c096eb44cd7eadb5e6a694dc19a01911ae41b75dec83ab0e96d4c
+generated: "2024-03-14T09:36:26.799022195Z"

charts/data-gateway/Chart.yaml

@@ -3,5 +3,10 @@ name: data-gateway
 description: A GraphQL router deployment forming the Diamond Data Gateway
 type: application
 
-version: 0.1.0
+version: 0.2.0
 
+dependencies:
+ - name: prometheus
+ repository: https://prometheus-community.github.io/helm-charts
+ version: 25.17.0
+ condition: prometheus.enabled

charts/data-gateway/values.yaml

@@ -0,0 +1,129 @@
+prometheus:
+ enabled: true
+ kube-state-metrics:
+ enabled: false
+ prometheus-node-exporter:
+ enabled: false
+ prometheus-pushgateway:
+ enabled: false
+ rbac:
+ create: false
+ configmapReload:
+ prometheus:
+ resources:
+ limits:
+ cpu: 50m
+ memory: 400Mi
+ serviceAccounts:
+ prometheus-node-exporter:
+ create: false
+ name: default-full-access-mounted
+ pushgateway:
+ create: false
+ name: default-full-access-mounted
+ server:
+ create: false
+ name: default-full-access-mounted
+ alertmanager:
+ persistence:
+ enabled: false
+ server:
+ persistentVolume:
+ enabled: false
+ serverFiles:
+ prometheus.yml:
+ scrape_configs:
+ - job_name: prometheus
+ static_configs:
+ - targets:
+ - localhost:9090
+ - job_name: "kubernetes-service-endpoints"
+ kubernetes_sd_configs:
+ - role: endpoints
+ namespaces:
+ own_namespace: true
+ relabel_configs:
+ - source_labels:
+ [__meta_kubernetes_service_annotation_prometheus_io_scrape]
+ action: keep
+ regex: true
+ - source_labels:
+ [__meta_kubernetes_service_annotation_prometheus_io_scheme]
+ action: replace
+ target_label: __scheme__
+ regex: (https?)
+ - 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
+ target_label: __address__
+ regex: (.+?)(?::\d+)?;(\d+)
+ replacement: $1:$2
+ - action: labelmap
+ regex: __meta_kubernetes_service_annotation_prometheus_io_param_(.+)
+ replacement: __param_$1
+ - action: labelmap
+ regex: __meta_kubernetes_service_label_(.+)
+ - source_labels: [__meta_kubernetes_namespace]
+ action: replace
+ target_label: namespace
+ - source_labels: [__meta_kubernetes_service_name]
+ action: replace
+ target_label: service
+ - source_labels: [__meta_kubernetes_pod_node_name]
+ action: replace
+ target_label: node
+ - job_name: "kubernetes-pods"
+ kubernetes_sd_configs:
+ - role: pod
+ namespaces:
+ own_namespace: true
+ relabel_configs:
+ - source_labels:
+ [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
+ action: keep
+ regex: true
+ - source_labels:
+ [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
+ action: keep
+ regex: true
+ - source_labels:
+ [__meta_kubernetes_pod_annotation_prometheus_io_scheme]
+ action: replace
+ regex: (https?)
+ target_label: __scheme__
+ - source_labels:
+ [__meta_kubernetes_pod_annotation_prometheus_io_path]
+ action: replace
+ target_label: __metrics_path__
+ regex: (.+)
+ - source_labels:
+ [
+ __address__,
+ __meta_kubernetes_pod_annotation_prometheus_io_port,
+ ]
+ action: replace
+ regex: ([^:]+)(?::\d+)?;(\d+)
+ replacement: $1:$2
+ target_label: __address__
+ - action: labelmap
+ regex: __meta_kubernetes_pod_annotation_prometheus_io_param_(.+)
+ replacement: __param_$1
+ - action: labelmap
+ regex: __meta_kubernetes_pod_label_(.+)
+ - source_labels: [__meta_kubernetes_namespace]
+ action: replace
+ target_label: namespace
+ - source_labels: [__meta_kubernetes_pod_name]
+ action: replace
+ target_label: pod
+ - source_labels: [__meta_kubernetes_pod_phase]
+ regex: Pending|Succeeded|Failed|Completed
+ action: drop