feat: add tracing to chainlink-cluster (#11939)

* add init helmchart for tempo and otel-collector

* add grafana, otel-collector and tempo to helm chart

* update grafana version

* add securityContext for tempo and otel

* add storage to tempo

* format

* add tempo key

* update to latest charts

* update chart versions

* add charts-repo to ct.yml

* fix typo

* add another step to add helm repos

* explicit

.ct.yml

@@ -3,3 +3,8 @@ target-branch: develop
 chart-dirs: 'charts'
 check-version-increment: false
 validate-maintainers: false
+charts-repos:
+  - mockserver=https://www.mock-server.com
+  - opentelemetry-collector=https://open-telemetry.github.io/opentelemetry-helm-charts
+  - tempo=https://grafana.github.io/helm-charts
+  - grafana=https://grafana.github.io/helm-charts

.github/workflows/helm-chart.yml

@@ -14,6 +14,12 @@ jobs:
       contents: read
       actions: read
     steps:
+      - name: Add repositories
+        run: |
+          helm repo add mockserver https://www.mock-server.com
+          helm repo add opentelemetry-collector https://open-telemetry.github.io/opentelemetry-helm-charts
+          helm repo add tempo https://grafana.github.io/helm-charts
+          helm repo add grafana https://grafana.github.io/helm-charts
       - name: ci-lint-helm-charts
         uses: smartcontractkit/.github/actions/ci-lint-charts@9fd15fe8e698a5e28bfd06b3a91471c56568dcb3 # ci-lint-charts@0.1.1
         with:

charts/chainlink-cluster/Chart.lock

@@ -0,0 +1,15 @@
+dependencies:
+- name: mockserver
+  repository: https://www.mock-server.com
+  version: 5.14.0
+- name: opentelemetry-collector
+  repository: https://open-telemetry.github.io/opentelemetry-helm-charts
+  version: 0.81.2
+- name: tempo
+  repository: https://grafana.github.io/helm-charts
+  version: 1.7.2
+- name: grafana
+  repository: https://grafana.github.io/helm-charts
+  version: 7.3.2
+digest: sha256:fb13a8a7b490fd1e388a6b082e50d65a39f44a28030d66559d4640c687a70e20
+generated: "2024-02-23T15:22:09.284013-06:00"

charts/chainlink-cluster/Chart.yaml

@@ -1,10 +1,22 @@
 apiVersion: v2
 name: chainlink-cluster
 description: Chainlink nodes cluster
-version: 0.2.0
+version: 0.3.0
 appVersion: "2.6.0"
 dependencies:
   - name: mockserver
     version: "5.14.0"
     repository: "https://www.mock-server.com"
     condition: mockserver.enabled
+  - name: opentelemetry-collector
+    version: "0.81.2"
+    repository: "https://open-telemetry.github.io/opentelemetry-helm-charts"
+    condition: opentelemetry-collector.enabled
+  - name: tempo
+    version: "1.7.2"
+    repository: "https://grafana.github.io/helm-charts"
+    condition: tempo.enabled
+  - name: grafana
+    version: "7.3.2"
+    repository: "https://grafana.github.io/helm-charts"
+    condition: grafana.enabled

charts/chainlink-cluster/values.yaml

@@ -192,6 +192,110 @@ runner:
     type: NodePort
     port: 8080
 
+opentelemetry-collector:
+  enabled: true
+  mode: deployment
+  image:
+    repository: otel/opentelemetry-collector
+    tag: 0.81.2
+  command:
+    name: otelcol
+  extraVolumes:
+    - name: trace-data
+      emptyDir: {}
+  extraVolumeMounts:
+    - name: trace-data
+      mountPath: /tracing
+  podSecurityContext:
+    fsGroup: 10001
+  securityContext:
+    runAsNonRoot: true
+    runAsUser: 10001
+    runAsGroup: 10001
+  config:
+    receivers:
+      otlp:
+        protocols:
+          grpc:
+            endpoint: "0.0.0.0:4317"
+          http:
+            endpoint: "0.0.0.0:3100"
+    exporters:
+      file:
+        path: /tracing/trace-data.json
+      otlp:
+        endpoint: tempo:4317
+        tls:
+          insecure: true
+    service:
+      telemetry:
+        logs:
+          level: "debug"
+      pipelines:
+        traces:
+          receivers: [otlp]
+          exporters: [file, otlp]
+
+tempo:
+  enabled: true
+  image:
+    tag: "1.7.2"
+  server:
+    http_listen_port: 3200
+  # default storage path: /var/tempo/
+  readinessProbe:
+    httpGet:
+      path: /ready
+      port: 3200
+    initialDelaySeconds: 10
+    periodSeconds: 5
+  livenessProbe:
+    httpGet:
+      path: /ready
+      port: 3200
+    initialDelaySeconds: 20
+    periodSeconds: 10
+  securityContext:
+    runAsNonRoot: true
+    runAsUser: 10001
+    runAsGroup: 10001
+  tempo:
+    storage:
+      trace:
+        backend: local # backend configuration to use
+        wal:
+          path: /tmp/tempo/wal # where to store the the wal locally
+        local:
+          path: /tmp/tempo/blocks
+
+grafana:
+  enabled: true
+  image:
+    tag: 7.3.2
+  datasources:
+    datasources.yaml:
+      apiVersion: 1
+      datasources:
+        - name: Tempo
+          type: tempo
+          access: proxy
+          orgId: 1
+          url: http://tempo:3200
+          basicAuth: false
+          isDefault: true
+          version: 1
+          editable: false
+          uid: tempo
+          jsonData:
+            httpMethod: GET
+            serviceMap:
+              datasourceUid: prometheus
+  env:
+    GF_AUTH_ANONYMOUS_ENABLED: "true"
+    GF_AUTH_ANONYMOUS_ORG_ROLE: "Admin"
+    GF_AUTH_DISABLE_LOGIN_FORM: "true"
+    GF_FEATURE_TOGGLES_ENABLE: "traceqlEditor"
+
 ingress:
   enabled: false
   annotations: {}