feat(chart): install OpenTelemetry collector via operator helm chart

(by including the official OpenTelemetry collector helm chart as a
dependency/sub-chart)

Also: Install the OpenTelemetry collector instance into the operator's
namespace instead of installing it into each monitored namespace.

Makefile

@@ -208,7 +208,16 @@ undeploy-via-kustomize: ## Undeploy the controller via kustomize from the K8s cl
 
 .PHONY: deploy-via-helm
 deploy-via-helm: ## Deploy the controller via helm to the K8s cluster specified in ~/.kube/config.
-	helm install --namespace dash0-operator-system --create-namespace --set operator.image.repository=${IMG_REPOSITORY} --set operator.image.tag=${IMG_TAG} --set operator.image.pullPolicy=Never dash0-operator helm-chart/dash0-operator
+	test-resources/bin/render-templates.sh manual-testing
+	helm install \
+		--namespace dash0-operator-system \
+		--create-namespace \
+		--values test-resources/helm/manual.values.yaml \
+		--set operator.image.repository=${IMG_REPOSITORY} \
+		--set operator.image.tag=${IMG_TAG} \
+		dash0-operator \
+		helm-chart/dash0-operator
+
 
 .PHONY: undeploy-via-helm
 undeploy-via-helm: ## Undeploy the controller via helm from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.

cmd/main.go

@@ -139,6 +139,12 @@ func startOperatorManager(
 		return fmt.Errorf("unable to create the clientset client")
 	}
 
+	otelCollectorBaseUrl, isSet := os.LookupEnv("DASH0_OTEL_COLLECTOR_BASE_URL")
+	if !isSet {
+		return fmt.Errorf("cannot start Dash0 operator, the mandatory environment variable " +
+			"\"DASH0_OTEL_COLLECTOR_BASE_URL\" is missing")
+	}
+
 	operatorImage, isSet := os.LookupEnv("DASH0_OPERATOR_IMAGE")
 	if !isSet {
 		return fmt.Errorf("cannot start Dash0 operator, the mandatory environment variable " +
@@ -165,13 +171,15 @@ func startOperatorManager(
 		}
 	}
 	setupLog.Info(
-		"version information",
-		"operator image and version",
+		"configuration:",
+		"operator image",
 		operatorImage,
-		"init container image and version",
+		"init container image",
 		initContainerImage,
 		"init container image pull policy override",
 		initContainerImagePullPolicy,
+		"otel collector base url",
+		otelCollectorBaseUrl,
 	)
 
 	images := util.Images{
@@ -181,20 +189,22 @@ func startOperatorManager(
 	}
 
 	if err = (&controller.Dash0Reconciler{
-		Client:    mgr.GetClient(),
-		ClientSet: clientSet,
-		Scheme:    mgr.GetScheme(),
-		Recorder:  mgr.GetEventRecorderFor("dash0-controller"),
-		Images:    images,
+		Client:               mgr.GetClient(),
+		ClientSet:            clientSet,
+		Scheme:               mgr.GetScheme(),
+		Recorder:             mgr.GetEventRecorderFor("dash0-controller"),
+		Images:               images,
+		OtelCollectorBaseUrl: otelCollectorBaseUrl,
 	}).SetupWithManager(mgr); err != nil {
 		return fmt.Errorf("unable to set up the Dash0 reconciler: %w", err)
 	}
 	setupLog.Info("Dash0 reconciler has been set up.")
 
 	if os.Getenv("ENABLE_WEBHOOKS") != "false" {
 		if err = (&dash0webhook.Handler{
-			Recorder: mgr.GetEventRecorderFor("dash0-webhook"),
-			Images:   images,
+			Recorder:             mgr.GetEventRecorderFor("dash0-webhook"),
+			Images:               images,
+			OtelCollectorBaseUrl: otelCollectorBaseUrl,
 		}).SetupWebhookWithManager(mgr); err != nil {
 			return fmt.Errorf("unable to create the Dash0 webhook: %w", err)
 		}

helm-chart/dash0-operator/Chart.lock

@@ -0,0 +1,6 @@
+dependencies:
+- name: opentelemetry-collector
+  repository: https://open-telemetry.github.io/opentelemetry-helm-charts
+  version: 0.93.1
+digest: sha256:0d1653fa32255a0807c9a6757d7fe58abfb466a530fd6161993747955514ee4e
+generated: "2024-06-07T10:59:38.555357+02:00"

helm-chart/dash0-operator/Chart.yaml

@@ -20,3 +20,8 @@ maintainers:
     email: [email protected]
 icon: icon/logo.svg
 appVersion: "1.0.0"
+dependencies:
+  - name: opentelemetry-collector
+    version: 0.93.1
+    repository: https://open-telemetry.github.io/opentelemetry-helm-charts
+    condition: opentelemetry-collector.enabled

helm-chart/dash0-operator/charts/.gitignore

@@ -0,0 +1 @@
+*.tgz

helm-chart/dash0-operator/templates/operator/deployment.yaml

@@ -44,6 +44,20 @@ spec:
         - --metrics-bind-address=127.0.0.1:8080
         - --leader-elect
         env:
+        - name: DASH0_OTEL_COLLECTOR_BASE_URL
+          {{/*
+          Note: This reuses an internal template of the opentelmetry-collector Helm chart, to make sure we render the
+          exact same service name for the collector URL as the collector Helm chart does. This might need to be updated
+          if the collector Helm chart changes its service name template. Since we control the version of the collector
+          Helm chart we use and run rigorous tests when updating to a newer version, this approach should be safe.
+          */}}
+          {{ $collectorSubChartValues :=
+               dict
+                 "Values" (index .Values "opentelemetry-collector")
+                 "Chart" (dict "Name" "opentelemetry-collector")
+                 "Release" .Release
+          }}
+          value: http://{{ include "opentelemetry-collector.fullname" $collectorSubChartValues }}.{{ .Release.Namespace }}.svc.cluster.local:4318
         - name: DASH0_OPERATOR_IMAGE
           value: {{ include "dash0-operator.image" . | quote }}
         - name: DASH0_INIT_CONTAINER_IMAGE

helm-chart/dash0-operator/tests/operator/__snapshot__/deployment_test.yaml.snap

@@ -34,6 +34,8 @@ deployment should match snapshot (default values):
               command:
                 - /manager
               env:
+                - name: DASH0_OTEL_COLLECTOR_BASE_URL
+                  value: http://RELEASE-NAME-opentelemetry-collector.NAMESPACE.svc.cluster.local:4318
                 - name: DASH0_OPERATOR_IMAGE
                   value: dash0-operator-controller:1.0.0
                 - name: DASH0_INIT_CONTAINER_IMAGE

helm-chart/dash0-operator/tests/operator/deployment_test.yaml

@@ -82,21 +82,27 @@ tests:
           value: Never
       - equal:
           path: spec.template.spec.containers[0].env[0].name
-          value: DASH0_OPERATOR_IMAGE
+          value: DASH0_OTEL_COLLECTOR_BASE_URL
       - equal:
           path: spec.template.spec.containers[0].env[0].value
+          value: http://RELEASE-NAME-opentelemetry-collector.NAMESPACE.svc.cluster.local:4318
+      - equal:
+          path: spec.template.spec.containers[0].env[1].name
+          value: DASH0_OPERATOR_IMAGE
+      - equal:
+          path: spec.template.spec.containers[0].env[1].value
           value: custom-operator-image:1.2.3
       - equal:
-         path: spec.template.spec.containers[0].env[1].name
+         path: spec.template.spec.containers[0].env[2].name
          value: DASH0_INIT_CONTAINER_IMAGE
       - equal:
-          path: spec.template.spec.containers[0].env[1].value
+          path: spec.template.spec.containers[0].env[2].value
           value: custom-init-container-image:4.5.6
       - equal:
-          path: spec.template.spec.containers[0].env[2].name
+          path: spec.template.spec.containers[0].env[3].name
           value: DASH0_INIT_CONTAINER_IMAGE_PULL_POLICY
       - equal:
-          path: spec.template.spec.containers[0].env[2].value
+          path: spec.template.spec.containers[0].env[3].value
           value: Always
       - equal:
           path: spec.template.spec.containers[0].resources.limits.cpu

helm-chart/dash0-operator/values.yaml

@@ -92,8 +92,88 @@ operator:
     pullPolicy:
 
   # the image pull secrets to pull the container images
-  imagePullSecrets: []
+  imagePullSecrets: [ ]
 
-# settings for the OpenTelemetry collector instance
-collector:
-  placeholder: "value"
+# settings for the OpenTelemetry collector instance that Dash0 will use for reporting data to Dash0
+opentelemetry-collector:
+  enabled: true
+
+  image:
+    repository: otel/opentelemetry-collector-k8s
+
+  mode: daemonset
+
+  service:
+    enabled: true
+
+  presets:
+    kubernetesAttributes:
+      enabled: true
+    # kubeletMetrics:
+    #   enabled: true
+
+  additionalLabels:
+    dash0.com/opt-out: "true"
+
+  resources:
+    limits:
+      memory: 500Mi
+
+  config:
+    extensions:
+      bearertokenauth/dash0:
+        scheme: "Bearer"
+        # needs to be provided via --set or an additional values file for now
+        token:
+
+    receivers:
+      jaeger: {}
+      prometheus: {}
+      zipkin: {}
+
+    exporters:
+      otlp:
+        auth:
+          authenticator: bearertokenauth/dash0
+        # needs to be provided via --set or an additional values file for now
+        endpoint:
+
+    service:
+      pipelines:
+        traces:
+          receivers:
+            - otlp
+          processors:
+            - k8sattributes
+            - memory_limiter
+            - batch
+          exporters:
+            - otlp
+        metrics:
+          receivers:
+            - otlp
+          processors:
+            - k8sattributes
+            - memory_limiter
+            - batch
+          exporters:
+            - otlp
+        logs:
+          receivers:
+            - otlp
+          processors:
+            - k8sattributes
+            - memory_limiter
+            - batch
+          exporters:
+            - otlp
+
+  ports:
+    jaeger-compact:
+      enabled: false
+    jaeger-thrift:
+      enabled: false
+    jaeger-grpc:
+      enabled: false
+    zipkin:
+      enabled: false