[Chore] Add e2e test case for OpenTelemetry collector instance monitoring.

tests/e2e-openshift/monitoring/00-assert.yaml

@@ -0,0 +1,4 @@
+apiVersion: kuttl.dev/v1beta1
+kind: TestAssert
+commands:
+- script: ./tests/e2e-openshift/monitoring/check_user_workload_monitoring.sh

tests/e2e-openshift/monitoring/00-workload-monitoring.yaml

@@ -0,0 +1,13 @@
+# oc -n openshift-user-workload-monitoring get pod
+# https://docs.openshift.com/container-platform/4.13/monitoring/enabling-monitoring-for-user-defined-projects.html#accessing-metrics-from-outside-cluster_enabling-monitoring-for-user-defined-projects
+
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: cluster-monitoring-config
+  namespace: openshift-monitoring
+data:
+  config.yaml: |
+    enableUserWorkload: true 
+    alertmanagerMain:
+      enableUserAlertmanagerConfig: true

tests/e2e-openshift/monitoring/01-assert.yaml

@@ -0,0 +1,111 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  annotations:
+    prometheus.io/path: /metrics
+    prometheus.io/port: "8888"
+    prometheus.io/scrape: "true"
+  labels:
+    app.kubernetes.io/component: opentelemetry-collector
+    app.kubernetes.io/managed-by: opentelemetry-operator
+    app.kubernetes.io/name: cluster-collector-collector
+    app.kubernetes.io/part-of: opentelemetry
+  name: cluster-collector-collector
+status:
+  availableReplicas: 1
+  readyReplicas: 1
+  replicas: 1
+
+---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  labels:
+    app.kubernetes.io/managed-by: opentelemetry-operator
+    app.kubernetes.io/name: cluster-collector-collector
+  name: cluster-collector-collector
+spec:
+  endpoints:
+  - port: monitoring
+  selector:
+    matchLabels:
+      app.kubernetes.io/managed-by: opentelemetry-operator
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app.kubernetes.io/component: opentelemetry-collector
+    app.kubernetes.io/managed-by: opentelemetry-operator
+    app.kubernetes.io/name: cluster-collector-collector
+    app.kubernetes.io/part-of: opentelemetry
+  name: cluster-collector-collector
+spec:
+  ports:
+  - appProtocol: grpc
+    name: otlp-grpc
+    port: 4317
+    protocol: TCP
+    targetPort: 4317
+  - appProtocol: http
+    name: otlp-http
+    port: 4318
+    protocol: TCP
+    targetPort: 4318
+  selector:
+    app.kubernetes.io/component: opentelemetry-collector
+    app.kubernetes.io/managed-by: opentelemetry-operator
+    app.kubernetes.io/part-of: opentelemetry
+  type: ClusterIP
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app.kubernetes.io/component: opentelemetry-collector
+    app.kubernetes.io/managed-by: opentelemetry-operator
+    app.kubernetes.io/name: cluster-collector-collector
+    app.kubernetes.io/part-of: opentelemetry
+    operator.opentelemetry.io/collector-headless-service: Exists
+  name: cluster-collector-collector-headless
+spec:
+  ports:
+  - appProtocol: grpc
+    name: otlp-grpc
+    port: 4317
+    protocol: TCP
+    targetPort: 4317
+  - appProtocol: http
+    name: otlp-http
+    port: 4318
+    protocol: TCP
+    targetPort: 4318
+  selector:
+    app.kubernetes.io/component: opentelemetry-collector
+    app.kubernetes.io/managed-by: opentelemetry-operator
+    app.kubernetes.io/part-of: opentelemetry
+  type: ClusterIP
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app.kubernetes.io/component: opentelemetry-collector
+    app.kubernetes.io/managed-by: opentelemetry-operator
+    app.kubernetes.io/name: cluster-collector-collector-monitoring
+    app.kubernetes.io/part-of: opentelemetry
+  name: cluster-collector-collector-monitoring
+spec:
+  ports:
+  - name: monitoring
+    port: 8888
+    protocol: TCP
+    targetPort: 8888
+  selector:
+    app.kubernetes.io/component: opentelemetry-collector
+    app.kubernetes.io/managed-by: opentelemetry-operator
+    app.kubernetes.io/part-of: opentelemetry
+  type: ClusterIP

tests/e2e-openshift/monitoring/01-otel-collector.yaml

@@ -0,0 +1,24 @@
+apiVersion: opentelemetry.io/v1alpha1
+kind: OpenTelemetryCollector
+metadata:
+  name: cluster-collector
+spec:
+  mode: deployment
+  observability:
+    metrics:
+      enableMetrics: true
+  config: |
+    receivers:
+      otlp:
+        protocols:
+          grpc:
+          http:
+    processors:
+    exporters:
+      debug:
+    service:
+      pipelines:
+        traces:
+          receivers: [otlp]
+          processors: []
+          exporters: [debug]

tests/e2e-openshift/monitoring/02-assert.yaml

@@ -0,0 +1,6 @@
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: telemetrygen-traces
+status:
+  active: 1

tests/e2e-openshift/monitoring/02-generate-traces.yaml

@@ -0,0 +1,25 @@
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: telemetrygen-traces
+spec:
+  completions: 1
+  parallelism: 1
+  template:
+    metadata:
+      labels:
+        app: telemetrygen-traces
+    spec:
+      containers:
+        - name: telemetrygen-traces
+          image: ghcr.io/open-telemetry/opentelemetry-collector-contrib/telemetrygen:latest
+          command: ["./telemetrygen"]
+          args:
+            - "--otlp-endpoint=cluster-collector-collector-headless:4317"
+            - "--otlp-insecure=true"
+            - "--rate=1"
+            - "--duration=5s"
+            - "--otlp-attributes=telemetrygen=\"traces\""
+            - "--otlp-header=telemetrygen=\"traces\""
+            - "traces"
+      restartPolicy: Never

tests/e2e-openshift/monitoring/03-assert.yaml

@@ -0,0 +1,5 @@
+---
+apiVersion: kuttl.dev/v1beta1
+kind: TestAssert
+commands:
+- script: ./tests/e2e-openshift/monitoring/check_metrics.sh

tests/e2e-openshift/monitoring/check_metrics.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+SECRET=$(oc get secret -n openshift-user-workload-monitoring | grep prometheus-user-workload-token | head -n 1 | awk '{print $1}')
+TOKEN=$(echo $(oc get secret $SECRET -n openshift-user-workload-monitoring -o json | jq -r '.data.token') | base64 -d)
+THANOS_QUERIER_HOST=$(oc get route thanos-querier -n openshift-monitoring -o json | jq -r '.spec.host')
+
+#Check metrics used in the prometheus rules created for TempoStack. Refer issue https://issues.redhat.com/browse/TRACING-3399 for skipped metrics.
+metrics="otelcol_exporter_enqueue_failed_spans otelcol_exporter_sent_spans otelcol_process_cpu_seconds otelcol_process_memory_rss otelcol_process_runtime_heap_alloc_bytes otelcol_process_runtime_total_alloc_bytes otelcol_process_runtime_total_sys_memory_bytes otelcol_process_uptime otelcol_receiver_accepted_spans otelcol_receiver_refused_spans"
+
+for metric in $metrics; do
+  query="$metric"
+
+  response=$(curl -k -H "Authorization: Bearer $TOKEN" -H "Content-type: application/json" "https://$THANOS_QUERIER_HOST/api/v1/query?query=$query")
+
+  count=$(echo "$response" | jq -r '.data.result | length')
+
+  if [[ $count -eq 0 ]]; then
+    echo "No metric '$metric' with value present. Exiting with status 1."
+    exit 1
+  else
+    echo "Metric '$metric' with value is present."
+  fi
+done

tests/e2e-openshift/monitoring/check_user_workload_monitoring.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+
+set -e
+
+check_replicas() {
+  replicas=$(oc get $1 $2 -n openshift-user-workload-monitoring -o 'jsonpath={.status.availableReplicas} {.status.readyReplicas} {.status.replicas}')
+  for count in $replicas; do
+    if [[ $count =~ ^[0-9]+$ ]]; then
+      if ((count < 1)); then
+        echo "The number of replicas is 0 for $1 $2"
+        exit 1
+      fi
+    else
+      echo "Error: Replica count is not a valid number for $1 $2"
+      exit 1
+    fi
+  done
+}
+
+check_replicas deployment prometheus-operator
+check_replicas statefulset prometheus-user-workload
+check_replicas statefulset thanos-ruler-user-workload