Merge d6a6637aff into 7706b2da4f

Signed-off-by: Tarun Singh <tarun.singh@opstree.com>

charts/otel-config/Chart.yaml

@@ -0,0 +1,6 @@
+apiVersion: v2
+name: opentelemetry-chart
+description: A Helm chart for OpenTelemetry configurations
+type: application
+version: 0.1.0
+appVersion: 1.0.0

charts/otel-config/templates/otel-collector-metrics.yaml

@@ -0,0 +1,24 @@
+{{- if .Values.serviceScrape.enabled }}
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMServiceScrape
+metadata:
+  labels:
+    {{- range $key, $value := .Values.serviceScrape.labels }}
+    {{ $key }}: {{ $value }}
+    {{- end }}
+  name: {{ .Values.serviceScrape.name }}
+  namespace: {{ .Values.serviceScrape.namespace }}
+spec:
+  endpoints:
+  - interval: {{ .Values.serviceScrape.endpoints.interval }}
+    path: {{ .Values.serviceScrape.endpoints.path }}
+    targetPort: {{ .Values.serviceScrape.endpoints.targetPort }}
+  namespaceSelector:
+    matchNames:
+    - {{ .Values.serviceScrape.namespace }}
+  selector:
+    matchLabels:
+      {{- range $key, $value := .Values.serviceScrape.selector }}
+      {{ $key }}: {{ $value }}
+      {{- end }}
+{{- end }}

charts/otel-config/templates/otel-collector.yaml

@@ -0,0 +1,22 @@
+{{- if .Values.collector.enabled }}
+apiVersion: opentelemetry.io/v1beta1
+kind: OpenTelemetryCollector
+metadata:
+  name: {{ .Values.collector.name }}
+  namespace: {{ .Values.collector.namespace }}
+spec:
+  mode: {{ .Values.collector.mode }}
+  resources:
+    requests:
+      cpu: {{ .Values.collector.resources.requests.cpu }}
+      memory: {{ .Values.collector.resources.requests.memory }}
+    limits:
+      cpu: {{ .Values.collector.resources.limits.cpu }}
+      memory: {{ .Values.collector.resources.limits.memory }}
+  autoscaler:
+    minReplicas: {{ .Values.collector.autoscaler.minReplicas }}
+    maxReplicas: {{ .Values.collector.autoscaler.maxReplicas }}
+    targetCPUUtilization: {{ .Values.collector.autoscaler.targetCPUUtilization }}
+    targetMemoryUtilization: {{ .Values.collector.autoscaler.targetMemoryUtilization }}
+  config: {{ .Values.collector.config | toYaml | nindent 4 }}
+{{- end }}

charts/otel-config/templates/otel-instrumentation.yaml

@@ -0,0 +1,29 @@
+{{- if .Values.instrumentation.enabled }}
+apiVersion: opentelemetry.io/v1alpha1
+kind: Instrumentation
+metadata:
+  name: {{ .Values.instrumentation.name }}
+  namespace: {{ .Values.instrumentation.namespace }}
+spec:
+  {{- if .Values.instrumentation.exporter }}
+  exporter:
+    endpoint: {{ .Values.instrumentation.exporter.endpoint }}
+  {{- end }}
+  propagators:
+{{- range .Values.instrumentation.propagators }}
+    - {{ . }}
+{{- end }}
+  sampler:
+    type: {{ .Values.instrumentation.sampler.type }}
+    argument: {{ .Values.instrumentation.sampler.argument | quote }}
+  {{- if .Values.instrumentation.languages }}
+  {{- range $language, $envs := .Values.instrumentation.languages }}
+  {{ $language }}:
+    env:
+    {{- range $envs }}
+      - name: {{ .name }}
+        value: {{ .value }}
+    {{- end }}
+  {{- end }}
+  {{- end }}
+{{- end }}

charts/otel-config/values.yaml

@@ -0,0 +1,168 @@
+instrumentation:
+  enabled: true
+  name: otel-instrumentation
+  namespace: observability
+
+  exporter:
+    endpoint: http://opentelemetry-collector.observability.svc.cluster.local:4317
+
+  propagators:
+    - tracecontext
+    - baggage
+    - b3
+
+  sampler:
+    type: parentbased_traceidratio
+    argument: "0.10"
+
+  languages:
+    python:
+      - name: OTEL_EXPORTER_OTLP_ENDPOINT
+        value: http://opentelemetry-collector.observability.svc.cluster.local:4318
+    dotnet:
+      - name: OTEL_EXPORTER_OTLP_ENDPOINT
+        value: http://opentelemetry-collector.observability.svc.cluster.local:4318
+    go:
+      - name: OTEL_EXPORTER_OTLP_ENDPOINT
+        value: http://opentelemetry-collector.observability.svc.cluster.local:4318
+
+serviceScrape:
+  enabled: true
+  name: otel-collector-metrics-sm
+  namespace: observability
+  endpoints:
+    interval: 30s
+    path: /metrics
+    targetPort: 8888
+  labels:
+    app: otel-collector-metrics
+    exclude: "true"
+    prometheus: kube
+  selector:
+    app.kubernetes.io/name: opentelemetry-collector-monitoring
+    operator.opentelemetry.io/collector-service-type: monitoring
+
+collector:
+  enabled: true
+  name: opentelemetry
+  namespace: observability
+  mode: deployment
+  resources:
+    requests:
+      cpu: 0.5
+      memory: 500Mi
+    limits:
+      cpu: 0.5
+      memory: 500Mi
+  autoscaler:
+    minReplicas: 1
+    maxReplicas: 10
+    targetCPUUtilization: 80
+    targetMemoryUtilization: 80
+  config: |
+    connectors:
+      spanmetrics:
+        dimensions:
+        - name: http.method
+        - name: http.status_code
+        - default: /
+          name: http.route
+        dimensions_cache_size: 1000
+        events:
+          dimensions:
+          - name: exception.type
+          - name: exception.message
+          enabled: true
+        exemplars:
+          enabled: true
+        metrics_expiration: 5m
+        metrics_flush_interval: 15s
+    exporters:
+      debug: {}
+      otlp:
+        endpoint: tempo:4317
+        tls:
+          insecure: true
+      prometheusremotewrite:
+        endpoint: http://vminsert-vm.monitoring.svc:8480/insert/0/prometheus/api/v1/write
+        export_created_metric:
+          enabled: true
+        max_batch_size_bytes: 8192
+        remote_write_queue:
+          enabled: true
+          num_consumers: 100
+          queue_size: 100000
+        retry_on_failure:
+          enabled: true
+          initial_interval: 5s
+          max_elapsed_time: 300s
+          max_interval: 30s
+        timeout: 300s
+        tls:
+          insecure_skip_verify: true
+    processors:
+      batch:
+        send_batch_max_size: 8192
+        send_batch_size: 1024
+        timeout: 60s
+      memory_limiter:
+        check_interval: 10s
+        limit_percentage: 75
+        spike_limit_percentage: 50
+      tail_sampling:
+        decision_wait: 60s
+        policies:
+        - name: error-policy
+          status_code:
+            status_codes:
+            - ERROR
+          type: status_code
+        - latency:
+            threshold_ms: 500
+          name: latency-policy
+          type: latency
+        - name: probabilistic
+          probabilistic:
+            sampling_percentage: 10
+          type: probabilistic
+    receivers:
+      otlp:
+        protocols:
+          grpc:
+            endpoint: 0.0.0.0:4317
+            keepalive:
+              server_parameters:
+                max_connection_age: 5m
+                max_connection_age_grace: 5m
+                max_connection_idle: 1m
+                time: 3m
+                timeout: 5m
+          http:
+            endpoint: 0.0.0.0:4318
+    service:
+      pipelines:
+        metrics:
+          exporters:
+          - debug
+          - prometheusremotewrite
+          processors:
+          - memory_limiter
+          - batch
+          receivers:
+          - spanmetrics
+          - otlp
+        traces:
+          exporters:
+          - debug
+          - otlp
+          - spanmetrics
+          processors:
+          - memory_limiter
+          - batch
+          - tail_sampling
+          receivers:
+          - otlp
+      telemetry:
+        metrics:
+          address: 0.0.0.0:8888
+          level: detailed