feat(service/telegram-bot): added all resources to deploy otel for observability (o11y)

services/telegram-bot/deploy/grafana/datasources/datasource-prometheus.yaml

@@ -0,0 +1,15 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    uid: prometheus
+    access: proxy
+    orgId: 1
+    url: http://prometheus:9090
+    basicAuth: false
+    isDefault: false
+    version: 1
+    editable: false
+    jsonData:
+      httpMethod: GET

services/telegram-bot/deploy/grafana/datasources/datasource-tempo.yaml

@@ -0,0 +1,20 @@
+apiVersion: 1
+
+datasources:
+  - name: Tempo
+    type: tempo
+    access: proxy
+    orgId: 1
+    url: http://tempo:3200
+    basicAuth: false
+    isDefault: true
+    version: 1
+    editable: false
+    apiVersion: 1
+    uid: tempo
+    jsonData:
+      httpMethod: GET
+      serviceMap:
+        datasourceUid: prometheus
+      streamingEnabled:
+        search: true

services/telegram-bot/deploy/otel-collector/collector-config.yaml

@@ -0,0 +1,45 @@
+extensions:
+  health_check:
+    endpoint: 127.0.0.1:13133
+
+receivers:
+  prometheus:
+    config:
+      scrape_configs:
+        - job_name: otel-collector-metrics
+          scrape_interval: 10s
+          static_configs:
+            - targets: ['127.0.0.1:8888']
+
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+
+exporters:
+  prometheusremotewrite:
+    endpoint: http://prometheus:9090/api/v1/write
+    tls:
+      insecure: true
+
+  otlp:
+    endpoint: tempo:4317
+    tls:
+      insecure: true
+
+  debug:
+    verbosity: detailed
+
+service:
+  pipelines:
+    metrics:
+      receivers: [prometheus]
+      exporters: [prometheusremotewrite]
+    traces:
+      receivers: [otlp]
+      exporters: [otlp]
+    logs:
+      receivers: [otlp]
+      exporters: [debug]

services/telegram-bot/deploy/prometheus/prometheus.yml

@@ -0,0 +1,11 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+  - job_name: 'tempo'
+    static_configs:
+      - targets: ['tempo:3200']

services/telegram-bot/deploy/tempo/tempo.yaml

@@ -0,0 +1,57 @@
+stream_over_http_enabled: true
+server:
+  http_listen_port: 3200
+  log_level: info
+
+query_frontend:
+  search:
+    duration_slo: 5s
+    throughput_bytes_slo: 1.073741824e+09
+    metadata_slo:
+      duration_slo: 5s
+      throughput_bytes_slo: 1.073741824e+09
+  trace_by_id:
+    duration_slo: 5s
+
+distributor:
+  receivers:
+    otlp:
+      protocols:
+        grpc:
+          endpoint: 0.0.0.0:4317
+        http:
+          endpoint: 0.0.0.0:4318
+
+ingester:
+  max_block_duration: 5m # cut the headblock when this much time passes. this is being set for demo purposes and should probably be left alone normally
+
+compactor:
+  compaction:
+    block_retention: 1h # overall Tempo trace retention. set for demo purposes
+
+metrics_generator:
+  registry:
+    external_labels:
+      source: tempo
+      cluster: docker-compose
+  storage:
+    path: /var/tempo/generator/wal
+    remote_write:
+      - url: http://prometheus:9090/api/v1/write
+        send_exemplars: true
+  traces_storage:
+    path: /var/tempo/generator/traces
+
+storage:
+  trace:
+    backend: local # backend configuration to use
+    wal:
+      path: /var/tempo/wal # where to store the wal locally
+    local:
+      path: /var/tempo/blocks
+
+overrides:
+  defaults:
+    metrics_generator:
+      processors: [service-graphs, span-metrics, local-blocks] # enables metrics generator
+      generate_native_histograms: both

services/telegram-bot/docker-compose.yaml

@@ -14,3 +14,76 @@ services:
       interval: 10s
       timeout: 5s
       retries: 5
+
+  grafana:
+    image: grafana/grafana
+    environment:
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+      - GF_AUTH_DISABLE_LOGIN_FORM=true
+      - GF_FEATURE_TOGGLES_ENABLE=traceqlEditor
+    ports:
+      - '3000:3000'
+    volumes:
+      - grafana-data:/var/lib/grafana
+      - ./deploy/grafana/dashboards:/etc/grafana/provisioning/dashboards
+      - ./deploy/grafana/datasources:/etc/grafana/provisioning/datasources
+    depends_on:
+      - tempo
+      - prometheus
+
+  tempo:
+    image: grafana/tempo:latest
+    ports:
+      # - "14268:14268" # jaeger ingest
+      # - "9411:9411" # zipkin
+      - '3200:3200' # tempo
+      - '9095:9095' # tempo grpc
+    volumes:
+      - ./deploy/tempo/tempo.yaml:/etc/tempo.yaml
+      - tempo-data:/var/tempo
+    command: ['-config.file=/etc/tempo.yaml']
+
+  prometheus:
+    image: prom/prometheus
+    restart: always
+    ports:
+      - 9090:9090
+    volumes:
+      - ./deploy/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
+      - prometheus-data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--web.enable-otlp-receiver'
+      - '--enable-feature=exemplar-storage'
+
+  otel-collector:
+    image: otel/opentelemetry-collector
+    restart: always
+    ports:
+      - 4317:4317
+      - 4318:4318
+    volumes:
+      - ./deploy/otel-collector/collector-config.yaml:/etc/otelcol/config.yaml
+    command: ['--config', '/etc/otelcol/config.yaml']
+    depends_on:
+      - tempo
+      - prometheus
+
+  otel-tracing-test:
+    profiles:
+      - test
+    image: ghcr.io/grafana/xk6-client-tracing:v0.0.7
+    environment:
+      - ENDPOINT=otel-collector:4317
+    restart: always
+    depends_on:
+      - otel-collector
+
+volumes:
+  grafana-data:
+    driver: local
+  tempo-data:
+    driver: local
+  prometheus-data:
+    driver: local