# Copyright 2024 RustFS Team # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. services: tempo-init: image: busybox:latest command: [ "sh", "-c", "chown -R 10001:10001 /var/tempo" ] volumes: - ./tempo-data:/var/tempo user: root networks: - otel-network restart: "no" tempo: image: grafana/tempo:latest user: "10001" # The container must be started with root to execute chown in the script command: [ "-config.file=/etc/tempo.yaml" ] # This is passed as a parameter to the entry point script volumes: - ./tempo.yaml:/etc/tempo.yaml:ro - ./tempo-data:/var/tempo ports: - "3200:3200" # tempo - "24317:4317" # otlp grpc - "24318:4318" # otlp http restart: unless-stopped networks: - otel-network healthcheck: test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3200/metrics" ] interval: 10s timeout: 5s retries: 3 start_period: 15s otel-collector: image: otel/opentelemetry-collector-contrib:latest environment: - TZ=Asia/Shanghai volumes: - ./otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml:ro ports: - "1888:1888" # pprof - "8888:8888" # Prometheus metrics for Collector - "8889:8889" # Prometheus metrics for application indicators - "13133:13133" # health check - "4317:4317" # OTLP gRPC - "4318:4318" # OTLP HTTP - "55679:55679" # zpages networks: - otel-network depends_on: jaeger: condition: service_started tempo: condition: service_started prometheus: condition: service_started loki: condition: service_started healthcheck: test: [ "CMD", "wget", "--spider", "-q", "http://localhost:13133" ] interval: 10s timeout: 5s retries: 3 jaeger: image: jaegertracing/jaeger:latest environment: - TZ=Asia/Shanghai - SPAN_STORAGE_TYPE=memory - COLLECTOR_OTLP_ENABLED=true ports: - "16686:16686" # Web UI - "14317:4317" # OTLP gRPC - "14318:4318" # OTLP HTTP - "18888:8888" # collector networks: - otel-network healthcheck: test: [ "CMD", "wget", "--spider", "-q", "http://localhost:16686" ] interval: 10s timeout: 5s retries: 3 prometheus: image: prom/prometheus:latest environment: - TZ=Asia/Shanghai volumes: - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro - ./prometheus-data:/prometheus ports: - "9090:9090" command: - '--config.file=/etc/prometheus/prometheus.yml' - '--web.enable-otlp-receiver' # Enable OTLP - '--web.enable-remote-write-receiver' # Enable remote write - '--enable-feature=promql-experimental-functions' # Enable info() - '--storage.tsdb.min-block-duration=15m' # Minimum block duration - '--storage.tsdb.max-block-duration=1h' # Maximum block duration - '--log.level=info' - '--storage.tsdb.retention.time=30d' - '--storage.tsdb.path=/prometheus' - '--web.console.libraries=/usr/share/prometheus/console_libraries' - '--web.console.templates=/usr/share/prometheus/consoles' restart: unless-stopped networks: - otel-network healthcheck: test: [ "CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy" ] interval: 10s timeout: 5s retries: 3 loki: image: grafana/loki:latest environment: - TZ=Asia/Shanghai volumes: - ./loki-config.yaml:/etc/loki/local-config.yaml:ro ports: - "3100:3100" command: -config.file=/etc/loki/local-config.yaml networks: - otel-network healthcheck: test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3100/ready" ] interval: 10s timeout: 5s retries: 3 grafana: image: grafana/grafana:latest ports: - "3000:3000" # Web UI volumes: - ./grafana-datasources.yaml:/etc/grafana/provisioning/datasources/datasources.yaml environment: - GF_SECURITY_ADMIN_PASSWORD=admin - GF_SECURITY_ADMIN_USER=admin - TZ=Asia/Shanghai - GF_INSTALL_PLUGINS=grafana-pyroscope-datasource restart: unless-stopped networks: - otel-network depends_on: - prometheus - tempo - loki healthcheck: test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health" ] interval: 10s timeout: 5s retries: 3 volumes: prometheus-data: tempo-data: networks: otel-network: driver: bridge name: "network_otel_config" ipam: config: - subnet: 172.28.0.0/16 driver_opts: com.docker.network.enable_ipv6: "true"