# Docker Compose workload harness for telemetry validation.
#
# Runs the OTel telemetry backend only. There are no validator services here:
#   - OTel Collector (traces + native OTLP metrics)
#   - Tempo (trace backend + search API)
#   - Prometheus (metrics)
#   - Loki (log aggregation for log-trace correlation)
#   - Grafana (dashboards + trace/log exploration)
#
# The validator cluster runs as host processes, not containers.
# run-full-validation.sh starts NUM_NODES (default 5) xrpld instances on
# 127.0.0.1, each with a cfg it generates inline, peered to each other via
# [ips_fixed]. They reach the collector through the published ports below and
# write their logs into the bind-mounted workdir for the filelog receiver.
#
# Usage:
#   # Start the telemetry backend on its own:
#   docker compose -f docker/telemetry/docker-compose.workload.yaml up -d
#
#   # Or let the orchestrator start this stack and the node cluster together:
#   docker/telemetry/workload/run-full-validation.sh
#
# Prerequisites (for the orchestrator, not for this stack):
#   - xrpld binary built with -DXRPL_ENABLE_TELEMETRY=ON
#   - Validator keys generated via generate-validator-keys.sh
#
# Image tags are pinned to the same versions as docker-compose.yml, which
# mounts these same collector, Tempo and Prometheus config files. Floating
# tags would let an upstream release change the harness result.
#
# Note: No Docker healthchecks are defined here. The orchestrator script
# (run-full-validation.sh) polls each service endpoint directly from the
# host, which avoids issues with missing curl/wget in container images.

services:
  # ---------------------------------------------------------------------------
  # Telemetry Backend Stack
  # ---------------------------------------------------------------------------

  otel-collector:
    image: otel/opentelemetry-collector-contrib:0.158.0
    command: ["--config=/etc/otel-collector-config.yaml"]
    ports:
      - "4317:4317" # OTLP gRPC
      - "4318:4318" # OTLP HTTP (traces + beast::insight metrics)
      - "8889:8889" # Prometheus metrics endpoint
      - "13133:13133" # Health check
    volumes:
      - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml:ro
      # Mount the validation workdir so the filelog receiver can tail node
      # logs. run-full-validation.sh sets XRPLD_LOG_DIR to its workdir; the
      # default matches that workdir so a bare `docker compose up` also works.
      - ${XRPLD_LOG_DIR:-/tmp/xrpld-validation}:/var/log/xrpld:ro
    depends_on:
      - tempo
    networks:
      - workload-net

  tempo:
    image: grafana/tempo:2.9.4
    command: ["-config.file=/etc/tempo.yaml"]
    ports:
      - "3200:3200" # Tempo HTTP API
    volumes:
      - ./tempo.yaml:/etc/tempo.yaml:ro
      - tempo-data:/var/tempo
    networks:
      - workload-net

  prometheus:
    image: prom/prometheus:v3.13.2
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
    depends_on:
      - otel-collector
    networks:
      - workload-net

  loki:
    image: grafana/loki:3.7.6
    ports:
      - "3100:3100" # Loki HTTP API
    command: ["-config.file=/etc/loki/local-config.yaml"]
    networks:
      - workload-net

  grafana:
    image: grafana/grafana:13.1.2
    environment:
      - GF_AUTH_ANONYMOUS_ENABLED=true
      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
    ports:
      - "3000:3000"
    volumes:
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
    depends_on:
      - tempo
      - prometheus
      - loki
    networks:
      - workload-net

volumes:
  tempo-data:

networks:
  workload-net:
    driver: bridge