eSlider
ea062af86a
Explorer and exporter were scanning the full Parquet lake every 1–5s (~2000 files, 200MB+), driving ~2.2 CPU cores. Limit metrics to the last N flights, cache DuckDB views and the partition tree, slow live polls to 2s, and keep drones alive after seal to stop restart churn. Add node-exporter, scan-duration metrics, and a Swarm Platform Grafana dashboard for node CPU/memory and scan health.
76 lines
2.2 KiB
YAML
76 lines
2.2 KiB
YAML
services:
|
|
drone:
|
|
build: .
|
|
# Scale the swarm: docker compose up --build --scale drone=${DRONE_COUNT:-5}
|
|
deploy:
|
|
replicas: ${DRONE_COUNT:-5}
|
|
environment:
|
|
FLIGHT_ID: ${FLIGHT_ID:-}
|
|
SEED: ${SEED:-42}
|
|
DURATION_S: ${DURATION_S:-120}
|
|
SPEEDUP: ${SPEEDUP:-1.0}
|
|
IMU_HZ: ${IMU_HZ:-50}
|
|
STATE_HZ: ${STATE_HZ:-5}
|
|
# Compose default bridge network: subnet-directed broadcast works
|
|
BROADCAST_ADDR: ${BROADCAST_ADDR:-255.255.255.255}
|
|
volumes:
|
|
- ${SWARM_T1_DIR:-../var/t1}:/data
|
|
|
|
# --- Monitoring profile: docker compose --profile monitoring up ---
|
|
|
|
exporter:
|
|
build: .
|
|
profiles: [monitoring]
|
|
command: ["python", "monitoring/exporter.py"]
|
|
environment:
|
|
DATA_DIR: /data
|
|
SCAN_INTERVAL_S: "30"
|
|
METRIC_FLIGHT_WINDOW: "5"
|
|
volumes:
|
|
- ${SWARM_T1_DIR:-../var/t1}:/data:ro
|
|
- ./monitoring:/app/monitoring:ro
|
|
ports:
|
|
- "${EXPORTER_PORT:-9105}:9105"
|
|
|
|
explorer:
|
|
build: .
|
|
profiles: [monitoring]
|
|
command: ["python", "explorer/server.py"]
|
|
environment:
|
|
DATA_DIR: /data
|
|
VIEW_REFRESH_S: "30"
|
|
TREE_CACHE_S: "15"
|
|
METRIC_FLIGHT_WINDOW: "5"
|
|
volumes:
|
|
- ${SWARM_T1_DIR:-../var/t1}:/data:ro
|
|
- ./explorer:/app/explorer:ro
|
|
ports:
|
|
- "${EXPLORER_UI_PORT:-8088}:8088"
|
|
|
|
prometheus:
|
|
image: prom/prometheus:v2.53.0
|
|
profiles: [monitoring]
|
|
volumes:
|
|
- ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
|
ports:
|
|
- "${PROMETHEUS_PORT:-9090}:9090"
|
|
|
|
grafana:
|
|
image: grafana/grafana:11.1.0
|
|
profiles: [monitoring]
|
|
environment:
|
|
GF_AUTH_ANONYMOUS_ENABLED: "true"
|
|
GF_AUTH_ANONYMOUS_ORG_ROLE: Admin
|
|
GF_AUTH_DISABLE_LOGIN_FORM: "true"
|
|
# Air-gap hygiene: no phone-home, no update checks, no plugin fetches
|
|
GF_ANALYTICS_REPORTING_ENABLED: "false"
|
|
GF_ANALYTICS_CHECK_FOR_UPDATES: "false"
|
|
GF_ANALYTICS_CHECK_FOR_PLUGIN_UPDATES: "false"
|
|
volumes:
|
|
- ./monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
|
|
- ./monitoring/grafana/dashboards:/var/lib/grafana/dashboards:ro
|
|
ports:
|
|
- "${GRAFANA_PORT:-3000}:3000"
|
|
depends_on:
|
|
- prometheus
|