feat(observability): add Traefik routing and required absolute data root

- Make OBSERVABILITY_DATA_ROOT required in docker-compose.observability.yml
  so Portainer deployments must set an absolute host path.
- Add Traefik labels and the web external network to Grafana, Prometheus,
  and Alertmanager with env-driven hostnames, router/service names,
  internal ports, entrypoint, and cert resolver.
- Keep direct host ports as a fallback for local debugging.
- Update docs/observability-runbooks.md with required variables,
  Traefik hostname column, and a .env.observability example.
This commit is contained in:
Developer
2026-06-16 16:23:54 +00:00
parent 53dcd16735
commit 2d1674cb08
2 changed files with 82 additions and 29 deletions
+41 -10
View File
@@ -1,14 +1,22 @@
# Standalone observability stack.
#
# Run this on a host where you want Grafana, Prometheus, Loki, Alertmanager,
# Alloy and Node Exporter without the rest of Manage. It exposes the usual
# ports directly; no Traefik or OIDC integration is required.
# Alloy and Node Exporter without the rest of Manage.
#
# cp .env.example .env
# # optionally edit OBSERVABILITY_* paths and ports
# Required environment variables:
# - OBSERVABILITY_DATA_ROOT (absolute path, e.g. /var/lib/manage/observability)
# - CERT_RESOLVER (Traefik cert resolver name)
# - GRAFANA_APP_HOST, PROMETHEUS_APP_HOST, ALERTMANAGER_APP_HOST
#
# Optional environment variables:
# - TRAEFIK_ENTRYPOINT (default: websecure)
# - *_APP_NAME router/service names (defaults below)
# - all *_PORT variables for direct host ports
#
# Deploy:
# docker compose -f docker-compose.observability.yml up -d
#
# Then open Grafana at http://localhost:3000 (admin / admin by default).
# Then open Grafana at the configured host (default admin / admin).
#
# To scrape a Manage backend as well, edit monitoring/prometheus/prometheus.standalone.yml
# and add a static target for it, or drop a file-SD JSON file into
@@ -29,11 +37,12 @@ services:
- ./monitoring/prometheus/prometheus.standalone.yml:/etc/prometheus/prometheus.yml:ro
- ./monitoring/prometheus/rules:/etc/prometheus/rules:ro
- ./monitoring/prometheus/file-sd:/etc/prometheus/file-sd:ro
- ${OBSERVABILITY_DATA_ROOT:-./observability-data}/prometheus:/prometheus
- ${OBSERVABILITY_DATA_ROOT:?set OBSERVABILITY_DATA_ROOT}/prometheus:/prometheus
ports:
- "${PROMETHEUS_PORT:-9090}:9090"
networks:
- monitoring
- web
restart: unless-stopped
healthcheck:
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:9090/-/healthy"]
@@ -41,6 +50,12 @@ services:
timeout: 5s
retries: 3
start_period: 30s
labels:
- "traefik.enable=true"
- "traefik.http.routers.${PROMETHEUS_APP_NAME:-prometheus}.rule=Host(`${PROMETHEUS_APP_HOST:?set PROMETHEUS_APP_HOST}`)"
- "traefik.http.routers.${PROMETHEUS_APP_NAME:-prometheus}.entrypoints=${TRAEFIK_ENTRYPOINT:-websecure}"
- "traefik.http.routers.${PROMETHEUS_APP_NAME:-prometheus}.tls.certresolver=${CERT_RESOLVER:?set CERT_RESOLVER}"
- "traefik.http.services.${PROMETHEUS_APP_NAME:-prometheus}.loadbalancer.server.port=${PROMETHEUS_APP_PORT:-9090}"
deploy:
resources:
limits:
@@ -56,7 +71,7 @@ services:
command: -config.file=/etc/loki/loki.yml
volumes:
- ./monitoring/loki/loki.yml:/etc/loki/loki.yml:ro
- ${OBSERVABILITY_DATA_ROOT:-./observability-data}/loki:/loki
- ${OBSERVABILITY_DATA_ROOT:?set OBSERVABILITY_DATA_ROOT}/loki:/loki
ports:
- "${LOKI_PORT:-3100}:3100"
networks:
@@ -88,7 +103,7 @@ services:
- ./monitoring/alloy/config.alloy:/etc/alloy/config.alloy:ro
- /var/run/docker.sock:/var/run/docker.sock:ro
- /var/lib/docker/containers:/var/lib/docker/containers:ro
- ${OBSERVABILITY_DATA_ROOT:-./observability-data}/alloy:/var/lib/alloy
- ${OBSERVABILITY_DATA_ROOT:?set OBSERVABILITY_DATA_ROOT}/alloy:/var/lib/alloy
ports:
- "${ALLOY_PORT:-12345}:12345"
networks:
@@ -128,11 +143,12 @@ services:
volumes:
- ./monitoring/grafana/grafana.ini:/etc/grafana/grafana.ini:ro
- ./monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
- ${OBSERVABILITY_DATA_ROOT:-./observability-data}/grafana:/var/lib/grafana
- ${OBSERVABILITY_DATA_ROOT:?set OBSERVABILITY_DATA_ROOT}/grafana:/var/lib/grafana
ports:
- "${GRAFANA_PORT:-3000}:3000"
networks:
- monitoring
- web
depends_on:
prometheus:
condition: service_healthy
@@ -145,6 +161,12 @@ services:
timeout: 5s
retries: 3
start_period: 30s
labels:
- "traefik.enable=true"
- "traefik.http.routers.${GRAFANA_APP_NAME:-grafana}.rule=Host(`${GRAFANA_APP_HOST:?set GRAFANA_APP_HOST}`)"
- "traefik.http.routers.${GRAFANA_APP_NAME:-grafana}.entrypoints=${TRAEFIK_ENTRYPOINT:-websecure}"
- "traefik.http.routers.${GRAFANA_APP_NAME:-grafana}.tls.certresolver=${CERT_RESOLVER:?set CERT_RESOLVER}"
- "traefik.http.services.${GRAFANA_APP_NAME:-grafana}.loadbalancer.server.port=${GRAFANA_APP_PORT:-3000}"
deploy:
resources:
limits:
@@ -169,11 +191,12 @@ services:
ALERT_EMAIL_TO: ${ALERT_EMAIL_TO:-admin@example.com}
volumes:
- ./monitoring/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
- ${OBSERVABILITY_DATA_ROOT:-./observability-data}/alertmanager:/alertmanager
- ${OBSERVABILITY_DATA_ROOT:?set OBSERVABILITY_DATA_ROOT}/alertmanager:/alertmanager
ports:
- "${ALERTMANAGER_PORT:-9093}:9093"
networks:
- monitoring
- web
restart: unless-stopped
healthcheck:
test: ["CMD", "wget", "-qO-", "http://127.0.0.1:9093/-/healthy"]
@@ -181,6 +204,12 @@ services:
timeout: 5s
retries: 3
start_period: 30s
labels:
- "traefik.enable=true"
- "traefik.http.routers.${ALERTMANAGER_APP_NAME:-alertmanager}.rule=Host(`${ALERTMANAGER_APP_HOST:?set ALERTMANAGER_APP_HOST}`)"
- "traefik.http.routers.${ALERTMANAGER_APP_NAME:-alertmanager}.entrypoints=${TRAEFIK_ENTRYPOINT:-websecure}"
- "traefik.http.routers.${ALERTMANAGER_APP_NAME:-alertmanager}.tls.certresolver=${CERT_RESOLVER:?set CERT_RESOLVER}"
- "traefik.http.services.${ALERTMANAGER_APP_NAME:-alertmanager}.loadbalancer.server.port=${ALERTMANAGER_APP_PORT:-9093}"
deploy:
resources:
limits:
@@ -219,3 +248,5 @@ services:
networks:
monitoring:
web:
external: true