Files
LedgerLine/docker-compose.traefik.yml
Movses AslanyanandClaude Opus 5.5 b3e7c14958 Scrape Ledgerline's metrics from falken through czy's Traefik
czy publishes no service ports, so Traefik exposes each service's :9464
as https://ledgerline.vione.cloud/metrics/<service> behind basic auth,
and the platform's Prometheus gets a `ledgerline` job with one target
per service. The targets share an address; a `service` label tells them
apart, and relabels derive __metrics_path__ and instance from it.

create-secrets.sh now also creates the prometheus-scrape-auth secret
(mounted optional, so a missing secret fails only this job) and writes
the gitignored htpasswd file Traefik reads, which is copied to czy like
.env.observability.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-19 20:31:10 +03:30

149 lines
6.5 KiB
YAML

# Production-style override: put the gateway (frontend + API) behind Traefik
# with automatic Let's Encrypt TLS. Use together with the base file:
#
# docker compose -f docker-compose.yml -f docker-compose.traefik.yml up -d --build
#
# Only Traefik publishes host ports (80/443). Everything else is reachable
# only on the compose network.
#
# Metrics: every Ledgerline service serves OTel metrics on :9464 (see
# common/telemetry.py). Traefik exposes each one as
# https://ledgerline.vione.cloud/metrics/<service>, behind basic auth, so the
# platform's Prometheus on falken can scrape it (k8s/prometheus/prometheus.yml,
# job `ledgerline`). The htpasswd file is written by k8s/create-secrets.sh and
# copied here once, like .env.observability.
services:
traefik:
image: traefik:v3.6
restart: unless-stopped
command:
- --providers.docker=true
- --providers.docker.exposedByDefault=false
- --entrypoints.web.address=:80
- --entrypoints.web.http.redirections.entryPoint.to=websecure
- --entrypoints.web.http.redirections.entryPoint.scheme=https
- --entrypoints.websecure.address=:443
- --certificatesresolvers.le.acme.httpchallenge=true
- --certificatesresolvers.le.acme.httpchallenge.entrypoint=web
- --certificatesresolvers.le.acme.storage=/letsencrypt/acme.json
- --log.level=INFO
- --accesslog=true
ports:
- "80:80"
- "443:443"
volumes:
- /var/run/docker.sock:/var/run/docker.sock:ro
- letsencrypt:/letsencrypt
- ./observability/traefik/metrics-users:/etc/traefik/metrics-users:ro
gateway:
ports: !reset []
labels:
- traefik.enable=true
- traefik.http.routers.ledgerline.rule=Host(`ledgerline.vione.cloud`)
- traefik.http.routers.ledgerline.entrypoints=websecure
- traefik.http.routers.ledgerline.tls.certresolver=le
- traefik.http.services.ledgerline.loadbalancer.server.port=8000
# gateway now has two Traefik services, so each router names its own.
- traefik.http.routers.ledgerline.service=ledgerline
- traefik.http.routers.gateway-metrics.rule=Host(`ledgerline.vione.cloud`) && Path(`/metrics/gateway`)
- traefik.http.routers.gateway-metrics.entrypoints=websecure
- traefik.http.routers.gateway-metrics.tls.certresolver=le
- traefik.http.routers.gateway-metrics.middlewares=metrics-auth,metrics-path
- traefik.http.routers.gateway-metrics.service=gateway-metrics
- traefik.http.services.gateway-metrics.loadbalancer.server.port=9464
# Shared by every <service>-metrics router. Declared here because a
# middleware needs an enabled container to carry it.
- traefik.http.middlewares.metrics-auth.basicauth.usersfile=/etc/traefik/metrics-users
- traefik.http.middlewares.metrics-path.replacepath.path=/metrics
postgres:
ports: !reset []
redis:
ports: !reset []
ledger:
ports: !reset []
labels:
- traefik.enable=true
- traefik.http.routers.ledger-metrics.rule=Host(`ledgerline.vione.cloud`) && Path(`/metrics/ledger`)
- traefik.http.routers.ledger-metrics.entrypoints=websecure
- traefik.http.routers.ledger-metrics.tls.certresolver=le
- traefik.http.routers.ledger-metrics.middlewares=metrics-auth,metrics-path
- traefik.http.services.ledger-metrics.loadbalancer.server.port=9464
fraud:
ports: !reset []
labels:
- traefik.enable=true
- traefik.http.routers.fraud-metrics.rule=Host(`ledgerline.vione.cloud`) && Path(`/metrics/fraud`)
- traefik.http.routers.fraud-metrics.entrypoints=websecure
- traefik.http.routers.fraud-metrics.tls.certresolver=le
- traefik.http.routers.fraud-metrics.middlewares=metrics-auth,metrics-path
- traefik.http.services.fraud-metrics.loadbalancer.server.port=9464
sanctions:
ports: !reset []
labels:
- traefik.enable=true
- traefik.http.routers.sanctions-metrics.rule=Host(`ledgerline.vione.cloud`) && Path(`/metrics/sanctions`)
- traefik.http.routers.sanctions-metrics.entrypoints=websecure
- traefik.http.routers.sanctions-metrics.tls.certresolver=le
- traefik.http.routers.sanctions-metrics.middlewares=metrics-auth,metrics-path
- traefik.http.services.sanctions-metrics.loadbalancer.server.port=9464
insights:
ports: !reset []
labels:
- traefik.enable=true
- traefik.http.routers.insights-metrics.rule=Host(`ledgerline.vione.cloud`) && Path(`/metrics/insights`)
- traefik.http.routers.insights-metrics.entrypoints=websecure
- traefik.http.routers.insights-metrics.tls.certresolver=le
- traefik.http.routers.insights-metrics.middlewares=metrics-auth,metrics-path
- traefik.http.services.insights-metrics.loadbalancer.server.port=9464
notifier:
ports: !reset []
labels:
- traefik.enable=true
- traefik.http.routers.notifier-metrics.rule=Host(`ledgerline.vione.cloud`) && Path(`/metrics/notifier`)
- traefik.http.routers.notifier-metrics.entrypoints=websecure
- traefik.http.routers.notifier-metrics.tls.certresolver=le
- traefik.http.routers.notifier-metrics.middlewares=metrics-auth,metrics-path
- traefik.http.services.notifier-metrics.loadbalancer.server.port=9464
audit:
labels:
- traefik.enable=true
- traefik.http.routers.audit-metrics.rule=Host(`ledgerline.vione.cloud`) && Path(`/metrics/audit`)
- traefik.http.routers.audit-metrics.entrypoints=websecure
- traefik.http.routers.audit-metrics.tls.certresolver=le
- traefik.http.routers.audit-metrics.middlewares=metrics-auth,metrics-path
- traefik.http.services.audit-metrics.loadbalancer.server.port=9464
# Ships every container's stdout/stderr to the platform's Loki on falken
# (k8s/), labelled `container`. Credentials come from .env.observability,
# generated by k8s/create-secrets.sh and copied to the server once.
# Publishes no ports; memory-capped because czy has 1 GB of RAM. Steady
# state is ~70 MiB, but the initial backfill of every container's log
# history peaked at ~150 MiB in testing, hence the headroom.
alloy-agent:
image: grafana/alloy:v1.10.2
restart: unless-stopped
command:
- run
- --storage.path=/var/lib/alloy/data
- /etc/alloy/config.alloy
env_file: .env.observability
mem_limit: 256m
volumes:
- ./observability/alloy-agent/config.alloy:/etc/alloy/config.alloy:ro
- /var/run/docker.sock:/var/run/docker.sock:ro
- alloy-agent-data:/var/lib/alloy/data
volumes:
letsencrypt:
alloy-agent-data: