Two issues would each stop a clean production `docker compose up` for the event: 1. Healthchecks probed http://localhost:{3000,3001}, but the app and frontend bind IPv4 (0.0.0.0) while `localhost` resolves to ::1 (IPv6) first inside the container — so the probe got "connection refused" and neither container ever turned healthy. Caddy is gated on `condition: service_healthy` for both, so on a fresh boot it would block forever and nothing gets served. Switch both probes to 127.0.0.1. (Verified: both containers now report healthy.) 2. The prod caddy service never received DOMAIN, so the Caddyfile's `{$DOMAIN}` site address expanded to empty — malformed site block, no TLS, no serving. Add `environment: { DOMAIN: ${DOMAIN} }` to the caddy service. Also make .env.example honest and event-ready: - Add DATABASE_MAX_CONNECTIONS (real env lever; recommend 30 for ~100 guests). - The DEFAULT_* upload/rate/capacity vars are NOT read from env — they are seeded into the DB config table and managed at runtime via the admin dashboard. Replace the misleading entries (e.g. upload rate showed 10; live value is 100 via migration 015) with a note pointing to the admin UI and the real seeded defaults. - Document that raising COMPRESSION_WORKER_CONCURRENCY also needs the app memory limit raised (ffmpeg), so a video burst can't OOM the box. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
122 lines
3.8 KiB
YAML
122 lines
3.8 KiB
YAML
services:
|
|
db:
|
|
image: postgres:16-alpine
|
|
restart: unless-stopped
|
|
env_file: .env
|
|
environment:
|
|
POSTGRES_USER: ${POSTGRES_USER}
|
|
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
|
|
POSTGRES_DB: ${POSTGRES_DB}
|
|
volumes:
|
|
- postgres_data:/var/lib/postgresql/data
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER} -d ${POSTGRES_DB}"]
|
|
interval: 5s
|
|
timeout: 5s
|
|
retries: 10
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 512M
|
|
|
|
app:
|
|
build:
|
|
context: ./backend
|
|
dockerfile: Dockerfile
|
|
restart: unless-stopped
|
|
env_file: .env
|
|
environment:
|
|
# Activates the production secret guard in config.rs — refuses to boot with
|
|
# placeholder JWT_SECRET / ADMIN_PASSWORD_HASH.
|
|
APP_ENV: production
|
|
# The media volume is mounted at /media (below), so the app MUST write there.
|
|
# Pin it here rather than trusting .env: if MEDIA_PATH in .env points elsewhere
|
|
# (e.g. a host path used for running the backend natively) the container can't
|
|
# create it and every upload 500s with EACCES. `environment` overrides `env_file`,
|
|
# so this is authoritative for the container.
|
|
MEDIA_PATH: /media
|
|
depends_on:
|
|
db:
|
|
condition: service_healthy
|
|
volumes:
|
|
- media_data:/media
|
|
# Export archives live OUTSIDE /media so the public media ServeDir can't
|
|
# serve them — downloads go only through the ticket-gated handler.
|
|
- exports_data:/exports
|
|
expose:
|
|
- "3000"
|
|
healthcheck:
|
|
# Use 127.0.0.1, NOT localhost: the app binds IPv4 (0.0.0.0) but `localhost`
|
|
# resolves to ::1 (IPv6) first inside the container, so a localhost probe gets
|
|
# "connection refused" and the container never turns healthy — which would leave
|
|
# Caddy (gated on `condition: service_healthy` below) blocked forever on boot.
|
|
test: ["CMD-SHELL", "wget -q -O- http://127.0.0.1:3000/health || exit 1"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
start_period: 20s
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
# Bounds a runaway ffmpeg transcode (large uploads, 2 workers) so it can't
|
|
# OOM the single box and take down Postgres.
|
|
memory: 1G
|
|
|
|
frontend:
|
|
build:
|
|
context: ./frontend
|
|
dockerfile: Dockerfile
|
|
restart: unless-stopped
|
|
env_file: .env
|
|
environment:
|
|
# adapter-node behind Caddy TLS needs the public origin for CSRF checks on
|
|
# POST form actions — without it they fail only in production.
|
|
ORIGIN: "https://${DOMAIN}"
|
|
depends_on:
|
|
- app
|
|
expose:
|
|
- "3001"
|
|
healthcheck:
|
|
# 127.0.0.1, not localhost — see the app healthcheck note above (IPv4 bind vs
|
|
# ::1 resolution would leave this container permanently unhealthy).
|
|
test: ["CMD-SHELL", "wget -q -O- http://127.0.0.1:3001/ >/dev/null 2>&1 || exit 1"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
start_period: 15s
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 256M
|
|
|
|
caddy:
|
|
image: caddy:2-alpine
|
|
restart: unless-stopped
|
|
environment:
|
|
# The Caddyfile's site address is `{$DOMAIN}`, read from THIS container's env.
|
|
# Without it, `{$DOMAIN}` expands to empty, the site block collapses, and Caddy
|
|
# serves nothing / fails to obtain a TLS cert. `env_file` alone wouldn't help —
|
|
# Caddy needs it in `environment`, and this keeps the Caddyfile the single source.
|
|
DOMAIN: ${DOMAIN}
|
|
ports:
|
|
- "80:80"
|
|
- "443:443"
|
|
volumes:
|
|
- ./Caddyfile:/etc/caddy/Caddyfile:ro
|
|
- caddy_data:/data
|
|
depends_on:
|
|
app:
|
|
condition: service_healthy
|
|
frontend:
|
|
condition: service_healthy
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 256M
|
|
|
|
volumes:
|
|
postgres_data:
|
|
media_data:
|
|
exports_data:
|
|
caddy_data:
|