Bernard Siebens
fe19a6f08a
- gunicorn: 3 workers -> 2 (this workload isn't CPU-bound per DEPLOYMENT.md's own sizing), add --preload so workers share immutable memory via copy-on-write instead of each independently importing Django, add --max-requests so a worker that renders a WeasyPrint invoice doesn't carry that memory forever. - Postgres: trim shared_buffers/max_connections from the image defaults (128MB/100), sized for a ~0.2GB dataset instead. - Redis: cap with --maxmemory as a ceiling, not a saving.
89 lines
3.4 KiB
YAML
89 lines
3.4 KiB
YAML
# One server. The same image and the same environment variables run a multi-server
|
|
# deployment: point DJANGO_DATABASE_URL / DJANGO_REDIS_URL at your central services, set a
|
|
# bucket, drop the `db` and `redis` services, and run several `web` containers behind a load
|
|
# balancer. Nothing in the code changes.
|
|
|
|
name: rosterchief
|
|
|
|
services:
|
|
caddy:
|
|
build:
|
|
context: ./deploy/caddy
|
|
restart: unless-stopped
|
|
ports:
|
|
- "80:80"
|
|
- "443:443"
|
|
- "443:443/udp"
|
|
environment:
|
|
# A wildcard certificate for *.rosterchief.app cannot be issued over HTTP-01 — Let's
|
|
# Encrypt only does wildcards via DNS-01. That is why Caddy needs a DNS API token, and
|
|
# why this image is built with the provider's DNS plugin rather than pulled as-is.
|
|
ROSTERCHIEF_BASE_DOMAIN: ${ROSTERCHIEF_BASE_DOMAIN:?set the base domain, e.g. rosterchief.app}
|
|
ACME_EMAIL: ${ACME_EMAIL:?set an email for Let's Encrypt}
|
|
CLOUDFLARE_API_TOKEN: ${CLOUDFLARE_API_TOKEN:?DNS-01 needs an API token with DNS:Edit on the zone}
|
|
volumes:
|
|
- ./deploy/caddy/Caddyfile:/etc/caddy/Caddyfile:ro
|
|
- caddy_data:/data
|
|
- caddy_config:/config
|
|
# Read-only: Caddy serves club logos straight off disk instead of round-tripping every
|
|
# image request through a gunicorn worker. Same volume `web` writes uploads into.
|
|
- media_data:/srv/media:ro
|
|
depends_on:
|
|
- web
|
|
|
|
web:
|
|
build: .
|
|
restart: unless-stopped
|
|
env_file: .env.production
|
|
volumes:
|
|
# Uploaded club logos, while storage is local disk (see rosterchief/urls.py). Without
|
|
# this, a rebuild or recreate wipes MEDIA_ROOT even though the container itself keeps
|
|
# running fine in between.
|
|
- media_data:/app/media
|
|
depends_on:
|
|
db:
|
|
condition: service_healthy
|
|
redis:
|
|
condition: service_started
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-fsS", "http://localhost:8000/healthz"]
|
|
interval: 30s
|
|
timeout: 5s
|
|
retries: 3
|
|
start_period: 20s
|
|
|
|
db:
|
|
image: postgres:17-alpine
|
|
restart: unless-stopped
|
|
environment:
|
|
POSTGRES_DB: ${POSTGRES_DB:-rosterchief}
|
|
POSTGRES_USER: ${POSTGRES_USER:-rosterchief}
|
|
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?set a database password}
|
|
# shared_buffers/max_connections default to 128MB / 100 — sized for a much bigger database
|
|
# than this app's (DEPLOYMENT.md: ~0.2GB after 5 years). 20 connections is comfortably above
|
|
# 2 gunicorn workers x 4 threads plus the odd `manage.py` one-off; trimmed both for the box,
|
|
# not for the data.
|
|
command: ["postgres", "-c", "shared_buffers=64MB", "-c", "max_connections=20"]
|
|
volumes:
|
|
- pgdata:/var/lib/postgresql/data
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-rosterchief}"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
|
|
redis:
|
|
image: redis:7-alpine
|
|
restart: unless-stopped
|
|
# Cache only, so nothing here needs to survive a restart. It is not optional though: it
|
|
# is what keeps every gunicorn worker agreeing about which feature flags are on. maxmemory
|
|
# is a ceiling, not a saving — this is already the smallest process in the stack — but on a
|
|
# memory-limited box it should evict cache entries under pressure, not grow unbounded.
|
|
command: ["redis-server", "--save", "", "--appendonly", "no", "--maxmemory", "32mb", "--maxmemory-policy", "allkeys-lru"]
|
|
|
|
volumes:
|
|
pgdata:
|
|
caddy_data:
|
|
caddy_config:
|
|
media_data:
|