Add production compose stack and stop idle load in containers #2
14 changed files with 424 additions and 118 deletions
2
.gitignore
vendored
Normal file → Executable file
2
.gitignore
vendored
Normal file → Executable file
|
|
@ -1,6 +1,8 @@
|
|||
node_modules/
|
||||
dist/
|
||||
.next/
|
||||
# Stray tsc output; drizzle-kit reads drizzle.config.ts.
|
||||
/drizzle.config.js
|
||||
data/*.db
|
||||
data/backups/*.db
|
||||
.codex/*.log
|
||||
|
|
|
|||
33
AGENTS.md
Normal file → Executable file
33
AGENTS.md
Normal file → Executable file
|
|
@ -531,13 +531,44 @@ Users must be able to override sizing suggestions.
|
|||
- Preserve stable UUIDs and explicit transaction boundaries for a later
|
||||
PostgreSQL adapter.
|
||||
|
||||
## Deployment Rules
|
||||
|
||||
There are two compose files and they must stay separate.
|
||||
|
||||
- `compose.yaml` is development only. Project name `leistungsbilanz-dev`, ports
|
||||
bound to `127.0.0.1`, watch-mode servers, source bind mounts.
|
||||
- `compose.prod.yaml` is the deployment. Project name `leistungsbilanz`, image
|
||||
target `prod`, compiled output, no bind mounts, no file watchers.
|
||||
|
||||
Rules that a running deployment depends on:
|
||||
|
||||
- Never run the development stack permanently. `next dev` and `tsx watch`
|
||||
produce load and grow in memory with no user activity.
|
||||
- Never reintroduce `CHOKIDAR_USEPOLLING` or `WATCHPACK_POLLING`. They make the
|
||||
watcher poll the source tree continuously.
|
||||
- Container healthchecks target `/health` only. `/` is a redirect to
|
||||
`/projects`, and `fetch` follows redirects, so probing `/` renders a full
|
||||
page on every interval.
|
||||
- Every service keeps a `mem_limit`; production services also keep a
|
||||
`memswap_limit` of the same size so a leak kills the container instead of the
|
||||
host.
|
||||
- The production image runs as `node`. Data volumes written by an earlier root
|
||||
container need a one-time `chown` (see `docs/deployment.md`).
|
||||
- The Express API is not published on the host. It has no authentication and is
|
||||
reached through the Next.js rewrite.
|
||||
- Development migrates with `drizzle-kit`; the production image has no
|
||||
devDependencies and migrates with `node scripts/run-migrations.js`.
|
||||
- `SIGTERM`/`SIGINT` must close the HTTP server and the SQLite handle and then
|
||||
exit. Do not reduce these handlers to logging.
|
||||
|
||||
## Current Deferred Work
|
||||
|
||||
- Revit/CSV/IFCGUID round-trip, except when Phase 14 is explicitly requested and
|
||||
`docs/spec/revit-csv-integration-requirements.md` is being followed
|
||||
- full electrical sizing
|
||||
- multi-user/PostgreSQL operation
|
||||
- supported production deployment
|
||||
- authentication, authorization and TLS termination; until they exist the
|
||||
deployment belongs in a trusted network or behind an authenticating proxy
|
||||
|
||||
Do not implement these while working on an unrelated phase.
|
||||
|
||||
|
|
|
|||
51
Dockerfile
Normal file → Executable file
51
Dockerfile
Normal file → Executable file
|
|
@ -1,14 +1,51 @@
|
|||
FROM node:22
|
||||
WORKDIR /app
|
||||
# syntax=docker/dockerfile:1
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# deps: complete dependency tree, shared by the build and the dev target.
|
||||
# Stays on the full node image because better-sqlite3 needs a toolchain.
|
||||
# ---------------------------------------------------------------------------
|
||||
FROM node:22 AS deps
|
||||
WORKDIR /app
|
||||
COPY package*.json ./
|
||||
RUN npm ci
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# dev: watch-mode target used by compose.yaml. Keeps devDependencies so
|
||||
# tsx, drizzle-kit and next dev are available. Sources come from bind mounts.
|
||||
# ---------------------------------------------------------------------------
|
||||
FROM deps AS dev
|
||||
ENV NODE_ENV=development
|
||||
COPY . .
|
||||
RUN mkdir -p data
|
||||
EXPOSE 3000 3001
|
||||
CMD ["npm", "run", "dev:api"]
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# build: compile the API to dist/ and the frontend to .next/, then drop
|
||||
# devDependencies so the runtime stage carries only what it executes.
|
||||
# ---------------------------------------------------------------------------
|
||||
FROM deps AS build
|
||||
ENV NEXT_TELEMETRY_DISABLED=1
|
||||
# Next.js resolves next.config.mjs rewrites at build time and writes the literal
|
||||
# destination into .next/routes-manifest.json. Setting API_INTERNAL_URL only at
|
||||
# runtime has no effect on `next start`, so the API address of the target
|
||||
# topology has to be known here. Server components read the variable at runtime.
|
||||
ARG API_INTERNAL_URL=http://localhost:3000
|
||||
ENV API_INTERNAL_URL=$API_INTERNAL_URL
|
||||
COPY . .
|
||||
RUN npm run build:api && npm run build:web
|
||||
RUN npm prune --omit=dev
|
||||
|
||||
RUN mkdir -p data && chmod +x scripts/docker-start.sh
|
||||
|
||||
EXPOSE 3001
|
||||
|
||||
CMD ["sh", "scripts/docker-start.sh"]
|
||||
# ---------------------------------------------------------------------------
|
||||
# prod: runtime image. node:22-slim shares the Debian release of the build
|
||||
# stage, so the compiled better-sqlite3 binding stays loadable.
|
||||
# ---------------------------------------------------------------------------
|
||||
FROM node:22-slim AS prod
|
||||
ENV NODE_ENV=production
|
||||
ENV NEXT_TELEMETRY_DISABLED=1
|
||||
WORKDIR /app
|
||||
COPY --from=build --chown=node:node /app ./
|
||||
RUN mkdir -p data && chown node:node data
|
||||
USER node
|
||||
EXPOSE 3000 3001
|
||||
CMD ["node", "dist/server/index.js"]
|
||||
|
|
|
|||
23
README.md
Normal file → Executable file
23
README.md
Normal file → Executable file
|
|
@ -4,8 +4,9 @@ Leistungsbilanz ist eine Webanwendung für die elektrische Ausführungsplanung.
|
|||
Mittelpunkt steht ein tabellenähnlicher Stromkreislisten-Editor, der Stromkreise,
|
||||
Gerätezeilen und wiederverwendbare Projektgeräte fachlich getrennt behandelt.
|
||||
|
||||
Das Projekt befindet sich in aktiver Entwicklung. Der lokale Entwicklungsbetrieb
|
||||
mit SQLite und Docker Compose ist unterstützt. Ein Produktionsdeployment,
|
||||
Das Projekt befindet sich in aktiver Entwicklung. Unterstützt sind der lokale
|
||||
Entwicklungsbetrieb (`compose.yaml`) und ein Einzelbenutzer-Deployment im
|
||||
vertrauenswürdigen Netz (`compose.prod.yaml`). Authentifizierung,
|
||||
Mehrbenutzerbetrieb und der Revit-/IFCGUID-Datenaustausch sind noch nicht
|
||||
implementiert.
|
||||
|
||||
|
|
@ -62,9 +63,21 @@ docker compose logs --follow
|
|||
docker compose down
|
||||
```
|
||||
|
||||
Der Compose-Stack startet Entwicklungsserver mit Quellcode-Mounts. Er ist kein
|
||||
Produktionsdeployment. Details stehen in
|
||||
[Deployment und Betrieb](docs/deployment.md).
|
||||
`compose.yaml` startet Entwicklungsserver mit Quellcode-Mounts, veröffentlicht
|
||||
seine Ports nur auf `127.0.0.1` und ist **kein Produktionsdeployment**. Es
|
||||
gehört nicht in den Dauerbetrieb: `next dev` und `tsx watch` erzeugen auch ohne
|
||||
Benutzer dauerhaft Last und wachsen im Speicher.
|
||||
|
||||
## Deployment
|
||||
|
||||
```bash
|
||||
docker compose -f compose.prod.yaml up --build --detach
|
||||
```
|
||||
|
||||
Startet die kompilierte API und `next start` in getrennten Containern, mit
|
||||
Speicherlimits und ohne Dateibeobachter. Das Frontend hört auf Port 3090, die
|
||||
API ist nur intern erreichbar. Vorbereitung eines bestehenden Datenvolumes und
|
||||
weitere Details stehen in [Deployment und Betrieb](docs/deployment.md).
|
||||
|
||||
## Direkte lokale Entwicklung
|
||||
|
||||
|
|
|
|||
102
compose.prod.yaml
Executable file
102
compose.prod.yaml
Executable file
|
|
@ -0,0 +1,102 @@
|
|||
# Production deployment.
|
||||
#
|
||||
# Differences to compose.yaml that matter operationally:
|
||||
# - runs compiled output (node dist/, next start) instead of watch mode
|
||||
# - no source bind mounts and no file watchers, so an idle stack costs ~0% CPU
|
||||
# - healthchecks hit the cheap /health JSON endpoint, not a rendered page
|
||||
# - every service has a hard memory limit and may not spill into host swap
|
||||
# - the Express API is reachable only inside the compose network
|
||||
#
|
||||
# Usage:
|
||||
# docker compose -f compose.prod.yaml up --build --detach
|
||||
name: leistungsbilanz
|
||||
|
||||
x-service-defaults: &service-defaults
|
||||
init: true
|
||||
restart: unless-stopped
|
||||
stop_grace_period: 20s
|
||||
logging:
|
||||
driver: json-file
|
||||
options:
|
||||
max-size: "20m"
|
||||
max-file: "10"
|
||||
|
||||
services:
|
||||
api:
|
||||
<<: *service-defaults
|
||||
build:
|
||||
context: .
|
||||
target: prod
|
||||
args:
|
||||
# Baked into the Next.js rewrite manifest; see the build stage in the
|
||||
# Dockerfile. Must match the API service address in this network.
|
||||
API_INTERNAL_URL: http://api:3000
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
- node scripts/run-migrations.js && exec node dist/server/index.js
|
||||
environment:
|
||||
NODE_ENV: production
|
||||
PORT: "3000"
|
||||
LOG_LEVEL: "${LOG_LEVEL:-info}"
|
||||
# Not published on the host: the API has no authentication and is reached
|
||||
# through the Next.js rewrite in the web service.
|
||||
expose:
|
||||
- "3000"
|
||||
mem_limit: 512m
|
||||
memswap_limit: 512m
|
||||
volumes:
|
||||
- leistungsbilanz-data:/app/data
|
||||
healthcheck:
|
||||
test:
|
||||
- CMD
|
||||
- node
|
||||
- -e
|
||||
- fetch('http://127.0.0.1:3000/health').then(response=>process.exit(response.ok?0:1)).catch(()=>process.exit(1))
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 3
|
||||
start_period: 30s
|
||||
|
||||
web:
|
||||
<<: *service-defaults
|
||||
build:
|
||||
context: .
|
||||
target: prod
|
||||
args:
|
||||
# Baked into the Next.js rewrite manifest; see the build stage in the
|
||||
# Dockerfile. Must match the API service address in this network.
|
||||
API_INTERNAL_URL: http://api:3000
|
||||
command:
|
||||
- node_modules/.bin/next
|
||||
- start
|
||||
- -p
|
||||
- "3001"
|
||||
- --hostname
|
||||
- 0.0.0.0
|
||||
environment:
|
||||
NODE_ENV: production
|
||||
API_INTERNAL_URL: http://api:3000
|
||||
LOG_LEVEL: "${LOG_LEVEL:-info}"
|
||||
depends_on:
|
||||
api:
|
||||
condition: service_healthy
|
||||
ports:
|
||||
- "3090:3001"
|
||||
mem_limit: 1g
|
||||
memswap_limit: 1g
|
||||
healthcheck:
|
||||
# /health is rewritten to the API, so this verifies the web process and
|
||||
# its API connectivity for the cost of one JSON response.
|
||||
test:
|
||||
- CMD
|
||||
- node
|
||||
- -e
|
||||
- fetch('http://127.0.0.1:3001/health').then(response=>process.exit(response.ok?0:1)).catch(()=>process.exit(1))
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 3
|
||||
start_period: 30s
|
||||
|
||||
volumes:
|
||||
leistungsbilanz-data:
|
||||
70
compose.yaml
Normal file → Executable file
70
compose.yaml
Normal file → Executable file
|
|
@ -1,26 +1,39 @@
|
|||
name: leistungsbilanz
|
||||
# Local development only. Runs watch-mode servers against bind-mounted sources.
|
||||
# For a deployment use compose.prod.yaml.
|
||||
#
|
||||
# The project name must stay distinct from the production project so that
|
||||
# `docker compose down` in this directory can never tear down a running
|
||||
# production stack.
|
||||
name: leistungsbilanz-dev
|
||||
|
||||
x-service-defaults: &service-defaults
|
||||
init: true
|
||||
restart: unless-stopped
|
||||
stop_grace_period: 20s
|
||||
logging:
|
||||
driver: json-file
|
||||
options:
|
||||
max-size: "20m"
|
||||
max-file: "10"
|
||||
|
||||
services:
|
||||
api:
|
||||
<<: *service-defaults
|
||||
build:
|
||||
context: .
|
||||
target: dev
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
- npm run db:migrate && npm run db:verify:circuit-schema && npm run dev:api
|
||||
environment:
|
||||
PORT: "3000"
|
||||
CHOKIDAR_USEPOLLING: "true"
|
||||
LOG_LEVEL: "${LOG_LEVEL:-info}"
|
||||
init: true
|
||||
restart: unless-stopped
|
||||
logging:
|
||||
driver: json-file
|
||||
options:
|
||||
max-size: "20m"
|
||||
max-file: "10"
|
||||
# Development ports stay on the loopback interface; nothing here is
|
||||
# authenticated and the API must not be reachable from the LAN.
|
||||
ports:
|
||||
- "3000:3000"
|
||||
- "127.0.0.1:3000:3000"
|
||||
mem_limit: 1g
|
||||
volumes:
|
||||
- ./src:/app/src
|
||||
- ./scripts:/app/scripts
|
||||
|
|
@ -32,15 +45,17 @@ services:
|
|||
- CMD
|
||||
- node
|
||||
- -e
|
||||
- fetch('http://localhost:3000/health').then(response=>{if(!response.ok)process.exit(1)}).catch(()=>process.exit(1))
|
||||
interval: 5s
|
||||
timeout: 3s
|
||||
retries: 12
|
||||
start_period: 20s
|
||||
- fetch('http://127.0.0.1:3000/health').then(response=>process.exit(response.ok?0:1)).catch(()=>process.exit(1))
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 5
|
||||
start_period: 30s
|
||||
|
||||
web:
|
||||
<<: *service-defaults
|
||||
build:
|
||||
context: .
|
||||
target: dev
|
||||
command:
|
||||
- npm
|
||||
- run
|
||||
|
|
@ -50,33 +65,30 @@ services:
|
|||
- 0.0.0.0
|
||||
environment:
|
||||
API_INTERNAL_URL: http://api:3000
|
||||
WATCHPACK_POLLING: "true"
|
||||
NEXT_TELEMETRY_DISABLED: "1"
|
||||
LOG_LEVEL: "${LOG_LEVEL:-info}"
|
||||
init: true
|
||||
restart: unless-stopped
|
||||
logging:
|
||||
driver: json-file
|
||||
options:
|
||||
max-size: "20m"
|
||||
max-file: "10"
|
||||
depends_on:
|
||||
api:
|
||||
condition: service_healthy
|
||||
ports:
|
||||
- "3001:3001"
|
||||
- "127.0.0.1:3001:3001"
|
||||
# next dev grows steadily under long-running use; the limit turns that into
|
||||
# a container restart instead of host-wide swapping.
|
||||
mem_limit: 2g
|
||||
volumes:
|
||||
- ./src:/app/src
|
||||
- ./next.config.mjs:/app/next.config.mjs:ro
|
||||
- ./tsconfig.json:/app/tsconfig.json:ro
|
||||
- ./tsconfig.next.json:/app/tsconfig.next.json:ro
|
||||
healthcheck:
|
||||
# Must stay on /health: "/" redirects to /projects and Node's fetch
|
||||
# follows redirects, which turned every probe into a full page render.
|
||||
test:
|
||||
- CMD
|
||||
- node
|
||||
- -e
|
||||
- fetch('http://localhost:3001/').then(response=>{if(!response.ok)process.exit(1)}).catch(()=>process.exit(1))
|
||||
interval: 5s
|
||||
timeout: 3s
|
||||
retries: 12
|
||||
start_period: 20s
|
||||
- fetch('http://127.0.0.1:3001/health').then(response=>process.exit(response.ok?0:1)).catch(()=>process.exit(1))
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 5
|
||||
start_period: 30s
|
||||
|
|
|
|||
135
docs/deployment.md
Normal file → Executable file
135
docs/deployment.md
Normal file → Executable file
|
|
@ -2,21 +2,40 @@
|
|||
|
||||
## Aktueller Status
|
||||
|
||||
Es gibt derzeit kein unterstütztes Produktionsdeployment.
|
||||
Es gibt zwei getrennte Compose-Dateien. Sie dürfen nicht verwechselt werden.
|
||||
|
||||
`compose.yaml` ist ausschließlich für lokale Entwicklung vorgesehen. Es startet
|
||||
`tsx watch` und `next dev`, bindet Quellcode vom Host ein und enthält weder TLS,
|
||||
Authentifizierung, Reverse Proxy, Prozesshärtung noch ein zentral betriebenes
|
||||
Datenbanksystem. Der Stack darf deshalb nicht als produktionsreif bezeichnet oder
|
||||
öffentlich erreichbar gemacht werden.
|
||||
| Datei | Projektname | Zweck |
|
||||
| --- | --- | --- |
|
||||
| `compose.yaml` | `leistungsbilanz-dev` | ausschließlich lokale Entwicklung |
|
||||
| `compose.prod.yaml` | `leistungsbilanz` | Dauerbetrieb im LAN |
|
||||
|
||||
## Entwicklungs-Topologie
|
||||
`compose.yaml` startet `tsx watch` und `next dev` und bindet Quellcode vom Host
|
||||
ein. Dieser Stack ist **nicht** für Dauerbetrieb geeignet (siehe
|
||||
[Warum kein Dev-Stack im Dauerbetrieb](#warum-kein-dev-stack-im-dauerbetrieb)).
|
||||
Seine Ports sind deshalb an `127.0.0.1` gebunden.
|
||||
|
||||
| Komponente | Port | Healthcheck | Persistenz |
|
||||
| --- | ---: | --- | --- |
|
||||
| Next.js Web | 3001 | `GET /` | keine |
|
||||
| Express API | 3000 | `GET /health` | `./data:/app/data` |
|
||||
| SQLite | Datei | Integritäts-/FK-Prüfung via Backup und Skript | `data/leistungsbilanz.db` |
|
||||
`compose.prod.yaml` startet kompilierten Code ohne Dateibeobachter. Es enthält
|
||||
weiterhin weder TLS, Authentifizierung noch ein Benutzer-/Rollenmodell; die
|
||||
Express-API wird deshalb nicht auf dem Host veröffentlicht, sondern nur über den
|
||||
Next.js-Rewrite erreicht. Der Stack gehört hinter einen Reverse Proxy mit
|
||||
Authentifizierung und darf nicht öffentlich erreichbar gemacht werden.
|
||||
|
||||
## Topologie
|
||||
|
||||
Entwicklung (`compose.yaml`):
|
||||
|
||||
| Komponente | Port | Healthcheck | Speicherlimit | Persistenz |
|
||||
| --- | ---: | --- | ---: | --- |
|
||||
| Next.js Web | `127.0.0.1:3001` | `GET /health` alle 30 s | 2 GB | keine |
|
||||
| Express API | `127.0.0.1:3000` | `GET /health` alle 30 s | 1 GB | `./data:/app/data` |
|
||||
|
||||
Produktion (`compose.prod.yaml`):
|
||||
|
||||
| Komponente | Port | Healthcheck | Speicherlimit | Persistenz |
|
||||
| --- | ---: | --- | ---: | --- |
|
||||
| Next.js Web | `3090` | `GET /health` alle 30 s | 1 GB, kein Swap | keine |
|
||||
| Express API | nur intern | `GET /health` alle 30 s | 512 MB, kein Swap | Volume `leistungsbilanz-data` |
|
||||
| SQLite | Datei | Integritäts-/FK-Prüfung via Backup und Skript | – | `data/leistungsbilanz.db` |
|
||||
|
||||
Verwendete Umgebungsvariablen:
|
||||
|
||||
|
|
@ -24,15 +43,66 @@ Verwendete Umgebungsvariablen:
|
|||
- `API_INTERNAL_URL` – internes API-Ziel des Next.js-Rewrites, im Compose-Netz
|
||||
`http://api:3000`
|
||||
- `NEXT_TELEMETRY_DISABLED=1`
|
||||
- `CHOKIDAR_USEPOLLING=true` und `WATCHPACK_POLLING=true` für lokale
|
||||
Dateibeobachtung in Docker
|
||||
- `NODE_ENV=production` – nur in `compose.prod.yaml`
|
||||
- `LOG_LEVEL` – steuert für beide Dienste die Ausgabestufe des strukturierten
|
||||
JSON-Loggers (`error`, `warn`, `info`, `verbose`, `debug`), Standard `info`.
|
||||
Setzbar über eine `.env`-Datei neben `compose.yaml` oder
|
||||
`LOG_LEVEL=verbose docker compose up`.
|
||||
|
||||
Beim API-Start laufen zuerst `npm run db:migrate` und
|
||||
`npm run db:verify:circuit-schema`.
|
||||
Beim API-Start laufen in der Entwicklung zuerst `npm run db:migrate` und
|
||||
`npm run db:verify:circuit-schema` (drizzle-kit, eine devDependency). Das
|
||||
Produktionsimage enthält keine devDependencies und migriert stattdessen über
|
||||
`node scripts/run-migrations.js`, das denselben Migrationsordner mit
|
||||
`drizzle-orm` anwendet.
|
||||
|
||||
## Warum kein Dev-Stack im Dauerbetrieb
|
||||
|
||||
`compose.yaml` lief einmal fünf Tage durchgehend auf einem Server. Ergebnis:
|
||||
10,3 GB belegter Arbeitsspeicher im Web-Container, 12,2 % Dauer-CPU im
|
||||
API-Container und ein Host, der 13 GB Swap belegt hatte. Vier Ursachen wirkten
|
||||
zusammen; alle vier sind inzwischen behoben:
|
||||
|
||||
1. **Polling-Dateibeobachter.** `CHOKIDAR_USEPOLLING` und `WATCHPACK_POLLING`
|
||||
ließen `tsx watch` permanent den Quellbaum abklappern. Beide Variablen sind
|
||||
entfernt; unter Linux funktioniert `inotify` auf Bind-Mounts.
|
||||
2. **Healthcheck als Seitenrendering.** Der Web-Healthcheck rief `/` alle fünf
|
||||
Sekunden auf. `/` ist ein `redirect("/projects")`, und Node's `fetch` folgt
|
||||
Redirects – jede Prüfung rendert also die vollständige Projektliste, rund
|
||||
16.000-mal pro Tag. Der Healthcheck zeigt jetzt auf `/health` und läuft alle
|
||||
30 Sekunden.
|
||||
3. **Kein Speicherlimit.** `next dev` hält Kompilierungs-State und wächst unter
|
||||
Dauerlast unbegrenzt. Beide Compose-Dateien setzen jetzt `mem_limit`; in der
|
||||
Produktion zusätzlich `memswap_limit` in gleicher Höhe, damit ein Leck den
|
||||
Container beendet statt den Host in den Swap zu ziehen.
|
||||
4. **Kollidierender Projektname.** `compose.yaml` hieß `leistungsbilanz` und
|
||||
damit genauso wie das Produktionsprojekt; ein `docker compose down` im
|
||||
Entwicklungsverzeichnis zielte auf den Produktionsstack. Der Entwicklungsname
|
||||
ist jetzt `leistungsbilanz-dev`.
|
||||
|
||||
## Produktionsdeployment
|
||||
|
||||
```bash
|
||||
docker compose -f compose.prod.yaml up --build --detach
|
||||
docker compose -f compose.prod.yaml ps
|
||||
docker compose -f compose.prod.yaml logs --follow
|
||||
```
|
||||
|
||||
Das Frontend hört danach auf Port 3090. Die API ist nur innerhalb des
|
||||
Compose-Netzes erreichbar.
|
||||
|
||||
Das Produktionsimage läuft als Benutzer `node` statt als `root`. Wenn ein
|
||||
bestehendes Datenvolume von einem früheren root-Container beschrieben wurde,
|
||||
müssen dessen Dateien einmalig übereignet werden, sonst schlagen Schreibzugriffe
|
||||
mit `SQLITE_READONLY` fehl:
|
||||
|
||||
```bash
|
||||
docker run --rm -v leistungsbilanz_leistungsbilanz-data:/data alpine \
|
||||
chown -R 1000:1000 /data
|
||||
```
|
||||
|
||||
Ein bestehendes Ein-Container-Deployment über `scripts/docker-start.sh` wird
|
||||
abgelöst, indem dessen Stack gestoppt und `compose.prod.yaml` mit demselben
|
||||
Projektnamen `leistungsbilanz` gestartet wird; das Volume bleibt dabei erhalten.
|
||||
|
||||
## Logging
|
||||
|
||||
|
|
@ -68,23 +138,40 @@ einem unbekannten Zustand weiterzulaufen. Beide Dienste laufen deshalb mit
|
|||
`restart: unless-stopped`, damit Docker sie danach automatisch neu startet;
|
||||
ohne diese Policy würde ein Crash den Dienst dauerhaft unerreichbar lassen.
|
||||
|
||||
## Voraussetzungen für ein späteres Produktionssetup
|
||||
Anfragen von Healthcheck- und Monitoring-Clients (`node`, `curl`, `wget`, …)
|
||||
werden anhand des User-Agents aus dem Navigationslog gefiltert und `/health`
|
||||
läuft gar nicht erst durch `src/proxy.ts`.
|
||||
|
||||
Vor einer produktiven Installation werden mindestens benötigt:
|
||||
## Herunterfahren
|
||||
|
||||
`SIGTERM` und `SIGINT` schließen den HTTP-Server, danach das SQLite-Handle, und
|
||||
beenden den Prozess mit Code 0. Kommt der Server binnen 15 Sekunden nicht
|
||||
herunter, beendet sich der Prozess trotzdem. Vorher wurde das Signal nur
|
||||
geloggt: jeder `docker stop` lief in die Grace Period und endete mit `SIGKILL`,
|
||||
möglicherweise mitten in einem Schreibvorgang. `stop_grace_period` steht in
|
||||
beiden Compose-Dateien auf 20 s und liegt damit über dem internen Timeout.
|
||||
|
||||
## Offene Punkte für einen vollwertigen Produktionsbetrieb
|
||||
|
||||
Umgesetzt:
|
||||
|
||||
- reproduzierbares Produktionsimage und Next.js-Produktionsstart
|
||||
- kontrollierter Migrationsschritt vor dem API-Start
|
||||
- strukturierte Logs mit Rotation, Healthchecks, Speicherlimits
|
||||
- definiertes Herunterfahren
|
||||
|
||||
Weiterhin offen:
|
||||
|
||||
- reproduzierbare Produktionsimages und ein Next.js-Produktionsstartskript
|
||||
- TLS-Termination und Reverse Proxy
|
||||
- Authentifizierung, Autorisierung und Benutzer-/Rollenmodell
|
||||
- definierte Secrets- und Konfigurationsverwaltung
|
||||
- persistenter, gesicherter Datenbankbetrieb
|
||||
- kontrollierter einmaliger Migrationsschritt vor dem API-Rollout
|
||||
- Monitoring, strukturierte Logs und Alarmierung
|
||||
- Alarmierung auf Basis der Healthchecks
|
||||
- getestete Backup-, Restore- und Rollback-Prozeduren
|
||||
- Entscheidung, ob SQLite für einen einzelnen Prozess genügt oder PostgreSQL für
|
||||
Mehrbenutzerbetrieb erforderlich ist
|
||||
|
||||
Bis diese Punkte umgesetzt und getestet sind, besteht die „Installation“ aus dem
|
||||
lokalen Entwicklungsstart in der README.
|
||||
Solange Authentifizierung fehlt, gehört der Stack ausschließlich in ein
|
||||
vertrauenswürdiges Netz oder hinter einen authentifizierenden Reverse Proxy.
|
||||
|
||||
## Backup und Wiederherstellung
|
||||
|
||||
|
|
|
|||
|
|
@ -1,11 +0,0 @@
|
|||
"use strict";
|
||||
Object.defineProperty(exports, "__esModule", { value: true });
|
||||
const drizzle_kit_1 = require("drizzle-kit");
|
||||
exports.default = (0, drizzle_kit_1.defineConfig)({
|
||||
dialect: "sqlite",
|
||||
schema: "./src/db/schema/*.ts",
|
||||
out: "./src/db/migrations",
|
||||
dbCredentials: {
|
||||
url: "./data/leistungsbilanz.db",
|
||||
},
|
||||
});
|
||||
17
index.html
17
index.html
|
|
@ -1,17 +0,0 @@
|
|||
<!doctype html>
|
||||
<html lang="de">
|
||||
<head>
|
||||
<meta charset="UTF-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>Leistungsbilanz API</title>
|
||||
<link rel="stylesheet" href="./styles.css" />
|
||||
</head>
|
||||
<body>
|
||||
<main class="info">
|
||||
<h1>Leistungsbilanz Backend</h1>
|
||||
<p>Der aktuelle Stand laeuft als TypeScript Node/SQLite API.</p>
|
||||
<p>Serverstart: <code>npm run dev</code></p>
|
||||
<p>Healthcheck: <code>GET /health</code></p>
|
||||
</main>
|
||||
</body>
|
||||
</html>
|
||||
30
scripts/docker-start.sh
Normal file → Executable file
30
scripts/docker-start.sh
Normal file → Executable file
|
|
@ -1,4 +1,7 @@
|
|||
#!/bin/sh
|
||||
# Legacy single-container entrypoint. Kept for the existing deployment that
|
||||
# still runs both processes in one container; new deployments use
|
||||
# compose.prod.yaml, which runs the API and the web server separately.
|
||||
set -e
|
||||
|
||||
echo "Running migrations..."
|
||||
|
|
@ -6,11 +9,34 @@ node scripts/run-migrations.js
|
|||
|
||||
echo "Starting API server on :3000..."
|
||||
node dist/server/index.js &
|
||||
api_pid=$!
|
||||
|
||||
echo "Waiting for API..."
|
||||
until node -e "require('http').get('http://localhost:3000/health', r => process.exit(r.statusCode===200?0:1)).on('error',()=>process.exit(1))" 2>/dev/null; do
|
||||
until node -e "fetch('http://127.0.0.1:3000/health').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))" 2>/dev/null; do
|
||||
if ! kill -0 "$api_pid" 2>/dev/null; then
|
||||
echo "API process exited during startup."
|
||||
exit 1
|
||||
fi
|
||||
sleep 1
|
||||
done
|
||||
|
||||
echo "Starting Next.js on :3001..."
|
||||
exec node_modules/.bin/next start -p 3001
|
||||
node_modules/.bin/next start -p 3001 &
|
||||
web_pid=$!
|
||||
|
||||
terminate() {
|
||||
kill -TERM "$api_pid" "$web_pid" 2>/dev/null || true
|
||||
}
|
||||
trap terminate TERM INT
|
||||
|
||||
# Previously the API ran unsupervised in the background: when it died the
|
||||
# container stayed "up" and served a frontend whose every request failed.
|
||||
# Exiting here lets the restart policy replace the container instead.
|
||||
while kill -0 "$api_pid" 2>/dev/null && kill -0 "$web_pid" 2>/dev/null; do
|
||||
sleep 5
|
||||
done
|
||||
|
||||
echo "A server process exited; stopping the container."
|
||||
terminate
|
||||
wait "$api_pid" "$web_pid" 2>/dev/null || true
|
||||
exit 1
|
||||
|
|
|
|||
8
src/db/client.ts
Normal file → Executable file
8
src/db/client.ts
Normal file → Executable file
|
|
@ -7,3 +7,11 @@ const defaultDatabaseContext = createDatabaseContext(
|
|||
|
||||
export const db = defaultDatabaseContext.db;
|
||||
|
||||
/**
|
||||
* Closes the process-wide SQLite handle. Only the composition root calls this,
|
||||
* during shutdown, so pending writes are flushed before the process exits.
|
||||
*/
|
||||
export function closeDefaultDatabase(): void {
|
||||
defaultDatabaseContext.close();
|
||||
}
|
||||
|
||||
|
|
|
|||
11
src/proxy.ts
Normal file → Executable file
11
src/proxy.ts
Normal file → Executable file
|
|
@ -4,10 +4,13 @@ import { createLogger } from "./shared/logging/logger";
|
|||
|
||||
const logger = createLogger("web:navigation");
|
||||
|
||||
// Node's fetch() sends "User-Agent: node", so the previous "no User-Agent"
|
||||
// check never matched and every healthcheck was logged as page navigation.
|
||||
const PROBE_USER_AGENT = /^(node|curl|wget|go-http-client|kube-probe)\b/i;
|
||||
|
||||
export function proxy(request: NextRequest) {
|
||||
// The Docker healthcheck hits "/" every few seconds with no User-Agent
|
||||
// header; skip it so real navigation isn't drowned out in the logs.
|
||||
if (request.headers.get("user-agent")) {
|
||||
const userAgent = request.headers.get("user-agent") ?? "";
|
||||
if (userAgent && !PROBE_USER_AGENT.test(userAgent)) {
|
||||
logger.info("page request", {
|
||||
method: request.method,
|
||||
path: request.nextUrl.pathname,
|
||||
|
|
@ -17,5 +20,5 @@ export function proxy(request: NextRequest) {
|
|||
}
|
||||
|
||||
export const config = {
|
||||
matcher: ["/((?!_next/static|_next/image|favicon.ico|api).*)"],
|
||||
matcher: ["/((?!_next/static|_next/image|favicon.ico|api|health).*)"],
|
||||
};
|
||||
|
|
|
|||
34
src/server/index.ts
Normal file → Executable file
34
src/server/index.ts
Normal file → Executable file
|
|
@ -4,6 +4,7 @@ import { projectDeviceRouter } from "./routes/project-device.routes.js";
|
|||
import { projectRouter } from "./routes/project.routes.js";
|
||||
import { errorMiddleware } from "./middleware/error.middleware.js";
|
||||
import { createLogger, toErrorMeta } from "../shared/logging/logger.js";
|
||||
import { closeDefaultDatabase } from "../db/client.js";
|
||||
|
||||
const logger = createLogger("api");
|
||||
const app = express();
|
||||
|
|
@ -62,8 +63,35 @@ process.on("unhandledRejection", (reason) => {
|
|||
process.exit(1);
|
||||
});
|
||||
|
||||
process.on("SIGTERM", () => logger.info("received SIGTERM"));
|
||||
process.on("SIGINT", () => logger.info("received SIGINT"));
|
||||
let shuttingDown = false;
|
||||
|
||||
function shutdown(signal: NodeJS.Signals): void {
|
||||
if (shuttingDown) return;
|
||||
shuttingDown = true;
|
||||
logger.info("shutting down", { signal });
|
||||
|
||||
// Without this the process only logged the signal and kept running, so every
|
||||
// stop waited for Docker's grace period and ended in SIGKILL mid-write.
|
||||
const forceExit = setTimeout(() => {
|
||||
logger.warn("shutdown timed out, exiting anyway");
|
||||
process.exit(1);
|
||||
}, 15_000);
|
||||
forceExit.unref();
|
||||
|
||||
server.close((error) => {
|
||||
if (error) logger.error("http server close failed", toErrorMeta(error));
|
||||
try {
|
||||
closeDefaultDatabase();
|
||||
} catch (closeError) {
|
||||
logger.error("database close failed", toErrorMeta(closeError));
|
||||
}
|
||||
logger.info("shutdown complete");
|
||||
process.exit(error ? 1 : 0);
|
||||
});
|
||||
}
|
||||
|
||||
process.on("SIGTERM", shutdown);
|
||||
process.on("SIGINT", shutdown);
|
||||
|
||||
setInterval(() => {
|
||||
const memory = process.memoryUsage();
|
||||
|
|
@ -74,6 +102,6 @@ setInterval(() => {
|
|||
});
|
||||
}, heartbeatIntervalMs).unref();
|
||||
|
||||
app.listen(port, () => {
|
||||
const server = app.listen(port, () => {
|
||||
logger.info("server started", { port });
|
||||
});
|
||||
|
|
|
|||
15
styles.css
15
styles.css
|
|
@ -1,15 +0,0 @@
|
|||
body {
|
||||
margin: 0;
|
||||
font-family: Arial, sans-serif;
|
||||
background: #f5f6f8;
|
||||
color: #1f2937;
|
||||
}
|
||||
|
||||
.info {
|
||||
max-width: 760px;
|
||||
margin: 40px auto;
|
||||
background: #ffffff;
|
||||
border: 1px solid #d1d5db;
|
||||
border-radius: 8px;
|
||||
padding: 24px;
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue