feat(ops): systemd units + smoke test

DEPLOYMENT.md

@@ -68,6 +68,22 @@ For VPS deployments, it is recommended to bind demo ports to localhost and put a
 - Point `API_BASE` at your public domain (for example `https://openlikwid.org`)
 - Serve the demo via the reverse proxy on `80/443`
 
+## Start on boot (systemd --user)
+
+This repo includes `systemd --user` unit templates:
+
+- `systemd/likwid-demo.service`
+- `systemd/likwid-prod.service`
+
+These units assume the repo is checked out at `~/likwid` for the target user, and they run `podman compose` using the env files under `compose/`.
+
+## Smoke test
+
+An operator smoke test script is provided:
+
+- `scripts/smoke-test.sh demo`
+- `scripts/smoke-test.sh prod`
+
 ## Demo Instance Details
 
 ### Demo Accounts

docs/admin/opensuse-operator-kit.md

@@ -44,26 +44,26 @@ If your Podman build does not provide `podman compose`, install the compose inte
 git clone https://codeberg.org/likwid/likwid.git ~/likwid
 ```
 
-2. Create the production env file:
+1. Create the production env file:
 
 ```bash
 cp ~/likwid/compose/.env.production.example ~/likwid/compose/.env.production
 ```
 
-3. Edit `~/likwid/compose/.env.production`:
+1. Edit `~/likwid/compose/.env.production`:
 
 - `POSTGRES_PASSWORD`
 - `JWT_SECRET`
 - `API_BASE` (should be your public URL, e.g. `https://your.domain`)
 
-4. Start services:
+1. Start services:
 
 ```bash
 cd ~/likwid
 podman compose --env-file compose/.env.production -f compose/production.yml up -d --build
 ```
 
-5. Create the first admin and complete setup:
+1. Create the first admin and complete setup:
 
 - Register the first user at `/register` (first user becomes platform admin)
 - Complete `/setup`
@@ -139,10 +139,12 @@ Podman is most reliable on openSUSE when managed as a rootless user service.
 sudo loginctl enable-linger deploy
 ```
 
-2. Create a systemd user unit:
+1. Create a systemd user unit:
 
 - File: `~/.config/systemd/user/likwid-demo.service`
 
+- Template: `systemd/likwid-demo.service` (from this repo)
+
 ```ini
 [Unit]
 Description=Likwid demo (podman compose)
@@ -153,7 +155,7 @@ After=network-online.target
 Type=oneshot
 RemainAfterExit=yes
 WorkingDirectory=%h/likwid
-ExecStart=/usr/bin/podman compose --env-file compose/.env.demo -f compose/demo.yml -f compose/demo.vps.override.yml up -d --build
+ExecStart=/usr/bin/podman compose --env-file compose/.env.demo -f compose/demo.yml -f compose/demo.vps.override.yml up -d
 ExecStop=/usr/bin/podman compose --env-file compose/.env.demo -f compose/demo.yml -f compose/demo.vps.override.yml down
 TimeoutStartSec=0
 
@@ -161,17 +163,23 @@ TimeoutStartSec=0
 WantedBy=default.target
 ```
 
-3. Enable and start it:
+1. Enable and start it:
 
 ```bash
 systemctl --user daemon-reload
 systemctl --user enable --now likwid-demo.service
 ```
 
-4. Inspect service logs:
+1. Inspect service logs:
 
 ```bash
 journalctl --user -u likwid-demo.service -f
 ```
 
 For production, create a separate unit (for example `likwid-prod.service`) with the production env file and compose file.
+
+## Smoke test
+
+After deploy/update, run:
+
+- `./scripts/smoke-test.sh demo`

scripts/smoke-test.sh

@@ -0,0 +1,122 @@
+#!/bin/bash
+set -euo pipefail
+
+MODE="${1:-}"
+
+if [ -z "$MODE" ] || { [ "$MODE" != "demo" ] && [ "$MODE" != "prod" ] && [ "$MODE" != "production" ]; }; then
+  echo "Usage: ./scripts/smoke-test.sh <demo|prod>" >&2
+  exit 2
+fi
+
+if [ "$MODE" = "production" ]; then
+  MODE="prod"
+fi
+
+if ! command -v curl >/dev/null 2>&1; then
+  echo "curl is required" >&2
+  exit 1
+fi
+
+if ! command -v podman >/dev/null 2>&1; then
+  echo "podman is required" >&2
+  exit 1
+fi
+
+ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+
+if [ "$MODE" = "demo" ]; then
+  ENV_FILE="$ROOT_DIR/compose/.env.demo"
+  BACKEND_CONTAINER="likwid-demo-backend"
+  FRONTEND_CONTAINER="likwid-demo-frontend"
+  DB_CONTAINER="likwid-demo-db"
+else
+  ENV_FILE="$ROOT_DIR/compose/.env.production"
+  BACKEND_CONTAINER="likwid-prod-backend"
+  FRONTEND_CONTAINER="likwid-prod-frontend"
+  DB_CONTAINER="likwid-prod-db"
+fi
+
+if [ ! -f "$ENV_FILE" ]; then
+  echo "Missing env file: $ENV_FILE" >&2
+  exit 1
+fi
+
+set -a
+# shellcheck disable=SC1090
+source <(sed 's/\r$//' "$ENV_FILE")
+set +a
+
+BACKEND_PORT="${BACKEND_PORT:-3000}"
+FRONTEND_PORT="${FRONTEND_PORT:-4321}"
+POSTGRES_USER="${POSTGRES_USER:-likwid}"
+POSTGRES_DB="${POSTGRES_DB:-likwid_prod}"
+
+if [ "$MODE" = "demo" ]; then
+  BACKEND_PORT="${BACKEND_PORT:-3001}"
+  FRONTEND_PORT="${FRONTEND_PORT:-4322}"
+  POSTGRES_USER="${POSTGRES_USER:-likwid_demo}"
+  POSTGRES_DB="${POSTGRES_DB:-likwid_demo}"
+fi
+
+BACKEND_HEALTH_URL="http://127.0.0.1:${BACKEND_PORT}/health"
+FRONTEND_URL="http://127.0.0.1:${FRONTEND_PORT}/"
+
+fail() {
+  echo "FAIL: $1" >&2
+  exit 1
+}
+
+ok() {
+  echo "OK: $1"
+}
+
+echo "=== Likwid smoke test ($MODE) ==="
+
+echo "[1/4] Containers present"
+podman container exists "$BACKEND_CONTAINER" || fail "Missing container: $BACKEND_CONTAINER"
+podman container exists "$FRONTEND_CONTAINER" || fail "Missing container: $FRONTEND_CONTAINER"
+podman container exists "$DB_CONTAINER" || fail "Missing container: $DB_CONTAINER"
+
+backend_running="$(podman inspect -f '{{.State.Running}}' "$BACKEND_CONTAINER" 2>/dev/null || true)"
+frontend_running="$(podman inspect -f '{{.State.Running}}' "$FRONTEND_CONTAINER" 2>/dev/null || true)"
+db_running="$(podman inspect -f '{{.State.Running}}' "$DB_CONTAINER" 2>/dev/null || true)"
+
+[ "$backend_running" = "true" ] || fail "$BACKEND_CONTAINER is not running"
+[ "$frontend_running" = "true" ] || fail "$FRONTEND_CONTAINER is not running"
+[ "$db_running" = "true" ] || fail "$DB_CONTAINER is not running"
+
+ok "containers running"
+
+echo "[2/4] Backend health: $BACKEND_HEALTH_URL"
+health_json="$(curl -fsS "$BACKEND_HEALTH_URL")" || fail "backend health check failed"
+echo "$health_json"
+ok "backend /health"
+
+echo "[3/4] Frontend reachable: $FRONTEND_URL"
+http_code="$(curl -fsS -o /dev/null -w "%{http_code}" "$FRONTEND_URL" || true)"
+case "$http_code" in
+  2*|3*) ok "frontend HTTP $http_code";;
+  *) fail "frontend not reachable (HTTP $http_code)";;
+esac
+
+echo "[4/4] Database reachable + migrations"
+podman exec "$DB_CONTAINER" pg_isready -U "$POSTGRES_USER" -d "$POSTGRES_DB" >/dev/null || fail "pg_isready failed"
+
+migration_table_check="$(podman exec "$DB_CONTAINER" psql -U "$POSTGRES_USER" -d "$POSTGRES_DB" -tAc "SELECT to_regclass('_sqlx_migrations');" | tr -d '[:space:]')"
+if [ "$migration_table_check" != "_sqlx_migrations" ]; then
+  fail "_sqlx_migrations table not found"
+fi
+
+failed_count="$(podman exec "$DB_CONTAINER" psql -U "$POSTGRES_USER" -d "$POSTGRES_DB" -tAc "SELECT COUNT(*) FROM _sqlx_migrations WHERE success = false;" | tr -d '[:space:]')"
+if [ "$failed_count" != "0" ]; then
+  fail "found failed migrations: $failed_count"
+fi
+
+installed_count="$(podman exec "$DB_CONTAINER" psql -U "$POSTGRES_USER" -d "$POSTGRES_DB" -tAc "SELECT COUNT(*) FROM _sqlx_migrations;" | tr -d '[:space:]')"
+if [ -z "$installed_count" ] || [ "$installed_count" -lt 1 ]; then
+  fail "no migrations recorded"
+fi
+
+ok "db reachable, migrations applied ($installed_count)"
+
+echo "=== Smoke test passed ==="

systemd/likwid-demo.service

@@ -0,0 +1,15 @@
+[Unit]
+Description=Likwid demo (podman compose)
+Wants=network-online.target
+After=network-online.target
+
+[Service]
+Type=oneshot
+RemainAfterExit=yes
+WorkingDirectory=%h/likwid
+ExecStart=/usr/bin/podman compose --env-file compose/.env.demo -f compose/demo.yml -f compose/demo.vps.override.yml up -d
+ExecStop=/usr/bin/podman compose --env-file compose/.env.demo -f compose/demo.yml -f compose/demo.vps.override.yml down
+TimeoutStartSec=0
+
+[Install]
+WantedBy=default.target

systemd/likwid-prod.service

@@ -0,0 +1,15 @@
+[Unit]
+Description=Likwid production (podman compose)
+Wants=network-online.target
+After=network-online.target
+
+[Service]
+Type=oneshot
+RemainAfterExit=yes
+WorkingDirectory=%h/likwid
+ExecStart=/usr/bin/podman compose --env-file compose/.env.production -f compose/production.yml up -d
+ExecStop=/usr/bin/podman compose --env-file compose/.env.production -f compose/production.yml down
+TimeoutStartSec=0
+
+[Install]
+WantedBy=default.target