The backup file (#5672 "Backup file: pg_dump of config + audit + alert history, the secret key and a manifest"): steward-<UTC>.tar holding a pg_dump --format=custom with metrics', check results' and Docker/Traefik/ UniFi rows left out, the secret key, and a manifest. Every table is named KEPT or EXCLUDED in steward/backup/contents.py, and a guard test fails on a new one. The image gains postgresql-client-17 (approved, System 180). The restore (#5674 "Restore: `steward restore` and a CI test that a dump brings Steward back"): pg_restore in its three sections. Between data and constraints, a kept row pointing at a left-out row gets what its foreign key's ON DELETE says (alert_events.ansible_run_id is cleared). It refuses a non-empty database unless --wipe, and puts the backup's key in /data/secret.key. Migrations run on Steward's next start. `steward` stays the server command: it is now a click group that serves when given no subcommand. The publish smoke step backs up the booted image's database, restores it into a second one, checks a marker setting came back and plugin_metrics is empty, and starts Steward on it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -221,6 +221,36 @@ jobs:
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# A backup made by the image restores into an empty database, and
|
||||
# Steward starts on it (milestone 507). It carries configuration
|
||||
# (the marker setting) and leaves metrics' rows out.
|
||||
sql() { docker exec "$SMOKE-pg" psql -U steward -v ON_ERROR_STOP=1 -tA "$@"; }
|
||||
sql -d steward -c "INSERT INTO app_settings (key, value_json, updated_at) VALUES ('smoke.backup', '\"kept\"', now())"
|
||||
sql -d steward -c "INSERT INTO plugin_metrics (id, source_module, resource_name, metric_name, value, recorded_at) VALUES ('smoke-metric', 'smoke', 'smoke', 'smoke', 1, now())"
|
||||
docker exec -u app "$SMOKE-app" steward backup --to /tmp/backups
|
||||
sql -d steward -c "CREATE DATABASE restored"
|
||||
docker exec -u app \
|
||||
-e "STEWARD_DATABASE_URL=postgresql+asyncpg://steward:steward@$SMOKE-pg:5432/restored" \
|
||||
"$SMOKE-app" sh -c 'steward restore /tmp/backups/steward-*.tar'
|
||||
test "$(sql -d restored -c "SELECT value_json FROM app_settings WHERE key = 'smoke.backup'")" = '"kept"'
|
||||
test "$(sql -d restored -c "SELECT count(*) FROM plugin_metrics")" = "0"
|
||||
test "$(sql -d restored -c "SELECT count(*) FROM alembic_version")" -ge 1
|
||||
docker run -d --name "$SMOKE-restored" --network "$SMOKE-net" \
|
||||
-e "STEWARD_DATABASE_URL=postgresql+asyncpg://steward:steward@$SMOKE-pg:5432/restored" \
|
||||
-e STEWARD_SECRET_KEY=smoke-test-placeholder \
|
||||
"$IMAGE"
|
||||
up=""
|
||||
for _ in $(seq 1 60); do
|
||||
if docker exec "$SMOKE-restored" python -c 'import urllib.request
|
||||
urllib.request.urlopen("http://127.0.0.1:5000/health", timeout=5)' >/dev/null 2>&1; then up=1; break; fi
|
||||
sleep 2
|
||||
done
|
||||
if [ -z "$up" ]; then
|
||||
echo "FATAL: Steward never started on the restored database"
|
||||
docker logs "$SMOKE-restored" 2>&1 | tail -80
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# A stop is a clean shutdown: SIGTERM through tini to Hypercorn, which
|
||||
# finishes within its graceful timeout and exits 0.
|
||||
docker stop -t 30 "$SMOKE-app"
|
||||
@@ -246,7 +276,8 @@ jobs:
|
||||
- name: Smoke clean-up
|
||||
if: always()
|
||||
run: |
|
||||
docker rm -f "steward-smoke-${{ github.run_id }}-app" "steward-smoke-${{ github.run_id }}-pg" >/dev/null 2>&1 || true
|
||||
docker rm -f "steward-smoke-${{ github.run_id }}-app" "steward-smoke-${{ github.run_id }}-restored" \
|
||||
"steward-smoke-${{ github.run_id }}-pg" >/dev/null 2>&1 || true
|
||||
docker network rm "steward-smoke-${{ github.run_id }}-net" >/dev/null 2>&1 || true
|
||||
- name: Prune dangling layers
|
||||
if: always()
|
||||
|
||||
Reference in New Issue
Block a user