Merge pull request 'Fix #196: one-command operator backup (pg_dump + MinIO)' (#234) from operator-backup-script into main

deploy/BACKUP.md

@@ -0,0 +1,55 @@
+# Backup & restore
+
+`backup.sh` produces a single bundle containing the Postgres database and the
+MinIO object store. Run it from this `deploy/` directory on the host that runs
+the stack.
+
+## Back up
+
+```bash
+./backup.sh
+# → backups/provenance-backup-20260609T140000Z.tar
+```
+
+The bundle contains:
+
+- `db.sql.gz` — `pg_dump --clean --if-exists` of the database, gzipped.
+- `minio-data.tar.gz` — the MinIO `/data` directory (objects + bucket metadata).
+- `MANIFEST.txt` — what's inside and when it was made.
+
+Optional retention: `BACKUP_RETAIN_DAYS=30 ./backup.sh` also deletes bundles
+older than 30 days. Schedule it from cron for off-box copies, e.g.:
+
+```cron
+15 3 * * *  cd /path/to/provenance/deploy && BACKUP_RETAIN_DAYS=30 ./backup.sh
+```
+
+(Copy the resulting bundle off the host — a backup on the same disk isn't one.)
+
+## Restore
+
+Restoring overwrites live data — stop the app first.
+
+```bash
+ts=20260609T140000Z                      # the bundle you're restoring
+mkdir -p /tmp/restore && tar xf backups/provenance-backup-$ts.tar -C /tmp/restore
+
+# 1. Database — the dump is --clean, so it drops & recreates objects.
+docker compose stop backend worker
+gunzip -c /tmp/restore/db.sql.gz \
+  | docker compose exec -T postgres psql -U "${POSTGRES_USER:-provenance}" -d "${POSTGRES_DB:-provenance}"
+
+# 2. Objects — replace the MinIO data directory.
+docker compose stop minio
+docker compose run --rm --no-deps -T -v provenance_miniodata:/data minio \
+  sh -c 'rm -rf /data/* && tar xzf - -C /data' < /tmp/restore/minio-data.tar.gz
+docker compose up -d
+
+rm -rf /tmp/restore
+```
+
+Notes:
+- The MinIO `/data` archive is filesystem-level; restore into the **same** MinIO
+  major version it was taken from.
+- Verify the volume name (`docker volume ls | grep miniodata`) — compose prefixes
+  it with the project name; adjust the `-v` mount accordingly.

deploy/backup.sh

@@ -0,0 +1,57 @@
+#!/usr/bin/env bash
+#
+# One-command backup of a Provenance deployment: the Postgres database and the
+# MinIO object store, into a single timestamped bundle under ./backups/.
+#
+#   ./backup.sh                 # write backups/provenance-backup-<UTC>.tar
+#   BACKUP_RETAIN_DAYS=30 ./backup.sh   # also prune bundles older than 30 days
+#
+# Run it from the host where `docker compose` manages the stack (i.e. this
+# deploy/ directory). Restore steps are in BACKUP.md.
+set -euo pipefail
+
+cd "$(dirname "$0")"  # the deploy/ directory (where docker-compose.yml lives)
+
+# Config comes from the compose .env (same file the stack uses); fall back to
+# the compose defaults so a vanilla stack still backs up.
+if [ -f .env ]; then set -a; . ./.env; set +a; fi
+PGUSER="${POSTGRES_USER:-provenance}"
+PGDB="${POSTGRES_DB:-provenance}"
+
+dc() { docker compose "$@"; }
+
+ts="$(date -u +%Y%m%dT%H%M%SZ)"
+work="backups/.work-$ts"
+mkdir -p "$work" backups
+
+cleanup() { rm -rf "$work"; }
+trap cleanup EXIT
+
+echo "→ Dumping Postgres database '$PGDB'…"
+dc exec -T postgres pg_dump -U "$PGUSER" -d "$PGDB" --no-owner --clean --if-exists \
+  | gzip > "$work/db.sql.gz"
+
+echo "→ Archiving MinIO object store…"
+# Tar MinIO's data directory straight from the container (objects + bucket
+# metadata). Restored by extracting back into the miniodata volume.
+dc exec -T minio tar czf - -C /data . > "$work/minio-data.tar.gz"
+
+cat > "$work/MANIFEST.txt" <<EOF
+Provenance backup
+created:   $ts
+database:  $PGDB  (pg_dump --clean --if-exists, gzip)
+objects:   MinIO /data (tar.gz)
+restore:   see deploy/BACKUP.md
+EOF
+
+bundle="backups/provenance-backup-$ts.tar"
+# Contents are already gzipped, so the outer archive is a plain tar.
+tar cf "$bundle" -C "$work" db.sql.gz minio-data.tar.gz MANIFEST.txt
+
+echo "✓ Backup written: $bundle ($(du -h "$bundle" | cut -f1))"
+
+if [ -n "${BACKUP_RETAIN_DAYS:-}" ]; then
+  echo "→ Pruning bundles older than ${BACKUP_RETAIN_DAYS} days…"
+  find backups -maxdepth 1 -name 'provenance-backup-*.tar' -type f \
+    -mtime "+${BACKUP_RETAIN_DAYS}" -print -delete
+fi