nextcloud-ng_backup/tests/integration/full-restore-roundtrip.sh

#!/bin/bash
# Disaster recovery: occ backup:key:import + backup:target:add + backup:restore:full on a
# SECOND, fresh Nextcloud instance that never saw the first one, sharing only the backup
# location (a local directory, bind-mounted into both containers) -- see PLAN.md 3.7.
# Usage: full-restore-roundtrip.sh <nextcloud-image-tag> [sqlite|pgsql|mysql] [legacy|sftp|salvage|to-pgsql|to-mysql|to-sqlite]
#   e.g. full-restore-roundtrip.sh 35-apache pgsql
# With "sftp" the location is an SFTP server instead of a shared directory, and the origin has a
# file spread over several packs: the restore reads them ahead on connections of its own.
# With "to-<db>" the restore instance runs that database whatever the origin runs (a MySQL or
# SQLite backup records no ID counters; after the restore new rows must not collide with restored
# ones, whatever the database on either side).
# With "salvage" the snapshot's database dump is damaged on the location: the restore must stop
# without changing anything, and with --salvage put the files in a folder of their own.
# With "legacy" the origin runs NG Backup 1.0.0-rc.1 (0.9.7), whose backups do not record the
# structure of their tables: the restore must then leave the tables of the disabled app out
# with --skip-missing-tables, as for a real backup made before 1.0.0-rc.2.
# With pgsql or mysql the origin also has what broke real disaster recoveries: the Mail app with a synced
# account (foreign keys between its tables) and Deck installed and then switched off (tables of
# an app that is not enabled). The restore instance has neither; --install-apps adds Mail.
set -euo pipefail
IMAGE="nextcloud:${1:-35-apache}"
DB="${2:-sqlite}"
MODE="${3:-}"
LEGACY=""
[ "$MODE" = legacy ] && LEGACY=legacy
APP=$(cd "$(dirname "$0")/../.." && pwd)
ORIGIN_APP="$APP"
NET=ngb-frt-net
SHARED=$(mktemp -d)
chmod 777 "$SHARED"
fail() { echo "FAIL: $*"; exit 1; }
ok() { echo "ok   $*"; }

cleanup() {
	docker rm -fv ngb-frt-origin ngb-frt-restore ngb-frt-db-origin ngb-frt-db-restore ngb-frt-imap ngb-frt-sftp >/dev/null 2>&1 || true
	docker network rm "$NET" >/dev/null 2>&1 || true
	docker run --rm -v "$SHARED:/target" alpine sh -c 'rm -rf /target/*' >/dev/null 2>&1 || true
	rmdir "$SHARED" 2>/dev/null || true
	rm -f /tmp/ngb-frt-kit.json /tmp/ngb-frt-pass
	[ -n "${LEGACY_DIR:-}" ] && rm -rf "$LEGACY_DIR"
	return 0
}
trap cleanup EXIT

if [ "$LEGACY" = legacy ]; then
	LEGACY_DIR=$(mktemp -d)
	curl -fsSL https://github.com/dillardblom/ng_backup/releases/download/v1.0.0-rc.1/ng_backup-0.9.7.tar.gz | tar -xz -C "$LEGACY_DIR"
	ORIGIN_APP="$LEGACY_DIR/ng_backup"
fi

run_on() { docker exec -u www-data "$1" php occ "${@:2}"; }
# The app store sends the whole app list (~38 MB) and Nextcloud gives up after 120 s: on a slow day
# an install fails for reasons outside this test. Up to three tries.
install_app() { # container app
	for i in 1 2 3; do run_on "$1" app:install "$2" >/dev/null 2>&1 && return 0; sleep 20; done
	return 1
}

# Database settings for an instance: SQLite inside the container, or its own PostgreSQL container
db_env() {
	if [ "$DB" = pgsql ]; then
		docker run -d --name "ngb-frt-db-$1" --network "$NET" -e POSTGRES_DB=nextcloud -e POSTGRES_USER=nextcloud \
			-e POSTGRES_PASSWORD=nextcloud postgres:16-alpine >/dev/null
		for i in $(seq 1 30); do docker exec "ngb-frt-db-$1" pg_isready -q 2>/dev/null && break; sleep 2; done
		echo "-e POSTGRES_HOST=ngb-frt-db-$1 -e POSTGRES_DB=nextcloud -e POSTGRES_USER=nextcloud -e POSTGRES_PASSWORD=nextcloud"
	elif [ "$DB" = mysql ]; then
		docker run -d --name "ngb-frt-db-$1" --network "$NET" -e MARIADB_DATABASE=nextcloud -e MARIADB_USER=nextcloud \
			-e MARIADB_PASSWORD=nextcloud -e MARIADB_ROOT_PASSWORD=nextcloud mariadb:11 >/dev/null
		for i in $(seq 1 60); do docker exec "ngb-frt-db-$1" mariadb-admin ping -unextcloud -pnextcloud --silent >/dev/null 2>&1 && break; sleep 2; done
		echo "-e MYSQL_HOST=ngb-frt-db-$1 -e MYSQL_DATABASE=nextcloud -e MYSQL_USER=nextcloud -e MYSQL_PASSWORD=nextcloud"
	else
		echo "-e SQLITE_DATABASE=nextcloud"
	fi
}

docker network create "$NET" >/dev/null
LOCATION=(local -a null::null -o datadir=/mnt/shared)
if [ "$MODE" = sftp ]; then
	docker run -d --name ngb-frt-sftp --network "$NET" atmoz/sftp:alpine ngbackup:ngbackuppw:::upload >/dev/null
	LOCATION=(sftp -a password::password -o host=ngb-frt-sftp -o root=/upload -o user=ngbackup -o password=ngbackuppw)
fi
ORIGIN_DB=$(db_env origin)
# shellcheck disable=SC2086
docker run -d --name ngb-frt-origin --network "$NET" $ORIGIN_DB \
	-e NEXTCLOUD_ADMIN_USER=admin -e NEXTCLOUD_ADMIN_PASSWORD=admin \
	-v "$ORIGIN_APP:/var/www/html/custom_apps/ng_backup:ro" -v "$SHARED:/mnt/shared" "$IMAGE" >/dev/null
for i in $(seq 1 90); do run_on ngb-frt-origin status 2>/dev/null | grep -q "installed: true" && break; sleep 3; done
docker exec ngb-frt-origin chown www-data:www-data /var/www/html/custom_apps
run_on ngb-frt-origin app:enable ng_backup >/dev/null
ok "origin instance up ($DB${LEGACY:+, NG Backup 0.9.7})"

docker exec ngb-frt-origin sh -c "printf 'full restore roundtrip passphrase 2026\n' > /tmp/pass"
run_on ngb-frt-origin backup:key:init --passphrase-file=/tmp/pass --label=CI >/dev/null || fail "key init"
run_on ngb-frt-origin backup:key:kit --output=/tmp/kit.json >/dev/null
CODE=$(run_on ngb-frt-origin backup:key:kit | php -r 'echo json_decode(stream_get_contents(STDIN), true)["confirmation_code"];')
run_on ngb-frt-origin backup:key:confirm -u admin --code="$CODE" --confirm="Yes, I confirm" >/dev/null || fail "confirm"
run_on ngb-frt-origin backup:target:add offsite "${LOCATION[@]}" --path=repo >/dev/null || fail "target add"
ok "key, kit and location on the origin"

NC_PASS=$(openssl rand -hex 16)
docker exec -u www-data -e OC_PASS="$NC_PASS" ngb-frt-origin php occ user:add --password-from-env frtest >/dev/null
docker exec ngb-frt-origin sh -c "mkdir -p /var/www/html/data/frtest/files/Docs && head -c 200000 /dev/urandom > /var/www/html/data/frtest/files/Docs/report.bin && echo 'hello disaster recovery' > /var/www/html/data/frtest/files/Docs/note.txt && chown -R www-data:www-data /var/www/html/data/frtest"
if [ "$MODE" = sftp ]; then
	# about three packs of 32 MiB
	docker exec ngb-frt-origin sh -c "head -c 90000000 /dev/urandom > /var/www/html/data/frtest/files/Docs/large.bin && chown www-data:www-data /var/www/html/data/frtest/files/Docs/large.bin"
	LARGE_SUM=$(docker exec ngb-frt-origin sha256sum /var/www/html/data/frtest/files/Docs/large.bin | cut -d' ' -f1)
fi
run_on ngb-frt-origin files:scan frtest >/dev/null

# SQL on an instance's own database (pgsql/mysql only)
sql() {
	if [ "$DB" = pgsql ]; then docker exec "ngb-frt-db-$1" psql -U nextcloud -d nextcloud -Atc "$2"
	else docker exec "ngb-frt-db-$1" mariadb -unextcloud -pnextcloud -N -B nextcloud -e "$2"; fi
}
if [ "$DB" != sqlite ]; then
	# Mail with a synced account: oc_mail_accounts points at oc_mail_mailboxes (foreign keys),
	# while the restore loads tables in name order, accounts before mailboxes.
	docker run -d --name ngb-frt-imap --network "$NET" -e MAILNAME=mail.domain.tld -e MAIL_ADDRESS=user@domain.tld \
		-e MAIL_PASS=mypassword ghcr.io/christophwurst/docker-imap-devel:latest >/dev/null
	install_app ngb-frt-origin mail || fail "install mail on the origin (app store unreachable?)"
	run_on ngb-frt-origin config:system:set app.mail.verify-tls-peer --type=boolean --value=false >/dev/null
	sleep 10
	run_on ngb-frt-origin mail:account:create frtest Test user@domain.tld ngb-frt-imap 993 ssl user@domain.tld mypassword \
		ngb-frt-imap 25 tls user@domain.tld mypassword >/dev/null || fail "mail account"
	run_on ngb-frt-origin mail:account:sync -f 1 >/dev/null || fail "mail sync"
	[ "$(sql origin 'select count(*) from oc_mail_accounts where drafts_mailbox_id is not null')" = 1 ] \
		|| fail "the mail account does not point at its mailboxes"
	# Deck installed and then switched off: its tables stay in the database and in the backup
	install_app ngb-frt-origin deck || fail "install deck on the origin (app store unreachable?)"
	# a 4-byte character (emoji) in a table the restore has to create: utf8mb4 on MySQL/MariaDB
	sql origin "insert into oc_deck_boards (title, owner, color, archived, deleted_at, last_modified) values ('Plan 📌', 'frtest', '0087C5', false, 0, 0)" >/dev/null
	run_on ngb-frt-origin app:disable deck >/dev/null
	ok "origin has a synced Mail account and the tables of a disabled app"
fi

RUN_OUT=$(run_on ngb-frt-origin backup:run offsite -l disaster-test)
SNAP=$(printf '%s\n' "$RUN_OUT" | head -1 | awk -F'snapshot ' '{print $2}' | tr -d ',')
[ -n "$SNAP" ] || fail "no snapshot id from backup:run"
ok "test data backed up, snapshot $SNAP"
if [ "$MODE" = salvage ]; then
	# The database dump of this snapshot damaged on the location: a byte flipped in its manifest
	docker exec -u www-data ngb-frt-origin php -r '$p = "/mnt/shared/repo/db/" . $argv[1]; $d = file_get_contents($p); $i = intdiv(strlen($d), 2); $d[$i] = ~$d[$i]; file_put_contents($p, $d);' "$SNAP" \
		|| fail "damage the database dump"
	ok "database dump of the snapshot damaged on the location"
fi

docker cp ngb-frt-origin:/tmp/kit.json /tmp/ngb-frt-kit.json
docker exec ngb-frt-origin sh -c "cat /tmp/pass" > /tmp/ngb-frt-pass
ORIGIN_DBTYPE=$DB
case "$MODE" in to-*) DB=${MODE#to-} ;; esac
RESTORE_DB=$(db_env restore)
# shellcheck disable=SC2086
docker run -d --name ngb-frt-restore --network "$NET" $RESTORE_DB \
	-e NEXTCLOUD_ADMIN_USER=admin -e NEXTCLOUD_ADMIN_PASSWORD=admin \
	-v "$APP:/var/www/html/custom_apps/ng_backup:ro" -v "$SHARED:/mnt/shared" "$IMAGE" >/dev/null
for i in $(seq 1 90); do run_on ngb-frt-restore status 2>/dev/null | grep -q "installed: true" && break; sleep 3; done
docker exec ngb-frt-restore chown www-data:www-data /var/www/html/custom_apps
run_on ngb-frt-restore app:enable ng_backup >/dev/null
docker cp /tmp/ngb-frt-kit.json ngb-frt-restore:/tmp/kit.json
docker exec ngb-frt-restore chmod 644 /tmp/kit.json
docker cp /tmp/ngb-frt-pass ngb-frt-restore:/tmp/pass
ok "fresh restore instance up"

run_on ngb-frt-restore backup:key:import /tmp/kit.json --passphrase-file=/tmp/pass >/dev/null || fail "key import"
ADD_OUT=$(run_on ngb-frt-restore backup:target:add offsite "${LOCATION[@]}" --path=repo 2>&1) || { printf '%s\n' "$ADD_OUT"; fail "target add on the restore instance"; }
LIST_OUT=$(run_on ngb-frt-restore backup:list offsite 2>&1)
printf '%s\n' "$LIST_OUT" | grep -q "$SNAP" || {
	printf 'target:add said:\n%s\nbackup:list said:\n%s\n' "$ADD_OUT" "$LIST_OUT"
	docker exec ngb-frt-restore sh -c 'grep -h ng_backup /var/www/html/data/nextcloud.log | tail -5' || true
	docker exec ngb-frt-restore sh -c 'ls -la /mnt/shared/repo /mnt/shared/repo/snapshots' || true
	fail "the origin's snapshot is not listed after connecting the location"
}
ok "recovery kit imported, existing repository adopted, snapshot visible"

if [ "$MODE" = salvage ]; then
	set +e
	OUT=$(run_on ngb-frt-restore backup:restore:full offsite "$SNAP" --no-interaction 2>&1); CODE=$?
	set -e
	[ "$CODE" = 1 ] || { printf '%s\n' "$OUT" | tail -20; fail "a restore with a damaged database dump did not stop (exit $CODE)"; }
	printf '%s\n' "$OUT" | grep -- "--salvage" >/dev/null || { printf '%s\n' "$OUT" | tail -20; fail "the stopped restore does not point at --salvage"; }
	run_on ngb-frt-restore status 2>&1 | grep "maintenance: false" >/dev/null || fail "maintenance mode stayed on after a restore that changed nothing"
	ok "damaged database dump: the restore stops before changing anything and points at --salvage"
	set +e
	OUT=$(run_on ngb-frt-restore backup:restore:full offsite "$SNAP" --no-interaction --salvage 2>&1); CODE=$?
	set -e
	[ "$CODE" = 2 ] || { printf '%s\n' "$OUT" | tail -30; fail "restore:full --salvage exited with $CODE, not 2"; }
	SALVAGE=/var/www/html/data/ngb-salvage-${SNAP:0:12}
	printf '%s\n' "$OUT" | grep "$SALVAGE" >/dev/null || { printf '%s\n' "$OUT" | tail -30; fail "the output does not name the salvage folder"; }
	[ "$(docker exec ngb-frt-restore cat "$SALVAGE/data/frtest/files/Docs/note.txt")" = "hello disaster recovery" ] || fail "the user's file is not in the salvage folder"
	docker exec ngb-frt-restore test -f "$SALVAGE/config/config.php" || fail "config.php is not in the salvage folder"
	run_on ngb-frt-restore user:list | grep frtest >/dev/null && fail "the fresh database was changed (the backed-up user is there)"
	run_on ngb-frt-restore status 2>&1 | grep "maintenance: false" >/dev/null || fail "maintenance mode is still on after the salvage"
	run_on ngb-frt-restore backup:status >/dev/null || fail "backup:status fails after the salvage"
	ok "with --salvage: the fresh database untouched, data and config of the backup in $SALVAGE (exit 2)"
	echo "FULL RESTORE ROUNDTRIP PASS ($DB, salvage)"
	exit 0
fi

RESTORE_OPTS=(--no-interaction --install-apps)
if [ "$LEGACY" = legacy ] && [ "$DB" != sqlite ]; then
	# Without --skip-missing-tables an older backup must be refused, naming the app's tables
	REFUSED=$(run_on ngb-frt-restore backup:restore:full offsite "$SNAP" "${RESTORE_OPTS[@]}" 2>&1) \
		&& fail "an older backup with tables of unknown structure was restored without --skip-missing-tables"
	printf '%s\n' "$REFUSED" | grep -q "oc_deck_boards" || { printf '%s\n' "$REFUSED" | tail -20; fail "the refusal does not name the missing tables"; }
	ok "older backup refused without --skip-missing-tables, missing tables named"
	RESTORE_OPTS+=(--skip-missing-tables)
fi
if [ "$DB" = sqlite ]; then
	# Another process writing while the restore starts (a cron job that was already running, or
	# the installer still finishing after it says "installed"): the restore must wait for it, not
	# stop with "database is locked". Short write transactions on a table of its own, until the
	# restore is done (/tmp/frt-side-stop; Nextcloud's own commands after it are not under test).
	docker exec -d -u www-data ngb-frt-restore php -r '
		$p = new PDO("sqlite:/var/www/html/data/nextcloud.db"); $p->setAttribute(PDO::ATTR_ERRMODE, PDO::ERRMODE_EXCEPTION);
		$p->exec("CREATE TABLE IF NOT EXISTS frt_side_writer (t REAL)");
		for ($end = microtime(true) + 300; microtime(true) < $end && !file_exists("/tmp/frt-side-stop");) {
			$p->beginTransaction(); $p->exec("INSERT INTO frt_side_writer VALUES (" . microtime(true) . ")"); usleep(300000); $p->commit(); usleep(20000);
		}
		touch("/tmp/frt-side-done");'
	sleep 1
fi
sftp_logins() { docker logs ngb-frt-sftp 2>&1 | grep -c "Accepted password" || true; }
[ "$MODE" = sftp ] && LOGINS_BEFORE=$(sftp_logins)
OUT=$(run_on ngb-frt-restore backup:restore:full offsite "$SNAP" "${RESTORE_OPTS[@]}" 2>&1) || {
	printf '%s\n' "$OUT" | tail -40
	docker exec ngb-frt-restore sh -c 'tail -c 6000 /var/www/html/data/nextcloud.log' || true
	fail "restore:full"
}
printf '%s\n' "$OUT" | grep -q "maintenance mode while the restore runs" || fail "the restore did not say it runs in maintenance mode"
run_on ngb-frt-restore status 2>&1 | grep "maintenance: false" >/dev/null || fail "maintenance mode is still on after the restore"
run_on ngb-frt-restore config:app:get ng_backup restore_full_started >/dev/null 2>&1 && fail "the restore left its 'started' marker behind"
ok "backup:restore:full completed, in maintenance mode and out of it again"
if [ "$DB" = sqlite ]; then
	docker exec ngb-frt-restore touch /tmp/frt-side-stop
	for i in $(seq 1 20); do docker exec ngb-frt-restore test -f /tmp/frt-side-done && break; sleep 0.5; done
	WRITES=$(docker exec -u www-data ngb-frt-restore php -r 'echo (new PDO("sqlite:/var/www/html/data/nextcloud.db"))->query("SELECT COUNT(*) FROM frt_side_writer")->fetchColumn();')
	[ "${WRITES:-0}" -gt 3 ] || fail "the other writer did not run alongside the restore ($WRITES writes)"
	ok "the restore waited for another process writing to SQLite ($WRITES writes alongside)"
fi

# Everything below must work in a FRESH occ process (a new PHP process per docker exec), since
# earlier bugs here only showed up after config.php's secret was rewritten mid-restore.
run_on ngb-frt-restore backup:status >/dev/null || fail "backup:status fails after restore (own key/target undecryptable?)"
# not grep -q: it stops reading at the first match, and occ, still writing, then fails (pipefail)
run_on ngb-frt-restore user:list | grep frtest >/dev/null || fail "the backed-up user is missing from the restored database"
docker exec ngb-frt-restore test -f /var/www/html/data/frtest/files/Docs/note.txt || fail "restored file is missing"
[ "$(docker exec ngb-frt-restore cat /var/www/html/data/frtest/files/Docs/note.txt)" = "hello disaster recovery" ] || fail "restored file content differs"
run_on ngb-frt-restore files:scan frtest >/dev/null || fail "files:scan fails after restore"
# New rows after the restore: a new file (file cache) and a new user must not collide with
# restored rows (ID counters after the data).
docker exec ngb-frt-restore sh -c "echo new > /var/www/html/data/frtest/files/Docs/after-restore.txt && chown www-data /var/www/html/data/frtest/files/Docs/after-restore.txt"
run_on ngb-frt-restore files:scan frtest >/dev/null || fail "a new file cannot be added after the restore"
if [ "$DB" != sqlite ]; then
	[ "$(sql restore "select count(*) from oc_filecache where path = 'files/Docs/after-restore.txt'")" = 1 ] \
		|| fail "a new file did not make it into the file cache after the restore (ID counters?)"
fi
docker exec -u www-data -e OC_PASS="$NC_PASS" ngb-frt-restore php occ user:add --password-from-env frnew >/dev/null || fail "a new user cannot be added after the restore"
ok "database, files and ng_backup's own state are all intact and usable after the restore"

# Mail and Deck were only set up on an origin with a database server (see above)
if [ "$ORIGIN_DBTYPE" != sqlite ] && [ "$DB" != sqlite ] && [ "$LEGACY" = legacy ]; then
	[ "$(sql restore "select count(*) from information_schema.tables where table_name = 'oc_deck_boards'")" = 0 ] || fail "a table of unknown structure was created"
	[ "$(sql restore "select count(*) from oc_mail_accounts where drafts_mailbox_id is not null")" = 1 ] || fail "the mail account was not restored"
	ok "older backup: tables of the disabled app left out, Mail restored"
elif [ "$ORIGIN_DBTYPE" != sqlite ] && [ "$DB" != sqlite ]; then
	[ "$(sql restore "select count(*) from information_schema.tables where table_name = 'oc_deck_boards'")" = 1 ] || fail "the tables of the disabled app were not created"
	[ "$(sql restore "select title from oc_deck_boards")" = "Plan 📌" ] || fail "a 4-byte character did not survive in a created table"
	[ "$(sql restore "select count(*) from oc_mail_accounts where drafts_mailbox_id is not null")" = 1 ] || fail "the mail account was not restored"
	[ "$(sql restore "select count(*) from information_schema.table_constraints where constraint_type = 'FOREIGN KEY' and table_name like 'oc_mail_%'")" -gt 0 ] \
		|| fail "the foreign keys of Mail are missing after the restore"
	printf '%s\n' "$OUT" | grep -q "Created .* tables" || fail "the restore did not report the tables it created"
	ok "tables of a disabled app created, Mail restored with its foreign keys"
fi

if [ "$MODE" = sftp ]; then
	[ "$(docker exec ngb-frt-restore sha256sum /var/www/html/data/frtest/files/Docs/large.bin | cut -d' ' -f1)" = "$LARGE_SUM" ] \
		|| fail "the large file differs after the restore"
	LOGINS=$(( $(sftp_logins) - LOGINS_BEFORE ))
	[ "$LOGINS" -gt 1 ] || fail "the restore did not read ahead on connections of its own ($LOGINS SFTP logins)"
	docker exec ngb-frt-restore sh -c 'ls -a /var/www/html/data' | grep -q ngb-restore-spool && fail "the spool folder was left behind"
	ok "over SFTP: read ahead on connections of its own ($LOGINS SFTP logins during the restore), large file identical, no spool left"
fi

run_on ngb-frt-restore backup:run offsite -l post-restore-check >/dev/null || fail "a new backup after the restore fails"
ok "the restored instance can run a new backup of its own"

echo "FULL RESTORE ROUNDTRIP PASS ($ORIGIN_DBTYPE${MODE:+, $MODE})"