Merge pull request #18 from dillardblom/rc5

Release 1.0.0-rc.5

.github/FUNDING.yml

@@ -0,0 +1 @@
+custom: ["https://www.ensembia.com"]

.github/ISSUE_TEMPLATE/experience.yml

@@ -0,0 +1,56 @@
+name: Experience report
+description: Tell us how NG Backup works for you, also when everything went fine.
+title: "Experience: "
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for trying NG Backup! Reports of what works are just as useful as bug reports:
+        they tell us which setups are tested. Please leave out host names, user names and keys.
+  - type: dropdown
+    id: location
+    attributes:
+      label: Backup location
+      multiple: true
+      options:
+        - S3 / S3-compatible
+        - SFTP
+        - WebDAV
+        - SMB/CIFS
+        - FTP
+        - Swift
+        - Local path (disk, NFS mount, ...)
+    validations:
+      required: true
+  - type: input
+    id: provider
+    attributes:
+      label: Storage provider (optional)
+      placeholder: e.g. Hetzner Storage Box, OVH, Backblaze B2, own NAS
+  - type: input
+    id: setup
+    attributes:
+      label: Nextcloud version and setup
+      placeholder: e.g. 32.0.1, AIO / Docker / bare metal, PostgreSQL / MariaDB
+  - type: input
+    id: size
+    attributes:
+      label: Rough size of the backup
+      placeholder: e.g. 50 GB, 200,000 files
+  - type: checkboxes
+    id: tried
+    attributes:
+      label: What did you try?
+      options:
+        - label: Full backup
+        - label: Incremental backup
+        - label: Verify
+        - label: Restore of files or folders
+        - label: Full restore on another server
+  - type: textarea
+    id: notes
+    attributes:
+      label: How did it go?
+      description: What worked, what was unclear, slow or broken.
+    validations:
+      required: true

.github/workflows/ci.yml

@@ -104,3 +104,23 @@ jobs:
           persist-credentials: false
       - name: Full restore round trip
         run: tests/integration/full-restore-roundtrip.sh 35-apache
+      - name: Full restore round trip on PostgreSQL, with Mail (foreign keys) and a disabled app
+        run: tests/integration/full-restore-roundtrip.sh 35-apache pgsql
+      - name: Full restore round trip on MariaDB, with Mail (foreign keys) and a disabled app
+        run: tests/integration/full-restore-roundtrip.sh 35-apache mysql
+      - name: Full restore of a backup made by 1.0.0-rc.1 (no table structure) on PostgreSQL
+        run: tests/integration/full-restore-roundtrip.sh 35-apache pgsql legacy
+      - name: Full restore of a backup made by 1.0.0-rc.1 (no table structure) on MariaDB
+        run: tests/integration/full-restore-roundtrip.sh 35-apache mysql legacy
+      - name: Full restore over SFTP on PostgreSQL, reading packs ahead on several connections
+        run: tests/integration/full-restore-roundtrip.sh 35-apache pgsql sftp
+      - name: Full restore of a MariaDB backup onto PostgreSQL (ID counters after the data)
+        run: tests/integration/full-restore-roundtrip.sh 35-apache mysql to-pgsql
+      - name: Full restore of a PostgreSQL backup onto MariaDB
+        run: tests/integration/full-restore-roundtrip.sh 35-apache pgsql to-mysql
+      - name: Full restore of a PostgreSQL backup onto SQLite
+        run: tests/integration/full-restore-roundtrip.sh 35-apache pgsql to-sqlite
+      - name: Full restore of a MariaDB backup onto SQLite
+        run: tests/integration/full-restore-roundtrip.sh 35-apache mysql to-sqlite
+      - name: Full restore of a SQLite backup onto PostgreSQL
+        run: tests/integration/full-restore-roundtrip.sh 35-apache sqlite to-pgsql

CHANGELOG.md

@@ -7,6 +7,145 @@ the app store accepts a `-beta` suffix, but Nextcloud servers then only offer th
 beta/daily update channel, which would hide the app from most admins. The stability stage is
 instead carried by the app description, the git tag, the release, and this file.
 
+## [1.0.0-rc.5] - 2026-10-22
+
+Fifth release candidate for 1.0.0; the app version is 0.9.11. A full restore of 1 TB over SFTP
+stopped after 13 hours with "Blob not in index"; the backup itself was fine.
+
+### Changed
+- README and app store description: NG Backup needs background jobs on system cron, with how to
+  set that up (issues #13, #17).
+
+### Fixed
+- A full restore no longer stops with "Blob not in index" after a pack could not be read for a
+  moment. Reading the index again then got an empty listing (from a connection the location had
+  dropped) and emptied the index. Reading the index again now only adds, an empty listing of a
+  location that has an index is an error instead of an empty index, and a pack that could not be
+  read is read once more before the restore gives up.
+- After a full restore of a MySQL/MariaDB or SQLite backup onto PostgreSQL, new files, users or
+  activities could not be added ("duplicate key", "File entry could not be inserted"): such
+  backups record no ID counters, and they stayed at 1. Every counter of a restored table now goes
+  after its data. Found in a disaster recovery simulation of 138 GB from MariaDB to PostgreSQL,
+  where all 15,772 files and every count were identical.
+- A full restore now runs in maintenance mode: a background job, a page visit or a user writing
+  into the instance meanwhile could collide with restored rows ("duplicate key") or be lost. It
+  is switched off when the restore completes; after an error it stays on, and the message gives
+  the one line to switch it off and run the restore again. Maintenance mode that was on before
+  the restore stays on.
+- Adding a location whose repository config could not be read, while backup data is there,
+  no longer creates a new repository over it: it stops with an explanation. A snapshot that
+  cannot be taken over when a location is added is now logged instead of left out silently.
+- An SFTP connection that a Hetzner Storage Box dropped without phpseclib noticing is now
+  recognised and replaced: the check asks the server and counts its answer.
+- The extra connection a full restore reads ahead on is replaced when it breaks (up to 20 times),
+  instead of reading the rest of the restore the slow way.
+
+## [1.0.0-rc.4] - 2026-10-19
+
+Fourth release candidate for 1.0.0; the app version is 0.9.10. 1.0.0-rc.3 (0.9.9) was not
+released: its fixes are in here.
+
+### Changed
+- A full restore over SFTP reads the packs ahead on a connection of its own, 32 requests in
+  flight, into temporary files in the restore folder. From a Hetzner Storage Box to a server in
+  Canada (122 ms) packs now come in at about 14 MiB/s instead of 2.8. More connections can be set
+  with `restore_sftp_connections` (README). A part that cannot be read this way is read as
+  before. Restores from other locations work as before.
+- App store description: the line about Ensembia.
+
+### Fixed
+- After a full restore stopped halfway, running it again with `--force` was refused when the
+  database was already restored: Nextcloud then first wants `occ upgrade`. The guide and the
+  error message now say so.
+- A full restore of a backup made before 1.0.0-rc.2 with `--skip-missing-tables` failed on
+  PostgreSQL with "relation ... does not exist": the left-out tables were still looked up to set
+  their ID counters. It now skips them. A new test restores a backup made by 1.0.0-rc.1 on
+  PostgreSQL and MariaDB.
+- The app store showed old screenshots: it keeps a copy per URL, and the URLs always pointed at
+  `main`. They now point at the release's tag.
+
+## [1.0.0-rc.2] - 2026-10-18
+
+Second release candidate for 1.0.0; the app version is 0.9.8. Fixes from a full disaster recovery
+test of a production instance (about 1 TB, Nextcloud All-in-One onto a plain Nextcloud with
+PostgreSQL).
+
+### Added
+- `docs/DISASTER-RECOVERY.md`: step-by-step guide for when your server is gone.
+- `occ backup:restore:full --install-apps` installs (from the app store) or enables the apps the
+  old server had enabled, before the restore starts.
+
+### Changed
+- Backups record the structure of every database table. A full restore creates tables that do not
+  exist on the new instance, for example those left behind by an app that was removed long ago or
+  is switched off, instead of stopping at the first one.
+- A full restore no longer refuses when apps are missing: it restores their data and lists the
+  apps to install afterwards. `nextcloud-aio` is never required, so a backup of Nextcloud
+  All-in-One can be restored onto a plain Nextcloud.
+- A full restore onto an installation with a different table prefix (`dbtableprefix`) is refused
+  before it starts, with what to change, instead of restoring into tables nobody uses.
+- All problems are listed at once, with the app each missing table probably belongs to. For
+  backups made before this version, `--skip-missing-tables` leaves out tables whose structure is
+  unknown.
+- A fuller app store description, ready for 1.0.0, and a note on paid restore help by Ensembia.
+- README: switching the server to TCP BBR made backups over a long distance about 3 times faster.
+
+### Fixed
+- A full restore failed on foreign keys (for example those of the Mail app), because tables are
+  restored in name order. Foreign keys are now checked after all rows are loaded, before the
+  restore commits.
+- `occ backup:target:add` without a key pointed to `backup:key:init`, which makes a new key that
+  cannot read existing backups. It now points to `backup:key:import` for a restore, and says that
+  connecting to a location with backups can take a while. While it reads the index of a location
+  with backups, it shows how far it is and about how long it still takes.
+- A restore stopped with "Not found: packs/..." when the location was cleaned up while it ran,
+  for example by the weekly cleanup of the original server during a recovery test on a second
+  server: blobs that were moved into new packs were still looked for in the old ones. A restore
+  now reloads the index and reads them from where they are now.
+- Removing a location left its cached index in the database (tens of thousands of rows for a large
+  backup). It is removed with the location now, and once for locations that are already gone.
+
+## [1.0.0-rc.1] - 2026-10-17
+
+Release candidate for 1.0.0; the app version is 0.9.7. Only bug fixes until 1.0.0. Tested on a
+production instance (about 1 TB, 150,000 files): full and incremental backups and a verify on
+SFTP and SMB (Hetzner Storage Box) and S3 (OVH), a deep verify on SFTP, and partial restores from
+SMB and S3 checked against checksums.
+
+### Added
+- The admin page asks for feedback, with a link to a short "Experience report" form on GitHub:
+  which location, setup and size you used, and how it went.
+
+### Changed
+- New passphrases must be at least 16 characters (was 12). The location stores the key
+  encrypted with each passphrase, so the passphrase is what really protects the backups.
+  Existing passphrases keep working. The README and the how-to now say so, and why the
+  recovery kit must still be kept off the server.
+- Dates and times in the web interface follow the locale in the user's Nextcloud settings instead
+  of the browser's language, so a 24-hour locale shows 16:00 rather than 4:00 PM.
+- The list of backup runs (web interface and `occ backup:status`) shows the runs of the last 7
+  days, those still running, and at least the 5 newest; a failed run stays visible for that week.
+  `occ backup:status --all` and "Show older runs" in the web interface list all of them.
+- `occ backup:status` and `occ backup:verify` show durations of a day or more with the days
+  ("1d 12:10:13" instead of "12:10:13").
+
+### Fixed
+- With system cron, a running backup moved forward only every other cron run: Nextcloud
+  skipped the background job when cron came a few seconds before its 5-minute interval was
+  over, so a backup was idle 6 of every 10 minutes. The job now runs at every cron run.
+- Photos, video and other compressed data are no longer deflated only to throw the result away:
+  a quick test on three small slices of each block skips it. Compressing was the slowest part of
+  a backup (about 24 MiB/s).
+- Checking a backup on an S3 location (`occ backup:verify`) took hours on a large repository:
+  the index files were downloaded one at a time, at about two a second. They are now downloaded
+  16 at a time: on a production instance (27,585 index files, 1 TB) the check went from about
+  4 hours to 3.5 minutes.
+- Writing the snapshot at the end of a long backup to S3 took a quarter of an hour without any
+  progress shown: it read back the file list of every step one at a time. These reads are now
+  done 16 at a time on S3 (96 reads: 82 seconds before, 2 now), blobs that follow each other in
+  a pack are read at once on every location, the snapshot is written in a step of its own, and
+  the run shows "commit" while it does so.
+
 ## [0.9.6-beta.7] - 2026-10-14
 
 Bugfix release for SMB locations, with `occ backup:cancel` to stop a backup that does not get
@@ -245,6 +384,7 @@ and not implemented yet.
 - See the "Storage backend experiences" section of the README for provider-specific quirks found
   so far (e.g. Hetzner Storage Box sub-accounts).
 
+[1.0.0-rc.1]: https://github.com/dillardblom/ng_backup/releases/tag/v1.0.0-rc.1
 [0.9.6-beta.7]: https://github.com/dillardblom/ng_backup/releases/tag/v0.9.6-beta.7
 [0.9.5-beta.6]: https://github.com/dillardblom/ng_backup/releases/tag/v0.9.5-beta.6
 [0.9.4-beta.5]: https://github.com/dillardblom/ng_backup/releases/tag/v0.9.4-beta.5

PLAN.md

@@ -377,6 +377,105 @@ in README "Known limitations":
 11. `backup:restore:full` in onderhoudsmodus en hervatbaar maken; nu: opnieuw draaien met `--force`.
 12. Config/rename op FTP/SMB-servers die geen rename over een bestaand bestand toestaan.
 
+**Plan richting 1.0.0 en 1.1.0 (besluit 2026-10-15/16):**
+- **1.0.0-rc.1:** wat nu op `polish` staat (snelle S3-verify en snapshot-commit, kortere runlijst,
+  duur met dagen, job bij elke cron-run, deflate-test, feedbackformulier, datums in de locale van
+  de gebruiker, wachtwoordzin min. 16 tekens). Geen nieuwe functies meer.
+- **Vóór 1.0.0 (verplicht):** volledige restore met kit op een tweede server (PVE02), alleen lezend
+  of op een kopie van de locatie; plus een user-restore. Zonder geslaagde test geen 1.0.0.
+- **1.0.0 (besluit 2026-10-18):** alleen betrouwbaarheid. rc2 uitgebracht; slaagt de grote
+  DR-test op VM 980 (snapshot van 12-10, met `--skip-missing-tables`), dan 1.0.0. Zo niet: fix,
+  rc3, en rc3 pas uitbrengen na een geslaagde volledige DR-test.
+- **rc4 (besluit 2026-10-19):** rc3 is niet uitgebracht. De DR-test met rc3 liep ~2,8 MiB/s
+  (~3,5 dag); parallel lezen over SFTP haalde vanaf VM 980 ~7,6 MiB/s. Daarom rc4 = rc3 +
+  vooruitlezen over SFTP (4 eigen verbindingen). Volgorde: volledige DR-test op VM 980 volgens de
+  gids (SFTP, Storage Box) → rc4 uitbrengen en om tests vragen → zelf een volledige DR van een
+  productie-instantie van ~250 GB via S3 en via SMB. Drie volledige DR-restores vóór 1.0.0.
+  Problemen of meldingen van gebruikers: rc5.
+- **1.0.1:**
+  1. (Naar rc4: herstelsnelheid over SFTP.) S3 leest al 16 tegelijk bij index en tree, maar een
+     restore leest de packs nog één voor één: ook vooruitlezen via de S3-client.
+  2. Waarschuwing in de beheerpagina en `backup:status` als achtergrondjobs niet op systeem-cron
+     staan, en "waiting for background jobs" als een lopende backup lang geen stap zette (issue
+     #13). Cron zelf aanzetten kan de app niet: zonder echte cron-regel stopt dan alles.
+  3. Volledige DR-test met een backup die al de tabelstructuur bevat (gemaakt met rc2 of later),
+     zonder `--skip-missing-tables`: dat pad is op 1 TB nog niet getest.
+- **1.1.0:**
+  1. `backup:key:import` zonder kit: de sleutel-slots van de locatie (`config`) lezen, met de kit
+     als reserve als `config` ontbreekt of niet opent. Vergt een andere volgorde van
+     `target:add` en sleutelimport (het gevoeligste pad), daarom niet in rc1. Daarna de
+     DR-test op PVE02 herhalen zonder kit.
+  2. Instelling "zware achtergrondjobs pauzeren tijdens een backup" (standaard aan, uit te zetten):
+     Memories, files_antivirus BackgroundScanner, Recognize, Preview Generator, fulltextsearch.
+     Via de reservering/last_run van die jobs (geen apps uitzetten), crashbestendig, maximaal
+     ~6 uur achter elkaar, zichtbaar in UI en log. Op nc01 met de hand getest tijdens SMB-run 10.
+  3. Snelheid: lezen en uploaden laten overlappen, meerdere bestanden tegelijk lezen, eventueel
+     een eigen worker (`occ background-job:worker`). Gemeten op nc01: 55% wachten op de schijf,
+     33% op de SMB-upload, ~7% CPU. Vergt extra PHP-processen; botst mogelijk met uitgangspunt 1.
+- **Bevindingen DR-test op PVE02 (2026-10-17, snapshot van nc01, 1 TB, AIO → gewone NC 34 met
+  PostgreSQL 18)** — voor **1.0.0-rc.2**:
+  1. Tabellen van apps die bij de backup **niet aanstonden** (restanten: Deck, ONLYOFFICE,
+     AppAPI, een archief-app) blokkeren de restore met één tabelnaam per poging. Standaard
+     overslaan met één waarschuwing per app; optie om ze toch terug te zetten.
+  2. Alle ontbrekende apps en tabellen **vooraf in één lijst**, per app benoemd (nu één per poging,
+     ook voor uitgeschakelde standaard-apps zoals `admin_audit`).
+  3. `--skip-missing-apps`; `nextcloud-aio` standaard overslaan (bestaat buiten AIO niet), zodat
+     AIO → gewone Nextcloud werkt.
+  4. `--install-apps`: ontbrekende apps uit de app store installeren.
+  5. Apps buiten de app store (eigen builds, `side_menu`, `nextcloud-aio`): documenteren; later
+     eventueel `custom_apps` meenemen in de backup.
+  6. Tabellen van een app die wél aanstond maar die hun tabel later zelf maakt (Memories:
+     `memories_planet_geometry`) netjes afhandelen.
+  7. `backup:target:add` zonder sleutel verwijst naar `key:init`; als er al een repository staat,
+     moet het naar `key:import <kit>` wijzen.
+  8. `backup:target:add` toont geen voortgang bij het ophalen van de index (27.582 bestanden).
+  9. `backup:target:remove` laat de index-cache van die locatie in de database staan; opruimen,
+     ook bestaande wezen.
+  10. Snapshot-meta uitbreiden: ook geïnstalleerde maar uitgeschakelde apps, met per app of hij
+      uit de app store komt; `occ backup:apps <locatie> <snapshot>` toont de lijst leesbaar
+      (geen platte tekst op de locatie: dat lekt welke apps/versies er draaien).
+  11. **Tabelstructuur meedumpen** (kolommen, typen, indexen, primary key), zodat de restore een
+      ontbrekende tabel zelf aanmaakt met de gegevens erin. Lost restanten van oude apps op zonder
+      ze over te slaan; een later opnieuw geïnstalleerde app vindt zijn oude gegevens terug.
+  12. **Foreign keys**: de restore zet tabellen op alfabet terug; `oc_mail_accounts` verwijst naar
+      `oc_mail_mailboxes` en PostgreSQL weigert (fk_61a7e87f59a77cdc). Iedereen met Mail loopt hier
+      vast. Oplossing: in de juiste volgorde terugzetten (afhankelijkheden eerst), of de controle
+      tijdelijk uitzetten en na afloop terugzetten en controleren. In de test: 15 FK's (alle van
+      Mail) tijdelijk verwijderd en na de restore teruggezet: alle 15 geldig op de teruggezette
+      data, dus "uitzetten, terugzetten, achteraf controleren" werkt.
+  13. **SFTP-restore over een lange lijn is traag**: 0,75 MiB/s vanaf Hetzner naar Canada (RTT 122 ms),
+      terwijl OpenSSH `sftp` 16,6 MiB/s haalt. De SFTP-stream van files_external (phpseclib) wacht na
+      elk klein blok op antwoord. Oplossing: pack-ranges bij SFTP met phpseclib's eigen `get()`
+      (veel verzoeken tegelijk) lezen in plaats van via de stream, zoals bij S3. 1 TB duurt nu ~2 weken.
+      Na meten: de grootste oorzaak was het netwerk (cubic, zie 14): met BBR gaat de restore van 0,75
+      naar 2,3 MiB/s, een hele pack lezen 4-5 MiB/s. Meer verzoeken in één stream (DEPTH 16/32) gaf geen
+      duidelijke winst. Verder komen vraagt meerdere verbindingen tegelijk: naar **1.1.0**.
+  14. **Uploaden over een lange lijn**: backup naar OVH S3 Warschau vanaf Canada (RTT 114 ms) haalt
+      ~1 MiB/s met één pack tegelijk; `aws s3 cp` (multipart, parallel) 6 MiB/s. Meerdere packs tegelijk
+      uploaden of S3 multipart. Minder dringend dan 13 (restore).
+      Oorzaak netwerk (met Sysop): pakketverlies trans-Atlantisch + cubic in de VM; met BBR gaat één
+      PUT van 2,4 naar 7,5 MiB/s, ng_backup van ~1 naar ~1,6 MiB/s (rest = serieel lezen/uploaden).
+      Tip over BBR in de README gezet. Let op: PVE02 staat in Canada; een restore in de EU gaat sneller.
+  15. DR-document: in het Docker-voorbeeld "je containernaam" (`docker ps`) i.p.v. `nextcloud`.
+  16. Grote restore (VM 980, snapshot aa7cce8d van de Storage Box) stopte na 22 uur met
+      `Not found: packs/26/2642ef39…`. Oorzaak: de wekelijkse opruiming van nc01 (zo 18-10) heeft
+      dat pakket tijdens de restore omgepakt (blob staat nu in `389567b7…`); de herstelserver had de
+      index van vóór de opruiming. Productie heel: `backup:verify` op nc01 OK (150.639 bestanden,
+      316.830 blobs). Opgelost in rc2: bij een mislukte pakketlezing de index herladen en de blob
+      lezen waar hij nu staat (test `testRestoreFollowsPacksRepackedByAnotherServer`).
+  **Kleine DR-test met rc2 (2026-10-18), volautomatisch geslaagd:** bron VM 981 (NC 34, PostgreSQL,
+  51 GB, Mail met gesynct account, Deck uitgeschakeld, Calendar/Contacts, admin_audit) → OVH S3 →
+  verse VM 982 met alleen de DR-gids en `--install-apps`: apps vanzelf geïnstalleerd, 10 Deck-tabellen
+  aangemaakt, 15 FK's in orde, 23.519/23.519 checksums gelijk, agenda/contact/mail/bord terug.
+  Restore 1 u 47 vanuit Warschau naar Canada (met BBR). Lokaal slaagt de test ook op SQLite en MariaDB.
+  **Daarna verplicht:** een tweede volledige restore op een verse VM, alleen met de HOWTO en de
+  nieuwe opties, zonder handwerk. Pas als die in één keer slaagt: 1.0.0.
+
+- **Later (geen versie):** optie om de sleutel niet op de locatie op te slaan (kit is dan de enige
+  kopie; uitdrukkelijke waarschuwing). Primaire object storage en External-storage-koppelingen
+  meenemen via de opslaglaag (§3.4; nu niet ondersteund, zie README "Known limitations").
+- **Open:** of de bevestigingscode van de kit dubbelop is (nog niet over besloten).
+
 Doorgeschoven naar **v1.3.0** (fase 3, niet meer fase 2): in-place volledige restore
 (eigen restore-modus i.p.v. onderhoudsmodus) en zelfbediening voor gebruikers (eigen bestanden
 terugzetten vanuit de Files-app).

README.md

@@ -7,11 +7,14 @@ installations and hosted Nextcloud. (Choosing SMB as a storage backend is the on
 see "Storage backend experiences" below — that requirement comes from files_external, not from
 ng_backup, and applies to any Nextcloud app that writes to an SMB share.)
 
-**Status: beta (0.9.6).** Tested thoroughly, usable alongside your current backup, but not yet a
-drop-in replacement for it. See "Known limitations" below, `PLAN.md` for the design and
-`docs/HOWTO.md` for a step-by-step guide from setup to a tested restore.
+**Status: release candidate for 1.0.0 (1.0.0-rc.1, app version 0.9.7).** Tested thoroughly, usable
+alongside your current backup, but not yet a drop-in replacement for it. See "Known limitations" below, `PLAN.md` for the design and
+`docs/HOWTO.md` for a step-by-step guide from setup to a tested restore. Server lost? See
+`docs/DISASTER-RECOVERY.md`.
 
-License: AGPL-3.0-or-later.
+License: AGPL-3.0-or-later. Developed and sponsored by [Ensembia](https://www.ensembia.com).
+Need help restoring a backup after a crash? Ensembia offers paid restore assistance:
+[www.ensembia.com](https://www.ensembia.com).
 
 ## How it works
 
@@ -23,9 +26,33 @@ License: AGPL-3.0-or-later.
   leaves the server, and streamed straight to the location: no local copy, no double disk space.
   Unchanged files are not read again; only new data is uploaded.
 - The database is dumped through Nextcloud's own connection, inside one consistent transaction.
+- A backup runs in short steps from Nextcloud's background jobs, and every step saves where it
+  got to. A restart of the server or the containers does not lose the run: it continues at the
+  next background job run. Tested on a production Nextcloud AIO instance: a 1 TB full backup over
+  SMB carried on through the nightly AIO update, which restarts every container.
 - Restores go through Nextcloud, so overwritten files keep their old content as a version and
   removed files go to the trash.
 
+## Requirements
+
+- **Background jobs on system cron.** NG Backup runs backups in steps from Nextcloud's
+  background job, so a backup only moves forward when that job runs. Choosing "Cron" under
+  **Administration settings → Basic settings → Background jobs** is not enough on its own: it
+  tells Nextcloud that the system will call it, so you also need a cron line that does. Without
+  it a backup stays at "running (db)", and so does one started with "Back up now".
+  `occ backup:run` in a terminal works without cron (it runs in the foreground).
+  - Regular server: `crontab -u www-data -e` and add
+    `*/5 * * * * php -f /var/www/nextcloud/cron.php` (your Nextcloud path).
+  - Docker (the official `nextcloud` image): on the host, `crontab -e` as root and add
+    `*/5 * * * * docker exec -u www-data <container> php -f /var/www/html/cron.php`, or add a
+    service with the same image and `entrypoint: /cron.sh` to your `docker-compose.yml`.
+  - Nextcloud All-in-One already runs cron.
+
+  After a few minutes, the Background jobs section shows that the last job ran just now. See the
+  [Nextcloud documentation on background jobs](https://docs.nextcloud.com/server/latest/admin_manual/configuration_server/background_jobs_configuration.html).
+- A storage location: S3 or compatible, SFTP, WebDAV, SMB (needs the PHP `smbclient` extension,
+  see below), FTP or a local path.
+
 ## Quick start
 
 ```
@@ -47,9 +74,19 @@ All backups of an installation are encrypted with one master key.
 - The **server** keeps the master key, encrypted with the instance secret, so scheduled backups
   and restores work without anyone typing a passphrase. Any administrator can restore from the
   web interface. Consequence: whoever fully controls the server can read the backups; whoever
-  only gets hold of the backup location cannot.
-- For a **restore on a new server** (disaster recovery) you need the **recovery kit** and **one
-  passphrase**. The kit contains the master key, encrypted separately with each passphrase.
+  only gets hold of the backup location cannot, as long as the passphrases are strong (see below).
+- The **location holds the key too**, by design (like restic and Borg in repokey mode): its
+  `config` file contains the master key, encrypted separately with each passphrase (Argon2id),
+  the same as in the recovery kit. Without a passphrase it is of no use, but whoever can read the
+  location can try passphrases offline. **Your passphrase is therefore the actual key**: it must
+  be at least 16 characters; five or more random words are a good choice.
+- The **recovery kit** is your own copy of that encrypted key. Still keep it off the server and
+  off the location: an attacker who gets write access to the location can damage or delete its
+  `config` file on purpose, and without the kit that makes every backup there unreadable.
+- For a **restore on a new server** (disaster recovery) you currently need the **recovery kit**
+  and **one passphrase**.
+- Planned: an option to not store the key on the location at all. Then the kit is the only copy,
+  and losing it means losing every backup; that option will come with an explicit warning.
 - Up to **three passphrases** ("slots") can open the key, so one person leaving or dying does not
   lock the company out. A suggested setup:
 
@@ -158,6 +195,17 @@ Contributions welcome via PR — add what you ran into with your own provider.
   the backend being listed is not proof it will work here. Once the extension is present it works
   the same as any other backend; no ng_backup-specific config beyond host/share/user/password.
 
+- **Backups over a long distance (high latency):** on Linux, the default TCP congestion control
+  (cubic) slows a single connection down a lot on a long line with some packet loss. From Canada to
+  an S3 bucket in Warsaw (114 ms), one upload went from 2.4 to 7.5 MiB/s after switching the
+  server (or the VM/container host where TCP ends) to BBR:
+  `sysctl -w net.core.default_qdisc=fq net.ipv4.tcp_congestion_control=bbr`
+  (`modprobe tcp_bbr` first; make it permanent in `/etc/sysctl.d/`).
+  A full restore over SFTP reads the packs ahead on a second connection, with many requests in
+  flight. A server that handles parallel reads well (not a Hetzner Storage Box, which gets slower)
+  can be read on more connections: `occ config:app:set ng_backup restore_sftp_connections
+  --value=4` (at most 8; the server must allow that many plus one at once for the user).
+
 - **NFS is not a files_external backend at all.** Mount the NFS export on the server yourself
   (e.g. via `/etc/fstab` or a systemd `.mount` unit) and point ng_backup's `local` backend at the
   mount point; ng_backup never mounts or unmounts anything on its own, so an NFS mount dropping
@@ -168,6 +216,11 @@ Contributions welcome via PR — add what you ran into with your own provider.
 
 On the backlog; none of these block the beta or 1.0.0, but know them before you rely on it:
 
+- **Only the data directory is backed up.** Object storage as primary storage (`objectstore` in
+  `config.php`) is not supported: a backup refuses to start there. Folders mounted through the
+  External storage app are not in the data directory and are **not included**, without a warning.
+  Back them up separately. On the roadmap: reading files through Nextcloud's storage layer, which
+  covers both, with external mounts optional per mount (`PLAN.md` section 3.4).
 - **Very large instances** (well over 1 TB, millions of files): the blob index, cleanup, browsing a
   snapshot in the web interface and per-user export manifests are held in memory. Expect high
   memory use there; reports from such instances are very welcome.
@@ -194,7 +247,7 @@ On the backlog; none of these block the beta or 1.0.0, but know them before you
 | `backup:key:init`, `backup:key:kit`, `backup:key:confirm` | create the key, recovery kit, confirmation |
 | `backup:key:slots`, `backup:key:slot:add/replace/remove` | passphrase slots |
 | `backup:target:backends/add/edit/list/remove/append-only` | backup locations |
-| `backup:run`, `backup:status`, `backup:list` | back up, status, restore points |
+| `backup:run`, `backup:status`, `backup:list` | back up, status (runs of the last 7 days; `--all` for all), restore points |
 | `backup:cancel <run>` | stop a running backup |
 | `backup:browse`, `backup:restore` | browse and restore |
 | `backup:retention`, `backup:prune`, `backup:trash`, `backup:trash:restore` | retention, cleanup, trash |

appinfo/info.xml

@@ -3,13 +3,46 @@
     xsi:noNamespaceSchemaLocation="https://apps.nextcloud.com/schema/apps/info.xsd">
     <id>ng_backup</id>
     <name>NG Backup</name>
-    <summary>Encrypted, incremental backups of your Nextcloud with restore from the web interface</summary>
-    <description><![CDATA[Beta: scheduled, encrypted, incremental backups of the database, config and data
-directory to S3, SFTP, WebDAV, FTP, SMB or a local path, with restore of files and folders, of
-single users (via user_migration) and of the whole server onto a fresh installation. Tested
-thoroughly and usable alongside your current backup, but not yet a drop-in replacement for it.
-See the README for known limitations and the recovery kit before relying on it.]]></description>
-    <version>0.9.6</version>
+    <summary>Encrypted, incremental backups of your Nextcloud — files, database and config — with restore from the web interface</summary>
+    <description><![CDATA[Back up your whole Nextcloud — data directory, database and configuration — encrypted and
+incremental, to storage you choose. Restore single files, folders, a user, or the whole server from
+the web interface or `occ`. No shell access or external tools needed, so it also runs on Nextcloud
+All-in-One and hosted Nextcloud.
+
+**Where to**
+- S3 and S3-compatible storage, SFTP, WebDAV, SMB, FTP, Swift or a local path (NFS mount), through
+  the connection code of the External storage app. A location is never mounted and never shows up
+  in Files.
+
+**How**
+- Deduplicated, compressed and encrypted (XChaCha20-Poly1305) on the server before upload, streamed
+  straight to the location: no local copy, no double disk space. Unchanged files are not read again.
+- Database dump through Nextcloud's own connection, in one consistent transaction (PostgreSQL,
+  MySQL/MariaDB, SQLite).
+- Runs in short steps from the background jobs, so a server or container restart does not lose a
+  running backup.
+- Daily schedule, retention policy, and `occ backup:verify` (optionally `--deep`) to check that a
+  backup can be read.
+
+**Safe**
+- Up to three passphrases plus a recovery kit; the passphrase is the actual key.
+- Deletion delay and append-only locations against ransomware or a compromised server; S3 object
+  lock supported.
+- Admin notifications on failures, stale backups and changes to keys and locations.
+
+**Restore**
+- Files and folders into a new folder, merged, or replacing the original — through Nextcloud, so
+  overwritten files keep a version and removed ones go to the trash.
+- One user (account, files, calendars, contacts) via user_migration.
+- The whole server onto a fresh installation (disaster recovery).
+
+NG Backup needs Nextcloud's background jobs on system cron (a real cron line, not only the setting).
+Read "Known limitations" in the README before you rely on it, and test a restore. Feedback is very
+welcome: use the "Share your experience" link on the admin page.
+
+Developed and sponsored by [Ensembia](https://www.ensembia.com). We can offer (paid) assistance if
+you need help with restoring a backup after a crash.]]></description>
+    <version>0.9.11</version>
     <licence>agpl</licence>
     <author mail="dillard.blom@ensembia.com">Dillard Blom</author>
     <namespace>NgBackup</namespace>
@@ -20,9 +53,9 @@ See the README for known limitations and the recovery kit before relying on it.]
     <website>https://github.com/dillardblom/ng_backup</website>
     <bugs>https://github.com/dillardblom/ng_backup/issues</bugs>
     <repository type="git">https://github.com/dillardblom/ng_backup</repository>
-    <screenshot>https://raw.githubusercontent.com/dillardblom/ng_backup/main/screenshots/1-backups.png</screenshot>
-    <screenshot>https://raw.githubusercontent.com/dillardblom/ng_backup/main/screenshots/2-restore.png</screenshot>
-    <screenshot>https://raw.githubusercontent.com/dillardblom/ng_backup/main/screenshots/3-settings.png</screenshot>
+    <screenshot>https://raw.githubusercontent.com/dillardblom/ng_backup/v1.0.0-rc.5/screenshots/1-backups.png</screenshot>
+    <screenshot>https://raw.githubusercontent.com/dillardblom/ng_backup/v1.0.0-rc.5/screenshots/2-restore.png</screenshot>
+    <screenshot>https://raw.githubusercontent.com/dillardblom/ng_backup/v1.0.0-rc.5/screenshots/3-settings.png</screenshot>
     <dependencies>
         <php min-version="8.1"/>
         <lib>sodium</lib>

docs/DISASTER-RECOVERY.md

@@ -0,0 +1,138 @@
+# Disaster recovery: your server is gone
+
+Your Nextcloud server is lost. You have a new, empty server. These are the steps to get your
+Nextcloud back from an NG Backup location. Do them in this order.
+
+## What you need
+
+- [ ] The **recovery kit** file (`ng_backup-kit.json`) and **one passphrase** of it.
+- [ ] The **connection details of the backup location**: host, user, password or keys, bucket, folder.
+- [ ] A new server with the **same Nextcloud major version** as the old one (for example 34),
+      a database (PostgreSQL, MySQL/MariaDB or SQLite; it may differ from the old one) and room for
+      the whole backup plus a margin.
+- [ ] A list of the apps that are **not in the app store** (your own builds, apps copied in by
+      hand). Keep their packages somewhere safe beforehand.
+
+No kit? If the location still holds its `config` file, the key is there too, but this version
+can only import it from a kit. Keep the kit off the server, next to the passphrase.
+
+## Steps
+
+**1. Install a fresh Nextcloud** of the same major version. Create an admin account. Do not add
+users or files.
+
+**2. Do not let background jobs run yet.** A new Nextcloud runs them on page visits (AJAX).
+Switch that off:
+
+    occ background:cron
+
+As long as no cron is set up, nothing runs. Check that none is:
+
+- Regular server: `sudo crontab -u www-data -l`. If it shows a line with `cron.php`, remove it
+  for now with `sudo crontab -u www-data -e` (put it back in step 9).
+- Docker Compose with a cron service: `docker compose stop cron`.
+- Nextcloud All-in-One: cron runs inside the Nextcloud container; leave it. It does no harm here:
+  the restore keeps NG Backup's own settings of the new server, so it does not start backups.
+
+This keeps the new server quiet (no mail syncs, no notifications, no backups) until it is ready.
+
+**3. Install NG Backup** (the same version or newer) and enable it.
+
+**4. Import the backup key.** Copy the kit to the new server so the web server user can read it.
+
+From your own computer:
+
+    scp ng_backup-kit.json root@newserver:/tmp/
+
+Then on the server, one of:
+
+    chown www-data /tmp/ng_backup-kit.json                                    # regular server
+    docker cp /tmp/ng_backup-kit.json <container>:/tmp/ && \
+      docker exec <container> chown www-data /tmp/ng_backup-kit.json          # Docker
+
+`<container>` is the name of your Nextcloud container: `docker ps` shows it (for example
+`nextcloud-aio-nextcloud`, or `myproject-nextcloud-1` with Docker Compose).
+
+Import it; you type the passphrase yourself:
+
+    occ backup:key:import /tmp/ng_backup-kit.json
+
+It shows the key fingerprint: it must match the one of your old server (on the recovery kit).
+
+**5. Add the backup location** with the same details as before. On a large backup this first reads
+the index and shows how far it is, for example
+`Reading the index: 6,913/26,791 files (25%), about 12 min left`.
+
+    occ backup:target:add offsite sftp -a password::password -o host=... -o user=... -o password=... -o root=... --path=...
+
+If it says "No backup key yet", the key is not imported. Run step 4:
+
+    occ backup:key:import /tmp/ng_backup-kit.json
+
+Do **not** run `backup:key:init`, even though the message suggests it: that makes a brand new key,
+and your backups were encrypted with the old one. NG Backup then refuses the location ("created
+with a different key").
+
+**6. List the restore points** and pick one, normally the newest:
+
+    occ backup:list offsite
+
+**7. Start the restore, and let it install the apps.**
+
+    occ backup:restore:full offsite <snapshot> --install-apps
+
+`--install-apps` first installs every app the old server had enabled from the app store (or
+switches it on, if it is part of Nextcloud). Tables of apps that are missing or were removed long
+ago are created from the backup, so they do not stop the restore.
+
+At the end it lists the apps it could not install, usually your own builds that are not in the
+app store. Copy those into `custom_apps` and enable them (`occ app:enable <app>`); their data is
+already restored.
+
+Backups made before 1.0.0-rc.2 do not record the structure of their tables. If the restore lists
+tables that do not exist here, install the apps they belong to and run it again, or leave them
+out with `--skip-missing-tables`.
+
+**8. Let the restore run.** It restores the database, then the data directory, and takes hours for
+a large backup. Nextcloud is in maintenance mode meanwhile, so nobody and no background job
+writes into it; the restore switches it off when it completes. (If you had switched maintenance
+mode on yourself before, it stays on: switch it off with `occ maintenance:mode --off` when ready.)
+
+If it stops halfway, maintenance mode stays on (the instance may be partly restored). Fix the cause,
+then switch maintenance mode off and run the restore again with `--force`, in one line (the message
+prints it): `occ maintenance:mode --off && occ backup:restore:full <location> <snapshot> --force`.
+Leave out `--install-apps` this time, so that the instance is open only for the seconds until the
+restore has switched maintenance mode on again; apps the first run could not install are listed at
+the end of the restore, install those afterwards.
+If occ then says that Nextcloud or one of the apps requires an upgrade, the database is already
+the old server's: run `occ upgrade` first, then the same command with `--force`.
+
+**9. After the restore.** These worked in our tests:
+
+    occ upgrade
+    occ maintenance:repair
+    occ files:scan --all
+
+- Check `config/config.php`: `trusted_domains`, `overwrite.cli.url` and `overwritehost` come from
+  the old server; change them if the new server has another name. The database settings and the
+  data directory are kept from the new installation.
+- From Nextcloud All-in-One to a regular server: also check the cache settings (`memcache.*`,
+  `redis`), which point at AIO's containers.
+- Log in, open a few files, a calendar and a contact.
+- Start background jobs again (cron), as in step 2 in reverse.
+
+**10. Point your domain at the new server** and check that clients reconnect.
+
+**11. Make a backup of the new server** to the same location (`occ backup:run offsite`). The old
+server must stay off: two servers must never write to the same location.
+
+## Never
+
+- Never let the old server write to the location again if it comes back. Switch its backups off
+  first.
+- Never give your passphrase to anyone. Nobody helping you needs it.
+
+## Help
+
+Stuck? [Ensembia](https://www.ensembia.com), the developer of NG Backup, offers paid help with
+restoring a backup after a crash.

docs/HOWTO.md

@@ -12,13 +12,16 @@ occ backup:key:kit --output=/var/tmp/ng_backup-kit.json
 occ backup:key:confirm -u <your-admin-uid> --code=<code shown> --confirm="Yes, I confirm"
 ```
 
-- The passphrase protects the backup. Keep it somewhere other than this server.
+- The passphrase protects the backup: the location stores the key encrypted with it, so whoever
+  can read the location can try to guess it. Use at least 16 characters (five or more random
+  words work well) and keep it somewhere other than this server.
 - Optional: extra passphrases for other people with `occ backup:key:slot:add --label="..."`.
   Any one passphrase is enough to restore. Removing a slot later does not revoke access for someone
   who kept an old kit and that passphrase (see "Known limitations" in the README).
 - The recovery kit (`/var/tmp/ng_backup-kit.json` above) is also required for disaster recovery. The web
   user writes it there; then move it off the server as root, next to the passphrase, and delete the
-  copy in `/var/tmp`. Without the kit and a passphrase, the backup cannot be read.
+  copy in `/var/tmp`. The location holds the same encrypted key, but keep the kit anyway: if
+  someone damages or deletes the key on the location, the kit is the only way back in.
 
 ## 2. Add a backup location
 
@@ -133,6 +136,8 @@ occ backup:user:restore offsite users/<uid>/<exportId> --mode=as-backup
 
 ## 7. Disaster recovery: restore the whole server
 
+Server lost? Follow the step-by-step [DISASTER-RECOVERY.md](DISASTER-RECOVERY.md).
+
 Use a fresh Nextcloud installation of the same major version, with NG Backup installed and
 the same location available. For a test, use a **copy** of the location: two servers writing to one
 location break each other's catalog.
@@ -150,6 +155,10 @@ starts; `--force` skips both (also needed to rerun it after it stopped halfway).
 Afterwards, check that users, files and the database are complete, and run a backup of the restored
 server. The restored installation keeps its own app configuration and secret.
 
+Stuck? [Ensembia](https://www.ensembia.com), the developer of NG Backup, offers paid help with
+restoring a backup after a crash. You keep your passphrase to yourself: it is never needed by
+anyone helping you.
+
 ## 8. Retention
 
 ```

lib/Backend/GetsOneByOne.php

@@ -7,7 +7,7 @@ declare(strict_types=1);
 
 namespace OCA\NgBackup\Backend;
 
-/** IBackend::getMany() for a backend where reading files one after the other costs nothing extra. */
+/** IBackend::getMany() and getRanges() for a backend where reading one after the other costs nothing extra. */
 trait GetsOneByOne {
 	/**
 	 * @param list<string> $paths
@@ -27,4 +27,14 @@ trait GetsOneByOne {
 			yield $path => $data;
 		}
 	}
+
+	/**
+	 * @param list<array{0:string, 1:int, 2:int}> $ranges
+	 * @return \Generator<int, string>
+	 */
+	public function getRanges(array $ranges): \Generator {
+		foreach ($ranges as $i => [$path, $offset, $length]) {
+			yield $i => $this->getRange($path, $offset, $length);
+		}
+	}
 }

lib/Backend/IBackend.php

@@ -35,6 +35,17 @@ interface IBackend {
 	/** @return string bytes [$offset, $offset + $length) of the object (used to fetch single blobs from a pack) */
 	public function getRange(string $path, int $offset, int $length): string;
 
+	/**
+	 * Many byte ranges, in the order given (blobs spread over many packs, such as the tree
+	 * segments of a backup). A backend where every request costs a round trip can fetch them
+	 * several at a time.
+	 *
+	 * @param list<array{0:string, 1:int, 2:int}> $ranges [path, offset, length] each
+	 * @return \Generator<int, string> contents by position in $ranges
+	 * @throws BackendException for a range that cannot be read
+	 */
+	public function getRanges(array $ranges): \Generator;
+
 	public function exists(string $path): bool;
 
 	/**

lib/Backend/IReadsAhead.php

@@ -0,0 +1,30 @@
+<?php
+
+declare(strict_types=1);
+
+// SPDX-FileCopyrightText: 2026 Dillard Blom
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+namespace OCA\NgBackup\Backend;
+
+/**
+ * A backend that can read many byte ranges ahead of use, several at a time over connections of
+ * its own (a full restore, where one connection at a time is bound by the round trip).
+ */
+interface IReadsAhead {
+	/** Whether readAhead() is worth planning for: false when it would return null anyway. */
+	public function canReadAhead(): bool;
+
+	/**
+	 * The ranges in the order given, each as a local stream at offset 0 holding its bytes, read a
+	 * few ranges ahead of the one the caller is at. A stream is closed when the generator is
+	 * resumed. Null for a range that could not be read this way (a missing object, a server or
+	 * connection error): the caller reads it the usual way, which reports why.
+	 *
+	 * @param list<array{0:string, 1:int, 2:int}> $ranges [path, offset, length] each
+	 * @param string $spool an existing local directory for the files that hold the ranges
+	 * @return \Generator<int, resource|null>|null by position in $ranges; null when this backend
+	 *                                             cannot read ahead now
+	 */
+	public function readAhead(array $ranges, string $spool): ?\Generator;
+}

lib/Backend/SftpRangeFetcher.php

@@ -0,0 +1,395 @@
+<?php
+
+declare(strict_types=1);
+
+// SPDX-FileCopyrightText: 2026 Dillard Blom
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+namespace OCA\NgBackup\Backend;
+
+/**
+ * Reads byte ranges of files on an SFTP location ahead of use, over several connections at once,
+ * into local files (StorageBackend::readAhead(), for a full restore).
+ *
+ * A restore that reads its packs as it goes is bound by the round trip: from a Hetzner Storage
+ * Box to Canada (RTT 122 ms) it reached about 2.8 MiB/s, with the PHP process mostly waiting.
+ * Here every connection reads its own range with DEPTH requests in flight, ahead of the restore. PHP runs one thing at a time: while it waits for an answer on one connection, the
+ * answers of the others arrive in the kernel's buffers, so the connections still transfer at the
+ * same time.
+ *
+ * Uses the same internal phpseclib 2 methods as SftpReadStream (see SftpReadStream::connection()).
+ * The connections are this class's own, never the storage's: no other request goes over them.
+ * A range that fails (missing file, server error, a connection that breaks) comes out as null,
+ * for the caller to read the usual way; a broken connection is not used again.
+ */
+final class SftpRangeFetcher {
+	/**
+	 * Connections a full restore uses, unless the app setting restore_sftp_connections says
+	 * otherwise. One: a Hetzner Storage Box gave about 14 MiB/s on one connection with DEPTH
+	 * requests in flight, and 4-6 MiB/s on 2 or 4 (it reads from disks, and parallel readers make
+	 * them seek). On a line with packet loss to a server that handles parallel reads well, 4
+	 * connections did better (21 against 14 MiB/s).
+	 */
+	public const DEFAULT_CONNECTIONS = 1;
+	public const MAX_CONNECTIONS = 8;
+	/** READ requests in flight per connection. */
+	public const DEPTH = 32;
+	/** Ranges read ahead of the one the caller is at, in flight or waiting in the spool. */
+	public const AHEAD = 8;
+	/**
+	 * Seconds ready() waits for any connection to answer before it waits for each in turn: short,
+	 * in case a connection holds an answer where ready() does not look.
+	 */
+	private const SELECT_TIMEOUT = 1;
+	/** See SftpReadStream::CHUNK and MIN_CHUNK. */
+	private const CHUNK = 261120;
+	private const MIN_CHUNK = 32768;
+
+	private const FXP_OPEN = 3;
+	private const FXP_CLOSE = 4;
+	private const FXP_READ = 5;
+	private const FXP_STATUS = 101;
+	private const FXP_HANDLE = 102;
+	private const FXP_DATA = 103;
+	private const FXF_READ = 1;
+	private const FX_OK = 0;
+
+	/** Connections that broke and are replaced, at most, in one restore. */
+	public const MAX_RECONNECTS = 20;
+
+	private const OPEN = 0;
+	private const READ = 1;
+	private const CLOSE = 2;
+
+	/** @var array<int, int> READ size per connection, lowered when a server answers less than asked */
+	private array $chunks = [];
+	/** @var array<int, SftpRangeJob> the range each busy connection reads */
+	private array $jobs = [];
+	/** @var array<int, resource|null> ranges read (or failed) and not yet given to the caller */
+	private array $done = [];
+	private int $requestId = 0x4e520000;
+	/** Connections replaced so far (see MAX_RECONNECTS). */
+	public int $reconnects = 0;
+
+	/**
+	 * @param array<int, object> $connections phpseclib 2 connections with their SFTP channel open
+	 * @param list<array{0:string, 1:int, 2:int}> $ranges paths below $root
+	 */
+	private function __construct(
+		private array $connections,
+		private string $root,
+		private array $ranges,
+		private string $spool,
+		private ?\Closure $connect = null,
+	) {
+		foreach (array_keys($connections) as $c) {
+			$this->chunks[$c] = self::CHUNK;
+		}
+	}
+
+	/**
+	 * See IReadsAhead::readAhead(). The connections are ended when the generator ends.
+	 *
+	 * @param list<object> $connections
+	 * @param list<array{0:string, 1:int, 2:int}> $ranges
+	 * @param (\Closure():?object)|null $connect a new connection in place of one that broke
+	 *                                         (null when it cannot be made)
+	 * @return \Generator<int, resource|null>
+	 */
+	public static function fetch(array $connections, string $root, array $ranges, string $spool, ?\Closure $connect = null): \Generator {
+		$fetcher = new self($connections, rtrim($root, '/'), $ranges, $spool, $connect);
+		try {
+			yield from $fetcher->run();
+		} finally {
+			$fetcher->end();
+		}
+	}
+
+	/** @return \Generator<int, resource|null> */
+	private function run(): \Generator {
+		$count = count($this->ranges);
+		$next = 0;
+		for ($want = 0; $want < $count; $want++) {
+			while (!array_key_exists($want, $this->done)) {
+				foreach (array_keys($this->connections) as $c) {
+					if (!isset($this->jobs[$c]) && $next < $count && $next < $want + self::AHEAD) {
+						$this->start($c, $next++);
+					}
+				}
+				if ($this->jobs === [] && !array_key_exists($want, $this->done)) {
+					// no connection left: the rest the usual way
+					$this->done[$want] = null;
+					$next = max($next, $want + 1);
+					break;
+				}
+				foreach ($this->ready() as $c) {
+					$this->step($c);
+				}
+			}
+			$fh = $this->done[$want];
+			unset($this->done[$want]);
+			try {
+				yield $want => $fh;
+			} finally {
+				if (is_resource($fh)) {
+					fclose($fh);
+				}
+			}
+		}
+	}
+
+	/**
+	 * The busy connections that have an answer waiting, so that a connection that waits for a
+	 * lost packet to be sent again does not hold up the others; all of them when the connections
+	 * do not tell (then they are taken in turn).
+	 *
+	 * @return list<int>
+	 */
+	private function ready(): array {
+		$sockets = [];
+		$ready = [];
+		foreach ($this->jobs as $c => $job) {
+			$sftp = $this->connections[$c];
+			$vars = get_object_vars($sftp); // only what is public: phpseclib 2's are
+			// Answers phpseclib has read already: the socket does not show them. Its request
+			// buffer holds whole answers read while it waited for another; its packet buffer and
+			// channel buffers hold what came in with the last packet it read (small answers, such
+			// as a CLOSE and the next OPEN, often arrive together).
+			$buffered = $vars['requestBuffer'] ?? null;
+			$channels = $vars['channel_buffers'] ?? null;
+			if ((is_array($buffered) && isset($job->queue[0]) && array_key_exists($job->queue[0][0], $buffered))
+				|| (is_string($vars['packet_buffer'] ?? null) && self::wholePacket($vars['packet_buffer']))
+				|| (is_array($channels) && array_filter($channels) !== [])) {
+				$ready[] = $c;
+				continue;
+			}
+			$socket = $vars['fsock'] ?? null;
+			if (!is_resource($socket)) {
+				return array_keys($this->jobs);
+			}
+			$sockets[$c] = $socket;
+		}
+		if ($ready !== [] || $sockets === []) {
+			return $ready;
+		}
+		$read = $sockets;
+		$write = null;
+		$except = null;
+		// Data in PHP's own buffer of a socket counts as readable. Nothing within the time:
+		// each in turn, where phpseclib's own timeout applies.
+		$n = @stream_select($read, $write, $except, self::SELECT_TIMEOUT);
+		return $n === false || $n === 0 ? array_keys($this->jobs) : array_keys($read);
+	}
+
+	/** Whether $buffer starts with a whole SFTP packet (length, then that many bytes). */
+	private static function wholePacket(string $buffer): bool {
+		$length = strlen($buffer) >= 4 ? unpack('N', $buffer) : false;
+		return is_array($length) && strlen($buffer) >= 4 + $length[1];
+	}
+
+	private function start(int $c, int $i): void {
+		[$path, $offset, $length] = $this->ranges[$i];
+		$fh = $this->spoolFile();
+		if ($fh === null) {
+			$this->done[$i] = null;
+			return;
+		}
+		if ($length <= 0) {
+			$this->done[$i] = $fh;
+			return;
+		}
+		$this->jobs[$c] = new SftpRangeJob($i, $fh, $offset, $offset + $length);
+		try {
+			$remote = $this->connections[$c]->_realpath($this->root . '/' . ltrim($path, '/'));
+			if (!is_string($remote)) {
+				$this->finish($c);
+				return;
+			}
+			$this->send($c, self::FXP_OPEN, pack('Na*N2', strlen($remote), $remote, self::FXF_READ, 0), self::OPEN);
+		} catch (\Throwable) {
+			$this->drop($c);
+		}
+	}
+
+	/** Take the oldest answer on connection $c, then keep its requests in flight. */
+	private function step(int $c): void {
+		$job = $this->jobs[$c];
+		[$id, $kind, $offset, $length] = array_shift($job->queue) ?? throw new \LogicException('no request in flight');
+		$sftp = $this->connections[$c];
+		try {
+			$response = $sftp->_get_sftp_packet($id);
+			if (!is_string($response)) {
+				throw new BackendException('SFTP connection lost');
+			}
+			$type = $sftp->packet_type;
+			if ($kind === self::OPEN) {
+				if ($type === self::FXP_HANDLE) {
+					$job->handle = substr($response, 4);
+				} else {
+					$job->failed = true; // missing, or no permission
+				}
+			} elseif ($kind === self::READ) {
+				if (!$job->failed) {
+					$this->received($c, $type, $response, $offset, $length);
+				}
+			} else {
+				$status = $type === self::FXP_STATUS && strlen($response) >= 4 ? unpack('N', $response) : false;
+				$closed = is_array($status) && $status[1] === self::FX_OK;
+				$this->finish($c);
+				if (!$closed) {
+					// handles might pile up on the server: not used again
+					$this->drop($c);
+				}
+				return;
+			}
+			$this->refill($c);
+		} catch (\Throwable) {
+			$this->drop($c);
+		}
+	}
+
+	private function received(int $c, int $type, string $response, int $offset, int $length): void {
+		$job = $this->jobs[$c];
+		$declared = strlen($response) >= 4 ? unpack('N', $response) : false;
+		$n = is_array($declared) ? $declared[1] : 0;
+		if ($type !== self::FXP_DATA || $n <= 0 || $n !== strlen($response) - 4 || $n > $length) {
+			// end of file before the end of the range, a server error or a malformed answer
+			$job->failed = true;
+			return;
+		}
+		if (fseek($job->fh, $offset - $job->start) !== 0 || fwrite($job->fh, substr($response, 4)) !== $n) {
+			$job->failed = true;
+			return;
+		}
+		$job->got += $n;
+		if ($n < $length) {
+			// a server that caps a READ: ask for the rest, and no more than it gives from now on
+			$job->redo[] = [$offset + $n, $length - $n];
+			$this->chunks[$c] = max(self::MIN_CHUNK, min($this->chunks[$c], $n));
+		}
+	}
+
+	/** Send READs until DEPTH are in flight; when nothing is left to ask for, close the file. */
+	private function refill(int $c): void {
+		$job = $this->jobs[$c];
+		if ($job->handle !== '' && !$job->failed) {
+			while (count($job->queue) < self::DEPTH) {
+				if ($job->redo !== []) {
+					[$offset, $length] = array_shift($job->redo);
+				} elseif ($job->next < $job->end) {
+					$offset = $job->next;
+					$length = min($this->chunks[$c], $job->end - $offset);
+					$job->next += $length;
+				} else {
+					break;
+				}
+				$packet = pack('Na*N3', strlen($job->handle), $job->handle, intdiv($offset, 4294967296), $offset % 4294967296, $length);
+				$this->send($c, self::FXP_READ, $packet, self::READ, $offset, $length);
+			}
+		}
+		if ($job->queue !== []) {
+			return;
+		}
+		if ($job->handle === '') {
+			$this->finish($c); // not opened: nothing to close
+			return;
+		}
+		$this->send($c, self::FXP_CLOSE, pack('Na*', strlen($job->handle), $job->handle), self::CLOSE);
+	}
+
+	private function send(int $c, int $type, string $packet, int $kind, int $offset = 0, int $length = 0): void {
+		$this->requestId = $this->requestId >= 0x7fffffff ? 0x4e520000 : $this->requestId + 1;
+		if (!$this->connections[$c]->_send_sftp_packet($type, $packet, $this->requestId)) {
+			throw new BackendException('SFTP connection failed while sending a request');
+		}
+		$this->jobs[$c]->queue[] = [$this->requestId, $kind, $offset, $length];
+	}
+
+	/** The range of connection $c is done: its stream for the caller, or null when it failed. */
+	private function finish(int $c): void {
+		$job = $this->jobs[$c];
+		unset($this->jobs[$c]);
+		if ($job->failed || $job->got !== $job->end - $job->start || !rewind($job->fh)) {
+			self::closeFile($job->fh);
+			$this->done[$job->i] = null;
+			return;
+		}
+		$this->done[$job->i] = $job->fh;
+	}
+
+	/** A connection in an unknown state: its range fails, and it is not used again. */
+	private function drop(int $c): void {
+		if (isset($this->jobs[$c])) {
+			$job = $this->jobs[$c];
+			unset($this->jobs[$c]);
+			self::closeFile($job->fh);
+			$this->done[$job->i] = null;
+		}
+		self::disconnect($this->connections[$c]);
+		unset($this->connections[$c]);
+		// A long restore outlives connections (a Storage Box drops one now and then): without a
+		// new one, the rest would be read the slow way.
+		if ($this->connect === null || $this->reconnects >= self::MAX_RECONNECTS) {
+			return;
+		}
+		$this->reconnects++;
+		try {
+			$new = ($this->connect)();
+		} catch (\Throwable) {
+			$new = null;
+		}
+		if (function_exists('OCP\Log\logger')) {
+			\OCP\Log\logger('ng_backup')->info($new === null
+				? 'Reading ahead: an SFTP connection broke and no new one could be made'
+				: 'Reading ahead: an SFTP connection broke; reading on with a new one');
+		}
+		if ($new !== null) {
+			$key = max(array_merge(array_keys($this->chunks), [-1])) + 1;
+			$this->connections[$key] = $new;
+			$this->chunks[$key] = self::CHUNK;
+		}
+	}
+
+	/** @return resource|null a new file in the spool, already unlinked: nothing is left behind if the process dies */
+	private function spoolFile() {
+		$path = $this->spool . '/' . bin2hex(random_bytes(8));
+		$fh = @fopen($path, 'x+b');
+		if ($fh === false) {
+			return null;
+		}
+		@unlink($path);
+		return $fh;
+	}
+
+	private function end(): void {
+		foreach ($this->jobs as $job) {
+			self::closeFile($job->fh);
+		}
+		foreach ($this->done as $fh) {
+			if (is_resource($fh)) {
+				fclose($fh);
+			}
+		}
+		$this->jobs = [];
+		$this->done = [];
+		foreach ($this->connections as $sftp) {
+			self::disconnect($sftp);
+		}
+		$this->connections = [];
+	}
+
+	private static function closeFile(mixed $fh): void {
+		if (is_resource($fh)) {
+			fclose($fh);
+		}
+	}
+
+	private static function disconnect(object $sftp): void {
+		try {
+			if (is_callable([$sftp, 'disconnect'])) {
+				$sftp->disconnect();
+			}
+		} catch (\Throwable) {
+		}
+	}
+}

lib/Backend/SftpRangeJob.php

@@ -0,0 +1,40 @@
+<?php
+
+declare(strict_types=1);
+
+// SPDX-FileCopyrightText: 2026 Dillard Blom
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+namespace OCA\NgBackup\Backend;
+
+/**
+ * One range that SftpRangeFetcher reads on one connection.
+ *
+ * @internal
+ */
+final class SftpRangeJob {
+	public string $handle = '';
+	/** Offset of the next READ to send. */
+	public int $next;
+	/** @var list<array{int, int}> offset and length of parts to ask for again (after a short answer) */
+	public array $redo = [];
+	/** @var list<array{int, int, int, int}> request id, kind, offset and length, in the order sent */
+	public array $queue = [];
+	/** Bytes received. */
+	public int $got = 0;
+	public bool $failed = false;
+
+	/** @var resource the spool file that holds the range */
+	public $fh;
+
+	/** @param resource $fh */
+	public function __construct(
+		public int $i,
+		$fh,
+		public int $start,
+		public int $end,
+	) {
+		$this->fh = $fh;
+		$this->next = $start;
+	}
+}

lib/Backend/SftpReadStream.php

@@ -144,9 +144,9 @@ final class SftpReadStream {
 
 	/**
 	 * The storage's phpseclib connection, with its SFTP channel open, when it offers what these
-	 * streams need; null otherwise.
+	 * streams (and SftpRangeFetcher) need; null otherwise.
 	 */
-	private static function connection(object $storage): ?object {
+	public static function connection(object $storage): ?object {
 		if (!is_callable([$storage, 'getConnection']) || !is_callable([$storage, 'getRoot'])) {
 			return null;
 		}

lib/Backend/StorageBackend.php

@@ -14,14 +14,23 @@ use OCP\Files\Storage\IWriteStreamStorage;
  * IBackend on top of a Nextcloud storage object (from files_external or core), below a base
  * directory on that storage.
  */
-final class StorageBackend implements IBackend {
+final class StorageBackend implements IBackend, IReadsAhead {
 	/** Object stores write whole objects atomically; other storages get a temp name + rename. */
 	private bool $atomicPut;
 	/** SFTP: read through SftpReadStream, which keeps several requests in flight. */
 	private bool $sftpReads;
+	/** S3: many small reads go straight to the storage's S3 client, several at a time. */
+	private bool $s3Reads;
+	/** S3 requests in flight at once for getMany() and getRanges(). */
+	public const S3_CONCURRENCY = 16;
+	/** Most ranges, and bytes, getRanges() holds in memory at once. */
+	private const RANGES_LOT = 64;
+	private const RANGES_LOT_BYTES = 64 * 1048576;
 	/** Seconds without a request after which an SFTP connection is checked before it is used. */
 	public const IDLE_CHECK = 60;
 	private float $lastUsed;
+	/** Connections readAhead() opens (see SftpRangeFetcher::DEFAULT_CONNECTIONS). */
+	public int $readAheadConnections = SftpRangeFetcher::DEFAULT_CONNECTIONS;
 	/** Times the storage was built anew after its connection died (for tests and diagnostics). */
 	public int $reconnects = 0;
 
@@ -40,6 +49,7 @@ final class StorageBackend implements IBackend {
 		self::validate($this->base, true);
 		$this->atomicPut = $storage->instanceOfStorage(\OCA\Files_External\Lib\Storage\AmazonS3::class);
 		$this->sftpReads = $storage->instanceOfStorage(\OCA\Files_External\Lib\Storage\SFTP::class);
+		$this->s3Reads = $storage instanceof \OCA\Files_External\Lib\Storage\AmazonS3;
 		if ($createBase && $this->base !== '') {
 			$this->mkdirs($this->base);
 		}
@@ -116,11 +126,19 @@ final class StorageBackend implements IBackend {
 		return $fh;
 	}
 
-	/** Over SFTP several at a time (SftpReadStream::readMany()); elsewhere one after the other. */
+	/**
+	 * Over SFTP and S3 several at a time (SftpReadStream::readMany(), s3Fetch()); elsewhere one
+	 * after the other.
+	 */
 	public function getMany(array $paths): \Generator {
-		foreach (array_chunk($paths, 8 * SftpReadStream::BATCH) as $chunk) {
+		$size = $this->s3Reads ? 16 * self::S3_CONCURRENCY : 8 * SftpReadStream::BATCH;
+		foreach (array_chunk($paths, $size) as $chunk) {
 			$fast = null;
-			if ($this->sftpReads) {
+			if ($this->s3Reads) {
+				$this->idleCheck();
+				$fast = $this->s3Fetch(array_map(fn (string $p): array => [$p, null], $chunk));
+				$fast = $fast === null ? null : array_combine($chunk, array_map(fn (int $i): ?string => $fast[$i] ?? null, array_keys($chunk)));
+			} elseif ($this->sftpReads) {
 				$abs = array_map(fn (string $p): string => $this->abs($p), $chunk);
 				$fast = $this->call(fn () => SftpReadStream::readMany($this->storage, $abs));
 				$fast = $fast === null ? null : array_combine($chunk, array_map(fn (string $a): ?string => $fast[$a] ?? null, $abs));
@@ -145,6 +163,144 @@ final class StorageBackend implements IBackend {
 		}
 	}
 
+	/** Over S3 several at a time (s3Fetch()); elsewhere one after the other. */
+	public function getRanges(array $ranges): \Generator {
+		$lot = [];
+		$bytes = 0;
+		foreach ($ranges as $i => $range) {
+			if ($lot !== [] && (count($lot) >= self::RANGES_LOT || $bytes + $range[2] > self::RANGES_LOT_BYTES)) {
+				yield from $this->rangesLot($lot);
+				$lot = [];
+				$bytes = 0;
+			}
+			$lot[$i] = $range;
+			$bytes += $range[2];
+		}
+		if ($lot !== []) {
+			yield from $this->rangesLot($lot);
+		}
+	}
+
+	/**
+	 * @param array<int, array{0:string, 1:int, 2:int}> $lot
+	 * @return \Generator<int, string>
+	 */
+	private function rangesLot(array $lot): \Generator {
+		$fast = null;
+		if ($this->s3Reads) {
+			$this->idleCheck();
+			$fast = $this->s3Fetch(array_map(fn (array $r): array => [$r[0], $r[1] . '-' . ($r[1] + $r[2] - 1)], $lot));
+		}
+		foreach ($lot as $i => [$path, $offset, $length]) {
+			$data = $fast[$i] ?? null;
+			// not read in the batch, or not all of it: the usual way, which also reports why
+			yield $i => ($data !== null && strlen($data) === $length) ? $data : $this->getRange($path, $offset, $length);
+		}
+	}
+
+	/**
+	 * Read objects (or byte ranges of them, "first-last") straight through the S3 client of
+	 * files_external's S3 storage, S3_CONCURRENCY at a time. Its own reads open a new HTTPS
+	 * connection per object, after a HEAD request: one after the other that is about two reads a
+	 * second, which made checking the index of a large repository take hours. What fails here
+	 * is left out of the result, for the caller to read the usual way (which reports the error).
+	 *
+	 * @param array<int, array{0:string, 1:?string}> $requests [path, range or null] by key
+	 * @return array<int, string>|null contents by key; null when the storage is not as expected
+	 * @psalm-suppress UndefinedClass the AWS SDK comes with Nextcloud, not with this app
+	 */
+	private function s3Fetch(array $requests): ?array {
+		try {
+			/** @psalm-suppress UndefinedMethod, UndefinedThisPropertyFetch */
+			[$client, $bucket, $sse] = (function (): array {
+				$sse = method_exists($this, 'getServerSideEncryptionParameters') ? $this->getServerSideEncryptionParameters()
+					: (method_exists($this, 'getSSECParameters') ? $this->getSSECParameters() : []);
+				return [$this->getConnection(), $this->getBucket(), $sse];
+			})->call($this->storage);
+			if (!$client instanceof \Aws\S3\S3Client || !is_string($bucket)) {
+				return null;
+			}
+			$results = [];
+			$keys = array_keys($requests); // the pool numbers results 0, 1, ...: mapped back below
+			$commands = (function () use ($requests, $client, $bucket, $sse): \Generator {
+				foreach (array_values($requests) as $n => [$path, $range]) {
+					$args = ['Bucket' => $bucket, 'Key' => trim($this->abs($path), '/')] + $sse;
+					if ($range !== null) {
+						$args['Range'] = 'bytes=' . $range;
+					}
+					yield $n => $client->getCommand('GetObject', $args);
+				}
+			})();
+			(new \Aws\CommandPool($client, $commands, [
+				'concurrency' => self::S3_CONCURRENCY,
+				'fulfilled' => function (mixed $result, int $n) use (&$results, $keys): void {
+					$results[$keys[$n]] = (string)$result['Body'];
+				},
+				'rejected' => static function (): void {
+				},
+			]))->promise()->wait();
+			return $results;
+		} catch (\Throwable) {
+			return null;
+		}
+	}
+
+	/**
+	 * Over SFTP: SftpRangeFetcher, on readAheadConnections new connections of its own (built with the
+	 * reconnect function), so the storage's connection stays free for other requests. Elsewhere
+	 * not (yet): null.
+	 */
+	public function canReadAhead(): bool {
+		return $this->sftpReads && $this->reconnect !== null;
+	}
+
+	public function readAhead(array $ranges, string $spool): ?\Generator {
+		$reconnect = $this->reconnect;
+		if (!$this->sftpReads || $reconnect === null || $ranges === []) {
+			return null;
+		}
+		// before any connection is opened: an invalid path throws
+		$abs = array_map(fn (array $r): array => [$this->abs($r[0]), $r[1], $r[2]], $ranges);
+		$storages = [];
+		$connections = [];
+		$root = '';
+		$wanted = max(1, min(SftpRangeFetcher::MAX_CONNECTIONS, $this->readAheadConnections));
+		for ($n = 0; $n < $wanted; $n++) {
+			try {
+				$storage = $reconnect();
+				$sftp = SftpReadStream::connection($storage);
+				if ($sftp === null || !is_callable([$storage, 'getRoot'])) {
+					break;
+				}
+				$root = (string)$storage->getRoot();
+			} catch (\Throwable) {
+				break; // the server may allow fewer connections: go on with those that work
+			}
+			$storages[] = $storage;
+			$connections[] = $sftp;
+		}
+		if ($connections === []) {
+			return null;
+		}
+		// in place of a connection that broke: a new storage, kept like the others
+		$connect = static function () use ($reconnect, &$storages): ?object {
+			$storage = $reconnect();
+			$sftp = SftpReadStream::connection($storage);
+			if ($sftp !== null) {
+				$storages[] = $storage;
+			}
+			return $sftp;
+		};
+		return (static function () use (&$storages, $connections, $root, $abs, $spool, $connect): \Generator {
+			// the storages hold their connections: kept until the fetcher is done
+			try {
+				yield from SftpRangeFetcher::fetch($connections, $root, $abs, $spool, $connect);
+			} finally {
+				unset($storages);
+			}
+		})();
+	}
+
 	public function getRange(string $path, int $offset, int $length): string {
 		return $this->call(fn () => $this->readRange($path, $offset, $length));
 	}
@@ -331,8 +487,9 @@ final class StorageBackend implements IBackend {
 		$this->lastUsed = microtime(true);
 	}
 
+	/** After a failed request: ask the server (one round trip), as phpseclib may not know it is gone. */
 	private function reopenIfDead(): bool {
-		if ($this->reconnect === null || !$this->sftpReads || $this->alive(false) !== false) {
+		if ($this->reconnect === null || !$this->sftpReads || $this->alive(true) !== false) {
 			return false;
 		}
 		$this->reopen();
@@ -361,8 +518,9 @@ final class StorageBackend implements IBackend {
 			if (is_callable([$sftp, 'clearStatCache'])) {
 				$sftp->clearStatCache(); // or stat() answers from memory
 			}
-			$sftp->stat('.');
-			return (bool)$sftp->isConnected();
+			// A Storage Box drops a quiet connection without phpseclib noticing: it still says
+			// connected, and every request fails. So the answer counts, not what it says after.
+			return $sftp->stat('.') !== false && (bool)$sftp->isConnected();
 		} catch (\Throwable) {
 			return false;
 		}

lib/BackgroundJob/BackupJob.php

@@ -34,7 +34,11 @@ final class BackupJob extends TimedJob {
 		private LoggerInterface $logger,
 	) {
 		parent::__construct($time);
-		$this->setInterval(300);
+		// Well below the usual 5-minute cron interval: the last run is stamped a moment after cron
+		// starts, so with 300 the next cron run came a few seconds too early and the job ran only
+		// every other time, idle for 6 of every 10 minutes during a backup. When nothing runs, the
+		// job only does a few cheap database checks.
+		$this->setInterval(60);
 		$this->setTimeSensitivity(IJob::TIME_SENSITIVE);
 	}
 

lib/Command/KeyInit.php

@@ -50,7 +50,7 @@ HELP);
 			$pass = rtrim((string)@file_get_contents($file), "\r\n");
 		} else {
 			$helper = $this->getHelper('question');
-			$q = (new Question('Passphrase (min. 12 characters): '))->setHidden(true)->setHiddenFallback(false);
+			$q = (new Question('Passphrase (min. ' . \OCA\NgBackup\Service\KeyService::MIN_PASSPHRASE . ' characters): '))->setHidden(true)->setHiddenFallback(false);
 			$pass = (string)$helper->ask($input, $output, $q);
 			$again = (string)$helper->ask($input, $output, (new Question('Repeat passphrase: '))->setHidden(true)->setHiddenFallback(false));
 			if ($pass !== $again) {

lib/Command/KeySlots.php

@@ -88,7 +88,7 @@ HELP;
 			return rtrim((string)@file_get_contents($file), "\r\n");
 		}
 		$h = $this->getHelper('question');
-		$p = (string)$h->ask($input, $output, (new Question('Passphrase (min. 12 characters): '))->setHidden(true)->setHiddenFallback(false));
+		$p = (string)$h->ask($input, $output, (new Question('Passphrase (min. ' . \OCA\NgBackup\Service\KeyService::MIN_PASSPHRASE . ' characters): '))->setHidden(true)->setHiddenFallback(false));
 		if ($p !== (string)$h->ask($input, $output, (new Question('Repeat: '))->setHidden(true)->setHiddenFallback(false))) {
 			throw new \InvalidArgumentException('The passphrases do not match');
 		}

lib/Command/RestoreFull.php

@@ -23,6 +23,7 @@ final class RestoreFull extends Command {
 		private TargetService $targets,
 		private RestoreFullService $restoreFull,
 		private IUserManager $userManager,
+		private \OCP\App\IAppManager $appManager,
 	) {
 		parent::__construct();
 	}
@@ -33,14 +34,19 @@ final class RestoreFull extends Command {
 			->addArgument('target', InputArgument::REQUIRED, 'Location name or id')
 			->addArgument('snapshot', InputArgument::REQUIRED, 'Snapshot id (see backup:list)')
 			->addOption('force', null, InputOption::VALUE_NONE, 'Also on an installation that already has more than one user, and without asking')
+			->addOption('install-apps', null, InputOption::VALUE_NONE, 'First install (from the app store) or enable the apps that were enabled at backup time and are missing here')
+			->addOption('skip-missing-tables', null, InputOption::VALUE_NONE, 'Older backups only: leave out tables that do not exist here and whose structure the backup does not record')
 			->setHelp(<<<'HELP'
 For a FRESH Nextcloud installation only, same major version as the backup, right after
 occ maintenance:install, occ backup:key:import and occ backup:target:add -- before anyone else
 uses this instance.
 
-Every app that was enabled when the snapshot was taken must already be installed here (its
-database tables must exist before the restore can write into them); the command lists what is
-missing and refuses to continue rather than guess.
+Apps: --install-apps first installs (from the app store) or enables every app that was enabled
+when the snapshot was taken. Apps that are not in the app store (own builds) must be copied into
+custom_apps by hand; the command lists what is still missing. Tables of apps that are missing or
+were removed long ago are created from the structure recorded in the backup (backups made with
+1.0.0-rc.2 or later), so they do not block the restore. Older backups do not record it: the
+command then lists those tables per app, and --skip-missing-tables leaves them out.
 
 Steps: the database is replaced (consistent, in one transaction); the data directory is restored
 directly in place; config.php is merged in -- everything from the backup except the database
@@ -75,10 +81,28 @@ HELP);
 		try {
 			$target = $this->targets->get($input->getArgument('target'));
 			$snapshot = (string)$input->getArgument('snapshot');
-			$result = $this->restoreFull->restoreFull($target, $snapshot);
+			$skipMissingTables = (bool)$input->getOption('skip-missing-tables');
+			if ($input->getOption('install-apps')) {
+				$check = $this->restoreFull->checkCompatibility($target, $snapshot, $skipMissingTables);
+				foreach ($check['missingApps'] as $app) {
+					$this->installApp($app, $output);
+				}
+			}
+			$output->writeln('Nextcloud is in maintenance mode while the restore runs; it is switched off when the restore completes.');
+			$result = $this->restoreFull->restoreFull($target, $snapshot, $skipMissingTables);
 		} catch (\Throwable $e) {
 			$output->writeln('<error>' . $e->getMessage() . '</error>');
-			$output->writeln('If this happened after the restore had started, the instance may be partly restored: fix the cause and run the same command again with --force.');
+			if (\OCP\Server::get(\OCP\IConfig::class)->getSystemValueBool('maintenance', false)) {
+				$output->writeln('The restore had started: the instance may be partly restored, and maintenance mode stays on so that nobody uses it like that.');
+				$output->writeln('Fix the cause, then switch maintenance mode off and run the same command again with --force, in one line:');
+				$again = 'occ backup:restore:full ' . escapeshellarg((string)$input->getArgument('target')) . ' ' . escapeshellarg((string)$input->getArgument('snapshot'))
+					. ($input->getOption('skip-missing-tables') ? ' --skip-missing-tables' : '') . ' --force --no-interaction';
+				$output->writeln('  occ maintenance:mode --off && ' . $again);
+				$output->writeln('(Without --install-apps, so the instance is open only for the seconds until the restore starts again. Apps the first run could not install are listed at the end: install those afterwards.)');
+			} else {
+				$output->writeln('If this happened after the restore had started, the instance may be partly restored: fix the cause and run the same command again with --force.');
+			}
+			$output->writeln('If occ then says that Nextcloud needs an upgrade (the database is already the old server\'s), run occ upgrade first.');
 			return 1;
 		}
 		$output->writeln(sprintf(
@@ -88,10 +112,49 @@ HELP);
 			$result['configKeys'],
 			$result['dataFiles'],
 		));
+		if ($result['dbReport']['created'] !== []) {
+			$output->writeln(sprintf('Created <info>%d</info> tables that did not exist here (apps that are missing or were removed): %s',
+				count($result['dbReport']['created']), implode(', ', $result['dbReport']['created'])));
+		}
+		foreach ($result['dbReport']['foreignKeyErrors'] ?? [] as $error) {
+			$output->writeln('<comment>Could not add a foreign key to a created table (the data is restored): ' . $error . '</comment>');
+		}
+		if ($result['dbReport']['missing'] !== []) {
+			$output->writeln('<comment>Left out (structure unknown): ' . implode(', ', $result['dbReport']['missing']) . '</comment>');
+		}
+		if ($result['missingApps'] !== []) {
+			$output->writeln('<comment>These apps were enabled on the old server but are not installed here. Their data is restored; install them so they work again:</comment>');
+			foreach ($result['missingApps'] as $app) {
+				$output->writeln("  occ app:install $app   (not in the app store? copy it into custom_apps and run occ app:enable $app)");
+			}
+		}
 		if (!$result['dbConsistent']) {
 			$output->writeln('<comment>Warning: this snapshot\'s database dump was made over several steps (web cron), so it is not one consistent point in time. Check the instance carefully; prefer a snapshot made with system cron.</comment>');
 		}
+		if ($result['maintenanceLeftOn']) {
+			$output->writeln('<comment>Maintenance mode was on before the restore and stays on: switch it off with occ maintenance:mode --off when the instance is ready.</comment>');
+		}
 		$output->writeln('Next: check trusted_domains and overwritehost/overwriteprotocol match this server, then occ maintenance:repair.');
 		return 0;
 	}
+
+	/** Enable an app that is here but switched off, or install it from the app store. */
+	private function installApp(string $app, OutputInterface $output): void {
+		try {
+			$this->appManager->getAppPath($app);
+			$command = 'app:enable'; // here, but switched off
+		} catch (\OCP\App\AppPathNotFoundException) {
+			$command = 'app:install';
+		}
+		$output->writeln("Running occ $command $app ...");
+		try {
+			$code = $this->getApplication()?->find($command)->run(new \Symfony\Component\Console\Input\ArrayInput(['app-id' => $command === 'app:enable' ? [$app] : $app]), $output);
+		} catch (\Throwable $e) {
+			$code = 1;
+			$output->writeln('<comment>' . $e->getMessage() . '</comment>');
+		}
+		if ($code !== 0) {
+			$output->writeln("<comment>Could not $command $app (not in the app store?). Copy it into custom_apps and enable it, or restore without it.</comment>");
+		}
+	}
 }

lib/Command/Status.php

@@ -14,9 +14,13 @@ use OCA\NgBackup\Service\VerifyService;
 use Symfony\Component\Console\Command\Command;
 use Symfony\Component\Console\Helper\Table;
 use Symfony\Component\Console\Input\InputInterface;
+use Symfony\Component\Console\Input\InputOption;
 use Symfony\Component\Console\Output\OutputInterface;
 
 final class Status extends Command {
+	/** Runs of the last days that are listed by default (failed ones stay visible that long). */
+	public const RECENT_DAYS = 7;
+
 	public function __construct(
 		private KeyService $keys,
 		private TargetService $targets,
@@ -27,7 +31,8 @@ final class Status extends Command {
 	}
 
 	protected function configure(): void {
-		$this->setName('backup:status')->setDescription('Show the backup key, locations and recent runs');
+		$this->setName('backup:status')->setDescription('Show the backup key, locations and recent runs')
+			->addOption('all', null, InputOption::VALUE_NONE, 'List all runs, not only those of the last ' . self::RECENT_DAYS . ' days');
 	}
 
 	protected function execute(InputInterface $input, OutputInterface $output): int {
@@ -44,16 +49,22 @@ final class Status extends Command {
 		}
 		$output->writeln('Locations: ' . ($names === [] ? 'none' : implode(', ', $names)));
 		$rows = [];
-		foreach ($this->runs->findRecent(10) as $r) {
+		$all = (bool)$input->getOption('all');
+		$shown = $this->runs->findShown($all ? null : time() - self::RECENT_DAYS * 86400);
+		foreach ($shown as $r) {
 			$s = json_decode($r->getStats() ?? '{}', true)['files'] ?? [];
 			$rows[] = [$r->getId(), $names[$r->getTargetId()] ?? '#' . $r->getTargetId(), $r->getKind(), $r->getStatus() . ($r->getStatus() === 'running' ? ' (' . $r->getPhase() . self::percent($r) . ')' : ''),
-				date('Y-m-d H:i', $r->getStartedAt()), $r->getFinishedAt() ? gmdate('H:i:s', $r->getFinishedAt() - $r->getStartedAt()) : '',
+				date('Y-m-d H:i', $r->getStartedAt()), $r->getFinishedAt() ? \OCA\NgBackup\Format::duration($r->getFinishedAt() - $r->getStartedAt()) : '',
 				$s['files'] ?? '', isset($s['bytes']) ? self::size((int)$s['bytes']) : '',
 				isset($s['uploaded']) ? self::size((int)$s['uploaded']) : '', mb_strimwidth((string)$r->getError(), 0, 50, '…')];
 		}
 		if ($rows !== []) {
 			(new Table($output))->setHeaders(['run', 'location', 'kind', 'status', 'started', 'took', 'files', 'size', 'uploaded', 'error'])->setRows($rows)->render();
 		}
+		$older = $all ? 0 : $this->runs->countAll() - count($shown);
+		if ($older > 0) {
+			$output->writeln(sprintf('%d older run%s not shown (--all)', $older, $older === 1 ? '' : 's'));
+		}
 		foreach ($this->verify->progress() as $targetId => $state) {
 			$output->writeln(sprintf('Verify of %s on %s: %s', mb_strimwidth((string)($state['what'] ?? ''), 0, 40, '…'),
 				$names[$targetId] ?? '#' . $targetId, VerifyService::describe($state)));

lib/Command/TargetAdd.php

@@ -44,7 +44,10 @@ HELP);
 
 	protected function execute(InputInterface $input, OutputInterface $output): int {
 		if (!$this->keys->isInitialized()) {
-			$output->writeln('<error>No backup key yet: run occ backup:key:init first.</error>');
+			$output->writeln('<error>No backup key yet.</error>');
+			$output->writeln('Restoring from a location that already has backups (disaster recovery)? Import the key from the recovery kit first:');
+			$output->writeln('  occ backup:key:import /path/to/ng_backup-kit.json');
+			$output->writeln('Only for a new location without backups: create a new key with occ backup:key:init. A new key cannot read existing backups.');
 			return 1;
 		}
 		$options = [];
@@ -60,9 +63,16 @@ HELP);
 			$output->writeln('<error>--auth is required (see occ backup:target:backends)</error>');
 			return 1;
 		}
+		// Adopting an existing repository reads its whole index first, which takes a while on a
+		// large backup or a slow line; show how far it is instead of looking stuck.
+		$output->writeln('Connecting to the location; with existing backups this reads their index first ...');
 		try {
-			$r = $this->targets->add($input->getArgument('name'), $input->getArgument('backend'), $input->getOption('auth'), $options, (string)$input->getOption('path'));
+			$r = $this->targets->add($input->getArgument('name'), $input->getArgument('backend'), $input->getOption('auth'), $options,
+				(string)$input->getOption('path'), self::progress($output));
 		} catch (\Throwable $e) {
+			if ($output->isDecorated()) {
+				$output->write("\r\033[K"); // clear an unfinished progress line
+			}
 			$output->writeln('<error>' . $e->getMessage() . '</error>');
 			return 1;
 		}
@@ -70,4 +80,34 @@ HELP);
 			$r['target']->getRepositoryId(), $r['created'] ? 'created' : 'found and adopted'));
 		return 0;
 	}
+
+	/**
+	 * Progress of reading the index: on a terminal one line that is updated in place, otherwise
+	 * (a log, a pipe) a line every 30 seconds. The time left is estimated from the rate so far.
+	 *
+	 * @return callable(int, int): void
+	 */
+	private static function progress(OutputInterface $output): callable {
+		$start = microtime(true);
+		$shown = 0.0;
+		$inPlace = $output->isDecorated();
+		return static function (int $done, int $total) use ($output, $start, &$shown, $inPlace): void {
+			$now = microtime(true);
+			if ($done < $total && $now - $shown < ($inPlace ? 1 : 30)) {
+				return;
+			}
+			$shown = $now;
+			$line = sprintf('Reading the index: %s/%s files (%d%%)', number_format($done), number_format($total), intdiv(100 * $done, max(1, $total)));
+			$elapsed = $now - $start;
+			if ($done < $total && $done > 0 && $elapsed >= 5) {
+				$left = (int)ceil($elapsed / (float)$done * (float)($total - $done) / 60.0);
+				$line .= $left <= 1 ? ', less than a minute left' : sprintf(', about %d min left', $left);
+			}
+			if ($inPlace) {
+				$output->write("\r\033[K" . $line . ($done >= $total ? "\n" : ''));
+			} else {
+				$output->writeln($line);
+			}
+		};
+	}
 }

lib/Controller/AdminApiController.php

@@ -51,14 +51,16 @@ final class AdminApiController extends Controller {
 		parent::__construct(Application::APP_ID, $request);
 	}
 
-	public function status(): JSONResponse {
+	/** @param bool $allRuns all runs instead of those of the last days (Status::RECENT_DAYS) */
+	public function status(bool $allRuns = false): JSONResponse {
 		$targets = [];
 		foreach ($this->targets->list() as $t) {
 			$targets[] = ['id' => $t->getId(), 'name' => $t->getName(), 'backend' => $t->getBackend(), 'path' => $t->getBasePath(),
 				'repositoryId' => $t->getRepositoryId(), 'createdAt' => $t->getCreatedAt(), 'appendOnly' => (bool)$t->getAppendOnly(),
 				'maxBytes' => $t->getMaxBytes(), 'storedBytes' => $this->alerts->lastStoredBytes($t)];
 		}
-		$runs = array_map(fn (Run $r) => $this->runJson($r), $this->runs->findRecent(15));
+		$shown = $this->runs->findShown($allRuns ? null : time() - \OCA\NgBackup\Command\Status::RECENT_DAYS * 86400);
+		$runs = array_map(fn (Run $r) => $this->runJson($r), $shown);
 		return new JSONResponse([
 			'key' => ['initialized' => $this->keys->isInitialized(), 'fingerprint' => $this->keys->fingerprint(),
 				'confirmation' => $this->keys->recoveryKitConfirmation(), 'everConfirmed' => $this->keys->isInitialized() && $this->keys->everConfirmed(),
@@ -68,6 +70,8 @@ final class AdminApiController extends Controller {
 			'confirmationPhrase' => KeyConfirm::CONFIRMATION,
 			'targets' => $targets,
 			'runs' => $runs,
+			'olderRuns' => $allRuns ? 0 : $this->runs->countAll() - count($shown),
+			'recentDays' => \OCA\NgBackup\Command\Status::RECENT_DAYS,
 			'schedule' => $this->appConfig->getValueString(Application::APP_ID, 'schedule_time', ''),
 		]);
 	}

lib/Db/DbDumper.php

@@ -23,8 +23,12 @@ use OCA\NgBackup\Repository\Repository;
  *   sets, so a single big SELECT would not stream).
  * - Each table becomes its own blob stream of JSON lines: a header line, then one JSON array per
  *   row. A table that did not change produces the same blobs and costs nothing in the next run.
- * - The schema itself is not dumped: it comes from Nextcloud's migrations on the instance that is
- *   restored into (same Nextcloud and app versions). The dump records those versions.
+ * - The structure of each table (columns, types, primary key, indexes) is recorded in the manifest,
+ *   so a restore can create a table that does not exist on the new instance, for example one left
+ *   behind by an app that was removed long ago. Tables that exist keep the structure the new
+ *   instance's migrations gave them.
+ * - Foreign keys are not checked while rows are loaded (tables are restored in name order, not in
+ *   dependency order), and are checked again before the restore commits.
  *
  * Phase 0 uses the Doctrine connection behind IDBConnection (private API) for schema
  * introspection; to be replaced by information_schema queries or a public API.
@@ -108,7 +112,7 @@ final class DbDumper {
 						break;
 					}
 					$state['result'][$table] = ['blobs' => array_merge(...$state['segments']), 'rows' => $state['rows'],
-						'bytes' => $state['bytes'], 'sha256' => hash_final($hash)];
+						'bytes' => $state['bytes'], 'sha256' => hash_final($hash), 'schema' => self::structure($schema)];
 					$state = array_merge($state, ['i' => $state['i'] + 1, 'after' => null, 'segments' => [], 'rows' => 0, 'bytes' => 0, 'hash' => null]);
 					if (microtime(true) >= $deadline && $state['i'] < count($state['tables'])) {
 						break;
@@ -137,18 +141,38 @@ final class DbDumper {
 	 * Replace the contents of every table in the dump. Tables that exist but are not in the dump
 	 * are left alone (e.g. a newer app); the caller decides whether that is acceptable.
 	 *
-	 * @param array{tables: array<string, array{blobs: list<string>, rows: int}>} $manifest
+	 * @param array{tables: array<string, array{blobs: list<string>, rows: int, sha256: string, schema?: array}>, sequences?: array} $manifest
 	 */
-	public function restore(Repository $repo, array $manifest, ?array &$report = null, ?callable $heartbeat = null): int {
-		$sm = $this->db->createSchemaManager();
-		$existing = array_flip($sm->listTableNames());
+	public function restore(Repository $repo, array $manifest, ?array &$report = null, ?callable $heartbeat = null, bool $skipMissing = false): int {
+		$report = ['skipped' => [], 'restored' => [], 'created' => [], 'missing' => []];
+		$source = self::dumpPrefix($manifest);
+		if ($source !== null && $source !== $this->prefix) {
+			// Every table would look missing and be created under the old prefix, unused.
+			throw new \RuntimeException("The backup's tables use the prefix '$source', this installation '{$this->prefix}'. Install Nextcloud again with 'dbtableprefix' => '$source' in config/config.php before occ maintenance:install, and restore again.");
+		}
+		$missing = $this->missingTables($manifest);
+		$unknown = array_values(array_filter($missing, fn (string $t) => !isset($manifest['tables'][$t]['schema'])));
+		if ($unknown !== [] && !$skipMissing) {
+			throw new \RuntimeException(self::describeMissing($unknown, $this->prefix));
+		}
+		// Tables the backup knows the structure of are created first (DDL is not transactional
+		// everywhere); tables it does not know are left out, as asked.
+		foreach ($missing as $table) {
+			if (isset($manifest['tables'][$table]['schema'])) {
+				$this->db->createSchemaManager()->createTable(self::tableFromStructure($table, $manifest['tables'][$table]['schema']));
+				$report['created'][] = $table;
+			} else {
+				$report['missing'][] = $table;
+			}
+		}
 		$total = 0;
-		$report = ['skipped' => [], 'restored' => []];
+		$foreignKeys = [];
 		$this->db->beginTransaction();
 		try {
+			$foreignKeys = $this->suspendForeignKeys();
 			foreach ($manifest['tables'] as $table => $info) {
-				if (!isset($existing[$table])) {
-					throw new \RuntimeException("Table $table from the backup does not exist here (different app versions?)");
+				if (in_array($table, $report['missing'], true)) {
+					continue;
 				}
 				// Unchanged since the backup: leave it alone (much faster than delete + insert).
 				$live = $this->checksum($table);
@@ -192,15 +216,206 @@ final class DbDumper {
 				}
 				$report['restored'][] = $table;
 			}
-			$this->restoreSequences($manifest['sequences'] ?? []);
+			// unchanged tables too: a restore that stopped earlier may have left their counters at 1
+			$this->restoreSequences($manifest['sequences'] ?? [], $report['missing'], array_merge($report['restored'], $report['skipped']));
+			$this->resumeForeignKeys($foreignKeys);
 			$this->db->commit();
+			// Foreign keys of the tables created above, now their rows are in. Not inside the
+			// transaction: MySQL commits on DDL. A failure is reported, not fatal: the data is
+			// restored either way.
+			foreach ($report['created'] as $table) {
+				$structure = $manifest['tables'][$table]['schema'] ?? [];
+				foreach ($structure['foreignKeys'] ?? [] as $fk) {
+					try {
+						$this->db->createSchemaManager()->createForeignKey(
+							new \Doctrine\DBAL\Schema\ForeignKeyConstraint($fk['columns'], $fk['table'], $fk['foreign'], $fk['name'], $fk['options'] ?? []),
+							$table);
+					} catch (\Throwable $e) {
+						$report['foreignKeyErrors'][] = $table . '.' . $fk['name'] . ': ' . $e->getMessage();
+					}
+				}
+			}
 		} catch (\Throwable $e) {
 			$this->db->rollBack();
+			// PostgreSQL rolls the dropped foreign keys back with the transaction; MySQL's session
+			// switch must be turned on again by hand.
+			if (in_array('SET FOREIGN_KEY_CHECKS = 1', $foreignKeys, true)) {
+				$this->db->executeStatement('SET FOREIGN_KEY_CHECKS = 1');
+			}
 			throw $e;
 		}
 		return $total;
 	}
 
+	/**
+	 * The table prefix of the instance the dump was made on (from its appconfig table), or null
+	 * when the dump has none.
+	 *
+	 */
+	public static function dumpPrefix(array $manifest): ?string {
+		/** @var list<string> $tables table names */
+		$tables = array_keys($manifest['tables'] ?? []);
+		foreach ($tables as $name) {
+			if (str_ends_with($name, 'appconfig') && !str_ends_with($name, '_ex_appconfig')) {
+				return substr($name, 0, -strlen('appconfig'));
+			}
+		}
+		return null;
+	}
+
+	/**
+	 * Tables in the dump that do not exist on this instance.
+	 *
+	 * @return list<string>
+	 */
+	public function missingTables(array $manifest): array {
+		$existing = array_flip($this->db->createSchemaManager()->listTableNames());
+		return array_values(array_filter(array_keys($manifest['tables']), fn (string $t) => !isset($existing[$t])));
+	}
+
+	/** One message for all missing tables of an older backup, grouped by the app they probably belong to. */
+	public static function describeMissing(array $tables, string $prefix): string {
+		$groups = [];
+		foreach ($tables as $t) {
+			$name = substr($t, strlen($prefix));
+			$groups[explode('_', $name, 2)[0]][] = $t;
+		}
+		$lines = [];
+		foreach ($groups as $app => $list) {
+			$lines[] = '- ' . $app . ': ' . implode(', ', $list);
+		}
+		return "These tables from the backup do not exist here, and this backup does not record their structure (made before 1.0.0-rc.2):\n"
+			. implode("\n", $lines)
+			. "\nInstall the apps they belong to (often apps that were removed or switched off long ago) and run the restore again, or leave these tables out with --skip-missing-tables.";
+	}
+
+	/**
+	 * Portable description of a table: enough to create it again, also on another database type.
+	 *
+	 * @return array{columns: list<array<string, mixed>>, pk: list<string>, indexes: list<array{name: string, columns: list<string>, unique: bool}>}
+	 */
+	private static function structure(\Doctrine\DBAL\Schema\Table $table): array {
+		$columns = [];
+		foreach ($table->getColumns() as $c) {
+			$columns[] = ['name' => $c->getName(), 'type' => \Doctrine\DBAL\Types\Type::lookupName($c->getType()),
+				'length' => $c->getLength(), 'precision' => $c->getPrecision(), 'scale' => $c->getScale(),
+				'unsigned' => $c->getUnsigned(), 'fixed' => $c->getFixed(), 'notnull' => $c->getNotnull(),
+				'default' => $c->getDefault(), 'autoincrement' => $c->getAutoincrement()];
+		}
+		$indexes = [];
+		foreach ($table->getIndexes() as $i) {
+			if (!$i->isPrimary()) {
+				// options holds the prefix lengths MySQL needs for indexes on long text columns
+				$indexes[] = ['name' => $i->getName(), 'columns' => array_values($i->getColumns()), 'unique' => $i->isUnique(),
+					'flags' => array_values($i->getFlags()), 'options' => $i->getOptions()];
+			}
+		}
+		$foreignKeys = [];
+		foreach ($table->getForeignKeys() as $fk) {
+			$foreignKeys[] = ['name' => $fk->getName(), 'columns' => array_values($fk->getLocalColumns()),
+				'table' => $fk->getForeignTableName(), 'foreign' => array_values($fk->getForeignColumns()), 'options' => $fk->getOptions()];
+		}
+		return ['columns' => $columns, 'pk' => array_values($table->getPrimaryKey()?->getColumns() ?? []), 'indexes' => $indexes,
+			'foreignKeys' => $foreignKeys];
+	}
+
+	private static function tableFromStructure(string $name, array $structure): \Doctrine\DBAL\Schema\Table {
+		$table = new \Doctrine\DBAL\Schema\Table($name);
+		foreach ($structure['columns'] as $c) {
+			$table->addColumn($c['name'], $c['type'], array_filter([
+				'length' => $c['length'], 'precision' => $c['precision'], 'scale' => $c['scale'],
+				'unsigned' => $c['unsigned'], 'fixed' => $c['fixed'], 'notnull' => $c['notnull'],
+				'default' => $c['default'], 'autoincrement' => $c['autoincrement'],
+			], fn ($v) => $v !== null));
+		}
+		if ($structure['pk'] !== []) {
+			$table->setPrimaryKey($structure['pk']);
+		}
+		foreach ($structure['indexes'] as $i) {
+			$i['unique']
+				? $table->addUniqueIndex($i['columns'], $i['name'], $i['options'] ?? [])
+				: $table->addIndex($i['columns'], $i['name'], $i['flags'] ?? [], $i['options'] ?? []);
+		}
+		return $table;
+	}
+
+	/**
+	 * Stop checking foreign keys while rows are loaded in name order. PostgreSQL has no session
+	 * switch for this without superuser rights, so its foreign keys of Nextcloud tables are dropped
+	 * here and added back (and so checked) by resumeForeignKeys(), inside the same transaction.
+	 *
+	 * @return list<string> statements that restore the foreign keys
+	 */
+	private function suspendForeignKeys(): array {
+		$platform = $this->db->getDatabasePlatform();
+		if ($platform instanceof \Doctrine\DBAL\Platforms\PostgreSQLPlatform) {
+			$rows = $this->db->fetchAllAssociative(
+				"SELECT conrelid::regclass::text AS tbl, conname, pg_get_constraintdef(oid) AS def
+				 FROM pg_constraint WHERE contype = 'f' AND connamespace = current_schema()::regnamespace");
+			$restore = [];
+			foreach ($rows as $r) {
+				if (!str_starts_with(trim($r['tbl'], '"'), $this->prefix)) {
+					continue;
+				}
+				$this->db->executeStatement(sprintf('ALTER TABLE %s DROP CONSTRAINT %s', $r['tbl'], $this->db->quoteIdentifier($r['conname'])));
+				$restore[] = sprintf('ALTER TABLE %s ADD CONSTRAINT %s %s', $r['tbl'], $this->db->quoteIdentifier($r['conname']), $r['def']);
+			}
+			return $restore;
+		}
+		if ($platform instanceof \Doctrine\DBAL\Platforms\AbstractMySQLPlatform) {
+			// MySQL does not check rows again when FOREIGN_KEY_CHECKS goes back to 1, and its DDL
+			// would commit the transaction halfway. So every foreign key is checked explicitly,
+			// with a query that finds rows pointing at nothing (resumeForeignKeys()).
+			$rows = $this->db->fetchAllAssociative(
+				'SELECT TABLE_NAME AS tbl, CONSTRAINT_NAME AS name, COLUMN_NAME AS col, REFERENCED_TABLE_NAME AS rtbl, REFERENCED_COLUMN_NAME AS rcol
+				 FROM information_schema.KEY_COLUMN_USAGE
+				 WHERE TABLE_SCHEMA = DATABASE() AND REFERENCED_TABLE_NAME IS NOT NULL
+				 ORDER BY TABLE_NAME, CONSTRAINT_NAME, ORDINAL_POSITION');
+			$keys = [];
+			foreach ($rows as $r) {
+				if (str_starts_with((string)$r['tbl'], $this->prefix)) {
+					$keys[$r['tbl'] . "\0" . $r['name']][] = $r;
+				}
+			}
+			$q = fn (string $i): string => $this->db->quoteIdentifier($i);
+			$checks = ['SET FOREIGN_KEY_CHECKS = 1'];
+			foreach ($keys as $parts) {
+				$join = implode(' AND ', array_map(fn (array $r): string => 'c.' . $q($r['col']) . ' = p.' . $q($r['rcol']), $parts));
+				$set = implode(' AND ', array_map(fn (array $r): string => 'c.' . $q($r['col']) . ' IS NOT NULL', $parts));
+				$checks[] = sprintf('SELECT COUNT(*) FROM %s c LEFT JOIN %s p ON %s WHERE %s AND p.%s IS NULL /* %s */',
+					$q($parts[0]['tbl']), $q($parts[0]['rtbl']), $join, $set, $q($parts[0]['rcol']), $parts[0]['name']);
+			}
+			$this->db->executeStatement('SET FOREIGN_KEY_CHECKS = 0');
+			return $checks;
+		}
+		if ($platform instanceof \Doctrine\DBAL\Platforms\SqlitePlatform) {
+			$this->db->executeStatement('PRAGMA defer_foreign_keys = ON'); // checked at commit
+		}
+		return [];
+	}
+
+	/**
+	 * Check the foreign keys again; a row that breaks one fails the restore here, before it commits.
+	 * Statements add them back (PostgreSQL) or switch the checks on (MySQL); queries count the rows
+	 * that point at nothing (MySQL) and must find none.
+	 */
+	private function resumeForeignKeys(array $statements): void {
+		foreach ($statements as $sql) {
+			try {
+				if (str_starts_with($sql, 'SELECT ')) {
+					$orphans = (int)$this->db->fetchOne($sql);
+					if ($orphans > 0) {
+						throw new \RuntimeException("$orphans rows point at nothing");
+					}
+				} else {
+					$this->db->executeStatement($sql);
+				}
+			} catch (\Throwable $e) {
+				throw new \RuntimeException('The restored data breaks a foreign key (' . $sql . '): ' . $e->getMessage(), 0, $e);
+			}
+		}
+	}
+
 	/** Same checksum as dump(): sha256 over the row lines in primary-key order. */
 	public function checksum(string $table): array {
 		$hash = hash_init('sha256');
@@ -359,11 +574,21 @@ final class DbDumper {
 		return $name;
 	}
 
-	private function restoreSequences(array $sequences): void {
+	/**
+	 * @param list<string> $leftOut tables not restored (--skip-missing-tables): they do not exist here
+	 * @param list<string> $restored tables restored or unchanged: their other counters go after their data
+	 */
+	private function restoreSequences(array $sequences, array $leftOut = [], array $restored = []): void {
 		if (!$this->db->getDatabasePlatform() instanceof \Doctrine\DBAL\Platforms\PostgreSQLPlatform) {
 			return;
 		}
+		$leftOut = array_flip($leftOut);
+		$set = [];
 		foreach ($sequences as $info) {
+			if (isset($leftOut[$info['table']])) {
+				continue;
+			}
+			$set[$info['table'] . '.' . $info['column']] = true;
 			$seq = $this->db->fetchOne('SELECT pg_get_serial_sequence(quote_ident(?), ?)', [$info['table'], $info['column']]);
 			if ($seq === false || $seq === null) {
 				continue;
@@ -378,5 +603,26 @@ final class DbDumper {
 					[\Doctrine\DBAL\ParameterType::STRING, \Doctrine\DBAL\ParameterType::INTEGER, \Doctrine\DBAL\ParameterType::BOOLEAN]);
 			}
 		}
+		// A backup from MySQL/MariaDB or SQLite records no counters (those derive them from the
+		// data): every other counter of a restored table goes after its data, or new rows (a new
+		// file, an activity) would collide with restored ones.
+		$restored = array_flip($restored);
+		$rows = $this->db->fetchAllAssociative(
+			"SELECT c.table_name, c.column_name, pg_get_serial_sequence(quote_ident(c.table_name), c.column_name) AS seq
+			 FROM information_schema.columns c
+			 WHERE c.table_schema = current_schema() AND pg_get_serial_sequence(quote_ident(c.table_name), c.column_name) IS NOT NULL");
+		foreach ($rows as $r) {
+			if (!isset($restored[$r['table_name']]) || isset($set[$r['table_name'] . '.' . $r['column_name']])) {
+				continue;
+			}
+			$max = (int)$this->db->fetchOne(sprintf('SELECT COALESCE(MAX(%s), 0) FROM %s',
+				$this->db->quoteIdentifier($r['column_name']), $this->db->quoteIdentifier($r['table_name'])));
+			// never backwards: a counter already past the data stays where it is
+			$state = $this->db->fetchAssociative('SELECT last_value, is_called FROM ' . self::sequenceIdentifier($r['seq']));
+			$next = $state === false ? 1 : (int)$state['last_value'] + ($state['is_called'] ? 1 : 0);
+			if ($next <= $max) {
+				$this->db->executeQuery('SELECT setval(CAST(? AS regclass), ?, false)', [$r['seq'], $max + 1]);
+			}
+		}
 	}
 }

lib/Db/DbIndexCache.php

@@ -64,6 +64,13 @@ final class DbIndexCache implements IIndexCache {
 		}
 	}
 
+	/** Drop the cached index of a repository that no location uses any more. */
+	public function forget(string $repositoryId): void {
+		$qb = $this->db->getQueryBuilder();
+		$qb->delete('ngb_index')->where($qb->expr()->eq('repository_id', $qb->createNamedParameter($repositoryId)));
+		$qb->executeStatement();
+	}
+
 	/** All or nothing: when it fails, the cache stays as it was. */
 	public function replaceAll(string $repositoryId, array $packs): void {
 		$this->transaction(function () use ($repositoryId, $packs): void {

lib/Db/RunMapper.php

@@ -73,6 +73,40 @@ final class RunMapper extends QBMapper {
 		return $this->findEntities($qb);
 	}
 
+	/**
+	 * The runs to list, newest first: those started at or after $since, those still running, and
+	 * at least the newest $atLeast, so the list is never empty after a quiet week. All runs when
+	 * $since is null.
+	 *
+	 * @return list<Run>
+	 */
+	public function findShown(?int $since, int $atLeast = 5): array {
+		$qb = $this->db->getQueryBuilder();
+		$qb->select('*')->from($this->getTableName())->orderBy('id', 'DESC');
+		if ($since === null) {
+			return $this->findEntities($qb);
+		}
+		$qb->where($qb->expr()->orX(
+			$qb->expr()->gte('started_at', $qb->createNamedParameter($since, IQueryBuilder::PARAM_INT)),
+			$qb->expr()->eq('status', $qb->createNamedParameter(Run::RUNNING)),
+		));
+		$runs = [];
+		foreach ([...$this->findEntities($qb), ...$this->findRecent($atLeast)] as $r) {
+			$runs[$r->getId()] = $r;
+		}
+		krsort($runs);
+		return array_values($runs);
+	}
+
+	public function countAll(): int {
+		$qb = $this->db->getQueryBuilder();
+		$qb->select($qb->func()->count('*', 'n'))->from($this->getTableName());
+		$result = $qb->executeQuery();
+		$n = (int)$result->fetchOne();
+		$result->closeCursor();
+		return $n;
+	}
+
 	/** @return list<Run> runs of $kind started at or after $since, newest first */
 	public function startedSince(int $targetId, string $kind, int $since): array {
 		$qb = $this->db->getQueryBuilder();

lib/Format.php

@@ -0,0 +1,18 @@
+<?php
+
+declare(strict_types=1);
+
+// SPDX-FileCopyrightText: 2026 Dillard Blom
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+namespace OCA\NgBackup;
+
+final class Format {
+	/** "12:10:13", or "1d 12:10:13" from a day on (a long first backup takes days). */
+	public static function duration(int $seconds): string {
+		$seconds = max(0, $seconds);
+		$days = intdiv($seconds, 86400);
+		$time = gmdate('H:i:s', $seconds % 86400);
+		return $days > 0 ? $days . 'd ' . $time : $time;
+	}
+}

lib/Job/BackupRun.php

@@ -140,21 +140,21 @@ final class BackupRun {
 			$state['parentPos'] = $parent->position();
 			$state['stats'] = $stats;
 			if ($finishedWalk) {
+				// The snapshot is written in a step of its own, with its own time: after a long
+				// run it reads back thousands of segments, and the run reports that it got here.
 				$state['phase'] = 'finish';
 			}
+			return $state;
 		}
 
 		if ($state['phase'] === 'finish') {
-			$segments = $state['segments'];
+			// Every segment ends with a newline, so they read as one stream: fetched together,
+			// several at a time where the location allows it.
 			$repo->putSnapshot($state['snapshot'],
 				['time' => $state['started'], 'parent' => $state['parent'], 'label' => $state['label'],
 					'roots' => array_keys($state['roots']), 'stats' => $state['stats'],
 					'warnings' => self::warnings($state)] + $state['meta'],
-				(function () use ($repo, $segments) {
-					foreach ($segments as $blobs) {
-						yield from $repo->readLines($blobs);
-					}
-				})());
+				$repo->readLines(array_values(array_merge(...$state['segments']))));
 			$state['phase'] = 'commit';
 		}
 		return $state;

lib/Migration/Version000006Date20261018000000.php

@@ -0,0 +1,39 @@
+<?php
+
+declare(strict_types=1);
+
+// SPDX-FileCopyrightText: 2026 Dillard Blom
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+namespace OCA\NgBackup\Migration;
+
+use Closure;
+use OCP\IDBConnection;
+use OCP\Migration\IOutput;
+use OCP\Migration\SimpleMigrationStep;
+
+/**
+ * Removing a location left the cached index of its repository behind (tens of thousands of rows
+ * for a large backup). Drop the cache of repositories no location uses any more.
+ */
+final class Version000006Date20261018000000 extends SimpleMigrationStep {
+	public function __construct(
+		private IDBConnection $db,
+	) {
+	}
+
+	public function postSchemaChange(IOutput $output, Closure $schemaClosure, array $options): void {
+		$used = $this->db->getQueryBuilder();
+		$used->select('repository_id')->from('ngb_targets')->where($used->expr()->isNotNull('repository_id'));
+		$keep = array_column($used->executeQuery()->fetchAll(), 'repository_id');
+		$delete = $this->db->getQueryBuilder();
+		$delete->delete('ngb_index');
+		if ($keep !== []) {
+			$delete->where($delete->expr()->notIn('repository_id', $delete->createNamedParameter($keep, \OCP\DB\QueryBuilder\IQueryBuilder::PARAM_STR_ARRAY)));
+		}
+		$removed = $delete->executeStatement();
+		if ($removed > 0) {
+			$output->info("Removed $removed cached index rows of locations that no longer exist");
+		}
+	}
+}

lib/Repository/BlobIndex.php

@@ -7,6 +7,7 @@ declare(strict_types=1);
 
 namespace OCA\NgBackup\Repository;
 
+use OCA\NgBackup\Backend\BackendException;
 use OCA\NgBackup\Backend\IBackend;
 use OCA\NgBackup\Crypto\StreamCipher;
 
@@ -32,6 +33,8 @@ final class BlobIndex {
 	private const CACHE_LOT = 256;
 	/** @var int index files downloaded by the last load() (for tests and diagnostics) */
 	public int $downloaded = 0;
+	/** @var array<string, true> packs whose index file is loaded (refresh() fetches only others) */
+	private array $loaded = [];
 
 	public function __construct(
 		private IBackend $backend,
@@ -90,13 +93,14 @@ final class BlobIndex {
 	 * longer exist on the backend are dropped from the cache.
 	 */
 	public function load(bool $verify = false, ?callable $progress = null): void {
-		$this->blobs = [];
+		$hadIndex = $this->blobs !== [];
 		$cached = $verify ? [] : ($this->cache?->all($this->repositoryId) ?? []);
 		$present = [];
 		$this->downloaded = 0;
 		$order = []; // pack ids in listing order: where a blob is in two packs, the last listed wins
 		$fetch = [];
-		foreach ($this->backend->listFiles('index') as $path) {
+		$known = array_keys($this->loaded + $cached + ($verify ? ($this->cache?->all($this->repositoryId) ?? []) : []));
+		foreach ($this->listIndex($known) as $path) {
 			$packId = basename($path);
 			$present[$packId] = true;
 			$order[] = $packId;
@@ -104,6 +108,9 @@ final class BlobIndex {
 				$fetch[] = $path;
 			}
 		}
+		// only now: an empty listing that listIndex() refused leaves the index as it was
+		$this->blobs = [];
+		$this->loaded = $present;
 		// The rest is downloaded several at a time where the location allows it: on a large
 		// repository these are tens of thousands of small files. getMany() keeps their order, so
 		// the cached packs listed before each one are added first.
@@ -185,12 +192,80 @@ final class BlobIndex {
 		rewind($stream);
 		$this->backend->put('index/' . $packId, $stream);
 		$this->cachePut($packId, $entries);
+		$this->loaded[$packId] = true;
 		foreach ($entries as $e) {
 			$this->blobs[$e['id']] = [$packId, $e['offset'], $e['length'], $e['raw'], $e['flags']];
 			unset($this->pending[$e['id']]);
 		}
 	}
 
+	/**
+	 * Add the index files that appeared on the location since load(), such as those of packs
+	 * another server's cleanup wrote while a restore runs. Only adds and updates: a blob is
+	 * never dropped, as a listing that misses files (a connection that failed) must not make a
+	 * restore lose blobs it knows. A blob in a new pack takes that pack's place.
+	 */
+	public function refresh(): void {
+		$fetch = [];
+		$listed = 0;
+		foreach ($this->listIndex(array_keys($this->loaded)) as $path) {
+			$listed++;
+			if (!isset($this->loaded[basename($path)])) {
+				$fetch[] = $path;
+			}
+		}
+		$toCache = [];
+		foreach ($this->backend->getMany($fetch) as $path => $data) {
+			$packId = basename($path);
+			/** @var list<array{id:string, offset:int, length:int, raw:int, flags:int}> $entries authenticated: written by NG Backup */
+			$entries = json_decode($this->cipher->decryptString($data, 'index:' . $packId), true, 512, JSON_THROW_ON_ERROR);
+			$this->downloaded++;
+			$this->add($packId, $entries);
+			$this->loaded[$packId] = true;
+			$toCache[$packId] = $entries;
+		}
+		if ($toCache !== []) {
+			$this->cache?->putMany($this->repositoryId, $toCache);
+		}
+	}
+
+	/**
+	 * The index files on the location. An empty listing while index files are known ($known,
+	 * pack ids) is usually a connection that failed quietly; taken as is, it would empty the
+	 * index and the cache, make a check report every blob missing, or make a cleanup wipe the
+	 * cache. So the connection is checked (the repository's config must be there) and the folder
+	 * listed once more. Empty again, three of the known index files are looked up one by one:
+	 * only when they are gone too is the repository taken as empty (another server removed its
+	 * last snapshot and cleaned up). Even when that is wrong, nothing on the location is lost:
+	 * only this index and the cache are empty until the next load.
+	 *
+	 * @param list<string> $known
+	 * @return list<string>
+	 * @throws BackendException when the location does not answer as it should
+	 */
+	private function listIndex(array $known): array {
+		$paths = $this->backend->listFiles('index');
+		if ($paths !== [] || $known === []) {
+			return $paths;
+		}
+		if (!$this->backend->exists('config')) {
+			throw new BackendException('The location listed no index files and has no repository config: not trusting that listing');
+		}
+		$paths = $this->backend->listFiles('index');
+		if ($paths !== []) {
+			return $paths;
+		}
+		// spread over the list: first, middle and last (another server's cleanup removes packs
+		// here and there, not in this order)
+		$n = count($known);
+		foreach (array_unique([$known[0], $known[intdiv($n, 2)], $known[$n - 1]]) as $packId) {
+			if ($this->backend->exists('index/' . $packId)) {
+				throw new BackendException('The location listed no index files, while index/' . $packId . ' is there: not trusting that listing');
+			}
+		}
+		return [];
+	}
+
 	/** @return array<string, list<array{id:string, offset:int, length:int}>> packId => blobs currently located in that pack */
 	public function packs(): array {
 		$packs = [];
@@ -204,6 +279,7 @@ final class BlobIndex {
 	public function removePack(string $packId): void {
 		$this->backend->delete('index/' . $packId);
 		$this->cacheRemove([$packId]);
+		unset($this->loaded[$packId]);
 		foreach ($this->blobs as $id => $loc) {
 			if ($loc[0] === $packId) {
 				unset($this->blobs[$id]);

lib/Repository/PackReaderGuard.php

@@ -8,9 +8,10 @@ declare(strict_types=1);
 namespace OCA\NgBackup\Repository;
 
 use OCA\NgBackup\Backend\IBackend;
+use OCA\NgBackup\Backend\IReadsAhead;
 
 /** The location as Repository sees it: closes the PackReader's open stream before every other request. */
-final class PackReaderGuard implements IBackend {
+final class PackReaderGuard implements IBackend, IReadsAhead {
 	public function __construct(
 		private IBackend $inner,
 		private PackReader $reader,
@@ -38,6 +39,20 @@ final class PackReaderGuard implements IBackend {
 		return $this->inner->getRange($path, $offset, $length);
 	}
 
+	public function getRanges(array $ranges): \Generator {
+		$this->reader->close();
+		return $this->inner->getRanges($ranges);
+	}
+
+	public function canReadAhead(): bool {
+		return $this->inner instanceof IReadsAhead && $this->inner->canReadAhead();
+	}
+
+	/** Over connections of the location's own: the open stream may stay open. */
+	public function readAhead(array $ranges, string $spool): ?\Generator {
+		return $this->inner instanceof IReadsAhead ? $this->inner->readAhead($ranges, $spool) : null;
+	}
+
 	public function exists(string $path): bool {
 		$this->reader->close();
 		return $this->inner->exists($path);

lib/Repository/ReadAheadPlan.php

@@ -0,0 +1,123 @@
+<?php
+
+declare(strict_types=1);
+
+// SPDX-FileCopyrightText: 2026 Dillard Blom
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+namespace OCA\NgBackup\Repository;
+
+/**
+ * The ranges of packs a restore reads, in order, for IReadsAhead::readAhead(), and the reading of
+ * blobs from them as the restore goes.
+ *
+ * add() takes the blobs in the order the restore needs them. A blob in the same pack as the range
+ * before it, not before that range and at most GAP after its end, extends that range; anything
+ * else starts a new one. read() takes the same blobs in the same order: a blob is in the current
+ * range or in the next one, which then becomes current; a blob not in the plan is read elsewhere.
+ */
+final class ReadAheadPlan {
+	/** Unused bytes between two blobs of a pack that are read along rather than asked for apart. */
+	public const GAP = 4 * 1048576;
+	/** Longest range: packs are 32 MiB, repacked ones too. */
+	public const MAX_RANGE = 64 * 1048576;
+	/** Ranges after the current one that read() looks in for a blob. */
+	private const SEARCH = 16;
+
+	/** @var list<array{0:string, 1:int, 2:int}> [path, offset, length] */
+	private array $ranges = [];
+	/** @var \Generator<int, resource|null>|null */
+	private ?\Generator $streams = null;
+	private int $current = -1;
+	/** @var resource|null */
+	private $stream = null;
+
+	/** @param string $spool local folder for the ranges read ahead (see IReadsAhead::readAhead()) */
+	public function __construct(
+		public readonly string $spool,
+	) {
+	}
+
+	public function add(string $path, int $offset, int $length): void {
+		$last = array_pop($this->ranges);
+		if ($last !== null) {
+			[$p, $start, $len] = $last;
+			if ($p === $path && $offset >= $start && $offset <= $start + $len + self::GAP
+				&& $offset + $length - $start <= self::MAX_RANGE) {
+				$this->ranges[] = [$p, $start, max($len, $offset + $length - $start)];
+				return;
+			}
+			$this->ranges[] = $last;
+		}
+		$this->ranges[] = [$path, $offset, $length];
+	}
+
+	/** @return list<array{0:string, 1:int, 2:int}> */
+	public function ranges(): array {
+		return $this->ranges;
+	}
+
+	/** @param \Generator<int, resource|null> $streams what IReadsAhead::readAhead() gave for ranges() */
+	public function readFrom(\Generator $streams): void {
+		$this->streams = $streams;
+	}
+
+	/** The bytes of a blob, or null when its range could not be read ahead (read it the usual way). */
+	public function read(string $path, int $offset, int $length): ?string {
+		if ($this->streams === null) {
+			return null;
+		}
+		if (!$this->contains($this->current, $path, $offset, $length)) {
+			// Normally the next range. Further on when blobs before it were read elsewhere: the
+			// index was reloaded after another server's cleanup moved them to new packs.
+			$to = null;
+			for ($i = $this->current + 1; $i <= $this->current + self::SEARCH && $to === null; $i++) {
+				if ($this->contains($i, $path, $offset, $length)) {
+					$to = $i;
+				}
+			}
+			if ($to === null) {
+				return null; // not where the plan has it
+			}
+			if ($this->current < 0) {
+				$this->streams->current();
+				$this->current = 0;
+			}
+			while ($this->current < $to) {
+				$this->streams->next();
+				$this->current++;
+			}
+			$stream = $this->streams->valid() ? $this->streams->current() : null;
+			$this->stream = is_resource($stream) ? $stream : null;
+		}
+		$fh = $this->stream;
+		if ($fh === null || fseek($fh, $offset - $this->ranges[$this->current][1]) !== 0) {
+			return null;
+		}
+		$data = '';
+		while (strlen($data) < $length) {
+			$chunk = fread($fh, $length - strlen($data));
+			if ($chunk === false || $chunk === '') {
+				return null;
+			}
+			$data .= $chunk;
+		}
+		return $data;
+	}
+
+	/** Ends the reads ahead, also halfway: closes their streams and connections. */
+	public function close(): void {
+		$this->stream = null;
+		$streams = $this->streams;
+		$this->streams = null;
+		unset($streams); // the generator's finally blocks run when it is destroyed
+	}
+
+	private function contains(int $i, string $path, int $offset, int $length): bool {
+		if ($i < 0 || !isset($this->ranges[$i])) {
+			return false;
+		}
+		[$p, $start, $len] = $this->ranges[$i];
+		return $p === $path && $offset >= $start && $offset + $length <= $start + $len;
+	}
+}

lib/Repository/Repository.php

@@ -9,6 +9,7 @@ namespace OCA\NgBackup\Repository;
 
 use OCA\NgBackup\Backend\BackendException;
 use OCA\NgBackup\Backend\IBackend;
+use OCA\NgBackup\Backend\IReadsAhead;
 use OCA\NgBackup\Crypto\KeyRing;
 use OCA\NgBackup\Crypto\StreamCipher;
 
@@ -28,8 +29,14 @@ final class Repository {
 	public const FORMAT = 1;
 	public const BLOB_SIZE = 4 * 1048576;
 	private const FLAG_DEFLATE = 1;
+	/** Blobs from this size on get a quick compression test before the full compression. */
+	private const DEFLATE_PROBE_FROM = 256 * 1024;
+	/** Bytes of each of the three slices (start, middle, end) in that test. */
+	private const DEFLATE_PROBE_SLICE = 32 * 1024;
 	/** Reads per blob in a deep verify before it is reported as unreadable (not corrupted). */
 	private const VERIFY_READ_ATTEMPTS = 3;
+	/** Largest read that loadBlobs() makes of blobs that follow each other in a pack. */
+	private const MERGED_READ_MAX = 16 * 1048576;
 
 	private StreamCipher $cipher;
 	private BlobIndex $index;
@@ -65,6 +72,14 @@ final class Repository {
 		if ($backend->exists('config')) {
 			throw new RepositoryException('A repository already exists at this location');
 		}
+		// No config, but backup data: the config is missing (or could not be seen just now, a
+		// connection that failed). A new repository here would write a config over the one that
+		// opens this data; refuse instead.
+		foreach (['index', 'snapshots', 'trash/snapshots', 'catalog'] as $dir) {
+			if ($backend->listFiles($dir) !== []) {
+				throw new RepositoryException("This location holds backup data ($dir/) but no repository config could be read: not creating a new repository over it. Check the connection and the folder; a missing config can be restored from the recovery kit.");
+			}
+		}
 		$id = bin2hex(random_bytes(16));
 		$config = ['format' => self::FORMAT, 'id' => $id, 'created' => gmdate('c'), 'key' => $wrappedKey,
 			'check' => base64_encode((new StreamCipher($keys))->encryptString($id, 'config-check'))];
@@ -75,7 +90,8 @@ final class Repository {
 	}
 
 	/** Open with the master key the server holds (scheduled backups, no passphrase needed). */
-	public static function openWithKey(IBackend $backend, KeyRing $keys, ?IIndexCache $cache = null, ?ICatalogAnchor $anchor = null): self {
+	/** @param ?callable(int, int): void $progress index files downloaded so far, and in all (see BlobIndex::load()) */
+	public static function openWithKey(IBackend $backend, KeyRing $keys, ?IIndexCache $cache = null, ?ICatalogAnchor $anchor = null, ?callable $progress = null): self {
 		$config = self::readConfig($backend);
 		try {
 			$ok = isset($config['check']) && (new StreamCipher($keys))->decryptString((string)base64_decode($config['check'], true), 'config-check') === $config['id'];
@@ -89,7 +105,7 @@ final class Repository {
 		if ($cache !== null) {
 			$repo->index->setCache($cache, $config['id']);
 		}
-		$repo->index->load();
+		$repo->index->load(false, $progress);
 		$repo->loadCatalog($anchor);
 		return $repo;
 	}
@@ -209,6 +225,66 @@ final class Repository {
 		if ($prefix !== '' && !self::isSafePath(rtrim($prefix, '/'))) {
 			throw new RepositoryException('Invalid path prefix');
 		}
+		$plan = $this->readAhead($snapshotId, $prefix, $target);
+		try {
+			return $this->restoreEntries($snapshotId, $target, $prefix, $stripPrefix, $heartbeat, $plan);
+		} finally {
+			$plan?->close();
+			if ($plan !== null) {
+				@rmdir($plan->spool);
+			}
+		}
+	}
+
+	/**
+	 * Start reading the packs of a restore ahead, when the location can (IReadsAhead): a first
+	 * pass over the snapshot lists the ranges of packs it needs, in order. The spool is a
+	 * folder in the target, which has room for the restore anyway.
+	 */
+	private function readAhead(string $snapshotId, string $prefix, string $target): ?ReadAheadPlan {
+		if (!$this->backend instanceof IReadsAhead || !$this->backend->canReadAhead()) {
+			return null;
+		}
+		// what a restore that was stopped left behind: empty, its files were unlinked when opened
+		$stale = glob(rtrim($target, '/') . '/.ngb-restore-spool-*', GLOB_ONLYDIR);
+		foreach ($stale === false ? [] : $stale as $dir) {
+			@rmdir($dir);
+		}
+		$plan = new ReadAheadPlan(rtrim($target, '/') . '/.ngb-restore-spool-' . bin2hex(random_bytes(4)));
+		try {
+			foreach ($this->streamEntries($snapshotId) as $entry) {
+				if ($prefix !== '' && !str_starts_with($entry['p'], $prefix)) {
+					continue;
+				}
+				foreach ($entry['b'] as $id) {
+					try {
+						[$pack, $offset, $length] = $this->index->get($id);
+					} catch (RepositoryException) {
+						continue; // the restore reports it when it gets there
+					}
+					$plan->add('packs/' . substr($pack, 0, 2) . '/' . $pack, $offset, $length);
+				}
+			}
+		} catch (\Throwable) {
+			return null; // reading ahead is only faster: the restore itself reads the snapshot again and reports what is wrong
+		}
+		if (count($plan->ranges()) < 2 || (!is_dir($plan->spool) && !@mkdir($plan->spool, 0700, true))) {
+			return null;
+		}
+		try {
+			$streams = $this->backend->readAhead($plan->ranges(), $plan->spool);
+		} catch (\Throwable) {
+			$streams = null; // the usual reads report what is wrong
+		}
+		if ($streams === null) {
+			@rmdir($plan->spool);
+			return null;
+		}
+		$plan->readFrom($streams);
+		return $plan;
+	}
+
+	private function restoreEntries(string $snapshotId, string $target, string $prefix, bool $stripPrefix, ?callable $heartbeat, ?ReadAheadPlan $plan): int {
 		$count = 0;
 		foreach ($this->streamEntries($snapshotId) as $entry) {
 			if ($prefix !== '' && !str_starts_with($entry['p'], $prefix)) {
@@ -233,7 +309,7 @@ final class Repository {
 				throw new RepositoryException('Cannot create a temporary file for ' . $entry['p']);
 			}
 			foreach ($entry['b'] as $id) {
-				fwrite($out, $this->loadBlob($id));
+				fwrite($out, $this->restoreBlob($id, $plan));
 				if ($heartbeat !== null) {
 					$heartbeat();
 				}
@@ -288,8 +364,8 @@ final class Repository {
 	 */
 	public function readLines(array $blobIds): \Generator {
 		$carry = '';
-		foreach ($blobIds as $id) {
-			$data = $carry . $this->loadBlob($id);
+		foreach ($this->loadBlobs($blobIds) as $blob) {
+			$data = $carry . $blob;
 			$lines = explode("\n", $data);
 			$carry = array_pop($lines);
 			yield from $lines;
@@ -701,7 +777,7 @@ final class Repository {
 		}
 		$flags = 0;
 		$payload = $data;
-		$deflated = gzdeflate($data, 6);
+		$deflated = self::worthDeflating($data) ? gzdeflate($data, 6) : false;
 		if ($deflated !== false && strlen($deflated) < strlen($data) * 0.95) {
 			$payload = $deflated;
 			$flags |= self::FLAG_DEFLATE;
@@ -711,9 +787,116 @@ final class Repository {
 		return $id;
 	}
 
+	/**
+	 * Photos, video and archives are compressed already: deflating them takes most of a backup's
+	 * CPU time (about 24 MiB/s) only to be thrown away, as it saves less than the 5% that keeps
+	 * it. A fast deflate of three small slices tells first; below 10% savings there, the full
+	 * deflate is skipped.
+	 */
+	private static function worthDeflating(string $data): bool {
+		$n = strlen($data);
+		if ($n < self::DEFLATE_PROBE_FROM) {
+			return true;
+		}
+		$k = self::DEFLATE_PROBE_SLICE;
+		$probe = substr($data, 0, $k) . substr($data, intdiv($n - $k, 2), $k) . substr($data, $n - $k);
+		$deflated = gzdeflate($probe, 1);
+		return $deflated !== false && strlen($deflated) * 10 < strlen($probe) * 9;
+	}
+
+	/**
+	 * Blobs spread over many packs (the tree segments of a run, one per step), through
+	 * IBackend::getRanges(): on a remote location one at a time is a round trip each, which for
+	 * a long run made writing its snapshot take a quarter of an hour. Blobs that follow each
+	 * other in a pack are read as one range.
+	 *
+	 * @param list<string> $ids
+	 * @return \Generator<int, string> verified blob contents, in order
+	 */
+	private function loadBlobs(array $ids): \Generator {
+		/** @var list<array{0:string, 1:int, 2:int}> $ranges [path, offset, length] of each read */
+		$ranges = [];
+		/** @var list<list<array{0:string, 1:int, 2:int}>> $parts per read: [blob id, offset in the read, length] */
+		$parts = [];
+		// the read being extended
+		$curPath = null;
+		$curOffset = 0;
+		$curLength = 0;
+		$curParts = [];
+		foreach ($ids as $id) {
+			[$pack, $offset, $length] = $this->index->get($id);
+			$path = 'packs/' . substr($pack, 0, 2) . '/' . $pack;
+			if ($curPath === $path && $curOffset + $curLength === $offset && $curLength + $length <= self::MERGED_READ_MAX) {
+				$curParts[] = [$id, $curLength, $length];
+				$curLength += $length;
+				continue;
+			}
+			if ($curPath !== null) {
+				$ranges[] = [$curPath, $curOffset, $curLength];
+				$parts[] = $curParts;
+			}
+			[$curPath, $curOffset, $curLength, $curParts] = [$path, $offset, $length, [[$id, 0, $length]]];
+		}
+		if ($curPath !== null) {
+			$ranges[] = [$curPath, $curOffset, $curLength];
+			$parts[] = $curParts;
+		}
+		$done = 0;
+		try {
+			foreach ($this->backend->getRanges($ranges) as $i => $data) {
+				foreach ($parts[$i] as [$id, $at, $length]) {
+					yield $this->decodeBlob($id, substr($data, $at, $length));
+					$done++;
+				}
+			}
+		} catch (BackendException) {
+			// A pack moved, or the read failed for a while (see loadBlob()): the rest one blob at a
+			// time, each read once more after a failure.
+			foreach (array_slice($ids, $done) as $id) {
+				yield $this->loadBlob($id);
+			}
+		}
+	}
+
+	/** A blob for restore(): read ahead when it could be, otherwise (or when that copy is bad) the usual way. */
+	private function restoreBlob(string $id, ?ReadAheadPlan $plan): string {
+		if ($plan !== null) {
+			[$pack, $offset, $length] = $this->index->get($id);
+			$encrypted = $plan->read('packs/' . substr($pack, 0, 2) . '/' . $pack, $offset, $length);
+			if ($encrypted !== null) {
+				try {
+					return $this->decodeBlob($id, $encrypted);
+				} catch (\Exception) {
+					// read again from the location below, which reports what is wrong
+				}
+			}
+		}
+		return $this->loadBlob($id);
+	}
+
 	private function loadBlob(string $id): string {
 		[$pack, $offset, $length] = $this->index->get($id);
-		return $this->decodeBlob($id, $this->packReader->read($pack, $offset, $length));
+		try {
+			$encrypted = $this->packReader->read($pack, $offset, $length);
+		} catch (BackendException $e) {
+			// Another server's cleanup may have repacked this blob into a new pack since the index
+			// was loaded (a disaster recovery test while the original server still runs): add the
+			// new index files, and read the blob where it is now. Or the read failed for a while
+			// (a connection that died; the backend has replaced it by now): then read it once
+			// more where it was. A second failure is the real one.
+			try {
+				$this->index->refresh();
+			} catch (\Throwable) {
+				// the location could not be listed either: read again where the blob was
+			}
+			[$moved, $offset, $length] = $this->index->get($id);
+			try {
+				$encrypted = $this->packReader->read($moved, $offset, $length);
+			} catch (BackendException) {
+				throw $e;
+			}
+		}
+		return $this->decodeBlob($id, $encrypted);
 	}
 
 	/** Decrypts and checks a blob read from its pack; throws when it is corrupted or tampered with. */

lib/Service/BackupService.php

@@ -225,6 +225,9 @@ final class BackupService {
 			} else {
 				$state['files']['estimate'] ??= $this->estimateBytes($run, $state['files']);
 				$state['files'] = BackupRun::step($repo, $state['files'], $deadline);
+				if (in_array($state['files']['phase'], ['finish', 'commit'], true)) {
+					$run->setPhase('commit'); // all files read: writing and recording the snapshot
+				}
 				if ($state['files']['phase'] === 'commit') {
 					// Catalog write under the catalog lock, from a repository opened inside it: a per-user
 					// export or restore may have written the catalog since this step opened $repo.

lib/Service/KeyService.php

@@ -31,6 +31,11 @@ final class KeyService {
 	private const KEY_KIT_VERSION = 'recovery_kit_version';
 	private const KEY_KIT_CODE = 'recovery_kit_code';
 	public const DEFAULT_DELETE_DELAY = 7;
+	/**
+	 * The location holds the passphrase-wrapped key too, so whoever can read it can try
+	 * passphrases offline: the passphrase is what really protects the backups.
+	 */
+	public const MIN_PASSPHRASE = 16;
 
 	private ?KeyRing $cached = null;
 
@@ -56,9 +61,7 @@ final class KeyService {
 		if ($this->isInitialized()) {
 			throw new \RuntimeException('A backup key already exists');
 		}
-		if (strlen($passphrase) < 12) {
-			throw new \InvalidArgumentException('The passphrase must be at least 12 characters');
-		}
+		self::checkPassphrase($passphrase);
 		$keys = KeyRing::generate();
 		$this->appConfig->setValueString(Application::APP_ID, self::KEY_MASTER,
 			$this->crypto->encrypt(base64_encode($keys->exportMasterKey())), true, true);
@@ -234,8 +237,8 @@ final class KeyService {
 	}
 
 	private static function checkPassphrase(string $passphrase): void {
-		if (strlen($passphrase) < 12) {
-			throw new \InvalidArgumentException('The passphrase must be at least 12 characters');
+		if (strlen($passphrase) < self::MIN_PASSPHRASE) {
+			throw new \InvalidArgumentException('The passphrase must be at least ' . self::MIN_PASSPHRASE . ' characters');
 		}
 	}
 

lib/Service/RestoreFullService.php

@@ -27,9 +27,14 @@ final class RestoreFullService {
 	 * Config keys that must keep pointing at THIS installation's actual, already-working
 	 * database and data directory (set by occ maintenance:install), never at the old server's.
 	 */
+	/** App setting: when a full restore started that has not completed (see restoreFull()). */
+	private const INTERRUPTED_KEY = 'restore_full_started';
+
 	private const CONNECTION_KEYS = [
 		'dbtype', 'dbhost', 'dbport', 'dbname', 'dbuser', 'dbpassword', 'dbpersistent',
 		'dbtableprefix', 'dbdriveroptions', 'datadirectory',
+		// set by restoreFull() itself for the length of the restore
+		'maintenance',
 	];
 
 	public function __construct(
@@ -43,34 +48,93 @@ final class RestoreFullService {
 	) {
 	}
 
+	/** Apps that only exist in a particular setup and are never needed elsewhere. */
+	private const ENVIRONMENT_APPS = ['nextcloud-aio'];
+
 	/**
-	 * Whether this installation can receive $snapshotId: same Nextcloud major version, and every
-	 * app that was enabled at backup time already installed here (its tables must exist before
-	 * the database restore can write into them).
+	 * Whether this installation can receive $snapshotId, all problems at once:
+	 * - the same Nextcloud major version is required;
+	 * - apps that were enabled at backup time but are not here (they work again once installed);
+	 * - tables in the backup that do not exist here: a backup made from 1.0.0-rc.2 on records
+	 *   their structure and the restore creates them, an older one cannot (missingTables).
 	 *
-	 * @return array{ok:bool, currentMajor:string, snapshotMajor:string, missingApps:list<string>}
+	 * @return array{ok:bool, currentMajor:string, snapshotMajor:string, missingApps:list<string>, missingTables:list<string>}
 	 */
-	public function checkCompatibility(Target $target, string $snapshotId): array {
-		$meta = $this->targets->repository($target)->snapshotMeta($snapshotId);
+	public function checkCompatibility(Target $target, string $snapshotId, bool $skipMissingTables = false): array {
+		$repo = $this->targets->repository($target);
+		$meta = $repo->snapshotMeta($snapshotId);
 		$currentMajor = explode('.', $this->config->getSystemValueString('version'))[0];
 		$snapshotMajor = explode('.', (string)($meta['nextcloud'] ?? ''))[0];
 		$enabled = array_flip($this->appManager->getEnabledApps());
-		$missingApps = array_values(array_diff(array_keys($meta['apps'] ?? []), array_keys($enabled)));
+		$missingApps = array_values(array_diff(array_keys($meta['apps'] ?? []), array_keys($enabled), self::ENVIRONMENT_APPS));
+		$missingTables = [];
+		$prefixMismatch = null;
+		if (isset($meta['db'])) {
+			$manifest = json_decode($repo->getObject($meta['db']), true, 512, JSON_THROW_ON_ERROR);
+			$prefix = $this->config->getSystemValueString('dbtableprefix', 'oc_');
+			$sourcePrefix = DbDumper::dumpPrefix($manifest);
+			if ($sourcePrefix !== null && $sourcePrefix !== $prefix) {
+				$prefixMismatch = [$sourcePrefix, $prefix];
+			}
+			$dumper = new DbDumper($this->db->getInner(), $prefix);
+			$missingTables = array_values(array_filter($dumper->missingTables($manifest),
+				fn (string $t) => !isset($manifest['tables'][$t]['schema']) && !str_starts_with($t, $prefix . 'ngb_')));
+		}
 		return [
-			'ok' => $currentMajor === $snapshotMajor && $missingApps === [],
+			'ok' => $currentMajor === $snapshotMajor && $prefixMismatch === null && ($missingTables === [] || $skipMissingTables),
 			'currentMajor' => $currentMajor,
 			'snapshotMajor' => $snapshotMajor,
 			'missingApps' => $missingApps,
+			'missingTables' => $prefixMismatch === null ? $missingTables : [],
+			'prefixMismatch' => $prefixMismatch,
 		];
 	}
 
-	/** @return array{dbReport:array, dataFiles:int, configKeys:int, dbConsistent:bool} */
-	public function restoreFull(Target $target, string $snapshotId): array {
-		$check = $this->checkCompatibility($target, $snapshotId);
+	/** @return array{dbReport:array, dataFiles:int, configKeys:int, dbConsistent:bool, missingApps:list<string>, maintenanceLeftOn:bool} */
+	public function restoreFull(Target $target, string $snapshotId, bool $skipMissingTables = false): array {
+		// Maintenance mode for the whole restore: background jobs (cron.php stops in maintenance
+		// mode), page visits (AJAX cron) and users must not write into tables or the data
+		// directory while they are being replaced; a row written in between would collide with a
+		// restored one or be silently lost. Switched off after a restore that completed. After an
+		// error it stays on: the instance may be partly restored, and must not be used like that.
+		// occ only offers app commands outside maintenance mode, so the admin switches it off
+		// right before running the restore again (see RestoreFull). Already on before: left on.
+		// On before the checks below, so that a run again after an error leaves the partly
+		// restored instance open for seconds at most; off again when they refuse (nothing changed).
+		// A marker in ng_backup's own app settings (which the restore keeps) says a restore started
+		// and did not complete: then the instance may be partly restored, and a check that refuses
+		// a run again must not open it.
+		$appConfig = \OCP\Server::get(\OCP\IAppConfig::class);
+		$interrupted = $appConfig->getValueInt(\OCA\NgBackup\AppInfo\Application::APP_ID, self::INTERRUPTED_KEY, 0) > 0;
+		$wasInMaintenance = $this->config->getSystemValueBool('maintenance', false);
+		$this->config->setSystemValue('maintenance', true);
+		$reopen = function () use ($wasInMaintenance, $interrupted): void {
+			if (!$wasInMaintenance && !$interrupted) {
+				$this->config->setSystemValue('maintenance', false);
+			}
+		};
+		try {
+			$check = $this->checkCompatibility($target, $snapshotId, $skipMissingTables);
+		} catch (\Throwable $e) {
+			$reopen();
+			throw $e;
+		}
 		if (!$check['ok']) {
+			$reopen();
 			throw new \RuntimeException($this->describeBlockers($check));
 		}
-		return $this->withSharedLock($target, function (callable $refresh) use ($target, $snapshotId) {
+		$appConfig->setValueInt(\OCA\NgBackup\AppInfo\Application::APP_ID, self::INTERRUPTED_KEY, time());
+		$result = $this->restoreInMaintenance($target, $snapshotId, $skipMissingTables, $check);
+		$appConfig->deleteKey(\OCA\NgBackup\AppInfo\Application::APP_ID, self::INTERRUPTED_KEY);
+		if (!$wasInMaintenance) {
+			$this->config->setSystemValue('maintenance', false);
+		}
+		return $result + ['maintenanceLeftOn' => $wasInMaintenance];
+	}
+
+	/** @return array{dbReport:array, dataFiles:int, configKeys:int, dbConsistent:bool, missingApps:list<string>} */
+	private function restoreInMaintenance(Target $target, string $snapshotId, bool $skipMissingTables, array $check): array {
+		return $this->withSharedLock($target, function (callable $refresh) use ($target, $snapshotId, $skipMissingTables, $check) {
 			$beat = LeaseService::throttled($refresh);
 			$repo = $this->targets->repository($target);
 			$meta = $repo->snapshotMeta($snapshotId);
@@ -102,7 +166,7 @@ final class RestoreFullService {
 				$ownAppConfig = $this->preserveOwnAppConfig();
 				$dumper = new DbDumper($this->db->getInner(), $prefix);
 				try {
-					$dumper->restore($repo, $manifest, $dbReport, $beat);
+					$dumper->restore($repo, $manifest, $dbReport, $beat, $skipMissingTables);
 				} finally {
 					$this->restoreOwnAppConfig($ownAppConfig);
 				}
@@ -125,8 +189,8 @@ final class RestoreFullService {
 				);
 			}
 
-			return ['dbReport' => $dbReport ?? ['skipped' => [], 'restored' => []], 'dataFiles' => $dataFiles, 'configKeys' => count($backupConfig),
-				'dbConsistent' => (bool)($manifest['consistent'] ?? true)];
+			return ['dbReport' => $dbReport ?? ['skipped' => [], 'restored' => [], 'created' => [], 'missing' => []], 'dataFiles' => $dataFiles, 'configKeys' => count($backupConfig),
+				'dbConsistent' => (bool)($manifest['consistent'] ?? true), 'missingApps' => $check['missingApps']];
 		});
 	}
 
@@ -209,11 +273,15 @@ final class RestoreFullService {
 		if ($check['currentMajor'] !== $check['snapshotMajor']) {
 			$parts[] = "this installation is Nextcloud {$check['currentMajor']}, the backup is from {$check['snapshotMajor']} (same major version required)";
 		}
-		if ($check['missingApps'] !== []) {
-			$parts[] = 'install these apps first (their tables must exist before the database restore can use them): '
-				. implode(', ', array_map(fn (string $a) => "occ app:install $a", $check['missingApps']));
+		if (($check['prefixMismatch'] ?? null) !== null) {
+			[$source, $here] = $check['prefixMismatch'];
+			$parts[] = "the backup's tables use the prefix '$source', this installation '$here': install Nextcloud again with 'dbtableprefix' => '$source' in config/config.php before occ maintenance:install, and restore again";
 		}
-		return implode('; ', $parts);
+		if ($check['missingTables'] !== []) {
+			$prefix = $this->config->getSystemValueString('dbtableprefix', 'oc_');
+			$parts[] = DbDumper::describeMissing($check['missingTables'], $prefix);
+		}
+		return implode("\n", $parts);
 	}
 
 	private function withSharedLock(Target $target, callable $fn): mixed {

lib/Service/TargetService.php

@@ -48,15 +48,16 @@ final class TargetService {
 	 * installation's key), then save it.
 	 *
 	 * @param array<string, mixed> $options
+	 * @param ?callable(int, int): void $progress reading an existing repository's index: files done, and in all
 	 * @return array{target: Target, created: bool}
 	 */
-	public function add(string $name, string $backend, string $auth, array $options, string $basePath): array {
+	public function add(string $name, string $backend, string $auth, array $options, string $basePath, ?callable $progress = null): array {
 		$this->validateName($name);
 		$this->requireUsableBackend($backend);
 		$keys = $this->keys->keyRing();
 		$storageBackend = $this->buildBackend($backend, $auth, $options, $basePath);
 		if ($storageBackend->exists('config')) {
-			$repo = Repository::openWithKey($storageBackend, $keys, $this->indexCache, $this->anchor);
+			$repo = Repository::openWithKey($storageBackend, $keys, $this->indexCache, $this->anchor, $progress);
 			$created = false;
 		} else {
 			$repo = Repository::initWithKey($storageBackend, $keys, $this->keys->wrappedKey(), $this->anchor);
@@ -227,7 +228,8 @@ final class TargetService {
 				$s->setFiles((int)($meta['stats']['files'] ?? 0));
 				$s->setBytes((int)($meta['stats']['bytes'] ?? 0));
 				$this->snapshots->insert($s);
-			} catch (\Throwable) {
+			} catch (\Throwable $e) {
+				Server::get(\Psr\Log\LoggerInterface::class)->warning('NG Backup: snapshot ' . $snapshotId . ' on ' . $target->getName() . ' not listed: ' . $e->getMessage(), ['exception' => $e]);
 			}
 		}
 	}
@@ -259,6 +261,11 @@ final class TargetService {
 	/** Remove the target from NG Backup. The backups on the target itself are not touched. */
 	public function remove(Target $target): void {
 		$this->mapper->delete($target);
+		// The cached index of its repository is only of use while a location points at it
+		$repositoryId = $target->getRepositoryId();
+		if ($repositoryId !== null && !array_filter($this->list(), fn (Target $t) => $t->getRepositoryId() === $repositoryId)) {
+			$this->indexCache->forget($repositoryId);
+		}
 	}
 
 	public function backend(Target $target): IBackend {
@@ -281,7 +288,10 @@ final class TargetService {
 
 	private function buildBackend(string $backend, string $auth, array $options, string $basePath, bool $createBase = true): StorageBackend {
 		$create = fn (): IStorage => $this->factory()->create($backend, $auth, $options);
-		return new StorageBackend($create(), $basePath, $createBase, $create);
+		$storage = new StorageBackend($create(), $basePath, $createBase, $create);
+		$storage->readAheadConnections = Server::get(\OCP\IAppConfig::class)
+			->getValueInt('ng_backup', 'restore_sftp_connections', \OCA\NgBackup\Backend\SftpRangeFetcher::DEFAULT_CONNECTIONS);
+		return $storage;
 	}
 
 	private ?ExternalStorageFactory $factory = null;

lib/Service/VerifyService.php

@@ -64,7 +64,7 @@ final class VerifyService {
 				$age < 120 ? $age . ' s' : intdiv($age, 60) . ' min',
 				$age > 600 ? ' (no progress for a while: the process may have stopped)' : '');
 		}
-		$took = gmdate('H:i:s', max(0, (int)($s['finished'] ?? 0) - (int)($s['started'] ?? 0)));
+		$took = \OCA\NgBackup\Format::duration((int)($s['finished'] ?? 0) - (int)($s['started'] ?? 0));
 		return match ($s['status'] ?? '') {
 			'ok' => sprintf('%s OK on %s (took %s): %s files, %s blobs%s', $kind, date('Y-m-d H:i', (int)$s['finished']), $took,
 				number_format((int)($s['files'] ?? 0)), number_format((int)($s['blobs'] ?? 0)), $deep ? ', ' . $size((int)($s['bytes'] ?? 0)) . ' decrypted' : ''),

psalm-baseline.xml

@@ -153,10 +153,6 @@
     </PossiblyFalseArgument>
   </file>
   <file src="lib/Db/DbDumper.php">
-    <InvalidArrayOffset>
-      <code><![CDATA[$info['sha256']]]></code>
-      <code><![CDATA[$manifest['sequences']]]></code>
-    </InvalidArrayOffset>
     <MissingClosureReturnType>
       <code><![CDATA[fn ($c) => $end[array_search($c, $columns, true)]]]></code>
       <code><![CDATA[fn ($c) => $q($c)]]></code>
@@ -189,6 +185,12 @@
       <code><![CDATA[$this->db]]></code>
       <code><![CDATA[$this->db]]></code>
       <code><![CDATA[$this->db]]></code>
+      <code><![CDATA[$this->db]]></code>
+      <code><![CDATA[$this->db]]></code>
+      <code><![CDATA[$this->db]]></code>
+      <code><![CDATA[$this->db]]></code>
+      <code><![CDATA[$this->db]]></code>
+      <code><![CDATA[$this->db]]></code>
       <code><![CDATA[TransactionIsolationLevel]]></code>
       <code><![CDATA[\Doctrine\DBAL\ParameterType]]></code>
       <code><![CDATA[\Doctrine\DBAL\ParameterType]]></code>
@@ -196,6 +198,11 @@
       <code><![CDATA[\Doctrine\DBAL\Platforms\PostgreSQLPlatform]]></code>
       <code><![CDATA[\Doctrine\DBAL\Platforms\PostgreSQLPlatform]]></code>
       <code><![CDATA[\Doctrine\DBAL\Platforms\PostgreSQLPlatform]]></code>
+      <code><![CDATA[\Doctrine\DBAL\Platforms\PostgreSQLPlatform]]></code>
+      <code><![CDATA[\Doctrine\DBAL\Schema\ForeignKeyConstraint]]></code>
+      <code><![CDATA[\Doctrine\DBAL\Schema\Table]]></code>
+      <code><![CDATA[\Doctrine\DBAL\Schema\Table]]></code>
+      <code><![CDATA[\Doctrine\DBAL\Schema\Table]]></code>
       <code><![CDATA[\Doctrine\DBAL\Schema\Table]]></code>
       <code><![CDATA[\Doctrine\DBAL\Schema\Table]]></code>
       <code><![CDATA[\Doctrine\DBAL\Schema\Table]]></code>
@@ -218,16 +225,11 @@
     </PropertyNotSetInConstructor>
   </file>
   <file src="lib/Job/BackupRun.php">
-    <ArgumentTypeCoercion>
-      <code><![CDATA[$blobs]]></code>
-    </ArgumentTypeCoercion>
     <MissingParamType>
       <code><![CDATA[$fh]]></code>
     </MissingParamType>
     <PossiblyUndefinedArrayOffset>
       <code><![CDATA[$mtime]]></code>
-      <code><![CDATA[$state['phase']]]></code>
-      <code><![CDATA[$state['stats']]]></code>
     </PossiblyUndefinedArrayOffset>
   </file>
   <file src="lib/Job/ParentCursor.php">
@@ -443,6 +445,7 @@
     </EmptyArrayAccess>
     <UndefinedInterfaceMethod>
       <code><![CDATA[getInner]]></code>
+      <code><![CDATA[getInner]]></code>
     </UndefinedInterfaceMethod>
     <UnresolvableInclude>
       <code><![CDATA[include $path]]></code>

src/AdminSettings.vue

@@ -6,6 +6,10 @@
 	<div class="ng-backup">
 		<NcSettingsSection :name="t('ng_backup', 'NG Backup')"
 			:description="t('ng_backup', 'Encrypted, incremental backups of this Nextcloud (database, configuration and data). Backup locations are never mounted and are not visible in Files.')">
+			<p class="ngb-feedback">
+				{{ t('ng_backup', 'NG Backup is in beta. We would like to hear how it works for you, also when everything went fine.') }}
+				<a :href="feedbackUrl" target="_blank" rel="noopener noreferrer">{{ t('ng_backup', 'Share your experience ↗') }}</a>
+			</p>
 			<NcLoadingIcon v-if="!status" :size="32" />
 			<NcNoteCard v-if="error" type="error">{{ error }}</NcNoteCard>
 		</NcSettingsSection>
@@ -22,7 +26,7 @@
 			</template>
 			<template v-else-if="status.key.everConfirmed">
 				<template v-if="status.targets.length">
-					<Backups :status="status" @changed="refresh" />
+					<Backups :status="status" :all-runs="allRuns" @changed="refresh" @show-all-runs="showAllRuns" />
 					<RestoreBrowser :status="status" @changed="refresh" />
 				</template>
 				<NcNoteCard v-else type="info">{{ t('ng_backup', 'Add a backup location under "Settings" first.') }}</NcNoteCard>
@@ -45,15 +49,24 @@ import KeySetup from './components/KeySetup.vue'
 import Locations from './components/Locations.vue'
 import RestoreBrowser from './components/RestoreBrowser.vue'
 
+// Opens the experience report form in .github/ISSUE_TEMPLATE
+const feedbackUrl = 'https://github.com/dillardblom/ng_backup/issues/new?template=experience.yml'
+
 const status = ref(null)
+const allRuns = ref(false) // runs older than the last days too
 const error = ref('')
 const tab = ref('settings')
 let tabInitialized = false
 let timer = null
 
+function showAllRuns(all) {
+	allRuns.value = all
+	refresh()
+}
+
 async function refresh() {
 	try {
-		status.value = await api.status()
+		status.value = await api.status(allRuns.value)
 		error.value = ''
 		// Default to the daily-use tab once the key is set up; stay on Settings otherwise.
 		// Only decided on first load, so switching tabs ourselves isn't undone by polling.
@@ -79,6 +92,14 @@ onBeforeUnmount(() => clearTimeout(timer))
 .ng-backup :deep(.settings-section) {
 	max-width: 900px;
 }
+.ngb-feedback {
+	color: var(--color-text-maxcontrast);
+	margin-bottom: 12px;
+}
+.ngb-feedback a {
+	color: var(--color-primary-element);
+	text-decoration: underline;
+}
 .ngb-tabs {
 	display: flex;
 	gap: 8px;

src/api.js

@@ -16,7 +16,7 @@ async function call(method, path, data) {
 }
 
 export default {
-	status: () => call('get', '/status'),
+	status: (allRuns = false) => call('get', '/status', allRuns ? { allRuns: true } : undefined),
 	initKey: (passphrase, deleteDelayDays, label) => call('post', '/key', { passphrase, deleteDelayDays, label }),
 	addSlot: (passphrase, label) => call('post', '/key/slots', { passphrase, label }),
 	replaceSlot: (slot, passphrase, label) => call('put', `/key/slots/${slot}`, { passphrase, label }),

src/components/Backups.vue

@@ -22,8 +22,8 @@
 				<p class="ngb-muted">{{ t('ng_backup', 'Removed restore points can be brought back until they are deleted permanently.') }}</p>
 				<ul>
 					<li v-for="item in trash[target.id]" :key="item.id">
-						{{ item.time ? new Date(item.time).toLocaleString() : item.id }}{{ item.label ? ' – ' + item.label : '' }}
-						<span class="ngb-muted">{{ t('ng_backup', 'removed by {by}, deleted after {date}', { by: item.by, date: new Date(item.deleteAfter * 1000).toLocaleDateString() }) }}</span>
+						{{ item.time ? formatDateTime(item.time) : item.id }}{{ item.label ? ' – ' + item.label : '' }}
+						<span class="ngb-muted">{{ t('ng_backup', 'removed by {by}, deleted after {date}', { by: item.by, date: formatDate(item.deleteAfter) }) }}</span>
 						<NcButton variant="tertiary" @click="untrash(target, item)">{{ t('ng_backup', 'Restore') }}</NcButton>
 					</li>
 				</ul>
@@ -46,10 +46,10 @@
 				</thead>
 				<tbody>
 					<tr v-for="run in status.runs" :key="run.id" :title="run.error || ''">
-						<td>{{ new Date(run.startedAt * 1000).toLocaleString() }}</td>
+						<td>{{ formatDateTime(run.startedAt) }}</td>
 						<td>{{ targetName(run.targetId) }}</td>
 						<td>{{ run.kind }}</td>
-						<td>{{ run.snapshot ? new Date(run.snapshot.createdAt * 1000).toLocaleString() + (run.snapshot.label ? ' – ' + run.snapshot.label : '') : '' }}</td>
+						<td>{{ run.snapshot ? formatDateTime(run.snapshot.createdAt) + (run.snapshot.label ? ' – ' + run.snapshot.label : '') : '' }}</td>
 						<td :class="'ngb-' + run.status">{{ run.status }}{{ run.status === 'running' ? ' (' + run.phase + percent(run) + ')' : '' }}{{ run.error ? ': ' + run.error : '' }}</td>
 						<td>{{ run.stats?.files?.files ?? run.stats?.restored ?? '' }}</td>
 						<td>{{ run.stats?.files ? formatSize(run.stats.files.bytes) : '' }}</td>
@@ -58,23 +58,33 @@
 				</tbody>
 			</table>
 		</div>
+		<p v-if="allRuns || status.olderRuns" class="ngb-muted">
+			<template v-if="allRuns">
+				{{ t('ng_backup', 'All runs.') }}
+				<NcButton variant="tertiary" @click="emit('show-all-runs', false)">{{ n('ng_backup', 'Only the last day', 'Only the last %n days', status.recentDays) }}</NcButton>
+			</template>
+			<template v-else>
+				{{ n('ng_backup', 'Runs of the last day.', 'Runs of the last %n days.', status.recentDays) }}
+				<NcButton variant="tertiary" @click="emit('show-all-runs', true)">{{ n('ng_backup', 'Show %n older run', 'Show %n older runs', status.olderRuns) }}</NcButton>
+			</template>
+		</p>
 	</NcSettingsSection>
 </template>
 
 <script setup>
 import { ref, watch } from 'vue'
-import { t } from '@nextcloud/l10n'
+import { n, t } from '@nextcloud/l10n'
 import NcButton from '@nextcloud/vue/components/NcButton'
 import NcNoteCard from '@nextcloud/vue/components/NcNoteCard'
 import NcSettingsSection from '@nextcloud/vue/components/NcSettingsSection'
 import NcTextField from '@nextcloud/vue/components/NcTextField'
 import api from '../api.js'
-import { formatSize } from '../format.js'
+import { formatDateTime, formatDate, formatSize } from '../format.js'
 import { confirmPassword } from '@nextcloud/password-confirmation'
 import { reactive } from 'vue'
 
-const props = defineProps({ status: { type: Object, required: true } })
-const emit = defineEmits(['changed'])
+const props = defineProps({ status: { type: Object, required: true }, allRuns: { type: Boolean, default: false } })
+const emit = defineEmits(['changed', 'show-all-runs'])
 const schedule = ref(props.status.schedule)
 const error = ref('')
 watch(() => props.status.schedule, (s) => { schedule.value = s })

src/components/KeySetup.vue

@@ -8,13 +8,13 @@
 		<!-- 1. Create the key -->
 		<form v-if="!status.key.initialized" class="ngb-form" @submit.prevent="createKey">
 			<NcTextField v-model="label" :label="t('ng_backup', 'Who keeps this passphrase (e.g. Safe, CTO)')" />
-			<NcPasswordField v-model="pass1" :label="t('ng_backup', 'Passphrase (at least 12 characters)')" autocomplete="new-password" />
+			<NcPasswordField v-model="pass1" :label="t('ng_backup', 'Passphrase (at least 16 characters)')" autocomplete="new-password" />
 			<NcPasswordField v-model="pass2" :label="t('ng_backup', 'Repeat passphrase')" autocomplete="new-password"
 				:error="pass2 !== '' && pass1 !== pass2" :helper-text="pass2 !== '' && pass1 !== pass2 ? t('ng_backup', 'The passphrases do not match') : ''" />
 			<NcTextField v-model="delay" type="number" min="1" max="365"
 				:label="t('ng_backup', 'Days a removed backup stays in the trash before it is really deleted')"
 				:helper-text="t('ng_backup', 'Protects against a malicious or mistaken cleanup. Cannot be changed later.')" />
-			<NcButton type="submit" variant="primary" :disabled="busy || pass1.length < 12 || pass1 !== pass2 || !(delay >= 1 && delay <= 365)">
+			<NcButton type="submit" variant="primary" :disabled="busy || pass1.length < 16 || pass1 !== pass2 || !(delay >= 1 && delay <= 365)">
 				{{ t('ng_backup', 'Create backup key') }}
 			</NcButton>
 		</form>
@@ -35,7 +35,7 @@
 					<tr v-for="slot in status.key.slots" :key="slot.slot">
 						<td>{{ t('ng_backup', 'Slot {n}', { n: slot.slot }) }}</td>
 						<td><strong>{{ slot.label }}</strong></td>
-						<td class="ngb-muted">{{ slot.created ? new Date(slot.created * 1000).toLocaleDateString() : '' }}</td>
+						<td class="ngb-muted">{{ slot.created ? formatDate(slot.created) : '' }}</td>
 						<td class="ngb-actions">
 							<NcButton variant="tertiary" @click="openSlotForm(slot)">{{ t('ng_backup', 'New passphrase') }}</NcButton>
 							<NcButton v-if="status.key.slots.length > 1" variant="tertiary" @click="removeSlot(slot)">{{ t('ng_backup', 'Remove') }}</NcButton>
@@ -46,10 +46,10 @@
 			<NcButton v-if="!slotForm && status.key.slots.length < status.key.maxSlots" @click="openSlotForm(null)">{{ t('ng_backup', 'Add passphrase') }}</NcButton>
 			<form v-if="slotForm" class="ngb-form" @submit.prevent="saveSlot">
 				<NcTextField v-model="slotForm.label" :label="t('ng_backup', 'Who keeps this passphrase')" />
-				<NcPasswordField v-model="slotForm.pass1" :label="t('ng_backup', 'Passphrase (at least 12 characters)')" autocomplete="new-password" />
+				<NcPasswordField v-model="slotForm.pass1" :label="t('ng_backup', 'Passphrase (at least 16 characters)')" autocomplete="new-password" />
 				<NcPasswordField v-model="slotForm.pass2" :label="t('ng_backup', 'Repeat passphrase')" autocomplete="new-password" :error="slotForm.pass2 !== '' && slotForm.pass1 !== slotForm.pass2" />
 				<div class="ngb-row">
-					<NcButton type="submit" variant="primary" :disabled="busy || slotForm.pass1.length < 12 || slotForm.pass1 !== slotForm.pass2">{{ t('ng_backup', 'Save') }}</NcButton>
+					<NcButton type="submit" variant="primary" :disabled="busy || slotForm.pass1.length < 16 || slotForm.pass1 !== slotForm.pass2">{{ t('ng_backup', 'Save') }}</NcButton>
 					<NcButton @click="slotForm = null">{{ t('ng_backup', 'Cancel') }}</NcButton>
 				</div>
 			</form>
@@ -69,7 +69,7 @@
 				<NcButton variant="primary" :disabled="!downloaded || !accepted || code.length < 8 || busy" @click="confirm">{{ status.confirmationPhrase }}</NcButton>
 			</div>
 			<p v-else>
-				{{ t('ng_backup', 'Recovery kit confirmed by {user} on {date}.', { user: status.key.confirmation.uid, date: new Date(status.key.confirmation.time * 1000).toLocaleString() }) }}
+				{{ t('ng_backup', 'Recovery kit confirmed by {user} on {date}.', { user: status.key.confirmation.uid, date: formatDateTime(status.key.confirmation.time) }) }}
 				<NcButton variant="tertiary" @click="downloadKit">{{ t('ng_backup', 'Download the kit again') }}</NcButton>
 				<span class="ngb-muted">{{ t('ng_backup', 'Requires your password; all administrators are notified.') }}</span>
 			</p>
@@ -90,6 +90,7 @@ import NcPasswordField from '@nextcloud/vue/components/NcPasswordField'
 import NcSettingsSection from '@nextcloud/vue/components/NcSettingsSection'
 import NcTextField from '@nextcloud/vue/components/NcTextField'
 import api from '../api.js'
+import { formatDateTime, formatDate } from '../format.js'
 
 const props = defineProps({ status: { type: Object, required: true } })
 const emit = defineEmits(['changed'])

src/components/RestoreBrowser.vue

@@ -52,7 +52,7 @@ import NcSettingsSection from '@nextcloud/vue/components/NcSettingsSection'
 import { confirmPassword } from '@nextcloud/password-confirmation'
 import '@nextcloud/password-confirmation/style.css'
 import api from '../api.js'
-import { formatSize } from '../format.js'
+import { formatDateTime, formatSize } from '../format.js'
 
 const props = defineProps({ status: { type: Object, required: true } })
 const emit = defineEmits(['changed'])
@@ -74,7 +74,7 @@ const modes = [
 	{ id: 'replace', label: t('ng_backup', 'Into the original place, overwrite and move files that are not in the backup to the trash') },
 ]
 
-const snapshotLabel = (s) => new Date(s.createdAt * 1000).toLocaleString() + (s.label ? ' – ' + s.label : '')
+const snapshotLabel = (s) => formatDateTime(s.createdAt) + (s.label ? ' – ' + s.label : '')
 const join = (name) => path.value + '/' + name
 const restorable = (p) => /^data\/[^/]+\/files(\/.*)?$/.test(p)
 const crumbs = computed(() => {

src/format.js

@@ -1,5 +1,18 @@
 // SPDX-FileCopyrightText: 2026 Dillard Blom
 // SPDX-License-Identifier: AGPL-3.0-or-later
+import { getCanonicalLocale } from '@nextcloud/l10n'
+
+// The locale of the user's Nextcloud settings (Personal info > Locale), not the browser's:
+// a browser set to English would otherwise show 4:00 PM to someone with a 24-hour locale.
+const locale = getCanonicalLocale()
+
+// A number is a unix timestamp in seconds, a string an ISO 8601 date (snapshot times).
+const toDate = (value) => typeof value === 'number' ? new Date(value * 1000) : new Date(value)
+
+export const formatDateTime = (value) => toDate(value).toLocaleString(locale)
+
+export const formatDate = (value) => toDate(value).toLocaleDateString(locale)
+
 export function formatSize(bytes) {
 	if (bytes === null || bytes === undefined) {
 		return ''

tests/Unit/Backend/SftpRangeFetcherTest.php

@@ -0,0 +1,240 @@
+<?php
+
+declare(strict_types=1);
+
+namespace OCA\NgBackup\Tests\Unit\Backend;
+
+use OCA\NgBackup\Backend\SftpRangeFetcher;
+use OCA\NgBackup\Backend\SftpReadStream;
+use OCA\NgBackup\Tests\Unit\TempDirTrait;
+use PHPUnit\Framework\TestCase;
+
+require_once __DIR__ . '/SftpReadStreamTest.php'; // FakeSftpConnection, FakeSftpStorage
+
+/** SftpRangeFetcher against the fake SFTP server of SftpReadStreamTest, several connections at once. */
+class SftpRangeFetcherTest extends TestCase {
+	use TempDirTrait;
+
+	/** @var array<string, string> */
+	private array $files = [];
+
+	protected function setUp(): void {
+		SftpReadStream::reset();
+		for ($i = 0; $i < 10; $i++) {
+			$this->files["/home/repo/packs/p$i"] = random_bytes(3 * 1048576 + $i * 1000);
+		}
+	}
+
+	/** @return list<FakeSftpConnection> */
+	private function connections(int $n, array $options = []): array {
+		$result = [];
+		for ($c = 0; $c < $n; $c++) {
+			$result[] = new FakeSftpConnection($this->files, ...($options[$c] ?? []));
+		}
+		return $result;
+	}
+
+	/** @return list<object> what StorageBackend passes on: each with its SFTP channel open */
+	private static function opened(array $connections): array {
+		return array_map(fn (FakeSftpConnection $c): object => SftpReadStream::connection(new FakeSftpStorage($c)), $connections);
+	}
+
+	/** @return list<array{0:string, 1:int, 2:int}> */
+	private function ranges(): array {
+		$ranges = [];
+		for ($i = 0; $i < 10; $i++) {
+			$ranges[] = ["repo/packs/p$i", 1000 * $i, 2 * 1048576 + 333];
+		}
+		return $ranges;
+	}
+
+	/** @return array<int, string|null> sha1 of the contents by position (a failing comparison of MiBs would not fit in memory) */
+	private static function collect(\Generator $streams): array {
+		$result = [];
+		foreach ($streams as $i => $fh) {
+			$result[$i] = $fh === null ? null : sha1(stream_get_contents($fh));
+		}
+		return $result;
+	}
+
+	private function expected(array $ranges): array {
+		return array_map(fn (array $r): string => sha1(substr($this->files['/home/' . $r[0]], $r[1], $r[2])), $ranges);
+	}
+
+	public function testReadsEveryRangeInOrderOverAllConnections(): void {
+		$connections = $this->connections(4);
+		$ranges = $this->ranges();
+		$spool = $this->tempDir();
+
+		$this->assertSame($this->expected($ranges), self::collect(SftpRangeFetcher::fetch(self::opened($connections), '/home/', $ranges, $spool)));
+
+		foreach ($connections as $c) {
+			$this->assertGreaterThan(0, count($c->reads), 'every connection reads');
+			$this->assertLessThanOrEqual(SftpRangeFetcher::DEPTH, $c->maxInFlight);
+			$this->assertSame([], $c->openHandles);
+			$this->assertSame(0, $c->pending());
+			$this->assertTrue($c->disconnected, 'its own connections end with it');
+		}
+		$this->assertSame([], glob("$spool/*"), 'nothing left in the spool');
+	}
+
+	public function testKeepsSeveralRequestsInFlightOnEachConnection(): void {
+		$this->files['/home/repo/packs/big'] = random_bytes(10 * 1048576);
+		$connections = $this->connections(2);
+		self::collect(SftpRangeFetcher::fetch(self::opened($connections), '/home/', [['repo/packs/big', 0, 10 * 1048576], ['repo/packs/big', 5, 10 * 1048576 - 5]], $this->tempDir()));
+
+		$this->assertSame(SftpRangeFetcher::DEPTH, $connections[0]->maxInFlight);
+		$this->assertSame(SftpRangeFetcher::DEPTH, $connections[1]->maxInFlight);
+	}
+
+	public function testAnAnswerPhpseclibHasReadAlreadyIsTakenWithoutWaitingOnTheSocket(): void {
+		// The fake's answers are all "read already": its socket never becomes readable, and
+		// phpseclib's packet buffer holds data. Waiting on the socket would take a second a step.
+		$connections = $this->connections(2);
+		$sockets = [];
+		foreach ($connections as $c) {
+			$pair = stream_socket_pair(STREAM_PF_UNIX, STREAM_SOCK_STREAM, STREAM_IPPROTO_IP);
+			$sockets[] = $pair;
+			$c->fsock = $pair[0];
+			$c->packet_buffer = pack('N', 4) . 'more'; // a whole packet
+		}
+		$ranges = array_slice($this->ranges(), 0, 3);
+		$start = microtime(true);
+
+		$this->assertSame($this->expected($ranges), self::collect(SftpRangeFetcher::fetch(self::opened($connections), '/home/', $ranges, $this->tempDir())));
+
+		$this->assertLessThan(1.0, microtime(true) - $start);
+	}
+
+	public function testAServerThatCapsAReadStillGivesEveryByte(): void {
+		$connections = $this->connections(3, array_fill(0, 3, ['cap' => 100000]));
+		$ranges = $this->ranges();
+
+		$this->assertSame($this->expected($ranges), self::collect(SftpRangeFetcher::fetch(self::opened($connections), '/home/', $ranges, $this->tempDir())));
+		// learned: after the first short answers (and asking for their rest) it asks for no more than the server gives
+		foreach ($connections as $c) {
+			$this->assertLessThanOrEqual(2 * SftpRangeFetcher::DEPTH, count(array_filter($c->reads, fn (int $n): bool => $n > 100000)));
+		}
+	}
+
+	public function testAMissingFileIsLeftToTheCaller(): void {
+		$connections = $this->connections(2);
+		$ranges = $this->ranges();
+		$ranges[3][0] = 'repo/packs/gone';
+
+		$result = self::collect(SftpRangeFetcher::fetch(self::opened($connections), '/home/', $ranges, $this->tempDir()));
+
+		$expected = $this->expected($this->ranges());
+		$expected[3] = null;
+		$this->assertSame($expected, $result);
+		$this->assertSame([], $connections[0]->openHandles);
+	}
+
+	public function testARangePastTheEndOfTheFileIsLeftToTheCaller(): void {
+		$ranges = $this->ranges();
+		$ranges[5][2] = 10 * 1048576;
+
+		$result = self::collect(SftpRangeFetcher::fetch(self::opened($this->connections(2)), '/home/', $ranges, $this->tempDir()));
+
+		$this->assertNull($result[5]);
+		$this->assertSame($this->expected($this->ranges())[6], $result[6]);
+	}
+
+	public function testAServerErrorFailsOnlyThatRange(): void {
+		// every read from 1 MiB on fails on connection 0: its ranges, not those of the others
+		$connections = $this->connections(2, [['failAt' => 1048576]]);
+		$ranges = $this->ranges();
+
+		$result = self::collect(SftpRangeFetcher::fetch(self::opened($connections), '/home/', $ranges, $this->tempDir()));
+
+		$expected = $this->expected($ranges);
+		$failed = array_keys(array_filter($result, fn (?string $r): bool => $r === null));
+		$this->assertNotSame([], $failed);
+		foreach ($result as $i => $data) {
+			if ($data !== null) {
+				$this->assertSame($expected[$i], $data);
+			}
+		}
+		$this->assertLessThan(10, count($failed), 'the other connection goes on');
+		$this->assertSame([], $connections[0]->openHandles, 'a failed range is closed too');
+	}
+
+	public function testALostConnectionIsNotUsedAgainAndTheOthersGoOn(): void {
+		$connections = $this->connections(3, [['loseAt' => 1048576]]);
+		$ranges = $this->ranges();
+
+		$result = self::collect(SftpRangeFetcher::fetch(self::opened($connections), '/home/', $ranges, $this->tempDir()));
+
+		$expected = $this->expected($ranges);
+		$this->assertSame(1, count(array_filter($result, fn (?string $r): bool => $r === null)), 'only the range it was reading');
+		foreach ($result as $i => $data) {
+			if ($data !== null) {
+				$this->assertSame($expected[$i], $data);
+			}
+		}
+		$this->assertTrue($connections[0]->disconnected);
+		$this->assertLessThanOrEqual(1048576 / 261120 + SftpRangeFetcher::DEPTH + 1, count($connections[0]->reads), 'not used after it broke');
+	}
+
+	public function testWhenEveryConnectionIsLostTheRestIsLeftToTheCaller(): void {
+		$connections = $this->connections(2, [['throwAt' => 1048576], ['loseAt' => 1048576]]);
+
+		$result = self::collect(SftpRangeFetcher::fetch(self::opened($connections), '/home/', $this->ranges(), $this->tempDir()));
+
+		$this->assertSame(array_fill(0, 10, null), $result);
+	}
+
+	public function testABrokenConnectionIsReplacedAndTheRestIsReadAhead(): void {
+		$connections = $this->connections(1, [['loseAt' => 1048576]]);
+		$made = [];
+		$connect = function () use (&$made): object {
+			$made[] = $c = new FakeSftpConnection($this->files);
+			return SftpReadStream::connection(new FakeSftpStorage($c));
+		};
+		$ranges = $this->ranges();
+
+		$result = self::collect(SftpRangeFetcher::fetch(self::opened($connections), '/home/', $ranges, $this->tempDir(), $connect));
+
+		$expected = $this->expected($ranges);
+		$expected[0] = null; // the range it was reading when it broke: read the usual way
+		$this->assertSame($expected, $result);
+		$this->assertCount(1, $made);
+		$this->assertTrue($made[0]->disconnected, 'the new one ends with the fetcher too');
+	}
+
+	public function testConnectionsThatKeepBreakingAreReplacedOnlySoOften(): void {
+		$made = 0;
+		$connect = function () use (&$made): object {
+			$made++;
+			return SftpReadStream::connection(new FakeSftpStorage(new FakeSftpConnection($this->files, loseAt: 0)));
+		};
+		$ranges = array_merge($this->ranges(), $this->ranges(), $this->ranges());
+
+		$result = self::collect(SftpRangeFetcher::fetch(self::opened($this->connections(1, [['loseAt' => 0]])), '/home/', $ranges, $this->tempDir(), $connect));
+
+		$this->assertSame(array_fill(0, count($ranges), null), $result);
+		$this->assertSame(SftpRangeFetcher::MAX_RECONNECTS, $made);
+	}
+
+	public function testStoppingHalfwayEndsTheConnectionsAndLeavesNothingBehind(): void {
+		$connections = $this->connections(2);
+		$spool = $this->tempDir();
+		$streams = SftpRangeFetcher::fetch(self::opened($connections), '/home/', $this->ranges(), $spool);
+		$this->assertIsResource($streams->current());
+
+		unset($streams);
+
+		$this->assertTrue($connections[0]->disconnected);
+		$this->assertTrue($connections[1]->disconnected);
+		$this->assertSame([], glob("$spool/*"));
+	}
+
+	public function testReadsNoMoreThanAheadOfTheCaller(): void {
+		$connections = $this->connections(4);
+		$streams = SftpRangeFetcher::fetch(self::opened($connections), '/home/', $this->ranges(), $this->tempDir());
+		$streams->current();
+
+		$opened = array_sum(array_map(fn (FakeSftpConnection $c): int => count(array_unique(array_values($c->opened))), $connections));
+		$this->assertLessThanOrEqual(SftpRangeFetcher::AHEAD, $opened);
+	}
+}

tests/Unit/Backend/SftpReadStreamTest.php

@@ -466,6 +466,12 @@ final class FakeSftpConnection {
 	public array $reads = [];
 	/** @var array<string, string> */
 	public array $openHandles = [];
+	/** @var list<string> paths of every OPEN request */
+	public array $opened = [];
+	/** @var resource|null like phpseclib's socket (SftpRangeFetcher waits on it) */
+	public $fsock = null;
+	/** like phpseclib's: what came in with the last packet and is not read yet */
+	public string $packet_buffer = '';
 	/** Whether the SFTP channel is open: phpseclib 2 opens it on the first SFTP call. */
 	public bool $initialised = false;
 	/** Packets sent */
@@ -532,6 +538,7 @@ final class FakeSftpConnection {
 					return false;
 				}
 				$path = substr($data, 4, unpack('N', $data)[1]);
+				$this->opened[] = $path;
 				if (!isset($this->files[$path])) {
 					$this->answers[$id] = [101, pack('N', 2)];
 					break;

tests/Unit/Backend/StorageBackendReadAheadTest.php

@@ -0,0 +1,115 @@
+<?php
+
+declare(strict_types=1);
+
+namespace OCA\NgBackup\Tests\Unit\Backend;
+
+use OCA\NgBackup\Backend\SftpRangeFetcher;
+use OCA\NgBackup\Backend\SftpReadStream;
+use OCA\NgBackup\Backend\StorageBackend;
+use OCA\NgBackup\Tests\Unit\TempDirTrait;
+use OCP\Files\Storage\IStorage;
+use PHPUnit\Framework\TestCase;
+
+require_once __DIR__ . '/SftpReadStreamTest.php'; // FakeSftpConnection
+require_once __DIR__ . '/StorageBackendReconnectTest.php'; // SftpLikeStorage
+
+/** StorageBackend::readAhead(): over SFTP on connections of its own, built with the reconnect function. */
+class StorageBackendReadAheadTest extends TestCase {
+	use TempDirTrait;
+
+	/** @var list<FakeSftpConnection> */
+	private array $connections = [];
+	/** @var array<string, string> */
+	private array $files = [];
+	/** New storages after this many fail to connect. */
+	private ?int $connectLimit = null;
+
+	protected function setUp(): void {
+		SftpReadStream::reset();
+		for ($i = 0; $i < 6; $i++) {
+			$this->files["/home/base/repo/packs/p$i"] = random_bytes(1048576 + $i);
+		}
+	}
+
+	private function storage(): IStorage {
+		if ($this->connectLimit !== null && count($this->connections) >= $this->connectLimit) {
+			throw new \RuntimeException('Too many connections');
+		}
+		$sftp = new FakeSftpConnection($this->files);
+		$this->connections[] = $sftp;
+		$storage = $this->createMock(SftpLikeRootStorage::class);
+		$storage->method('instanceOfStorage')->willReturnCallback(fn (string $class): bool => $class === \OCA\Files_External\Lib\Storage\SFTP::class);
+		$storage->method('getConnection')->willReturn($sftp);
+		$storage->method('getRoot')->willReturn('/home/');
+		$storage->method('is_dir')->willReturn(true);
+		return $storage;
+	}
+
+	/** @return list<array{0:string, 1:int, 2:int}> */
+	private static function ranges(): array {
+		return array_map(fn (int $i): array => ["packs/p$i", 7, 1048576 - 7], range(0, 5));
+	}
+
+	public function testReadsAheadOnNewConnectionsOnly(): void {
+		$backend = new StorageBackend($this->storage(), 'base/repo', false, fn (): IStorage => $this->storage());
+		$backend->readAheadConnections = 4;
+		$this->assertTrue($backend->canReadAhead());
+
+		$result = [];
+		foreach ($backend->readAhead(self::ranges(), $this->tempDir()) as $i => $fh) {
+			$result[$i] = sha1(stream_get_contents($fh));
+		}
+
+		$expected = array_map(fn (int $i): string => sha1(substr($this->files["/home/base/repo/packs/p$i"], 7, 1048576 - 7)), range(0, 5));
+		$this->assertSame($expected, $result);
+		$this->assertCount(1 + 4, $this->connections);
+		$this->assertSame(0, $this->connections[0]->sent, 'the storage\'s own connection stays free');
+		foreach (array_slice($this->connections, 1) as $c) {
+			$this->assertTrue($c->disconnected);
+		}
+	}
+
+	public function testGoesOnWithTheConnectionsTheServerAllows(): void {
+		$this->connectLimit = 3;
+		$backend = new StorageBackend($this->storage(), 'base/repo', false, fn (): IStorage => $this->storage());
+		$backend->readAheadConnections = 4;
+
+		$count = 0;
+		foreach ($backend->readAhead(self::ranges(), $this->tempDir()) as $fh) {
+			$this->assertIsResource($fh);
+			$count++;
+		}
+
+		$this->assertSame(6, $count);
+		$this->assertCount(3, $this->connections);
+	}
+
+	public function testByDefaultOneConnectionNextToTheStoragesOwn(): void {
+		$backend = new StorageBackend($this->storage(), 'base/repo', false, fn (): IStorage => $this->storage());
+		foreach ($backend->readAhead(self::ranges(), $this->tempDir()) as $fh) {
+			$this->assertIsResource($fh);
+		}
+
+		$this->assertSame(1, SftpRangeFetcher::DEFAULT_CONNECTIONS);
+		$this->assertCount(2, $this->connections);
+	}
+
+	public function testNoNewConnectionMeansNoReadingAhead(): void {
+		$this->connectLimit = 1;
+		$backend = new StorageBackend($this->storage(), 'base/repo', false, fn (): IStorage => $this->storage());
+
+		$this->assertNull($backend->readAhead(self::ranges(), $this->tempDir()));
+	}
+
+	public function testWithoutAWayToConnectAgainItDoesNotReadAhead(): void {
+		$backend = new StorageBackend($this->storage(), 'base/repo', false, null);
+
+		$this->assertFalse($backend->canReadAhead());
+		$this->assertNull($backend->readAhead(self::ranges(), $this->tempDir()));
+	}
+}
+
+interface SftpLikeRootStorage extends SftpLikeStorage {
+	public function getRoot(): string;
+}

tests/Unit/Backend/StorageBackendReconnectTest.php

@@ -77,6 +77,24 @@ class StorageBackendReconnectTest extends TestCase {
 		$this->assertSame(1, $backend->reconnects);
 	}
 
+	public function testASilentlyDroppedConnectionIsReplacedAfterAPause(): void {
+		$backend = $this->backend();
+		$this->connections[0]->dropped = true;
+		$this->connections[0]->silent = true; // phpseclib still says connected
+		self::idle($backend);
+		$this->assertTrue($backend->exists('config'));
+		$this->assertSame(1, $backend->reconnects, 'the check failed, so the connection was replaced');
+	}
+
+	public function testAFailureOnASilentlyDroppedConnectionIsRepeated(): void {
+		$backend = $this->backend();
+		$this->connections[0]->dropped = true;
+		$this->connections[0]->silent = true;
+		$fh = $backend->get('config');
+		$this->assertSame('config', stream_get_contents($fh));
+		$this->assertSame(1, $backend->reconnects);
+	}
+
 	public function testAMissingFileOnALiveConnectionIsJustMissing(): void {
 		$backend = $this->backend();
 		$this->assertFalse($backend->exists('nothing'));
@@ -121,6 +139,8 @@ interface SftpLikeStorage extends IStorage {
 /** The public phpseclib calls the backend uses to tell a dead connection. */
 final class ReconnectFakeSftp {
 	public bool $dropped = false;
+	/** Dropped without phpseclib noticing (as a Hetzner Storage Box does): it still says connected. */
+	public bool $silent = false;
 	private bool $connected = true;
 	public int $requests = 0;
 
@@ -139,6 +159,9 @@ final class ReconnectFakeSftp {
 	public function request(): bool {
 		$this->requests++;
 		if ($this->dropped) {
+			if ($this->silent) {
+				return false;
+			}
 			$this->connected = false;
 		}
 		return $this->connected;

tests/Unit/FormatTest.php

@@ -0,0 +1,17 @@
+<?php
+
+declare(strict_types=1);
+
+namespace OCA\NgBackup\Tests\Unit;
+
+use OCA\NgBackup\Format;
+use PHPUnit\Framework\TestCase;
+
+class FormatTest extends TestCase {
+	public function testDurationShowsDaysFromOneDayOn(): void {
+		$this->assertSame('00:00:00', Format::duration(-5));
+		$this->assertSame('12:10:13', Format::duration(12 * 3600 + 10 * 60 + 13));
+		$this->assertSame('1d 00:00:00', Format::duration(86400));
+		$this->assertSame('1d 12:10:13', Format::duration(86400 + 12 * 3600 + 10 * 60 + 13));
+	}
+}

tests/Unit/Job/BackupRunTest.php

@@ -42,6 +42,61 @@ class BackupRunTest extends TestCase {
 		$this->assertSame(self::hashTree($src), self::hashTree($target));
 	}
 
+	public function testTheSnapshotIsWrittenInAStepOfItsOwnFromAllSegmentsAtOnce(): void {
+		$src = $this->tempDir();
+		for ($i = 0; $i < 60; $i++) {
+			file_put_contents("$src/f$i.txt", random_bytes(200000));
+		}
+		$backend = new RangeCountingBackend(new LocalBackend($this->tempDir()));
+		$keys = KeyRing::generate();
+		Repository::initWithKey($backend, $keys, $keys->wrap('pw'));
+
+		$state = BackupRun::start($src);
+		for ($i = 0; $i < 500 && $state['phase'] === 'files'; $i++) {
+			$state = BackupRun::step(Repository::openWithKey($backend, $keys), $state, microtime(true) + 0.01);
+		}
+		$this->assertSame('finish', $state['phase'], 'the step that read the last file does not write the snapshot');
+		$this->assertGreaterThan(2, count($state['segments']));
+		$backend->batches = [];
+
+		$state = BackupRun::step(Repository::openWithKey($backend, $keys), $state, microtime(true) + 0.01);
+
+		$this->assertSame('commit', $state['phase']);
+		// One batch; the blobs of a segment follow each other in its pack and are one read.
+		$this->assertSame([count($state['segments'])], $backend->batches);
+		Repository::openWithKey($backend, $keys)->recordSnapshot($state['snapshot']);
+		$target = $this->tempDir();
+		Repository::openWithKey($backend, $keys)->restore($state['snapshot'], $target);
+		$this->assertSame(self::hashTree($src), self::hashTree($target));
+	}
+
+	public function testBlobsThatFollowEachOtherInAPackAreReadAsOneRange(): void {
+		$backend = new RangeCountingBackend(new LocalBackend($this->tempDir()));
+		$keys = KeyRing::generate();
+		$repo = Repository::initWithKey($backend, $keys, $keys->wrap('pw'));
+		$stats = [];
+		$segments = [];
+		$expected = [];
+		for ($s = 0; $s < 3; $s++) {
+			$writer = new \OCA\NgBackup\Repository\BlobWriter(fn (string $data): string => $repo->storeData($data, $stats), 1000);
+			$lines = [];
+			for ($i = 0; $i < 100; $i++) {
+				$lines[] = json_encode(['segment' => $s, 'line' => $i, 'pad' => bin2hex(random_bytes(20))]);
+			}
+			$writer->write(implode("\n", $lines) . "\n");
+			$segments[] = $writer->finish();
+			$repo->flushPacks(); // one pack per segment, as one per step
+			array_push($expected, ...$lines);
+		}
+		$this->assertGreaterThan(3, count(array_merge(...$segments)));
+		$backend->batches = [];
+
+		$read = iterator_to_array(Repository::openWithKey($backend, $keys)->readLines(array_merge(...$segments)), false);
+
+		$this->assertSame($expected, array_values(array_filter($read, fn (string $l): bool => $l !== '')));
+		$this->assertSame([3], $backend->batches, 'one read per segment, all in one batch');
+	}
+
 	public function testFileChangedBetweenStepsIsReadAgain(): void {
 		$src = $this->tempDir();
 		file_put_contents("$src/big.bin", random_bytes(20 * 1048576));
@@ -100,3 +155,54 @@ class BackupRunTest extends TestCase {
 		$this->assertSame(self::hashTree($src), self::hashTree("$target/data"));
 	}
 }
+
+final class RangeCountingBackend implements \OCA\NgBackup\Backend\IBackend {
+	use \OCA\NgBackup\Backend\GetsOneByOne {
+		getRanges as private oneByOne;
+	}
+
+	/** @var list<int> number of ranges per getRanges() call */
+	public array $batches = [];
+
+	public function __construct(
+		private \OCA\NgBackup\Backend\IBackend $inner,
+	) {
+	}
+
+	public function getRanges(array $ranges): \Generator {
+		$this->batches[] = count($ranges);
+		return $this->oneByOne($ranges);
+	}
+
+	public function put(string $path, $stream): void {
+		$this->inner->put($path, $stream);
+	}
+
+	public function get(string $path) {
+		return $this->inner->get($path);
+	}
+
+	public function getRange(string $path, int $offset, int $length): string {
+		return $this->inner->getRange($path, $offset, $length);
+	}
+
+	public function exists(string $path): bool {
+		return $this->inner->exists($path);
+	}
+
+	public function move(string $from, string $to): void {
+		$this->inner->move($from, $to);
+	}
+
+	public function list(string $prefix): array {
+		return $this->inner->list($prefix);
+	}
+
+	public function listFiles(string $dir): array {
+		return $this->inner->listFiles($dir);
+	}
+
+	public function delete(string $path): void {
+		$this->inner->delete($path);
+	}
+}

tests/Unit/Repository/IndexCacheTest.php

@@ -54,6 +54,24 @@ class IndexCacheTest extends TestCase {
 		$this->assertCount(12, self::hashTree($target));
 	}
 
+	/** Connecting a new server to a location with backups reports how far reading the index is. */
+	public function testOpeningReportsIndexProgress(): void {
+		$src = $this->tempDir();
+		for ($i = 0; $i < 6; $i++) {
+			file_put_contents("$src/f$i", random_bytes(3 * 1048576));
+		}
+		$backend = new LocalBackend($this->tempDir());
+		$keys = KeyRing::generate();
+		Repository::initWithKey($backend, $keys, $keys->wrap('pw'))->backupDirectory($src);
+		$files = count($backend->list('index'));
+		$seen = [];
+		Repository::openWithKey($backend, $keys, null, null, function (int $done, int $total) use (&$seen): void {
+			$seen[] = [$done, $total];
+		});
+		$this->assertCount($files, $seen);
+		$this->assertSame([$files, $files], end($seen));
+	}
+
 	/** The database dump reads in a read-only transaction: a pack that fills up then must not write the cache yet. */
 	public function testHeldCacheWritesWaitForRelease(): void {
 		$cache = new class implements IIndexCache {

tests/Unit/Repository/IndexListingTest.php

@@ -0,0 +1,239 @@
+<?php
+
+declare(strict_types=1);
+
+namespace OCA\NgBackup\Tests\Unit\Repository;
+
+use OCA\NgBackup\Backend\BackendException;
+use OCA\NgBackup\Backend\IBackend;
+use OCA\NgBackup\Backend\LocalBackend;
+use OCA\NgBackup\Crypto\KeyRing;
+use OCA\NgBackup\Repository\IIndexCache;
+use OCA\NgBackup\Repository\Repository;
+use OCA\NgBackup\Tests\Unit\TempDirTrait;
+use PHPUnit\Framework\TestCase;
+
+/**
+ * A listing of the location that comes back empty because a connection failed quietly (an SFTP
+ * connection a Storage Box dropped) must not empty the index. In a 1 TB disaster recovery test a
+ * pack read failed after 13 hours, the reload of the index got an empty listing, and the restore
+ * stopped with "Blob not in index".
+ */
+class IndexListingTest extends TestCase {
+	use TempDirTrait;
+
+	private string $root;
+	private KeyRing $keys;
+	private string $src;
+	private string $snapshot;
+
+	protected function setUp(): void {
+		$this->root = $this->tempDir();
+		$this->keys = KeyRing::generate();
+		$this->src = $this->tempDir();
+		for ($i = 0; $i < 12; $i++) {
+			file_put_contents("$this->src/f$i", random_bytes(3 * 1048576));
+		}
+		$repo = Repository::initWithKey(new LocalBackend($this->root), $this->keys, $this->keys->wrap('pw'));
+		$this->snapshot = $repo->backupDirectory($this->src)['snapshot'];
+	}
+
+	private static function cache(): IIndexCache {
+		return indexCache();
+	}
+
+	public function testARestoreGoesOnAfterAPackReadFailedAndTheListingCameBackEmpty(): void {
+		$backend = new FlakyBackend(new LocalBackend($this->root));
+		$repo = Repository::openWithKey($backend, $this->keys);
+		$backend->failPackReads = 1;      // the read of a pack fails once
+		$backend->emptyIndexListings = 1; // and listing the index right after comes back empty
+		$target = $this->tempDir();
+
+		$this->assertSame(12, $repo->restore($this->snapshot, $target));
+
+		$this->assertSame(self::hashTree($this->src), self::hashTree($target));
+		$this->assertSame(0, $backend->failPackReads, 'the failure happened');
+		$this->assertSame(0, $backend->emptyIndexListings, 'the empty listing was seen');
+	}
+
+	public function testAPackThatStaysUnreadableIsStillReportedAsSuch(): void {
+		$backend = new FlakyBackend(new LocalBackend($this->root));
+		$repo = Repository::openWithKey($backend, $this->keys);
+		$backend->failPackReads = 1000;
+
+		try {
+			$repo->restore($this->snapshot, $this->tempDir());
+			$this->fail('the packs cannot be read');
+		} catch (BackendException $e) {
+			$this->assertStringStartsWith('Not found: packs/', $e->getMessage());
+		}
+	}
+
+	public function testACheckWithAnEmptyListingIsAnErrorNotEveryBlobMissing(): void {
+		$backend = new FlakyBackend(new LocalBackend($this->root));
+		$repo = Repository::openWithKey($backend, $this->keys);
+		$backend->dead = true;
+
+		$this->expectException(BackendException::class);
+		$this->expectExceptionMessage('listed no index files');
+		$repo->verify($this->snapshot);
+	}
+
+	public function testRefreshingFetchesOnlyIndexFilesItHasNotLoaded(): void {
+		$backend = new FlakyBackend(new LocalBackend($this->root));
+		$repo = Repository::openWithKey($backend, $this->keys);
+		$index = (new \ReflectionProperty($repo, 'index'))->getValue($repo);
+		$index->downloaded = 0;
+
+		$index->refresh();
+
+		$this->assertSame(0, $index->downloaded, 'every index file is loaded already, also those whose blobs are elsewhere too');
+	}
+
+	public function testARestoreGoesOnWhenTheLocationCannotBeListedAfterAFailedRead(): void {
+		$backend = new FlakyBackend(new LocalBackend($this->root));
+		$repo = Repository::openWithKey($backend, $this->keys);
+		$backend->failPackReads = 1;
+		$backend->dead = true; // listing and config look gone; reading packs works again
+		$target = $this->tempDir();
+
+		$this->assertSame(12, $repo->restore($this->snapshot, $target));
+
+		$this->assertSame(self::hashTree($this->src), self::hashTree($target));
+	}
+
+	public function testAnEmptyListingThatWasAHiccupIsListedAgain(): void {
+		$cache = self::cache();
+		$backend = new FlakyBackend(new LocalBackend($this->root));
+		Repository::openWithKey($backend, $this->keys, $cache);
+		$cached = $cache->data;
+		$backend->emptyIndexListings = 1;
+
+		$again = Repository::openWithKey($backend, $this->keys, $cache);
+
+		$this->assertSame($cached, $cache->data);
+		$this->assertSame(12, $again->restore($this->snapshot, $this->tempDir()));
+	}
+
+	public function testAListingThatStaysEmptyWhileIndexFilesAreThereIsNotTaken(): void {
+		$cache = self::cache();
+		$backend = new FlakyBackend(new LocalBackend($this->root));
+		Repository::openWithKey($backend, $this->keys, $cache);
+		$cached = $cache->data;
+		$backend->emptyIndexListings = 5; // the config answers, the listing keeps lying
+
+		try {
+			Repository::openWithKey($backend, $this->keys, $cache);
+			$this->fail('index files are there');
+		} catch (BackendException $e) {
+			$this->assertStringContainsString('is there', $e->getMessage());
+		}
+		$this->assertSame($cached, $cache->data);
+	}
+
+	public function testARepositoryThatReallyBecameEmptyIsTakenAsEmpty(): void {
+		$cache = self::cache();
+		$backend = new FlakyBackend(new LocalBackend($this->root));
+		Repository::openWithKey($backend, $this->keys, $cache);
+		$this->assertNotSame([], array_filter($cache->data));
+		// another server forgot the last snapshot and cleaned up: no packs and index files left
+		foreach (array_merge($backend->list('index'), $backend->list('packs')) as $path) {
+			$backend->delete($path);
+		}
+
+		Repository::openWithKey($backend, $this->keys, $cache);
+
+		$this->assertSame([], array_filter($cache->data), 'the stale cache rows are gone');
+	}
+
+	public function testOpeningWithAnEmptyListingKeepsTheCachedIndex(): void {
+		$cache = self::cache();
+		$backend = new FlakyBackend(new LocalBackend($this->root));
+		Repository::openWithKey($backend, $this->keys, $cache);
+		$cached = $cache->data;
+		$this->assertNotSame([], $cached);
+
+		$backend->dead = true;
+		try {
+			Repository::openWithKey($backend, $this->keys, $cache);
+			$this->fail('an empty listing of a repository with an index must not be taken as is');
+		} catch (BackendException $e) {
+			$this->assertStringContainsString('listed no index files', $e->getMessage());
+		}
+		$this->assertSame($cached, $cache->data, 'the cache is untouched');
+	}
+}
+
+/** @internal */
+function indexCache(): IIndexCache {
+	return new class implements IIndexCache {
+		public array $data = [];
+		public function all(string $r): array { return $this->data[$r] ?? []; }
+		public function put(string $r, string $p, array $e): void { $this->data[$r][$p] = $e; }
+		public function remove(string $r, array $ps): void { foreach ($ps as $p) { unset($this->data[$r][$p]); } }
+		public function putMany(string $r, array $packs): void { foreach ($packs as $p => $e) { $this->put($r, (string)$p, $e); } }
+		public function replaceAll(string $r, array $packs): void { $this->data[$r] = []; $this->putMany($r, $packs); }
+	};
+}
+
+/** A location whose pack reads fail, and whose index listings come back empty, a set number of times. */
+final class FlakyBackend implements IBackend {
+	use \OCA\NgBackup\Backend\GetsOneByOne;
+
+	public int $failPackReads = 0;
+	public int $emptyIndexListings = 0;
+	/** The connection is gone: also the repository config looks missing. */
+	public bool $dead = false;
+
+	public function __construct(
+		private IBackend $inner,
+	) {
+	}
+
+	public function put(string $path, $stream): void {
+		$this->inner->put($path, $stream);
+	}
+
+	public function get(string $path) {
+		if (str_starts_with($path, 'packs/') && $this->failPackReads > 0) {
+			$this->failPackReads--;
+			throw new BackendException('Not found: ' . $path);
+		}
+		return $this->inner->get($path);
+	}
+
+	public function getRange(string $path, int $offset, int $length): string {
+		if (str_starts_with($path, 'packs/') && $this->failPackReads > 0) {
+			$this->failPackReads--;
+			throw new BackendException('Not found: ' . $path);
+		}
+		return $this->inner->getRange($path, $offset, $length);
+	}
+
+	public function exists(string $path): bool {
+		return !$this->dead && $this->inner->exists($path);
+	}
+
+	public function move(string $from, string $to): void {
+		$this->inner->move($from, $to);
+	}
+
+	public function list(string $prefix): array {
+		return $this->inner->list($prefix);
+	}
+
+	public function listFiles(string $dir): array {
+		if ($dir === 'index' && $this->dead) {
+			return [];
+		}
+		if ($dir === 'index' && $this->emptyIndexListings > 0) {
+			$this->emptyIndexListings--;
+			return [];
+		}
+		return $this->inner->listFiles($dir);
+	}
+
+	public function delete(string $path): void {
+		$this->inner->delete($path);
+	}
+}

tests/Unit/Repository/PruneTest.php

@@ -88,6 +88,33 @@ class PruneTest extends TestCase {
 		$this->assertSame(self::hashTree($src), self::hashTree($target));
 	}
 
+	public function testRestoreFollowsPacksRepackedByAnotherServer(): void {
+		// A disaster recovery test on a second server reads the location while the original
+		// server's weekly cleanup repacks it: the restore must not stop at a pack that moved.
+		$src = $this->tempDir();
+		$backend = new LocalBackend($this->tempDir());
+		$keys = KeyRing::generate();
+		$repo = Repository::initWithKey($backend, $keys, $keys->wrap('pw'));
+		for ($i = 0; $i < 40; $i++) {
+			file_put_contents("$src/f$i", random_bytes(500000));
+		}
+		$a = $repo->backupDirectory($src);
+		for ($i = 0; $i < 40; $i++) {
+			if ($i % 5 !== 0) {
+				unlink("$src/f$i");
+			}
+		}
+		$b = $repo->backupDirectory($src, $a['snapshot']);
+		$reader = Repository::openWithKey($backend, $keys); // index loaded before the cleanup
+		$repo->forget($a['snapshot']);
+		$repo->purgeTrash(0);
+		$this->assertGreaterThan(0, $repo->prune(false, 0.5)['repacked']);
+
+		$target = $this->tempDir();
+		$reader->restore($b['snapshot'], $target);
+		$this->assertSame(self::hashTree($src), self::hashTree($target));
+	}
+
 	public function testUntrashRestoresAWorkingSnapshot(): void {
 		$src = $this->tempDir();
 		$backend = new LocalBackend($this->tempDir());

tests/Unit/Repository/ReadAheadTest.php

@@ -0,0 +1,298 @@
+<?php
+
+declare(strict_types=1);
+
+namespace OCA\NgBackup\Tests\Unit\Repository;
+
+use OCA\NgBackup\Backend\BackendException;
+use OCA\NgBackup\Backend\IBackend;
+use OCA\NgBackup\Backend\IReadsAhead;
+use OCA\NgBackup\Backend\LocalBackend;
+use OCA\NgBackup\Crypto\KeyRing;
+use OCA\NgBackup\Repository\ReadAheadPlan;
+use OCA\NgBackup\Repository\Repository;
+use OCA\NgBackup\Tests\Unit\TempDirTrait;
+use PHPUnit\Framework\TestCase;
+
+require_once __DIR__ . '/PackReadTest.php'; // PackOpenCountingBackend
+
+/** A full restore reads the packs ahead (IReadsAhead) and falls back to the usual reads per range. */
+class ReadAheadTest extends TestCase {
+	use TempDirTrait;
+
+	private string $root;
+	private KeyRing $keys;
+	private string $src;
+	private string $snapshot;
+
+	protected function setUp(): void {
+		$this->root = $this->tempDir();
+		$this->keys = KeyRing::generate();
+		$this->src = $this->tempDir();
+		// three packs of 32 MiB, and small files in between
+		for ($i = 0; $i < 4; $i++) {
+			file_put_contents(sprintf('%s/big%d', $this->src, $i), random_bytes(20 * 1048576));
+			for ($j = 0; $j < 20; $j++) {
+				file_put_contents(sprintf('%s/small%d-%02d', $this->src, $i, $j), random_bytes(30000));
+			}
+		}
+		file_put_contents("$this->src/same", file_get_contents("$this->src/small0-00")); // the same blob again, later
+		$repo = Repository::initWithKey(new LocalBackend($this->root), $this->keys, $this->keys->wrap('pw'));
+		$this->snapshot = $repo->backupDirectory($this->src)['snapshot'];
+	}
+
+	private function restore(ReadAheadBackend $backend, string $prefix = '', ?string $target = null): string {
+		$target ??= $this->tempDir();
+		$repo = Repository::openWithKey($backend, $this->keys, null, null);
+		$repo->restore($this->snapshot, $target, $prefix);
+		return $target;
+	}
+
+	private function assertRestored(string $target, string $prefix = ''): void {
+		$expected = array_filter(self::hashTree($this->src), fn (string $p): bool => str_starts_with($p, $prefix), ARRAY_FILTER_USE_KEY);
+		$this->assertSame($expected, self::hashTree($target));
+		$this->assertSame([], glob("$target/.ngb-restore-spool-*"), 'the spool is removed');
+	}
+
+	public function testARestoreReadsEveryPackAhead(): void {
+		$backend = new ReadAheadBackend(new LocalBackend($this->root));
+
+		$this->assertRestored($this->restore($backend));
+
+		$this->assertSame(0, $backend->counter->packOpens(), 'nothing read the usual way');
+		$this->assertGreaterThanOrEqual(3, count($backend->asked));
+		// in the order of the files, one range per pack the restore goes through (the same blob
+		// again later is a range of its own)
+		$this->assertLessThanOrEqual(count($backend->inner->list('packs')) + 1, count($backend->asked));
+	}
+
+	public function testAPlanThatCannotBeMadeLeavesTheRestoreToTheUsualReads(): void {
+		$backend = new ReadAheadBackend(new LocalBackend($this->root), failSnapshotReads: 1);
+
+		$this->assertRestored($this->restore($backend));
+
+		$this->assertSame([], $backend->asked, 'no reading ahead without a plan');
+		$this->assertSame(2, $backend->snapshotReads, 'the restore itself read the snapshot again');
+	}
+
+	public function testTheEmptySpoolOfAStoppedRestoreIsRemoved(): void {
+		$target = $this->tempDir();
+		mkdir("$target/.ngb-restore-spool-0badc0de", 0700); // a restore that was killed
+
+		$this->assertRestored($this->restore(new ReadAheadBackend(new LocalBackend($this->root)), '', $target));
+	}
+
+	public function testARangeThatCouldNotBeReadAheadIsReadTheUsualWay(): void {
+		$backend = new ReadAheadBackend(new LocalBackend($this->root), fail: [1]);
+
+		$this->assertRestored($this->restore($backend));
+
+		$this->assertGreaterThan(0, $backend->counter->packOpens());
+	}
+
+	public function testADamagedCopyIsReadAgainTheUsualWay(): void {
+		$backend = new ReadAheadBackend(new LocalBackend($this->root), damage: [0, 2]);
+
+		$this->assertRestored($this->restore($backend));
+
+		$this->assertGreaterThan(0, $backend->counter->packOpens());
+	}
+
+	public function testAPartialRestoreReadsOnlyWhatItNeeds(): void {
+		$backend = new ReadAheadBackend(new LocalBackend($this->root));
+
+		$this->assertRestored($this->restore($backend, 'big1'), 'big1');
+
+		$this->assertSame(0, $backend->counter->packOpens());
+		$this->assertCount(2, $backend->asked, 'the end of one pack and the start of the next');
+		$total = array_sum(array_map(fn (array $r): int => $r[2], $backend->asked));
+		$this->assertLessThan(21 * 1048576, $total, 'not the whole packs');
+	}
+
+	public function testABackendThatCannotReadAheadNowRestoresAsBefore(): void {
+		$backend = new ReadAheadBackend(new LocalBackend($this->root), unavailable: true);
+
+		$this->assertRestored($this->restore($backend));
+
+		$this->assertGreaterThan(0, $backend->counter->packOpens());
+	}
+
+	public function testAFailingRestoreStillEndsTheReadsAheadAndRemovesTheSpool(): void {
+		// the second range fails, and so does reading it the usual way
+		$backend = new ReadAheadBackend(new LocalBackend($this->root), fail: [1], packsGone: true);
+		$target = $this->tempDir();
+		$repo = Repository::openWithKey($backend, $this->keys, null, null);
+
+		try {
+			$repo->restore($this->snapshot, $target);
+			$this->fail('restore should fail');
+		} catch (BackendException $e) {
+			$this->assertStringStartsWith('Not found', $e->getMessage());
+		}
+
+		$this->assertTrue($backend->ended, 'the generator was ended');
+		$this->assertSame([], glob("$target/.ngb-restore-spool-*"));
+	}
+
+	public function testPlanJoinsBlobsThatFollowEachOtherInAPack(): void {
+		$plan = new ReadAheadPlan('/nowhere');
+		$plan->add('packs/aa/a', 0, 100);
+		$plan->add('packs/aa/a', 100, 100);
+		$plan->add('packs/aa/a', 50, 10); // the same blob again: inside the range
+		$plan->add('packs/aa/a', 200 + ReadAheadPlan::GAP, 100); // a gap it reads along
+		$plan->add('packs/aa/a', 300 + 3 * ReadAheadPlan::GAP, 100); // too far: a new range
+		$plan->add('packs/bb/b', 0, 100);
+		$plan->add('packs/bb/b', 0, 100); // backwards is fine as long as it is inside
+		$plan->add('packs/aa/a', 0, 100); // back to an earlier pack: a new range
+
+		$this->assertSame([
+			['packs/aa/a', 0, 300 + ReadAheadPlan::GAP],
+			['packs/aa/a', 300 + 3 * ReadAheadPlan::GAP, 100],
+			['packs/bb/b', 0, 100],
+			['packs/aa/a', 0, 100],
+		], $plan->ranges());
+	}
+
+	public function testPlanSkipsRangesWhoseBlobsWereReadElsewhere(): void {
+		$plan = new ReadAheadPlan('/nowhere');
+		foreach (range(0, 4) as $p) {
+			$plan->add("packs/0$p/p$p", 0, 10);
+		}
+		$plan->readFrom((function (): \Generator {
+			foreach (range(0, 4) as $p) {
+				$fh = fopen('php://temp', 'w+b');
+				fwrite($fh, str_repeat((string)$p, 10));
+				rewind($fh);
+				yield $p => $fh;
+			}
+		})());
+
+		$this->assertSame('00000', $plan->read('packs/00/p0', 0, 5));
+		$this->assertNull($plan->read('packs/77/moved', 0, 5), 'moved: not in the plan');
+		$this->assertSame('333', $plan->read('packs/03/p3', 2, 3), 'the ranges in between were read elsewhere');
+		$this->assertNull($plan->read('packs/01/p1', 0, 5), 'never backwards');
+		$this->assertSame('44', $plan->read('packs/04/p4', 0, 2));
+	}
+
+	public function testPlanKeepsARangeShorterThanTheMaximum(): void {
+		$plan = new ReadAheadPlan('/nowhere');
+		for ($o = 0; $o < 3 * ReadAheadPlan::MAX_RANGE; $o += 4 * 1048576) {
+			$plan->add('packs/aa/a', $o, 4 * 1048576);
+		}
+		$this->assertCount(3, $plan->ranges());
+		foreach ($plan->ranges() as $r) {
+			$this->assertLessThanOrEqual(ReadAheadPlan::MAX_RANGE, $r[2]);
+		}
+	}
+}
+
+/** Reads ahead from a local repository, one range after the other; can fail or damage ranges. */
+final class ReadAheadBackend implements IBackend, IReadsAhead {
+	public PackOpenCountingBackend $counter;
+	/** @var list<array{0:string, 1:int, 2:int}> */
+	public array $asked = [];
+	public bool $ended = false;
+
+	/**
+	 * @param list<int> $fail ranges given as null
+	 * @param list<int> $damage ranges given with a flipped byte in every blob
+	 */
+	public function __construct(
+		public LocalBackend $inner,
+		private array $fail = [],
+		private array $damage = [],
+		private bool $unavailable = false,
+		/** reading a pack the usual way fails */
+		private bool $packsGone = false,
+		/** this many reads of a snapshot fail, then they work */
+		private int $failSnapshotReads = 0,
+	) {
+		$this->counter = new PackOpenCountingBackend($inner);
+	}
+
+	public function canReadAhead(): bool {
+		return true;
+	}
+
+	public function readAhead(array $ranges, string $spool): ?\Generator {
+		if ($this->unavailable) {
+			return null;
+		}
+		\PHPUnit\Framework\Assert::assertDirectoryExists($spool);
+		$this->asked = $ranges;
+		return (function () use ($ranges): \Generator {
+			try {
+				foreach ($ranges as $i => [$path, $offset, $length]) {
+					if (in_array($i, $this->fail, true)) {
+						yield $i => null;
+						continue;
+					}
+					$data = $this->inner->getRange($path, $offset, $length);
+					if (in_array($i, $this->damage, true)) {
+						for ($k = 0; $k < strlen($data); $k += 4096) {
+							$data[$k] = chr(ord($data[$k]) ^ 1);
+						}
+					}
+					$fh = fopen('php://temp', 'w+b');
+					fwrite($fh, $data);
+					rewind($fh);
+					yield $i => $fh;
+					fclose($fh);
+				}
+			} finally {
+				$this->ended = true;
+			}
+		})();
+	}
+
+	public function put(string $path, $stream): void {
+		$this->counter->put($path, $stream);
+	}
+
+	public int $snapshotReads = 0;
+
+	public function get(string $path) {
+		if (str_starts_with($path, 'snapshots/')) {
+			$this->snapshotReads++;
+			if ($this->snapshotReads <= $this->failSnapshotReads) {
+				throw new BackendException('Connection lost reading ' . $path);
+			}
+		}
+		if ($this->packsGone && str_starts_with($path, 'packs/')) {
+			throw new BackendException('Not found: ' . $path);
+		}
+		return $this->counter->get($path);
+	}
+
+	public function getMany(array $paths): \Generator {
+		return $this->counter->getMany($paths);
+	}
+
+	public function getRange(string $path, int $offset, int $length): string {
+		return $this->counter->getRange($path, $offset, $length);
+	}
+
+	public function getRanges(array $ranges): \Generator {
+		return $this->counter->getRanges($ranges);
+	}
+
+	public function exists(string $path): bool {
+		return $this->counter->exists($path);
+	}
+
+	public function move(string $from, string $to): void {
+		$this->counter->move($from, $to);
+	}
+
+	public function list(string $prefix): array {
+		return $this->counter->list($prefix);
+	}
+
+	public function listFiles(string $dir): array {
+		return $this->counter->listFiles($dir);
+	}
+
+	public function delete(string $path): void {
+		$this->counter->delete($path);
+	}
+}

tests/Unit/Repository/RepositoryTest.php

@@ -66,6 +66,20 @@ class RepositoryTest extends TestCase {
 		$this->assertSame(1, $r2['newBlobs']);
 	}
 
+	public function testCompressedDataSkipsDeflateAndOtherDataIsStillCompressed(): void {
+		$repo = Repository::init($this->backend, 'pw');
+		$text = str_repeat("a line of a log file, much like the one before\n", 30000); // ~1.4 MiB
+		$noise = random_bytes(1048576); // like a photo: deflate saves nothing
+		$stats = [];
+		$textId = $repo->storeData($text, $stats);
+		$textUploaded = $stats['uploaded'];
+		$noiseId = $repo->storeData($noise, $stats);
+		$repo->flushPacks();
+		$this->assertLessThan(strlen($text) / 10, $textUploaded);
+		$this->assertLessThan(strlen($noise) + 1024, $stats['uploaded'] - $textUploaded);
+		$this->assertSame($text . $noise, implode('', iterator_to_array(Repository::open($this->backend, 'pw')->readBlobs([$textId, $noiseId]), false)));
+	}
+
 	public function testPartialRestore(): void {
 		$repo = Repository::init($this->backend, 'pw');
 		$r = $repo->backupDirectory($this->src);
@@ -85,6 +99,20 @@ class RepositoryTest extends TestCase {
 		Repository::init($this->backend, 'pw');
 	}
 
+	public function testInitRefusesALocationWithBackupDataButNoConfig(): void {
+		$repo = Repository::init($this->backend, 'pw');
+		$repo->backupDirectory($this->src);
+		$this->backend->delete('config'); // missing, or not seen for a moment
+
+		try {
+			Repository::init($this->backend, 'pw');
+			$this->fail('a new repository over existing backup data');
+		} catch (RepositoryException $e) {
+			$this->assertStringContainsString('holds backup data', $e->getMessage());
+		}
+		$this->assertFalse($this->backend->exists('config'), 'no new config written');
+	}
+
 	public function testTamperedPackIsDetected(): void {
 		$repo = Repository::init($this->backend, 'pw');
 		$r = $repo->backupDirectory($this->src);

tests/integration/full-restore-roundtrip.sh

@@ -2,11 +2,27 @@
 # 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>
-#   e.g. full-restore-roundtrip.sh 35-apache
+# Usage: full-restore-roundtrip.sh <nextcloud-image-tag> [sqlite|pgsql|mysql] [legacy|sftp|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 "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"
@@ -14,37 +30,99 @@ fail() { echo "FAIL: $*"; exit 1; }
 ok() { echo "ok   $*"; }
 
 cleanup() {
-	docker rm -fv ngb-frt-origin ngb-frt-restore >/dev/null 2>&1 || true
+	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}"; }
 
+# 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
-docker run -d --name ngb-frt-origin --network "$NET" -e SQLITE_DATABASE=nextcloud \
+LOCATION=(local -a null::null -o datadir=/mnt/shared)
+if [ "$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" $ORIGIN_DB \
 	-e NEXTCLOUD_ADMIN_USER=admin -e NEXTCLOUD_ADMIN_PASSWORD=admin \
-	-v "$APP:/var/www/html/custom_apps/ng_backup:ro" -v "$SHARED:/mnt/shared" "$IMAGE" >/dev/null
+	-v "$ORIGIN_APP:/var/www/html/custom_apps/ng_backup:ro" -v "$SHARED:/mnt/shared" "$IMAGE" >/dev/null
 for i in $(seq 1 90); do run_on ngb-frt-origin status 2>/dev/null | grep -q "installed: true" && break; sleep 3; done
 docker exec ngb-frt-origin chown www-data:www-data /var/www/html/custom_apps
 run_on ngb-frt-origin app:enable ng_backup >/dev/null
-ok "origin instance up"
+ok "origin instance up ($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 local -a null::null -o datadir=/mnt/shared --path=repo >/dev/null || fail "target add"
+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 "$NET" -e MAILNAME=mail.domain.tld -e MAIL_ADDRESS=user@domain.tld \
+		-e MAIL_PASS=mypassword ghcr.io/christophwurst/docker-imap-devel:latest >/dev/null
+	run_on ngb-frt-origin app:install mail >/dev/null || fail "install mail on the origin"
+	run_on ngb-frt-origin config:system:set app.mail.verify-tls-peer --type=boolean --value=false >/dev/null
+	sleep 10
+	run_on ngb-frt-origin mail:account:create frtest Test user@domain.tld ngb-frt-imap 993 ssl user@domain.tld mypassword \
+		ngb-frt-imap 25 tls user@domain.tld mypassword >/dev/null || fail "mail account"
+	run_on ngb-frt-origin mail:account:sync -f 1 >/dev/null || fail "mail sync"
+	[ "$(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
+	run_on ngb-frt-origin app:install deck >/dev/null || fail "install deck on the origin"
+	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"
@@ -52,7 +130,11 @@ ok "test data backed up, snapshot $SNAP"
 
 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
-docker run -d --name ngb-frt-restore --network "$NET" -e SQLITE_DATABASE=nextcloud \
+ORIGIN_DBTYPE=$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
@@ -64,16 +146,36 @@ 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"
-run_on ngb-frt-restore backup:target:add offsite local -a null::null -o datadir=/mnt/shared --path=repo >/dev/null || fail "target add on the restore instance"
-run_on ngb-frt-restore backup:list offsite | grep -q "$SNAP" || fail "the origin's snapshot is not listed after connecting the location"
+ADD_OUT=$(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"
 
-OUT=$(run_on ngb-frt-restore backup:restore:full offsite "$SNAP" --no-interaction 2>&1) || {
+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' "$REFUSED" | tail -20; fail "the refusal does not name the missing tables"; }
+	ok "older backup refused without --skip-missing-tables, missing tables named"
+	RESTORE_OPTS+=(--skip-missing-tables)
+fi
+sftp_logins() { docker logs ngb-frt-sftp 2>&1 | grep -c "Accepted password" || true; }
+[ "$MODE" = sftp ] && LOGINS_BEFORE=$(sftp_logins)
+OUT=$(run_on ngb-frt-restore backup:restore:full offsite "$SNAP" "${RESTORE_OPTS[@]}" 2>&1) || {
 	printf '%s\n' "$OUT" | tail -40
 	docker exec ngb-frt-restore sh -c 'tail -c 6000 /var/www/html/data/nextcloud.log' || true
 	fail "restore:full"
 }
-ok "backup:restore:full completed"
+printf '%s\n' "$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 -q "maintenance: false" || 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"
 
 # 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.
@@ -82,9 +184,41 @@ run_on ngb-frt-restore user:list | grep -q frtest || fail "the backed-up user is
 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"
+	[ "$(sql restore "select count(*) from oc_mail_accounts where drafts_mailbox_id is not null")" = 1 ] || fail "the mail account was not restored"
+	[ "$(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"
+echo "FULL RESTORE ROUNDTRIP PASS ($ORIGIN_DBTYPE${MODE:+, $MODE})"