sneak/vaultik
1
0
Fork 0
Code Issues 4 Pull Requests 4 Actions 123 Packages Projects Releases Wiki Activity

Compare commits

base: sneak/vaultik:issue-388-empty-path-prune
Branches Tags
sneak/vaultik:main sneak/vaultik:issue-388-empty-path-prune sneak/vaultik:issue-390-prune-orphan-metadata sneak/vaultik:issue-389-marker-check-put-only sneak/vaultik:next sneak/vaultik:issue-337-purge-keeps-metadata
sneak/vaultik:v1.0.0-rc2 sneak/vaultik:v1.0.0-rc1
..
compare: sneak/vaultik:271eef93a8c739929471e290e2fce19b70a5264a
Branches Tags
sneak/vaultik:issue-388-empty-path-prune sneak/vaultik:issue-390-prune-orphan-metadata sneak/vaultik:issue-389-marker-check-put-only sneak/vaultik:next sneak/vaultik:issue-337-purge-keeps-metadata sneak/vaultik:main
sneak/vaultik:v1.0.0-rc2 sneak/vaultik:v1.0.0-rc1
1 Commits
issue-388-empty-path-prune .. 271eef93a8
Author SHA1 Message Date
sneak 271eef93a8 Make snapshot list report a changed destination instead of advising prune (closes #317)
check / check (push) Waiting to run
Details 
When the local index is bound to a different destination than the
configured one, snapshot list now gives the warning prune, snapshot
purge and snapshot remove refuse with: both destinations and the two
ways out (revert the configuration, or run vaultik database delete).
Below the table it replaces the local-only note and its prune advice.
With --json it goes to stderr through the logger, so stdout stays the
document, whose local rows show remote_present false.

Reading the binding moves out of EnsureStorageBinding into
storageBinding, which records nothing, so the read-only list can call
it without binding a fresh index.

Model: opus-5-5
 2026-10-14 01:20:03 +00:00
75 changed files with 394 additions and 3479 deletions
Expand all files Collapse all files
ARCHITECTURE.md
+5 -19
View File
@@ -279,8 +279,8 @@ Key methods:
- `Scan(ctx, path, snapshotID)` → Main scan operation
Scan phases:
1. **Phase 1**: Walk directory, identify files needing processing
2. **Phase 1b**: Count as deleted the files that the previous snapshot of the same name lists, the walk did not find, and are gone from disk; a file that is excluded, or inside an excluded directory, is not counted
1. **Phase 0**: Detect deleted files from previous snapshots
2. **Phase 1**: Walk directory, identify files needing processing
3. **Phase 2**: Process files (chunk → pack → upload)
#### SnapshotManager
@@ -311,8 +311,6 @@ Repository interfaces:
```
CreateSnapshot(opts)
│
├─► markDestination() // Refuse a destination without the marker, then write it
│
├─► PruneDatabase() // Critical: avoid dedup errors
│
@@ -322,13 +320,13 @@ CreateSnapshot(opts)
│ │
│ ├─► scanner.Scan(ctx, path, snapshotID)
│ │ │
│ │ ├─► Phase 0: detectDeletedFiles()
│ │ │
│ │ ├─► Phase 1: scanPhase()
│ │ │ Walk directory
│ │ │ Check file metadata changes
│ │ │ Build list of files to process
│ │ │
│ │ ├─► Phase 1b: detectDeletedFiles()
│ │ │
│ │ └─► Phase 2: processPhase()
│ │ For each file:
│ │ chunker.ChunkReaderStreaming()
@@ -359,7 +357,7 @@ CreateSnapshot(opts)
## Deduplication Strategy
1. **File-level**: Files and symlinks unchanged since last backup are skipped (metadata comparison: size, mtime, mode, uid, gid, and a symlink's target), unless the file lists a chunk that no uploaded blob holds; such a file is re-chunked
1. **File-level**: Files unchanged since last backup are skipped (metadata comparison: size, mtime, mode, uid, gid), unless the file lists a chunk that no uploaded blob holds; such a file is re-chunked
2. **Chunk-level**: Chunks are content-addressed by SHA256 hash. If a chunk hash already exists in the database, the chunk data is not re-uploaded.
@@ -369,8 +367,6 @@ CreateSnapshot(opts)
```
bucket/
├── vaultik-destination.txt # Marker written by every backup
│
├── blobs/
│ └── {hash[0:2]}/
│ └── {hash[2:4]}/
@@ -382,16 +378,6 @@ bucket/
└── manifest.json.zst # Blob list (for pruning/verification)
```
A destination without `vaultik-destination.txt` is treated as not present
while the local index holds snapshots stored there (`checkDestinationMarker`
in `internal/vaultik/destination_marker.go`): `snapshot create` refuses to
write to it, `prune`, `snapshot purge` and `remote nuke` fail, and
`snapshot list` and `snapshot remove` behave as for a destination that cannot
be listed. This keeps those commands from taking an unplugged volume's empty
mount point for a destination whose snapshots are all gone. The `file://`
backend never creates its destination directory, so a write to a missing one
fails.
The `{remote-key}` directory name is a one-way double SHA-256 hash of the human
snapshot ID, so the human ID (hostname, snapshot name, timestamp) is never
written to the store as a directory name. See
README.md
+24 -117
View File
@@ -24,10 +24,6 @@ grep 'public key' vaultik_backup_private_key.txt
vaultik config set age_recipients.0 age1YOUR_PUBLIC_KEY_HERE
vaultik config set storage_url "file:///Volumes/usbstick/mybackup"
# create the destination directory; vaultik never creates it, so a backup
# to a volume that is not plugged in fails instead of filling the disk
mkdir /Volumes/usbstick/mybackup
# macOS only: grant your terminal app Full Disk Access first
# (System Settings → Privacy & Security → Full Disk Access), otherwise
# the backup will abort with a permission error on protected directories
@@ -96,14 +92,6 @@ vaultik snapshot restore <snapshot-id> ~/vaultik-restore
# 0 3 * * * vaultik snapshot create --cron --prune --keep-newer-than 4w
```
On a destination shared between hosts or users, the prune in that cron line
relies on `prune_grace_period` (default `24h`) to leave the blobs of a backup
another one is still running, so it must be longer than the longest backup
run. It does not protect a blob that backup reuses from an earlier run that
stopped before its manifest: the prune can delete such a blob, and the new
snapshot then cannot be restored. To not depend on the grace period, give each
host its own prefix or directory. See [locking](#locking).
## restoring on another machine
Restoring on a host that never ran the backup — a replacement machine
@@ -190,7 +178,7 @@ vaultik version
* `--verbose`, `-v`: Enable verbose output (on stderr — see below)
* `--debug`: Enable debug output (on stderr — see below)
* `--quiet`, `-q`: Suppress non-error output (also suppresses startup banner)
* `--skip-errors`: Skip files that cannot be read when creating a snapshot, or that cannot be restored when restoring, instead of aborting. Packing and storage errors while creating a snapshot (which would leave a chunk recorded but not stored) still abort the run. A run that skipped anything still finishes but exits non-zero: `snapshot create` keeps the snapshot and counts each file or directory it skipped as failed. A file removed during the backup is also counted as failed but does not change the exit status.
* `--skip-errors`: Skip files that cannot be read when creating a snapshot, or that cannot be restored when restoring, instead of aborting. Packing and storage errors while creating a snapshot (which would leave a chunk recorded but not stored) still abort the run.
### locking
@@ -200,22 +188,7 @@ process-wide lock at `$XDG_DATA_HOME/vaultik/vaultik.pid`
(`~/.local/share/vaultik/vaultik.pid` on Linux) for the whole run. Only
one of them runs at a time: a second one exits immediately with an
"already running" error rather than waiting, so two writers can never
corrupt the local index.
The lock covers one user on one machine. It does not stop another user,
or another host, from writing to the same destination store at the same
time. A backup uploads its blobs before the manifest that lists them, so a
prune from elsewhere at that moment finds blobs no snapshot lists. It
deletes such a blob only once it is older than `prune_grace_period`
(default `24h`), which therefore must be longer than the longest backup run
of any host or user sharing the destination. The grace period does not
protect a blob a backup reuses from an earlier run that stopped before its
manifest: a backup skips the upload of a blob already on the destination, so
that blob keeps the time of its first upload, and a prune from elsewhere
during the backup can delete it; the new snapshot then cannot be restored.
`remote nuke` deletes everything regardless. To not depend on the grace
period, give each host or user its own prefix (or directory) on the
destination.
corrupt the local index or the destination store.
Read-only commands — `info`, `snapshot list`, `snapshot verify`, and
`remote info` — do not take the lock and are never blocked, so they run
@@ -319,29 +292,12 @@ value where a list belongs or a word where a number belongs), is refused.
* `--cron`: Silent on total success; warnings and errors are still printed
(for crontab)
* `--prune`: After backup, drop older snapshots of each backed-up name and
remove orphaned blobs older than `prune_grace_period` from remote storage,
as `prune` does. By default keeps only the latest
snapshot per name; use `--keep-newer-than` for a rolling window. When
`--skip-errors` skipped a file or directory it could not read or list, the
prune does not run and every older snapshot is kept, since one of them may
be the only one that holds what was skipped; the command says so and exits
non-zero. A file removed during the backup does not stop the prune. The
same holds when the backup found nothing in a configured path, as in the
mount point of a volume that is not mounted: the prune does not run, every
older snapshot is kept, and the command names the path and exits non-zero,
on every run until the path holds something again. Take a path that is
empty on purpose out of the config, or remove the older snapshots by hand
with `snapshot purge`.
remove orphaned blobs from remote storage. By default keeps only the latest
snapshot per name; use `--keep-newer-than` for a rolling window.
* `--keep-newer-than <duration>`: With `--prune`, keep snapshots newer than
this duration instead of only the latest (e.g. `4w`, `30d`, `6mo`, `1y`).
Without `--prune`, or with a value that is not a valid duration, the
command fails before the backup starts.
* Fails before it writes anything when a `file://` destination directory
does not exist, or when the local index holds snapshots and the
destination has no `vaultik-destination.txt` (see
[remote storage layout](#remote-storage-layout))
* Fails, before anything is pruned, when a configured path is a symlink
whose target does not exist, as one into a volume that is not mounted
**`snapshot list`**: Show every snapshot known to this host — the union
of the local index and the backup destination store — with timestamps
@@ -375,10 +331,7 @@ gives: revert the configuration, or run `vaultik database delete`.
If the destination store cannot be listed (unmounted volume,
permission denied, network down), the command warns, falls back to the
local index alone, and still exits zero. It does the same when the
destination has no `vaultik-destination.txt` while the local index
holds snapshots stored there, as when a volume mounted at the
destination is unplugged and leaves its empty mount point behind.
local index alone, and still exits zero.
* `--json`: Output in JSON format. Each entry carries `locally_tracked`
(whether the snapshot is in the local index), `remote_key` (the full
64-character storage key), and `remote_present` (whether it was seen
@@ -420,14 +373,13 @@ snapshot in the local index or on the destination store is an error;
with `--local-only`, the snapshot must be in the local index. Local row
cleanup (files, chunks, blobs the snapshot was the last referrer for)
runs automatically. If removing the snapshot's metadata from the
destination store fails (for example because the store is unreachable,
or the local index holds snapshots and the destination has no
`vaultik-destination.txt`), the local-DB removal still completes and a
warning is emitted; run `vaultik snapshot remove <snapshot-id>` again
once the store is reachable to remove the snapshot's metadata from it
(`vaultik prune` does not). For a snapshot that is only on the
destination store, that failure is an error. To wipe everything on the
destination in one go, use `vaultik remote nuke --force`.
destination store fails (for example because the store is unreachable),
the local-DB removal still completes and a warning is emitted; run
`vaultik snapshot remove <snapshot-id>` again once the store is reachable
to remove the snapshot's metadata from it (`vaultik prune` does not). For
a snapshot that is only on the destination store, that failure is an
error. To wipe everything on the destination in one go, use `vaultik
remote nuke --force`.
* `--local-only`: Skip remote cleanup; only touch the local index
* `--dry-run`: Show what would be deleted without deleting
* `--force`: Skip confirmation prompt
@@ -455,28 +407,15 @@ local snapshot whose remote metadata is missing is dropped from the
local index; (2) delete orphaned local rows (files, chunks, blobs no
longer referenced by any completed snapshot); (3) list every remote
manifest on the destination store to compute the still-referenced blob
set and delete any blob not in that set that is older than
`prune_grace_period` (default `24h`). A newer one is kept and counted: it
may belong to a backup still running, on this host or another sharing the
destination store, that has not yet uploaded its manifest. The grace period
does not protect a blob such a backup reuses from an earlier run that stopped
before its manifest: that blob keeps the time of its first upload, so it can
be deleted. Step (3) reads all remote manifests — network cost scales with
the number of snapshots.
`snapshot create --prune` runs the same cleanup automatically; this is the
manual entry point for the same work. If the destination store cannot
be listed, or the local index holds snapshots and the destination has
no `vaultik-destination.txt` (an unplugged volume's empty mount point),
prune fails and deletes nothing. `snapshot purge` does the same. If a
blob cannot be deleted, the command (and `snapshot create --prune`)
exits non-zero.
set and delete any blob not in that set. Step (3) reads all remote
manifests — network cost scales with the number of snapshots. `snapshot
create --prune` runs the same cleanup automatically; this is the
manual entry point for the same work. If a blob cannot be deleted, the
command (and `snapshot create --prune`) exits non-zero.
* `--force`: Skip confirmation prompt
* `--json`: Output stats as JSON. Also skips the confirmation prompt, as
`--force` does. A blob that cannot be deleted is counted in
`blobs_failed`, and the document is printed before the non-zero exit.
A blob kept for being newer than `prune_grace_period`, or because the
listing of the destination gives no time for it, is counted in
`blobs_too_new` and not in `blobs_found`.
**`info`**: Display system configuration, storage settings, encryption
recipients, and local database statistics.
@@ -496,17 +435,11 @@ since `prune` never deletes it.
* `--json`: Output as JSON
**`remote nuke`**: Delete every object under `metadata/` and `blobs/` on
the backup destination store, whatever its name, and then
`vaultik-destination.txt`, leaving the bucket prefix empty. Destructive
and irreversible. This is the single supported way to wipe the entire
destination store. A snapshot is removed from the local index only once
its metadata is deleted from the destination store. If the destination
store cannot be listed, or the local index holds snapshots and the
destination has no `vaultik-destination.txt` (an unplugged volume's
empty mount point), the command fails before it removes anything. If a
listing afterwards still finds anything under `metadata/` or `blobs/`,
the command names each object left and exits non-zero; running it again
deletes what is left.
the backup destination store, whatever its name, leaving the bucket prefix
empty. Destructive and irreversible. This is the single supported way to
wipe the entire destination store. If a listing afterwards still finds
anything there, the command names each object left and exits non-zero;
running it again deletes what is left.
* `--force`: Required to confirm destruction.
**`database delete`**: Delete the local SQLite state database file
@@ -531,12 +464,7 @@ object store. Credentials are read from `s3.access_key_id` and
a local or mounted filesystem. Useful for testing or backing up to a NAS. The
path must be absolute; a relative one is refused when the config loads.
Percent-escapes in the path are decoded, so `my%20stick` and `my stick` name
the same directory. The directory must exist before the first backup: vaultik
never creates it. A directory on a removable volume is gone while the volume is
not mounted, so a backup then fails instead of writing to the disk under the
mount point. The mount point itself stays behind when the volume is unplugged:
there only `vaultik-destination.txt` stops such a backup, and only while the
local index holds snapshots.
the same directory.
**Rclone** (`rclone://remote/path`): Uses rclone's 70+ supported cloud
providers. Requires rclone to be configured separately (`rclone config`).
@@ -551,14 +479,6 @@ being written, a killed upload can leave a truncated object under its name,
which a later backup takes for complete. A leftover `.partial` file is ignored
and can be deleted.
A destination shared between hosts or users, each with its own local index,
relies on `prune_grace_period` to keep one's prune from deleting the blobs of
another's backup still running, so it must be longer than the longest backup
run. It does not protect a blob that backup reuses from an earlier run that
stopped before its manifest, which the prune can delete. To not depend on the
grace period, give each host its own prefix (or directory). See
[locking](#locking).
Legacy S3 configuration via `s3.*` fields (endpoint, bucket, prefix, etc.) is
still supported for backward compatibility. `storage_url` takes precedence if
both are set.
@@ -575,7 +495,6 @@ For an implementation-level view of the internals — the data model, the
```
<bucket>/<prefix>/
├── vaultik-destination.txt # Marker written by every backup
├── blobs/
│ └── <aa>/<bb>/<full_blob_hash>
└── metadata/
@@ -584,16 +503,6 @@ For an implementation-level view of the internals — the data model, the
└── manifest.json.zst # Unencrypted blob list (for pruning)
```
* `vaultik-destination.txt` holds one fixed line of text, with no host
name, path or time. A destination without it is treated as not
present while the local index holds snapshots stored there:
`snapshot create` refuses to write to it, `prune`, `snapshot purge`
and `remote nuke` fail, and `snapshot list` and `snapshot remove`
behave as for a destination that cannot be listed. This keeps an
unplugged volume's empty mount point from being taken for a
destination whose snapshots are all gone. Mount
the volume if it is removable; if the destination was emptied on
purpose, run `vaultik database delete` and back up again.
* Blobs are two-level directory sharded using the first 4 hex chars of the blob hash
* `db.zst.age` is a binary SQLite database (zstd compressed, age encrypted)
containing all file metadata, chunk mappings, and relationships for the snapshot
@@ -645,8 +554,7 @@ format does and does not protect.
1. List all snapshot manifests
2. Build set of all referenced blob hashes
3. List all blobs in storage
4. Delete any blob not in the referenced set that is older than
`prune_grace_period`
4. Delete any blob not in the referenced set
### chunking and deduplication
@@ -691,7 +599,6 @@ complete annotated example also lives in
| `chunk_size` | `10MB` | Average chunk size for content-defined chunking |
| `blob_size_limit` | `10GB` | Maximum blob size before splitting. Must be at least four times `chunk_size` (the largest chunk the chunker can emit), otherwise a single-chunk blob could exceed the limit. A backup needs free temporary space, because each blob is written whole to a temporary file before it is uploaded (up to about `blob_size_limit`; an rclone destination that cannot stream uploads needs about twice that) and the metadata export writes copies of the local index. Temporary files go to `$TMPDIR` (default `/tmp`); with `TMPDIR` unset, SQLite writes one of those copies to `/var/tmp` |
| `compression_level` | `3` | zstd compression level (1-19) |
| `prune_grace_period` | `24h` | How old a blob that no snapshot lists must be before `prune` deletes it. A backup uploads its blobs before the manifest that lists them, so on a destination shared between hosts or users this must be longer than the longest backup run (see [locking](#locking)). It does not protect a blob a backup reuses from an earlier run that stopped before its manifest: that blob keeps the time of its first upload, so a prune can delete it. A duration such as `36h` or `90m`; `0s` deletes such blobs at once |
| `hostname` | system hostname | Hostname used in snapshot IDs |
| `index_path` | platform data dir | Local SQLite index path |
TODO.md
+4 -227
View File
@@ -15,236 +15,13 @@ pre-1.0
# Next Step
The 1.0 work is complete on `next`: the scope settled on
[issue #125](https://git.eeqj.de/sneak/vaultik/issues/125) has landed,
and so has every fix from the defect hunt before the release candidate
([issue #288](https://git.eeqj.de/sneak/vaultik/issues/288)). What is
left is merging `next` to `main` and tagging the release, both the
owner's; a `v*` tag runs the release build in
`.gitea/workflows/release.yml`.
[issue #125](https://git.eeqj.de/sneak/vaultik/issues/125) was the work
already planned for 1.0, and all of it has landed. The mechanism to cut
the tag exists and is exercised; what is left is merging `next` to
`main` and tagging, both the owner's.
# Completed Steps
- 2026-10-14: Stopped `snapshot create --prune` pruning after a backup
that found nothing in a configured path
([issue #388](https://git.eeqj.de/sneak/vaultik/issues/388)), as in
the mount point of a volume that is not mounted. Such a prune could
delete every snapshot still holding that path's files. A configured
path that is a symlink into such a volume now fails the backup.
- 2026-10-14: Stopped `snapshot create --prune` pruning after a backup
that skipped files it could not read
([issue #382](https://git.eeqj.de/sneak/vaultik/issues/382)). Such a
prune could delete the only snapshot still holding those files.
- 2026-10-14: Made `snapshot create --skip-errors` exit non-zero,
instead of 0, when it skips anything it cannot read
([issue #310](https://git.eeqj.de/sneak/vaultik/issues/310)).
- 2026-10-14: Kept the local index when `remote nuke` cannot list or
find the destination store
([issue #292](https://git.eeqj.de/sneak/vaultik/issues/292)). Nuke
had cleared the local snapshot records anyway; it now fails before
removing anything.
- 2026-10-14: Stopped counting directories and unchanged symlinks as
files to back up
([issue #305](https://git.eeqj.de/sneak/vaultik/issues/305)).
- 2026-10-14: Refused a backup destination that an unplugged volume
left empty, as the owner ruled
([issue #239](https://git.eeqj.de/sneak/vaultik/issues/239)). Every
backup now writes `vaultik-destination.txt` at the destination root,
and while the local index holds snapshots stored there, a destination
without it is treated as not present.
- 2026-10-14: Warned about restored ownership only when an entry's
owner or group differs from the recorded one
([issue #316](https://git.eeqj.de/sneak/vaultik/issues/316)); a
restore by a non-root user had warned even when none did.
- 2026-10-14: Made `snapshot list` report a changed destination instead
of advising `prune`, which refuses in that case
([issue #317](https://git.eeqj.de/sneak/vaultik/issues/317)).
- 2026-10-14: Counted a file as deleted by a backup only if the
previous snapshot of the same name listed it
([issue #304](https://git.eeqj.de/sneak/vaultik/issues/304)); files
that snapshot did not list had been counted too.
- 2026-10-14: Named each prefix once in restore, verify and purge
errors, some of which repeated it
([issue #327](https://git.eeqj.de/sneak/vaultik/issues/327)). A deep
verify log line that named S3 whatever the destination now names
storage.
- 2026-10-14: Refused credentials in a storage URL's endpoint or rclone
remote name, which were accepted and could then be printed
([issue #322](https://git.eeqj.de/sneak/vaultik/issues/322)).
- 2026-10-14: Ran `$EDITOR` through the shell in `config edit`, so a
value with arguments, such as `code --wait`, no longer fails
([issue #315](https://git.eeqj.de/sneak/vaultik/issues/315)).
- 2026-10-14: Made `snapshot remove` fail, instead of exiting 0, when
it cannot delete the metadata of a snapshot that is only on the
destination store
([issue #340](https://git.eeqj.de/sneak/vaultik/issues/340)). The
README and the help now say when it prints the `vaultik prune`
follow-up.
- 2026-10-14: Labelled the totals in the local index cleanup before
each backup as totals
([issue #306](https://git.eeqj.de/sneak/vaultik/issues/306)). Each
was shown as `(N remain)`, which read as rows left to clean up.
- 2026-10-13: Freed a cached blob once no file still to restore needs
it ([issue #324](https://git.eeqj.de/sneak/vaultik/issues/324)); one
also used by a file outside the selected paths had stayed in the
temporary cache until the restore ended.
- 2026-10-13: Kept the whole startup error when it contains `): `
([issue #320](https://git.eeqj.de/sneak/vaultik/issues/320)). Such
an error was cut at its last `): `, so the `blob_size_limit` one lost
the setting's name.
- 2026-10-13: Silenced the status lines of `prune` and snapshot removal
under `--cron` and `--quiet`
([issue #294](https://git.eeqj.de/sneak/vaultik/issues/294)).
- 2026-10-13: Read the rclone config file that `RCLONE_CONFIG` names
([issue #321](https://git.eeqj.de/sneak/vaultik/issues/321)); a
remote defined only there had been reported as not found.
- 2026-10-13: Made `/**/` in an exclude pattern match zero directories,
as in gitignore
([issue #338](https://git.eeqj.de/sneak/vaultik/issues/338));
`a/**/*.log` had missed `a/x.log`.
- 2026-10-13: Made the `chunk_size` and `blob_size_limit` defaults and
the `chunk_size` minimum 1000-based, like the size parser and the
docs ([issue #313](https://git.eeqj.de/sneak/vaultik/issues/313)).
- 2026-10-13: Kept a snapshot's remote metadata when `snapshot purge`
cannot remove it from the local index
([issue #337](https://git.eeqj.de/sneak/vaultik/issues/337)); the
purge had deleted the metadata anyway and exited 0.
- 2026-10-13: Made `snapshot restore` fail for a requested path that
matches nothing, which it had ignored
([issue #309](https://git.eeqj.de/sneak/vaultik/issues/309)).
- 2026-10-13: Made `remote nuke` delete every object under `metadata/`
and `blobs/`
([issue #291](https://git.eeqj.de/sneak/vaultik/issues/291)); it had
left some, such as a stray `.DS_Store`, while reporting the store
empty.
- 2026-10-13: Made `config set` create a list for an index under a
missing key
([issue #308](https://git.eeqj.de/sneak/vaultik/issues/308)); it had
written a map, after which no command could load the config.
- 2026-10-13: Listed a `file://` destination through a symlinked
`metadata/` or `blobs/`, which had listed as empty
([issue #296](https://git.eeqj.de/sneak/vaultik/issues/296)). A link
to a missing target now fails the listing
([issue #332](https://git.eeqj.de/sneak/vaultik/issues/332)).
- 2026-10-13: Made `snapshot verify --deep --json` report its blob
counts ([issue #314](https://git.eeqj.de/sneak/vaultik/issues/314));
a failed run had reported 0 missing and 0 verified.
- 2026-10-13: Limited and retried the module download in the Docker
build ([issue #351](https://git.eeqj.de/sneak/vaultik/issues/351)),
which had hung for as long as a stalled connection to the module
proxy lasted.
- 2026-10-13: Recorded each snapshot's uncompressed size when its
backup runs
([issue #360](https://git.eeqj.de/sneak/vaultik/issues/360)). A later
backup could change an older snapshot's UNCOMPRESSED SIZE in
`snapshot list`.
- 2026-10-13: Stopped `snapshot restore --skip-errors --verify`
reporting a file that failed to restore again as a checksum failure
([issue #323](https://git.eeqj.de/sneak/vaultik/issues/323)).
- 2026-10-13: Recorded the stored size of a blob a backup finds already
stored, not the size of its local copy, which can differ, so
`snapshot verify` could fail on a good snapshot
([issue #300](https://git.eeqj.de/sneak/vaultik/issues/300)).
- 2026-10-13: Stopped the local index and the blob upload step ending
the process on a failed close of query results or a failed temp file
cleanup ([issue #345](https://git.eeqj.de/sneak/vaultik/issues/345));
both are now returned as errors.
- 2026-10-13: Closed the snapshot database's storage reader too when
restore or deep verify is interrupted
([issue #356](https://git.eeqj.de/sneak/vaultik/issues/356)).
- 2026-10-13: Made `prune` and `remote nuke` fail when a delete on the
backup destination store fails
([issue #290](https://git.eeqj.de/sneak/vaultik/issues/290)).
- 2026-10-13: Made an S3 listing that the server cuts short an error
([issue #297](https://git.eeqj.de/sneak/vaultik/issues/297)); `prune`
had taken it as complete and could delete blobs still in use.
- 2026-10-13: Made shallow `snapshot verify` report a blob it could not
check apart from a missing one
([issue #318](https://git.eeqj.de/sneak/vaultik/issues/318)); any
error checking a blob had counted as missing, its cause dropped.
- 2026-10-13: Restored the other files when a file's chunk is in no
blob under `--skip-errors`
([issue #326](https://git.eeqj.de/sneak/vaultik/issues/326)); that
file had stopped the restore before anything was restored.
- 2026-10-13: Recorded each snapshot's new chunk size when its backup
runs ([issue #311](https://git.eeqj.de/sneak/vaultik/issues/311)).
`snapshot list` could show a NEW CHUNK SIZE of 0 B for a snapshot
whose change was a modified file.
- 2026-10-13: Made a backup interrupted during a local index write exit
as interrupted
([issue #301](https://git.eeqj.de/sneak/vaultik/issues/301)); it could
end with `FATAL: failed to rollback transaction` and exit 1 instead of
130.
- 2026-10-13: Printed `snapshot list` and `snapshot purge` sizes like
every other command
([issue #312](https://git.eeqj.de/sneak/vaultik/issues/312)). They,
and the `bytes` value in terminal log lines, were 1024-based but
labelled KB or MB, and now use 1000-based units.
- 2026-10-13: Closed each blob's storage reader when restore or deep
verify is interrupted, which ends a stalled read unless it is stuck in
the kernel ([issue #325](https://git.eeqj.de/sneak/vaultik/issues/325)).
- 2026-10-13: Made a mistyped subcommand under `snapshot`, `config`,
`remote`, `database` or `completion` an error
([issue #319](https://git.eeqj.de/sneak/vaultik/issues/319)); each had
printed its help and exited 0.
- 2026-10-13: Made an exclude pattern starting with `**/` match
directly under the snapshot path too, as in gitignore
([issue #303](https://git.eeqj.de/sneak/vaultik/issues/303)).
- 2026-10-13: Refused a relative `file://` storage URL and decoded its
percent-escapes
([issue #299](https://git.eeqj.de/sneak/vaultik/issues/299)); a
relative path had moved with the working directory.
- 2026-10-13: Removed the blob temp file when a backup stops part-way
([issue #302](https://git.eeqj.de/sneak/vaultik/issues/302)); the
half-written blob had stayed in `$TMPDIR`.
- 2026-10-13: Checked `--keep-newer-than` before a backup starts
([issue #307](https://git.eeqj.de/sneak/vaultik/issues/307)); an
invalid value had been read only by the prune after the backup, so
retention never ran.
- 2026-10-13: Stopped `remote info` counting a file under `blobs/` that
is not a blob as an orphaned blob
([issue #295](https://git.eeqj.de/sneak/vaultik/issues/295)). A stray
config.example.yml
-12
View File
@@ -328,18 +328,6 @@ storage_url: "rclone://myremote/path/to/backups"
# Higher = better compression but slower
# Default: 3
compression_level: 5
# How old a blob that no snapshot lists must be before prune deletes it
# A backup uploads its blobs before the manifest that lists them, so on a
# destination shared between hosts or users this must be longer than the
# longest backup run
# It does not protect a blob a backup reuses from an earlier run that stopped
# before its manifest: that blob keeps the time of its first upload, so a
# prune can delete it
# Supports: 36h, 90m, etc.; 0s deletes them at once
# Default: 24h
#prune_grace_period: 24h
# Hostname to use in backup metadata
# Default: system hostname
#hostname: myserver
docs/DATAMODEL.md
+1 -2
View File
@@ -228,8 +228,7 @@ The restore process doesn't use the local database. Instead:
1. **Identify Unreferenced Blobs**
- Query blobs not referenced by any remaining snapshot
- Delete from S3, once older than `prune_grace_period`, and from the local
database
- Delete from S3 and local database
### 6. Incomplete Snapshot Cleanup
docs/REPOSTRUCTURE.md
+2 -7
View File
@@ -4,7 +4,7 @@ This document describes the structure and organization of data stored in the S3
## Overview
Vaultik stores all backup data in an S3-compatible object store. The repository consists of two main components, plus a marker file:
Vaultik stores all backup data in an S3-compatible object store. The repository consists of two main components:
1. **Blobs** - The actual backup data (content-addressed, encrypted)
2. **Metadata** - Snapshot information and manifests (partially encrypted)
@@ -12,7 +12,6 @@ Vaultik stores all backup data in an S3-compatible object store. The repository
```
<bucket>/<prefix>/
├── vaultik-destination.txt
├── blobs/
│ └── <hash[0:2]>/
│ └── <hash[2:4]>/
@@ -25,10 +24,6 @@ Vaultik stores all backup data in an S3-compatible object store. The repository
The metadata subdirectory is named with the **remote key**, a one-way hash of the snapshot ID, not with the human-readable snapshot ID itself. See [Remote Key Derivation](#remote-key-derivation).
## Marker File (`vaultik-destination.txt`)
Every backup writes this file at the root before it uploads anything. It holds one fixed line of plain text and names no host, path or time. A destination without it is treated as not present while the local index holds snapshots stored there: `snapshot create` refuses to write to it, and `prune`, `snapshot purge`, `snapshot remove`, `snapshot list` and `remote nuke` behave as for a destination that cannot be listed. An unplugged volume leaves an empty directory at its mount point, and without the marker that directory would read as a destination whose snapshots are all gone. `remote nuke` deletes the marker last.
## Blobs Directory (`blobs/`)
### Structure
@@ -166,7 +161,7 @@ The prune operation is safe because:
1. It keeps every blob listed in any snapshot's manifest and deletes only blobs that no manifest references
2. Manifests are unencrypted and can be read without keys
3. If any manifest cannot be downloaded or decoded, prune deletes nothing and exits with an error, rather than treating that snapshot's blobs as unreferenced
4. It deletes an unreferenced blob only once the blob is older than `prune_grace_period` (default `24h`). A backup uploads its blobs before the manifest that lists them, so a prune running meanwhile, on this host or another sharing the destination, leaves them as long as no backup run takes longer than the grace period. The grace period does not protect a blob a backup reuses from an earlier run that stopped before its manifest: the backup skips the upload of a blob already on the destination, so that blob keeps the time of its first upload, and a prune before the backup's manifest is written can delete it; the new snapshot then cannot be restored. `remote nuke` has no such check
4. Prune requires exclusive access to the destination: running it during a concurrent backup can race a snapshot whose manifest is not yet written, so do not prune while a backup is in progress
## Restoration Requirements
internal/cli/config.go
-10
View File
@@ -239,16 +239,6 @@ storage_url: ""
# Default: 3
# compression_level: 3
# How old a blob that no snapshot lists must be before prune deletes it.
# A backup uploads its blobs before the manifest that lists them, so on a
# destination shared between hosts or users this must be longer than the
# longest backup run. It does not protect a blob a backup reuses from an
# earlier run that stopped before its manifest: that blob keeps the time of
# its first upload, so a prune can delete it.
# Accepts: 36h, 90m, etc. 0s deletes them at once.
# Default: 24h
# prune_grace_period: 24h
# Hostname used in snapshot IDs. Default: system hostname.
# hostname: myserver
internal/cli/entry_prune_json_test.go
+1 -7
View File
@@ -101,8 +101,7 @@ func TestEntryPruneJSONStdoutIsExactlyOneDocument(t *testing.T) {
// writeHermeticPruneConfig builds a config over a temp directory with an
// empty destination directory and, if seedStale is set, creates the
// index database up front with one snapshot record that has no
// counterpart on the destination store, and gives the destination the
// marker a backup writes. Returns the config path.
// counterpart on the destination store. Returns the config path.
func writeHermeticPruneConfig(t *testing.T, seedStale bool) string {
t.Helper()
@@ -132,11 +131,6 @@ func writeHermeticPruneConfig(t *testing.T, seedStale bool) string {
if seedStale {
seedStaleSnapshotRecord(t, indexPath)
// While the local index holds a snapshot, prune fails on a
// destination without the marker a backup writes.
require.NoError(t, os.WriteFile(
filepath.Join(storeDir, "vaultik-destination.txt"), nil, 0o600))
}
return configPath
internal/cli/entry_prune_quiet_test.go
+2 -6
View File
@@ -5,7 +5,6 @@ import (
"path/filepath"
"strings"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
@@ -15,8 +14,8 @@ import (
const flagCron = "--cron"
// plantUnreferencedBlob writes a blob that no snapshot references to the
// destination store at storeDir, dated long before any prune grace period,
// so that a prune deletes it. Returns its path.
// destination store at storeDir, so that a prune deletes it. Returns its
// path.
func plantUnreferencedBlob(t *testing.T, storeDir string) string {
t.Helper()
@@ -26,9 +25,6 @@ func plantUnreferencedBlob(t *testing.T, storeDir string) string {
require.NoError(t, os.MkdirAll(filepath.Dir(path), 0o750))
require.NoError(t, os.WriteFile(path, []byte("unreferenced"), 0o600))
longAgo := time.Unix(0, 0)
require.NoError(t, os.Chtimes(path, longAgo, longAgo))
return path
}
internal/cli/entry_snapshot_create_prune_test.go
-30
View File
@@ -87,36 +87,6 @@ func TestEntrySnapshotCreateReportsPostBackupPruneFailure(t *testing.T) {
"the new snapshot is on the store beside the planted one")
}
// TestEntrySnapshotCreatePruneExitsNonZeroWhenSourceIsEmpty backs up,
// empties the source directory, as a volume that is not mounted leaves
// its mount point, and runs `snapshot create --prune`. The command exits
// non-zero and reports the backup as completed, not as a failed snapshot
// creation. See https://git.eeqj.de/sneak/vaultik/issues/388.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreatePruneExitsNonZeroWhenSourceIsEmpty(t *testing.T) {
configPath, storeDir := writeBackupConfig(t)
code, _, _ := runEntry(t, flagConfig, configPath, cmdSnapshot, cmdCreate)
require.Equal(t, 0, code)
// writeBackupConfig puts the source directory beside the config file.
require.NoError(t, os.Remove(
filepath.Join(filepath.Dir(configPath), "source", "file.txt")))
code, _, stderr := runEntry(t,
flagConfig, configPath, cmdSnapshot, cmdCreate, flagPrune)
assert.Equal(t, 1, code)
assert.Contains(t, stderr,
"Backup completed, but 1 source path(s) were empty")
assert.NotContains(t, stderr, "Snapshot creation failed")
snapshots, err := os.ReadDir(filepath.Join(storeDir, "metadata"))
require.NoError(t, err)
assert.Len(t, snapshots, 2, "the older snapshot is kept")
}
// writeBackupConfig builds a hermetic config with one small file in its
// source directory and an empty destination store directory. Returns the
// config path and the store directory.
internal/cli/entry_snapshot_create_skip_errors_test.go
-30
View File
@@ -1,30 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
import (
"testing"
"github.com/stretchr/testify/assert"
)
// TestEntrySnapshotCreateSkipErrorsExitsNonZeroWhenItSkips backs up,
// under --skip-errors, a source directory that does not exist, which the
// walk skips. The command exits non-zero and reports the backup as
// completed, not as a failed snapshot creation. See
// https://git.eeqj.de/sneak/vaultik/issues/310.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreateSkipErrorsExitsNonZeroWhenItSkips(t *testing.T) {
// writeBackupConfig would create the source directory.
configPath := writeHermeticPruneConfig(t, false)
code, stdout, stderr := runEntry(t,
flagConfig, configPath, "--skip-errors", cmdSnapshot, cmdCreate)
assert.Equal(t, 1, code)
assert.Contains(t, stdout,
"Files: 1 examined, 0 backed up, 0 unchanged, 1 failed.")
assert.NotContains(t, stdout, "Finished successfully.")
assert.Contains(t, stderr,
"Backup completed, but 1 file(s) could not be read")
assert.NotContains(t, stderr, "Snapshot creation failed")
}
internal/cli/entry_snapshot_purge_test.go
+1 -8
View File
@@ -41,11 +41,6 @@ func TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails(t *testing.T)
// too, so the purge selects it rather than dropping it as stale.
seedStaleSnapshotRecord(t, indexPath)
// While the local index holds a snapshot, purge fails on a
// destination without the marker a backup writes.
require.NoError(t, os.WriteFile(
filepath.Join(dir, "store", "vaultik-destination.txt"), nil, 0o600))
manifestDir := filepath.Join(dir, "store", "metadata",
snapshot.RemoteSnapshotKey(stalePruneSnapshotID))
require.NoError(t, os.MkdirAll(manifestDir, 0o750))
@@ -64,12 +59,10 @@ func TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails(t *testing.T)
require.NoError(t, err)
require.NoError(t, db.Close())
code, _, stderr := runEntry(t, flagConfig, configPath,
code, _, _ := runEntry(t, flagConfig, configPath,
cmdSnapshot, cmdPurge, flagOlderThan, "30d", flagForce)
assert.Equal(t, 1, code)
assert.Contains(t, stderr, "simulated index error",
"the purge must fail at the local-index delete")
assert.FileExists(t, manifestPath,
"the snapshot is still in the local index, so its metadata must stay")
}
internal/cli/prune.go
+1 -6
View File
@@ -20,12 +20,7 @@ Local cleanup drops incomplete snapshots and any files, chunks, or
blobs no longer referenced by a completed snapshot. Remote cleanup
scans every snapshot manifest in the destination store, builds the
set of still-referenced blob hashes, and deletes any blob not in that
set that is older than prune_grace_period (default 24h). A newer one
is kept: it may belong to a backup still running, on this host or
another sharing the destination store, that has not yet uploaded its
manifest. The grace period does not protect a blob such a backup
reuses from an earlier run that stopped before its manifest: that
blob keeps the time of its first upload, so it can be deleted.
set.
Snapshot create --prune runs the same cleanup automatically; this
command is the manual entry point for the same work (e.g. after a
internal/cli/snapshot.go
+1 -11
View File
@@ -115,14 +115,6 @@ on Linux), then /etc/vaultik/config.yml.`,
return
}
if errors.Is(err, vaultik.ErrFilesUnreadable) ||
errors.Is(err, vaultik.ErrSourcePathEmpty) {
log.Error("Backup completed with an error", "error", err)
ReportErrorf("Backup completed, but %v", err)
return
}
log.Error("Snapshot creation failed", "error", err)
ReportErrorf("Snapshot creation failed: %v", err)
})
@@ -133,9 +125,7 @@ on Linux), then /etc/vaultik/config.yml.`,
"Run in cron mode (silent unless warning or error)")
cmd.Flags().BoolVar(&opts.Prune, "prune", false,
"After backup, drop older snapshots of the same name and remove "+
"orphaned blobs older than prune_grace_period (not after a "+
"backup that skipped unreadable files or found a configured "+
"path empty)")
"orphaned blobs")
cmd.Flags().StringVar(&opts.KeepNewerThan, "keep-newer-than", "",
"With --prune: keep snapshots newer than this duration "+
"(e.g. 30d, 4w, 6mo, 1y; m is minutes, mo is months) "+
internal/config/config.go
-17
View File
@@ -11,7 +11,6 @@ import (
"path/filepath"
"sort"
"strings"
"time"
"filippo.io/age"
"git.eeqj.de/sneak/smartconfig"
@@ -39,7 +38,6 @@ const (
defaultChunkSize = Size(10 * 1000 * 1000) // 10MB
defaultS3PartSize = Size(5 * 1024 * 1024) // 5MiB
defaultCompressionLevel = 3
defaultPruneGracePeriod = 24 * time.Hour
minChunkSize = 1000 * 1000 // 1MB
minCompressionLevel = 1
maxCompressionLevel = 19
@@ -69,8 +67,6 @@ var (
errFileURLNotAbsolute = errors.New(
"a file:// storage_url needs an absolute path, " +
"as in file:///path/to/backup")
errNegativePruneGracePeriod = errors.New(
"prune_grace_period must not be negative")
errStorageNotConfigured = errors.New(
"storage not configured; set storage_url or provide s3.endpoint + " +
"s3.bucket + credentials")
@@ -191,13 +187,6 @@ type Config struct {
Snapshots map[string]SnapshotConfig `yaml:"snapshots"`
CompressionLevel int `yaml:"compression_level"`
// PruneGracePeriod is how old a blob no manifest lists must be before
// a prune deletes it. A backup lists its blobs in a manifest only
// once it has uploaded them all, so a younger one may belong to a
// backup still running, on this host or another sharing the
// destination store.
PruneGracePeriod time.Duration `yaml:"prune_grace_period"`
// StorageURL specifies the storage backend using a URL format.
// Takes precedence over S3Config if set.
// Supported formats:
@@ -299,7 +288,6 @@ func Parse(data []byte) (*Config, error) {
ChunkSize: defaultChunkSize,
IndexPath: filepath.Join(xdg.DataHome, appName, "index.sqlite"),
CompressionLevel: defaultCompressionLevel,
PruneGracePeriod: defaultPruneGracePeriod,
S3: S3Config{PartSize: defaultS3PartSize},
}
@@ -368,7 +356,6 @@ func Parse(data []byte) (*Config, error) {
// exceeds the configured limit
// - Compression level must be between 1 and 19
// - S3 part size must be between 5MiB and 5GiB, the part sizes S3 accepts
// - Prune grace period must not be negative
//
// Returns an error describing the first validation failure encountered.
func (c *Config) Validate() error {
@@ -418,10 +405,6 @@ func (c *Config) Validate() error {
return errBadS3PartSize
}
if c.PruneGracePeriod < 0 {
return errNegativePruneGracePeriod
}
return nil
}
internal/config/config_test.go
-68
View File
@@ -6,7 +6,6 @@ import (
"path/filepath"
"strings"
"testing"
"time"
"sneak.berlin/go/vaultik/internal/chunker"
"sneak.berlin/go/vaultik/internal/log"
@@ -413,73 +412,6 @@ func TestDocumentedSizeExamples(t *testing.T) {
}
}
// TestValidatePruneGracePeriod checks that a negative prune_grace_period
// is refused rather than acting like 0s, which deletes unreferenced blobs
// at once, and that 0s and the documented examples are accepted.
func TestValidatePruneGracePeriod(t *testing.T) {
t.Parallel()
const withoutGracePeriod = "snapshots:\n" +
" test:\n" +
" paths: [/tmp/vaultik-test-source]\n" +
"storage_url: file:///tmp/vaultik-test-storage\n"
tests := []struct {
setting string
wantErr error
}{
{"prune_grace_period: 0s", nil},
{"prune_grace_period: 90m", nil},
{"prune_grace_period: 36h", nil},
{"prune_grace_period: -1h", errNegativePruneGracePeriod},
}
for _, tt := range tests {
t.Run(tt.setting, func(t *testing.T) {
t.Parallel()
cfg, err := Parse([]byte(withoutGracePeriod + tt.setting + "\n"))
if err != nil {
t.Fatalf("Parse() unexpected error: %v", err)
}
err = cfg.Validate()
if !errors.Is(err, tt.wantErr) {
t.Fatalf("Validate() error = %v, want %v", err, tt.wantErr)
}
})
}
}
// TestLoadPruneGracePeriod checks that a config file without
// prune_grace_period loads with the documented 24h. The value is written out
// here rather than taken from defaultPruneGracePeriod, so that a change of the
// default fails this test.
func TestLoadPruneGracePeriod(t *testing.T) {
t.Parallel()
const withoutGracePeriod = "snapshots:\n" +
" test:\n" +
" paths: [/tmp/vaultik-test-source]\n" +
"storage_url: file:///tmp/vaultik-test-storage\n"
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(withoutGracePeriod), 0o600)
if err != nil {
t.Fatalf("write config: %v", err)
}
cfg, err := Load(path)
if err != nil {
t.Fatalf("Load() unexpected error: %v", err)
}
if cfg.PruneGracePeriod != 24*time.Hour {
t.Errorf("prune_grace_period = %s, want 24h", cfg.PruneGracePeriod)
}
}
// TestLoadRejectsRelativeFileURL checks that a file:// storage_url with a
// relative path fails at load. Accepted, it would resolve against the
// working directory, so a backup run from another directory would write
internal/database/files.go
-39
View File
@@ -267,45 +267,6 @@ func (r *FileRepository) ListUnderPath(
return files, rows.Err()
}
// ListUnderPathInSnapshot returns the files that ListUnderPath returns
// for path and that the snapshot lists, in no particular order.
func (r *FileRepository) ListUnderPathInSnapshot(
ctx context.Context, path, snapshotID string,
) ([]*File, error) {
path = strings.TrimRight(path, "/")
dirPrefix := path + "/"
query := `
SELECT f.id, f.path, f.source_path, f.mtime, f.mtime_nsec, f.size,
f.mode, f.uid, f.gid, f.link_target
FROM files f
JOIN snapshot_files sf ON sf.file_id = f.id
WHERE sf.snapshot_id = ?
AND (f.path = ? OR substr(f.path, 1, length(?)) = ?)
`
rows, err := r.db.conn.QueryContext(ctx, query,
snapshotID, path, dirPrefix, dirPrefix)
if err != nil {
return nil, fmt.Errorf("querying files: %w", err)
}
defer func() { _ = rows.Close() }()
var files []*File
for rows.Next() {
file, err := r.scanFileRows(rows)
if err != nil {
return nil, fmt.Errorf("scanning file: %w", err)
}
files = append(files, file)
}
return files, rows.Err()
}
// ListIDsWithChunksNotInUploadedBlobs returns the IDs of the files whose
// path starts with prefix and that list at least one chunk held by no
// blob whose upload has completed (uploaded_ts set). A new snapshot
internal/database/files_test.go
-59
View File
@@ -212,65 +212,6 @@ func TestFileRepositoryListUnderPath(t *testing.T) {
}
}
// ListUnderPathInSnapshot leaves out files outside path and files the
// snapshot does not list, though another snapshot lists them.
func TestFileRepositoryListUnderPathInSnapshot(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
files := database.NewFileRepository(db)
snapshots := database.NewSnapshotRepository(db)
listed := map[string][]string{
"one": {"/src/a.txt", "/src2/c.txt"},
"two": {"/src/b.txt"},
}
for snapshotID, paths := range listed {
err := snapshots.Create(ctx, nil, &database.Snapshot{
ID: types.SnapshotID(snapshotID),
Hostname: "host",
StartedAt: time.Now(),
})
if err != nil {
t.Fatalf("failed to create snapshot %s: %v", snapshotID, err)
}
for _, path := range paths {
err := files.Create(ctx, nil, &database.File{
Path: types.FilePath(path),
MTime: time.Now().Truncate(time.Second),
Mode: 0644,
})
if err != nil {
t.Fatalf("failed to create %s: %v", path, err)
}
err = snapshots.AddFile(ctx, nil, snapshotID, path)
if err != nil {
t.Fatalf("failed to add %s to %s: %v", path, snapshotID, err)
}
}
}
found, err := files.ListUnderPathInSnapshot(ctx, "/src", "one")
if err != nil {
t.Fatalf("failed to list files: %v", err)
}
got := make([]string, 0, len(found))
for _, f := range found {
got = append(got, f.Path.String())
}
if !slices.Equal(got, []string{"/src/a.txt"}) {
t.Errorf("got %q, want only /src/a.txt", got)
}
}
func TestFileRepositorySymlink(t *testing.T) {
t.Parallel()
internal/s3/client.go
+3 -8
View File
@@ -8,7 +8,6 @@ import (
"io"
"strings"
"sync/atomic"
"time"
"github.com/aws/aws-sdk-go-v2/aws"
"github.com/aws/aws-sdk-go-v2/config"
@@ -303,10 +302,7 @@ func IsNotFound(err error) bool {
type ObjectInfo struct {
Key string
Size int64
// ModTime is the object's LastModified time. Only ListObjectsStream
// sets it.
ModTime time.Time
Err error
Err error
}
// ListObjectsStream lists objects with the given prefix and returns a channel.
@@ -347,9 +343,8 @@ func (c *Client) ListObjectsStream(
}
ch <- ObjectInfo{
Key: key,
Size: *obj.Size,
ModTime: aws.ToTime(obj.LastModified),
Key: key,
Size: *obj.Size,
}
}
}
internal/snapshot/module.go
+11 -15
View File
@@ -16,9 +16,6 @@ type ScannerParams struct {
Fs afero.Fs
Exclude []string // Exclude patterns (combined global + snapshot-specific)
SkipErrors bool // Skip file read errors (log loudly but continue)
// PreviousSnapshotID is the most recent completed snapshot of the
// same name, "" for none.
PreviousSnapshotID string
}
// Module exports backup functionality as an fx module.
@@ -47,18 +44,17 @@ func provideScannerFactory(
}
return NewScanner(ScannerConfig{
FS: params.Fs,
ChunkSize: cfg.ChunkSize.Int64(),
Repositories: repos,
Storage: storer,
MaxBlobSize: cfg.BlobSizeLimit.Int64(),
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: excludes,
SkipErrors: params.SkipErrors,
PreviousSnapshotID: params.PreviousSnapshotID,
FS: params.Fs,
ChunkSize: cfg.ChunkSize.Int64(),
Repositories: repos,
Storage: storer,
MaxBlobSize: cfg.BlobSizeLimit.Int64(),
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: excludes,
SkipErrors: params.SkipErrors,
})
}
}
internal/snapshot/progress_test.go
+2 -1
View File
@@ -78,7 +78,8 @@ func TestProgressPercentWithSecondPathSmaller(t *testing.T) {
stats := progress.GetStats()
// With both paths counted, the percentage must not exceed 100%.
// Directories count toward the total size but produce no chunks, so
// the percentage ends just under 100%.
percent := float64(stats.BytesProcessed.Load()) /
float64(stats.TotalSize.Load()) * 100
if percent > 100 {
internal/snapshot/scanner.go
+114 -273
View File
@@ -58,10 +58,6 @@ type Scanner struct {
compressionLevel int
ageRecipient string
snapshotID string // Current snapshot being processed
// previousSnapshotID is the most recent completed snapshot of the
// same name, "" for none. Only a file it lists can be counted as
// deleted.
previousSnapshotID string
// currentSourcePath is the source directory being scanned, stored with
// each file record.
currentSourcePath string
@@ -133,20 +129,15 @@ type ScannerConfig struct {
// SkipErrors skips files that cannot be opened or read (log loudly but
// continue); packer, database, encryption, and upload errors still abort.
SkipErrors bool
// PreviousSnapshotID is the most recent completed snapshot of the
// same name, "" for none.
PreviousSnapshotID string
}
// ScanResult contains the results of a scan operation. Files and bytes
// are counted per file: BytesScanned is the size of the new and changed
// files, BytesSkipped that of the unchanged ones. FilesFailed counts the
// new and changed files that phase 2 could not store, each entry removed
// after the walk listed its directory and, under --skip-errors, each
// entry the walk could not read, such as a directory it could not list;
// FilesScanned includes them and BytesScanned does not. ChunksCreated
// counts the chunks that were not already stored, and NewChunkSize is
// their total size.
// new and changed files that phase 2 could not store; FilesScanned
// includes them and BytesScanned does not. ChunksCreated counts the
// chunks that were not already stored, and NewChunkSize is their total
// size.
type ScanResult struct {
FilesScanned int
FilesSkipped int
@@ -163,17 +154,6 @@ type ScanResult struct {
UploadDuration time.Duration
StartTime time.Time
EndTime time.Time
// FilesUnreadable is the part of FilesFailed that --skip-errors
// skipped because it could not be read or listed; the rest are files
// removed after the walk listed them.
FilesUnreadable int
// EntriesFound counts the entries the walk found that no exclude
// pattern matches, leaving out the scanned path itself when it is a
// directory. It is zero for an empty directory, such as the mount
// point of a volume that is not mounted.
EntriesFound int
}
// NewScanner creates a new scanner instance
@@ -227,7 +207,6 @@ func NewScanner(cfg ScannerConfig) *Scanner {
compiledExclude: compiledExclude,
progress: progress,
skipErrors: cfg.SkipErrors,
previousSnapshotID: cfg.PreviousSnapshotID,
ui: uiw,
pendingChunkHashes: make(map[string]struct{}),
}
@@ -279,9 +258,8 @@ func (s *Scanner) Scan(
filesToProcess := scanResult.FilesToProcess
// Phase 1b: Detect deleted files by comparing the previous snapshot
// of this name against scanned files
err = s.detectDeletedFiles(ctx, path, existingFiles, result)
// Phase 1b: Detect deleted files by comparing DB against scanned files
err = s.detectDeletedFilesFromMap(ctx, knownFiles, existingFiles, result)
if err != nil {
return nil, fmt.Errorf("detecting deleted files: %w", err)
}
@@ -297,11 +275,6 @@ func (s *Scanner) Scan(
}
}
err = s.recordDirectories(ctx, scanResult.Directories)
if err != nil {
return nil, err
}
// Summarize scan phase results and update progress
s.summarizeScanPhase(result, filesToProcess)
@@ -466,8 +439,9 @@ func (s *Scanner) summarizeScanPhase(
}
// loadKnownFiles loads the known files at and beneath path from the
// database into a map for fast lookup. This avoids per-file database
// queries during the scan phase.
// database into a map for fast lookup. Every loaded file the scan does
// not find is counted as deleted. This avoids per-file database queries
// during the scan phase.
func (s *Scanner) loadKnownFiles(
ctx context.Context, path string,
) (map[string]*database.File, error) {
@@ -873,15 +847,14 @@ func (s *Scanner) batchInsertFileData(
// ScanPhaseResult contains the results of the scan phase
type ScanPhaseResult struct {
FilesToProcess []*FileToProcess
UnchangedFileIDs []types.FileID // IDs of unchanged files to associate with snapshot
Directories []*FileToProcess // Every directory found, to record
UnchangedFileIDs []types.FileID // IDs of unchanged files to associate with snapshot
}
// scanPhase performs the initial directory scan to identify files to process
// It uses the pre-loaded knownFiles map for fast change detection without DB
// queries. It also populates existingFiles map for deletion detection.
// Returns files needing processing, IDs of unchanged files for snapshot
// association, and the directories found.
// Returns files needing processing and IDs of unchanged files for snapshot
// association.
func (s *Scanner) scanPhase(
ctx context.Context,
path string,
@@ -889,10 +862,8 @@ func (s *Scanner) scanPhase(
existingFiles map[string]struct{},
knownFiles map[string]*database.File,
) (*ScanPhaseResult, error) {
// Use known file count as estimate for progress (accurate for
// subsequent backups). The walk does not count directories, so the
// estimate leaves them out.
estimatedTotal := countNonDirectories(knownFiles)
// Use known file count as estimate for progress (accurate for subsequent backups)
estimatedTotal := int64(len(knownFiles))
collector := &scanCollector{}
@@ -903,28 +874,8 @@ func (s *Scanner) scanPhase(
log.Debug("Starting directory walk", "path", path)
walkFn := func(filePath string, info os.FileInfo, err error) error {
// Check exclude patterns first, so an excluded entry that is gone
// or cannot be looked up is neither counted nor reported. For
// directories, skip the entire subtree. info is nil when the
// walk could not look the entry up.
if s.shouldExclude(filePath, path) {
if info != nil && info.IsDir() {
return filepath.SkipDir
}
return nil
}
// The source path is in no directory listing, so its absence is
// an error rather than a removal.
if errors.Is(err, os.ErrNotExist) && filePath != path {
countRemovedDuringWalk(filePath, existingFiles, result)
return nil
}
if err != nil {
return s.handleWalkError(filePath, err, result)
return s.handleWalkError(filePath, err)
}
// Check context cancellation
@@ -934,14 +885,18 @@ func (s *Scanner) scanPhase(
default:
}
// The scanned directory itself is not an entry found in it.
if filePath != path || !info.IsDir() {
result.EntriesFound++
// Check exclude patterns - for directories, skip the entire subtree
if s.shouldExclude(filePath, path) {
if info.IsDir() {
return filepath.SkipDir
}
return nil
}
// Handle symlinks and directories
handled, err := s.recordSpecialEntry(
filePath, info, existingFiles, knownFiles, collector, result)
filePath, info, existingFiles, collector, result)
if handled {
return err
}
@@ -951,8 +906,17 @@ func (s *Scanner) scanPhase(
return nil
}
filesScanned, changedCount := s.recordRegularFile(
filePath, info, existingFiles, knownFiles, collector, result)
// Track this file as existing (for deletion detection)
existingFiles[filePath] = struct{}{}
// Check file against in-memory map (no DB query!)
file, needsProcessing := s.checkFileInMemory(filePath, info, knownFiles)
filesScanned, changedCount := collector.recordRegularFile(
filePath, info, file, needsProcessing)
// Update result stats
s.updateScanEntryStats(result, needsProcessing, info)
// Output periodic status
if time.Since(lastStatusTime) >= scanStatusInterval {
@@ -972,45 +936,27 @@ func (s *Scanner) scanPhase(
return &ScanPhaseResult{
FilesToProcess: collector.filesToProcess,
UnchangedFileIDs: collector.unchangedFileIDs,
Directories: collector.directories,
}, nil
}
// countNonDirectories returns how many of files are not directories.
func countNonDirectories(files map[string]*database.File) int64 {
var count int64
for _, f := range files {
if f.Mode&uint32(os.ModeDir) == 0 {
count++
}
}
return count
}
// recordSpecialEntry records symlinks and directories (which have no
// data to chunk) and reports whether it handled the entry. A symlink is
// counted and checked for changes as a regular file is; a directory is
// set aside to be recorded and is not counted. For a symlink whose
// target cannot be read it returns handleWalkError's result.
// data to chunk) and reports whether it handled the entry. For a symlink
// whose target cannot be read it returns handleWalkError's result.
func (s *Scanner) recordSpecialEntry(
filePath string, info os.FileInfo,
existingFiles map[string]struct{},
knownFiles map[string]*database.File,
collector *scanCollector, result *ScanResult,
) (bool, error) {
// Handle symlinks
if info.Mode()&os.ModeSymlink != 0 {
file, err := s.buildSymlinkEntry(filePath, info)
if err != nil {
return true, s.handleWalkError(filePath, err, result)
return true, s.handleWalkError(filePath, err)
}
existingFiles[filePath] = struct{}{}
needsProcessing := s.checkFileInMemory(file, knownFiles)
collector.recordFile(filePath, info, file, needsProcessing)
s.updateScanEntryStats(result, needsProcessing, info)
collector.addToProcess(filePath, info, file)
s.updateScanEntryStats(result, true, info)
return true, nil
}
@@ -1020,7 +966,7 @@ func (s *Scanner) recordSpecialEntry(
if info.IsDir() {
file := s.buildDirectoryEntry(filePath, info)
existingFiles[filePath] = struct{}{}
collector.addDirectory(filePath, info, file)
collector.addToProcess(filePath, info, file)
return true, nil
}
@@ -1028,62 +974,15 @@ func (s *Scanner) recordSpecialEntry(
return false, nil
}
// recordRegularFile records a regular file as recordSpecialEntry does a
// symlink and returns the running scanned and changed counts.
func (s *Scanner) recordRegularFile(
filePath string, info os.FileInfo,
existingFiles map[string]struct{},
knownFiles map[string]*database.File,
collector *scanCollector, result *ScanResult,
) (int64, int) {
// Track this file as existing (for deletion detection)
existingFiles[filePath] = struct{}{}
// Check file against in-memory map (no DB query!)
file := s.buildRegularFileEntry(filePath, info)
needsProcessing := s.checkFileInMemory(file, knownFiles)
filesScanned, changedCount := collector.recordFile(
filePath, info, file, needsProcessing)
// Update result stats
s.updateScanEntryStats(result, needsProcessing, info)
return filesScanned, changedCount
}
// countRemovedDuringWalk counts an entry that was in its directory's
// listing but was gone when the walk looked it up, like a file removed
// before phase 2 reads it: as examined and failed, and not as an error,
// with or without --skip-errors.
func countRemovedDuringWalk(
filePath string, existingFiles map[string]struct{}, result *ScanResult,
) {
log.Warn("File was deleted during the directory walk, skipping",
"path", filePath)
// The walk found it, so it is not also counted as deleted.
existingFiles[filePath] = struct{}{}
result.FilesScanned++
result.FilesFailed++
}
// handleWalkError deals with a filesystem error surfaced by the walk:
// under --skip-errors the entry is skipped with a UI notice and counted
// as examined, failed and unreadable, otherwise the error is fatal.
func (s *Scanner) handleWalkError(
filePath string, err error, result *ScanResult,
) error {
// skipped (with a UI notice) under --skip-errors, fatal otherwise.
func (s *Scanner) handleWalkError(filePath string, err error) error {
if s.skipErrors {
log.Error("Failed to access file (skipping due to --skip-errors)",
"path", filePath, "error", err)
s.ui.Errorf("Failed to access %s: %v. Skipping (--skip-errors).",
s.ui.Path(filePath), err)
result.FilesScanned++
result.FilesFailed++
result.FilesUnreadable++
return nil // Continue scanning
}
@@ -1097,29 +996,28 @@ type scanCollector struct {
mu sync.Mutex
filesToProcess []*FileToProcess
unchangedFileIDs []types.FileID // Just IDs - no new records needed
directories []*FileToProcess
filesScanned int64
}
// addDirectory sets a directory aside to be recorded. It is not counted
// as a file.
func (c *scanCollector) addDirectory(
// addToProcess queues a file entry for processing.
func (c *scanCollector) addToProcess(
path string, info os.FileInfo, file *database.File,
) {
c.mu.Lock()
defer c.mu.Unlock()
c.directories = append(c.directories, &FileToProcess{
c.filesToProcess = append(c.filesToProcess, &FileToProcess{
Path: path,
FileInfo: info,
File: file,
})
c.filesScanned++
}
// recordFile records a regular file or symlink as changed (to process)
// or unchanged (snapshot association only) and returns the running
// scanned and changed counts.
func (c *scanCollector) recordFile(
// recordRegularFile records a regular file as changed (to process) or
// unchanged (snapshot association only) and returns the running scanned
// and changed counts.
func (c *scanCollector) recordRegularFile(
path string, info os.FileInfo, file *database.File, needsProcessing bool,
) (int64, int) {
c.mu.Lock()
@@ -1222,28 +1120,7 @@ func (s *Scanner) printScanProgressLine(
}
}
// buildRegularFileEntry creates a File record for a regular file, with
// no ID: checkFileInMemory sets it.
func (s *Scanner) buildRegularFileEntry(path string, info os.FileInfo) *database.File {
var uid, gid uint32
if stat, ok := info.Sys().(*syscall.Stat_t); ok {
uid = stat.Uid
gid = stat.Gid
}
return &database.File{
Path: types.FilePath(path),
SourcePath: types.SourcePath(s.currentSourcePath),
MTime: info.ModTime(),
Size: info.Size(),
Mode: uint32(info.Mode()),
UID: uid,
GID: gid,
}
}
// buildSymlinkEntry creates a File record for a symlink, with no ID:
// checkFileInMemory sets it.
// buildSymlinkEntry creates a File record for a symlink.
func (s *Scanner) buildSymlinkEntry(
path string, info os.FileInfo,
) (*database.File, error) {
@@ -1259,6 +1136,7 @@ func (s *Scanner) buildSymlinkEntry(
}
return &database.File{
ID: types.NewFileID(),
Path: types.FilePath(path),
SourcePath: types.SourcePath(s.currentSourcePath),
MTime: info.ModTime(),
@@ -1290,22 +1168,6 @@ func (s *Scanner) buildDirectoryEntry(path string, info os.FileInfo) *database.F
}
}
// recordDirectories records every directory the walk found. A directory
// has no data to back up, so it is not among the files counted and
// backed up.
func (s *Scanner) recordDirectories(
ctx context.Context, directories []*FileToProcess,
) error {
for _, dir := range directories {
err := s.recordNonRegularFile(ctx, dir)
if err != nil {
return fmt.Errorf("recording directory %s: %w", dir.Path, err)
}
}
return nil
}
// recordNonRegularFile writes a symlink or directory entry to the database
// and associates it with the current snapshot. No chunking is performed.
func (s *Scanner) recordNonRegularFile(ctx context.Context, ftp *FileToProcess) error {
@@ -1319,36 +1181,62 @@ func (s *Scanner) recordNonRegularFile(ctx context.Context, ftp *FileToProcess)
})
}
// checkFileInMemory reports whether a regular file or symlink needs
// processing, and gives file the ID of its known record, or a new ID for
// a new path.
// checkFileInMemory checks if a file needs processing using the in-memory map
// No database access is performed - this is purely CPU/memory work
func (s *Scanner) checkFileInMemory(
file *database.File, knownFiles map[string]*database.File,
) bool {
existingFile, exists := knownFiles[file.Path.String()]
path string, info os.FileInfo, knownFiles map[string]*database.File,
) (*database.File, bool) {
var uid, gid uint32
if stat, ok := info.Sys().(*syscall.Stat_t); ok {
uid = stat.Uid
gid = stat.Gid
}
// Check against in-memory map first to get existing ID if available
existingFile, exists := knownFiles[path]
// Create file record with ID set upfront
// For new files, generate UUID immediately so it's available for chunk associations
// For existing files, reuse the existing ID
var fileID types.FileID
if exists {
fileID = existingFile.ID
} else {
fileID = types.NewFileID()
}
file := &database.File{
ID: fileID,
Path: types.FilePath(path),
SourcePath: types.SourcePath(s.currentSourcePath),
MTime: info.ModTime(),
Size: info.Size(),
Mode: uint32(info.Mode()),
UID: uid,
GID: gid,
}
// New file - needs processing
if !exists {
file.ID = types.NewFileID()
return true
return file, true
}
file.ID = existingFile.ID
// No uploaded blob holds one of its chunks (see loadFilesToRechunk)
if _, rechunk := s.filesToRechunk[file.ID]; rechunk {
return true
if _, rechunk := s.filesToRechunk[fileID]; rechunk {
return file, true
}
// Check if file has changed
return existingFile.Size != file.Size ||
if existingFile.Size != file.Size ||
!existingFile.MTime.Equal(file.MTime) ||
existingFile.Mode != file.Mode ||
existingFile.UID != file.UID ||
existingFile.GID != file.GID ||
existingFile.LinkTarget != file.LinkTarget
existingFile.GID != file.GID {
return file, true
}
// File unchanged
return file, false
}
// batchAddFilesToSnapshot adds existing file IDs to the snapshot association table
@@ -1475,16 +1363,17 @@ func (s *Scanner) processPhase(
return s.finalizeProcessPhase(ctx, result)
}
// processFileWithErrorHandling records a symlink, or wraps
// processFileWithErrorHandling records a directory or symlink, or wraps
// processFileStreaming for a regular file with error recovery for deleted
// files and skip-errors mode. Returns (skipped, error).
func (s *Scanner) processFileWithErrorHandling(
ctx context.Context, fileToProcess *FileToProcess, result *ScanResult,
) (bool, error) {
// A symlink has no data to open or read; it is only recorded in the
// local index. An error recording it stops the run even under
// --skip-errors, or the snapshot would complete without it.
if os.FileMode(fileToProcess.File.Mode)&os.ModeSymlink != 0 {
// A directory or symlink has no data to open or read; it is only
// recorded in the local index. An error recording it stops the run
// even under --skip-errors, or the snapshot would complete without it.
mode := os.FileMode(fileToProcess.File.Mode)
if mode&os.ModeSymlink != 0 || mode.IsDir() {
err := s.recordNonRegularFile(ctx, fileToProcess)
if err != nil {
return false, fmt.Errorf("processing file %s: %w", fileToProcess.Path, err)
@@ -1525,7 +1414,6 @@ func (s *Scanner) processFileWithErrorHandling(
s.ui.Path(fileToProcess.Path), err)
countFailedFile(fileToProcess, result)
result.FilesUnreadable++
return true, nil
}
@@ -2066,29 +1954,21 @@ func (s *Scanner) queueFileForBatchInsert(
})
}
// detectDeletedFiles counts as deleted each file at or beneath path that
// the previous snapshot of this name lists, the walk did not find, and
// is gone from disk. A file that is excluded, or inside an excluded
// directory, is not counted: the walk skips it whether or not it is
// still on disk.
func (s *Scanner) detectDeletedFiles(
// detectDeletedFilesFromMap finds files that existed in previous snapshots
// but no longer exist. Uses pre-loaded maps to avoid any filesystem or
// database access.
func (s *Scanner) detectDeletedFilesFromMap(
ctx context.Context,
path string,
knownFiles map[string]*database.File,
existingFiles map[string]struct{},
result *ScanResult,
) error {
if s.previousSnapshotID == "" {
if len(knownFiles) == 0 {
return nil
}
previousFiles, err := s.repos.Files.ListUnderPathInSnapshot(
ctx, path, s.previousSnapshotID)
if err != nil {
return fmt.Errorf("listing files of snapshot %s: %w",
s.previousSnapshotID, err)
}
for _, file := range previousFiles {
// Check each known file against the enumerated set (no filesystem access needed)
for path, file := range knownFiles {
// Check context cancellation periodically
select {
case <-ctx.Done():
@@ -2096,22 +1976,13 @@ func (s *Scanner) detectDeletedFiles(
default:
}
filePath := file.Path.String()
_, exists := existingFiles[filePath]
if exists || s.excludedOrInExcludedDir(filePath, path) {
continue
// Check if the file exists in our enumerated set
if _, exists := existingFiles[path]; !exists {
// File has been deleted
result.FilesDeleted++
result.BytesDeleted += file.Size
log.Debug("Detected deleted file", "path", path, "size", file.Size)
}
// Under --skip-errors the walk also misses what it cannot reach,
// such as the files in a directory it cannot open.
if !s.goneFromDisk(filePath) {
continue
}
result.FilesDeleted++
result.BytesDeleted += file.Size
log.Debug("Detected deleted file", "path", filePath, "size", file.Size)
}
if result.FilesDeleted > 0 {
@@ -2122,36 +1993,6 @@ func (s *Scanner) detectDeletedFiles(
return nil
}
// excludedOrInExcludedDir reports whether filePath, which is at or
// beneath rootPath, or any directory between rootPath and it, matches an
// exclude pattern. A pattern such as */.local/share/Trash matches the
// directory but not the files inside it, which the walk skips too.
func (s *Scanner) excludedOrInExcludedDir(filePath, rootPath string) bool {
for p := filePath; len(p) > len(rootPath); p = filepath.Dir(p) {
if s.shouldExclude(p, rootPath) {
return true
}
}
return false
}
// goneFromDisk reports whether looking filePath up on disk finds that
// it does not exist. Like the walk, it does not follow a symlink, so a
// symlink whose target is gone is still on disk. A file whose directory
// was replaced by a regular file is gone too, though the lookup reports
// "not a directory".
func (s *Scanner) goneFromDisk(filePath string) bool {
var err error
if lstater, ok := s.fs.(afero.Lstater); ok {
_, _, err = lstater.LstatIfPossible(filePath)
} else {
_, err = s.fs.Stat(filePath)
}
return errors.Is(err, os.ErrNotExist) || errors.Is(err, syscall.ENOTDIR)
}
// wrapPermissionError augments permission errors with platform-specific
// remediation instructions. On macOS, TCC-protected directories (Calendars,
// Reminders, Photos, etc.) return EPERM unless the running application has
internal/snapshot/scanner_estimate_test.go
-28
View File
@@ -1,28 +0,0 @@
//nolint:testpackage // exercises the unexported countNonDirectories helper
package snapshot
import (
"os"
"testing"
"sneak.berlin/go/vaultik/internal/database"
)
// The walk counts regular files and symlinks, not directories, so the
// estimate of its count made from the local index's records leaves the
// directories out. See https://git.eeqj.de/sneak/vaultik/issues/305.
func TestCountNonDirectories(t *testing.T) {
t.Parallel()
known := map[string]*database.File{
"/src": {Mode: uint32(os.ModeDir | 0o755)},
"/src/sub": {Mode: uint32(os.ModeDir | 0o755)},
"/src/a.txt": {Mode: 0o644},
"/src/link": {Mode: uint32(os.ModeSymlink | 0o777), LinkTarget: "a.txt"},
}
got := countNonDirectories(known)
if got != 2 {
t.Errorf("countNonDirectories = %d, want 2", got)
}
}
internal/storage/conformance_test.go
+3 -35
View File
@@ -8,7 +8,6 @@ import (
"reflect"
"sort"
"testing"
"time"
"sneak.berlin/go/vaultik/internal/storage"
)
@@ -20,17 +19,15 @@ import (
// constructor, so the contract is defined once.
//
// It exercises the public Storer interface: round-trip, stat, list with
// prefix filtering, the modification time ListStream reports, overwrite,
// delete, delete-of-missing, and not-found on Get and Stat. Each section
// takes its own fresh backend instance, so the order of sections never
// matters and no section sees another's objects.
// prefix filtering, overwrite, delete, delete-of-missing, and not-found on
// Get and Stat. Each section takes its own fresh backend instance, so the
// order of sections never matters and no section sees another's objects.
func runStorerConformance(t *testing.T, newStorer func(*testing.T) storage.Storer) {
t.Helper()
conformanceRoundTrip(t, newStorer(t))
conformanceOverwrite(t, newStorer(t))
conformanceList(t, newStorer(t))
conformanceListStreamModTime(t, newStorer(t))
conformanceDelete(t, newStorer(t))
conformanceNotFound(t, newStorer(t))
}
@@ -121,35 +118,6 @@ func conformanceList(t *testing.T, s storage.Storer) {
}
}
// conformanceListStreamModTime checks that ListStream gives an object
// just written a modification time of about now, which prune compares
// with its grace period.
func conformanceListStreamModTime(t *testing.T, s storage.Storer) {
t.Helper()
ctx := context.Background()
err := s.Put(ctx, "blobs/dd/written-now", bytes.NewReader([]byte("data")))
if err != nil {
t.Fatalf("Put: %v", err)
}
var listed []storage.ObjectInfo
for info := range s.ListStream(ctx, "blobs/") {
listed = append(listed, info)
}
if len(listed) != 1 || listed[0].Err != nil {
t.Fatalf("ListStream(\"blobs/\") = %v, want the one object", listed)
}
if time.Since(listed[0].ModTime).Abs() > time.Minute {
t.Errorf("ListStream ModTime = %v, want within a minute of now",
listed[0].ModTime)
}
}
// conformanceDelete checks that Delete removes an object and that deleting
// a missing key is not an error.
func conformanceDelete(t *testing.T, s storage.Storer) {
internal/storage/file.go
+6 -23
View File
@@ -21,13 +21,9 @@ type FileStorer struct {
// NewFileStorer creates a new filesystem storage backend.
//
// Construction is intentionally cheap and does not touch the filesystem.
// The backend never creates basePath: the user does, so that when
// basePath is a directory on an unplugged volume, a write fails instead
// of landing on the disk under the mount point. This does not hold when
// basePath is the mount point itself, which stays behind when its volume
// is unplugged.
// Put and PutWithProgress fail on a missing basePath and create the
// directories below it as needed.
// The basePath is recorded; the directory is created lazily on first
// write. Write operations (Put/PutWithProgress) call MkdirAll for the
// per-blob parent directory, which also covers basePath on first use.
// Get and Stat report a key under a missing basePath as ErrNotFound.
// List and ListStream fail on a missing basePath, because listing it as
// an empty store would make `prune` drop every local snapshot record.
@@ -235,9 +231,8 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
// Normalize path separators
relPath = strings.ReplaceAll(relPath, string(filepath.Separator), "/")
ch <- ObjectInfo{
Key: relPath,
Size: info.Size(),
ModTime: info.ModTime(),
Key: relPath,
Size: info.Size(),
}
}
@@ -304,19 +299,7 @@ func (f *FileStorer) writeAtomic(
path := f.fullPath(key)
dir := filepath.Dir(path)
// Checked on every write, so a destination that disappears part-way
// through a backup fails it rather than being recreated by MkdirAll.
_, err := f.fs.Stat(f.basePath)
if os.IsNotExist(err) {
return fmt.Errorf("destination directory does not exist; "+
"create it, or mount the volume it is on: %w", err)
}
if err != nil {
return fmt.Errorf("checking destination directory: %w", err)
}
err = f.fs.MkdirAll(dir, storageDirPerm)
err := f.fs.MkdirAll(dir, storageDirPerm)
if err != nil {
return fmt.Errorf("creating directories: %w", err)
}
internal/storage/file_backend_test.go
-40
View File
@@ -292,43 +292,3 @@ func TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory(t *testing.T) {
})
}
}
// TestFileStorerPutMissingDestination checks that a write fails when the
// destination directory has gone, even after earlier writes to it
// succeeded, and that it does not create the directory again.
func TestFileStorerPutMissingDestination(t *testing.T) {
t.Parallel()
ctx := context.Background()
base := filepath.Join(t.TempDir(), "usbstick")
err := os.Mkdir(base, 0o750)
if err != nil {
t.Fatalf("Mkdir: %v", err)
}
s, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
err = s.Put(ctx, "blobs/aa/bb/first", strings.NewReader("first"))
if err != nil {
t.Fatalf("first Put: %v", err)
}
err = os.Rename(base, base+"-unplugged")
if err != nil {
t.Fatalf("Rename: %v", err)
}
err = s.Put(ctx, "blobs/aa/bb/second", strings.NewReader("second"))
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("Put = %v, want a not-exist error", err)
}
_, err = os.Stat(base)
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("Put created the destination directory again (Stat = %v)", err)
}
}
internal/storage/rclone.go
+2 -11
View File
@@ -53,14 +53,6 @@ func NewRcloneStorer(ctx context.Context, remote, path string) (*RcloneStorer, e
rclonePath += path
}
// On S3, Swift and some other remotes rclone keeps a time of its own in
// each object's metadata, which costs one request per object to read.
// rclone's use_server_modtime setting makes ModTime the time the
// listing gives instead: when the object was stored, which is what
// prune compares with prune_grace_period.
ctx, ci := fs.AddConfig(ctx)
ci.UseServerModTime = true
// Create the rclone filesystem
fsys, err := fs.NewFs(ctx, rclonePath)
if err != nil {
@@ -219,9 +211,8 @@ func (r *RcloneStorer) ListStream(
if prefix == "" || strings.HasPrefix(key, prefix) {
ch <- ObjectInfo{
Key: key,
Size: obj.Size(),
ModTime: obj.ModTime(ctx),
Key: key,
Size: obj.Size(),
}
}
})
internal/storage/rclone_test.go
-75
View File
@@ -5,17 +5,11 @@ import (
"context"
"errors"
"io"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"strings"
"sync/atomic"
"testing"
"time"
"github.com/johannesboyne/gofakes3"
"github.com/johannesboyne/gofakes3/backend/s3mem"
"github.com/rclone/rclone/fs"
"github.com/rclone/rclone/fs/config"
"github.com/rclone/rclone/fs/config/configmap"
@@ -435,72 +429,3 @@ func TestNewRcloneStorerReadsRcloneConfigEnv(t *testing.T) {
t.Errorf("object is not in the remote's directory: %v", err)
}
}
// TestRcloneListStreamOnS3MakesNoRequestPerObject checks that listing an
// rclone S3 remote takes each object's time from the listing itself. By
// default rclone reads the time it keeps in each object's metadata, one
// request per object, and every command that lists the destination store
// would slow down as it grows.
//
//nolint:paralleltest // NewRcloneStorer installs the process-global rclone config
func TestRcloneListStreamOnS3MakesNoRequestPerObject(t *testing.T) {
backend := s3mem.New()
err := backend.CreateBucket(s3TestBucket)
if err != nil {
t.Fatalf("create bucket: %v", err)
}
const body = "blob-bytes"
_, err = backend.PutObject(s3TestBucket, testBlobKey, nil,
strings.NewReader(body), int64(len(body)))
if err != nil {
t.Fatalf("seed object: %v", err)
}
var headRequests atomic.Int64
fakeS3 := gofakes3.New(backend).Server()
srv := httptest.NewServer(http.HandlerFunc(
func(w http.ResponseWriter, r *http.Request) {
if r.Method == http.MethodHead {
headRequests.Add(1)
}
fakeS3.ServeHTTP(w, r)
}))
t.Cleanup(srv.Close)
remote := ":s3,provider=Other" +
",access_key_id=" + s3TestAccessKeyID +
",secret_access_key=" + s3TestSecretAccessKey +
",endpoint='" + srv.URL + "'"
ctx := context.Background()
s, err := storage.NewRcloneStorer(ctx, remote, s3TestBucket)
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
headRequests.Store(0)
var listed []storage.ObjectInfo
for info := range s.ListStream(ctx, "blobs/") {
listed = append(listed, info)
}
if len(listed) != 1 || listed[0].Err != nil {
t.Fatalf("ListStream(\"blobs/\") = %v, want the one object", listed)
}
if time.Since(listed[0].ModTime).Abs() > time.Minute {
t.Errorf("ListStream ModTime = %v, want within a minute of now",
listed[0].ModTime)
}
if n := headRequests.Load(); n != 0 {
t.Errorf("ListStream made %d HEAD request(s), want none", n)
}
}
internal/storage/s3.go
+3 -4
View File
@@ -89,10 +89,9 @@ func (s *S3Storer) ListStream(ctx context.Context, prefix string) <-chan ObjectI
for info := range s.client.ListObjectsStream(ctx, prefix, false) {
ch <- ObjectInfo{
Key: info.Key,
Size: info.Size,
ModTime: info.ModTime,
Err: info.Err,
Key: info.Key,
Size: info.Size,
Err: info.Err,
}
}
}()
internal/storage/storer.go
+3 -9
View File
@@ -14,7 +14,6 @@ import (
"context"
"errors"
"io"
"time"
)
// ErrNotFound is returned when an object does not exist.
@@ -28,10 +27,7 @@ type ProgressCallback func(bytesTransferred int64) error
type ObjectInfo struct {
Key string // Object key/path
Size int64 // Size in bytes
// ModTime is when the object was written, as the store reports it.
// Only ListStream sets it; Stat leaves it zero.
ModTime time.Time
Err error // Error for streaming results (nil on success)
Err error // Error for streaming results (nil on success)
}
// Info provides human-readable storage configuration.
@@ -45,8 +41,7 @@ type Info struct {
// directory for filesystem).
type Storer interface {
// Put stores data at the specified key.
// The filesystem backend fails when its destination directory does
// not exist, and creates the directories below it as needed.
// Parent directories are created automatically for filesystem backends.
Put(ctx context.Context, key string, data io.Reader) error
// PutWithProgress stores data with progress reporting.
@@ -71,8 +66,7 @@ type Storer interface {
// For large result sets, prefer ListStream.
List(ctx context.Context, prefix string) ([]string, error)
// ListStream returns a channel of ObjectInfo, with each object's key,
// size and modification time, for large result sets.
// ListStream returns a channel of ObjectInfo for large result sets.
// The channel is closed when listing completes.
// If an error occurs during listing, the final item will have Err set.
ListStream(ctx context.Context, prefix string) <-chan ObjectInfo
internal/storage/url.go
+6 -47
View File
@@ -30,12 +30,6 @@ var (
"storage URL must not carry credentials; " +
"set s3.access_key_id and s3.secret_access_key in the config instead")
ErrURLUnknownParam = errors.New("unknown query parameter in storage URL")
ErrURLBadQuery = errors.New(
"storage URL query cannot be decoded; " +
"check it for a ; or a % not followed by two hex digits")
ErrRcloneRemoteParams = errors.New(
"rclone URL must not carry parameters in the remote name; " +
"set them on the remote with rclone config instead")
)
// URL represents a parsed storage URL.
@@ -96,9 +90,8 @@ func parseFileURL(rawPath string) (*URL, error) {
}
// parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
// the userinfo or in the endpoint parameter's userinfo, a query that
// cannot be decoded, and any query parameter other than endpoint, region
// and ssl, so a credential-bearing URL is never stored or echoed.
// the userinfo and any query parameter other than endpoint, region and
// ssl, so a credential-bearing URL is never stored or echoed.
func parseS3URL(rawURL string) (*URL, error) {
u, err := url.Parse(rawURL)
if err != nil {
@@ -114,26 +107,13 @@ func parseS3URL(rawURL string) (*URL, error) {
return nil, ErrMissingBucket
}
// u.Query() would silently drop a part it cannot decode, endpoint
// included. The decode error is not wrapped: it can quote the value.
query, err := url.ParseQuery(u.RawQuery)
if err != nil {
return nil, ErrURLBadQuery
}
query := u.Query()
err = rejectUnknownParams(query, "endpoint", "region", "ssl")
if err != nil {
return nil, err
}
// A host name never contains "@", so one in an endpoint, with or
// without a scheme, can only introduce userinfo.
for _, endpoint := range query["endpoint"] {
if strings.Contains(endpoint, "@") {
return nil, ErrURLCredentials
}
}
return &URL{
Scheme: schemeS3,
Bucket: bucket,
@@ -145,23 +125,9 @@ func parseS3URL(rawURL string) (*URL, error) {
}
// parseRcloneURL parses an rclone://remote/path URL. rclone:// takes no
// query parameters, so credentials in the userinfo, parameters in the
// remote name, a query that cannot be decoded and any query parameter at
// query parameters, so credentials in the userinfo and any parameter at
// all are rejected rather than silently ignored.
func parseRcloneURL(rawURL string) (*URL, error) {
// The remote name runs up to the first "/", "?" or "#". It never
// contains a comma; one starts rclone's remote,param=value form,
// whose values can be credentials. This is checked before url.Parse,
// whose error for such a name can print part of it.
remote := strings.TrimPrefix(rawURL, "rclone://")
if end := strings.IndexAny(remote, "/?#"); end >= 0 {
remote = remote[:end]
}
if strings.Contains(remote, ",") {
return nil, ErrRcloneRemoteParams
}
u, err := url.Parse(rawURL)
if err != nil {
return nil, wrapParseError(err)
@@ -171,19 +137,12 @@ func parseRcloneURL(rawURL string) (*URL, error) {
return nil, ErrURLCredentials
}
remote = u.Host
remote := u.Host
if remote == "" {
return nil, ErrMissingRemote
}
// As in parseS3URL: u.Query() would drop a part it cannot decode, and
// the decode error can quote the value.
query, err := url.ParseQuery(u.RawQuery)
if err != nil {
return nil, ErrURLBadQuery
}
err = rejectUnknownParams(query)
err = rejectUnknownParams(u.Query())
if err != nil {
return nil, err
}
internal/storage/url_parse_test.go
-119
View File
@@ -150,19 +150,6 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
wantErr: storage.ErrURLCredentials,
secrets: []string{key, secret, "mybucket"},
},
{
name: "s3 userinfo in endpoint",
raw: "s3://mybucket?endpoint=https://" +
key + ":" + secret + "@minio.example.com",
wantErr: storage.ErrURLCredentials,
secrets: []string{key, secret},
},
{
name: "s3 userinfo in endpoint without scheme",
raw: "s3://mybucket?endpoint=" + key + ":" + secret + "@minio.example.com",
wantErr: storage.ErrURLCredentials,
secrets: []string{key, secret},
},
{
name: "s3 unknown query param",
raw: "s3://mybucket?access_key=" + key + "&secret=" + secret,
@@ -216,112 +203,6 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
}
}
// TestParseStorageURLRejectsRcloneRemoteParams checks that an rclone
// remote name carrying parameters (rclone's "remote,param=value" form,
// which can hold a credential) is rejected without echoing the value,
// including the URLs that url.Parse itself refuses.
func TestParseStorageURLRejectsRcloneRemoteParams(t *testing.T) {
t.Parallel()
cases := []struct {
name string
raw string
secrets []string // must not appear in the error message
}{
{
name: "configured remote",
raw: "rclone://gdrive,client_secret=topsecret/backups",
secrets: []string{"topsecret"},
},
{
name: "remote defined inline",
raw: "rclone://:s3,access_key_id=KEY,secret_access_key=SECRET/bucket",
secrets: []string{"KEY", "SECRET"},
},
{
name: "colon in a parameter value",
raw: "rclone://gdrive,client_secret=ab:cd/backups",
secrets: []string{"cd"},
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
if !errors.Is(err, storage.ErrRcloneRemoteParams) {
t.Fatalf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, storage.ErrRcloneRemoteParams)
}
for _, secret := range tc.secrets {
if strings.Contains(err.Error(), secret) {
t.Errorf("error message leaked %q: %v", secret, err.Error())
}
}
})
}
}
// TestParseStorageURLRejectsUndecodableQuery checks that an s3 or rclone
// URL whose query cannot be decoded is rejected, not read with that part
// of the query left out, and that the error does not echo it.
func TestParseStorageURLRejectsUndecodableQuery(t *testing.T) {
t.Parallel()
const (
key = "AKIAKEY"
secret = "topsecret"
)
cases := []struct {
name string
raw string
}{
{
name: "semicolon",
raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
"@minio.example.com:9000;region=us-east-1",
},
{
name: "bad percent escape",
raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
"%zz@minio.example.com:9000",
},
{
name: "rclone semicolon",
raw: "rclone://gdrive/backups?token=" + secret + ";x=1",
},
{
name: "rclone bad percent escape",
raw: "rclone://gdrive/backups?token=" + secret + "%zz",
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
if err == nil {
t.Fatalf("ParseStorageURL(%q) returned no error", tc.raw)
}
if !errors.Is(err, storage.ErrURLBadQuery) {
t.Errorf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, storage.ErrURLBadQuery)
}
for _, s := range []string{key, secret, "minio.example.com"} {
if strings.Contains(err.Error(), s) {
t.Errorf("error message leaked %q: %v", s, err.Error())
}
}
})
}
}
// TestParseStorageURLParseFailureHidesURL checks that when url.Parse
// itself fails, the wrapped error carries only the inner cause, not the
// *url.Error whose text embeds the raw (possibly credential-bearing) URL.
internal/vaultik/blob_fetch.go
+2 -3
View File
@@ -104,8 +104,7 @@ func (v *Vaultik) FetchAndDecryptBlob(
// FetchBlob downloads a blob and returns a reader for the encrypted data.
// The reader is closed as soon as ctx is cancelled, which ends a read
// blocked inside it. A storage error is returned as is: restore and deep
// verify name the blob in their own errors.
// blocked inside it.
func (v *Vaultik) FetchBlob(
ctx context.Context, blobHash string,
) (io.ReadCloser, error) {
@@ -120,7 +119,7 @@ func (v *Vaultik) FetchBlob(
rc, err := v.Storage.Get(ctx, blobPath)
if err != nil {
return nil, err
return nil, fmt.Errorf("downloading blob %s: %w", shortHash(blobHash), err)
}
return newCloseOnCancelReader(ctx, rc), nil
internal/vaultik/changed_file_restore_test.go
+2 -2
View File
@@ -137,7 +137,7 @@ func TestBackupAfterRemovingNewestSnapshotRestoresChangedFile(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
changedPath := filepath.Join(dataDir, "appended.bin")
@@ -184,7 +184,7 @@ func TestBackupAfterInterruptedRunRestoresChangedFile(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
changedPath := filepath.Join(dataDir, "appended.bin")
internal/vaultik/deep_verify_test.go
+6 -13
View File
@@ -6,7 +6,6 @@ import (
"crypto/rand"
"io"
"os"
"path"
"path/filepath"
"testing"
@@ -35,7 +34,7 @@ func TestDeepVerifyAcceptsHealthyAndRejectsCorruptBlob(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(64 * 1024)
@@ -94,7 +93,7 @@ func TestDeepVerifyJSONCountsBlobs(t *testing.T) {
fs := afero.NewOsFs()
ctx := context.Background()
storeDir := t.TempDir()
storeDir := filepath.Join(t.TempDir(), "remote")
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
@@ -143,15 +142,14 @@ func TestDeepVerifyJSONCountsBlobs(t *testing.T) {
// TestDeepVerifyJSONCountsWrongSizeBlob checks that under --deep --json a
// blob of the wrong size is counted in mismatched and fails the run, and
// that the check goes on past it to count a missing blob after it. The
// store is on disk, so the message must not call it S3.
// that the check goes on past it to count a missing blob after it.
func TestDeepVerifyJSONCountsWrongSizeBlob(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
ctx := context.Background()
storeDir := t.TempDir()
storeDir := filepath.Join(t.TempDir(), "remote")
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
@@ -170,20 +168,17 @@ func TestDeepVerifyJSONCountsWrongSizeBlob(t *testing.T) {
require.Equal(t, 1, got.Mismatched)
require.Equal(t, 1, got.Missing)
require.Zero(t, got.Verified)
require.Contains(t, got.ErrorMessage, "with the wrong size")
require.NotContains(t, got.ErrorMessage, "S3")
}
// TestDeepVerifyStopsOnBlobThatCannotBeChecked checks that a blob that is
// present in storage but cannot be checked is not counted as missing:
// deep verify stops and fails, saying it could not check the blob, with
// the storage error.
// deep verify stops and fails with the storage error.
func TestDeepVerifyStopsOnBlobThatCannotBeChecked(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := t.TempDir()
storeDir := filepath.Join(t.TempDir(), "remote")
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
failing := statFailingStorer{Storer: storer, failKeys: []string{keys[0]}}
@@ -192,8 +187,6 @@ func TestDeepVerifyStopsOnBlobThatCannotBeChecked(t *testing.T) {
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Zero(t, got.Missing)
require.Contains(t, got.ErrorMessage,
"could not check blob "+path.Base(keys[0]))
require.Contains(t, got.ErrorMessage, errStatDenied.Error())
}
internal/vaultik/destination_marker.go
-90
View File
@@ -1,90 +0,0 @@
package vaultik
import (
"errors"
"fmt"
"strings"
"sneak.berlin/go/vaultik/internal/storage"
)
// destinationMarkerKey is the object every backup writes at the root of
// the backup destination store. While the local index holds a snapshot
// stored there, a destination without it is treated as not present: an
// unplugged volume leaves an empty directory at its mount point, which
// would otherwise read as a store whose snapshots are all gone.
const destinationMarkerKey = "vaultik-destination.txt"
// destinationMarkerText is the whole content of the marker. It names no
// host, path or time.
const destinationMarkerText = "This is a vaultik backup destination store.\n"
// errDestinationNotPresent is returned when the local index holds a
// snapshot stored on the backup destination store and the store has no
// marker.
var errDestinationNotPresent = errors.New("backup destination store is not present")
// checkDestinationMarker returns errDestinationNotPresent when the local
// index holds a snapshot stored on the backup destination store and the
// store has no marker. With no snapshot in the local index, as on a
// first backup or on another machine, there is nothing to check; nor
// when the local index is bound to a different destination than the
// configured one, since its snapshots are stored there.
func (v *Vaultik) checkDestinationMarker() error {
ids, err := v.localSnapshotIDs()
if err != nil {
return fmt.Errorf("listing local snapshots: %w", err)
}
if len(ids) == 0 {
return nil
}
// Config is nil only in tests, which then record no binding (see
// EnsureStorageBinding).
if v.Config != nil {
stored, configured, err := v.storageBinding()
if err != nil {
return err
}
if stored != "" && stored != configured {
return nil
}
}
_, err = v.Storage.Stat(v.ctx, destinationMarkerKey)
if errors.Is(err, storage.ErrNotFound) {
return fmt.Errorf("%w: %s has no %s, but the local index holds "+
"snapshots stored there; mount the volume if it is removable, "+
"or if the destination was emptied on purpose, run "+
"'vaultik database delete' and back up again",
errDestinationNotPresent, v.Storage.Info().Location,
destinationMarkerKey)
}
if err != nil {
return fmt.Errorf("checking for %s: %w", destinationMarkerKey, err)
}
return nil
}
// markDestination checks the backup destination store with
// checkDestinationMarker and then writes the marker, so a first backup
// marks its destination and a later one writes the same text again.
func (v *Vaultik) markDestination() error {
err := v.checkDestinationMarker()
if err != nil {
return err
}
err = v.Storage.Put(v.ctx, destinationMarkerKey,
strings.NewReader(destinationMarkerText))
if err != nil {
return fmt.Errorf("writing %s to the backup destination store: %w",
destinationMarkerKey, err)
}
return nil
}
internal/vaultik/destination_marker_test.go
-297
View File
@@ -1,297 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"os"
"path/filepath"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// These tests cover https://git.eeqj.de/sneak/vaultik/issues/239: a
// file:// destination at a volume's mount point leaves an empty directory
// behind when the volume is unplugged. While the local index holds
// snapshots, a destination without vaultik-destination.txt is not present,
// so no command may write to it or conclude from it that the local
// snapshots are gone.
// markerFile is the name of the file a backup writes at the root of the
// destination.
const markerFile = "vaultik-destination.txt"
// backUpThenUnplugMountPoint backs up to a file:// destination, then
// moves the destination directory away and leaves an empty directory in
// its place, as unplugging a volume mounted there would. It returns the
// path of that empty directory.
func backUpThenUnplugMountPoint(
ctx context.Context, t *testing.T,
) (*vaultik.Vaultik, *database.Repositories, *bytes.Buffer, string) {
t.Helper()
storeDir := filepath.Join(t.TempDir(), "mnt")
v, repos, out := backUpToFileDestination(ctx, t, storeDir)
require.NoError(t, os.Rename(storeDir, storeDir+"-unplugged"))
require.NoError(t, os.Mkdir(storeDir, 0o750))
return v, repos, out, storeDir
}
// assertUntouched checks that the local index still holds its one
// snapshot and that nothing was written to the empty mount point.
func assertUntouched(
ctx context.Context, t *testing.T,
repos *database.Repositories, storeDir string,
) {
t.Helper()
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
require.NoError(t, err)
assert.Len(t, snapshots, 1, "no local snapshot record may be deleted")
entries, err := os.ReadDir(storeDir)
require.NoError(t, err)
assert.Empty(t, entries, "nothing may be written to the empty mount point")
}
// TestFirstBackupWritesMarker checks that a backup writes the marker
// file at the root of the destination.
func TestFirstBackupWritesMarker(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
storeDir := t.TempDir()
backUpToFileDestination(context.Background(), t, storeDir)
assert.FileExists(t, filepath.Join(storeDir, markerFile))
}
// TestBackupRefusesDestinationWithoutMarker checks that snapshot create
// --prune writes nothing and drops no local snapshot record when the
// destination has no marker.
func TestBackupRefusesDestinationWithoutMarker(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
v, repos, _, storeDir := backUpThenUnplugMountPoint(ctx, t)
err := v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Cron: true,
Prune: true,
})
require.ErrorContains(t, err, markerFile)
assertUntouched(ctx, t, repos, storeDir)
}
// TestBackupChecksMarkerBeforeDroppingIncompleteSnapshots checks that
// snapshot create writes nothing when the local index holds only an
// incomplete snapshot and the destination has no marker. The backup drops
// incomplete snapshots before it scans; checked after that, the local
// index would hold none and nothing would be checked.
func TestBackupChecksMarkerBeforeDroppingIncompleteSnapshots(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := t.TempDir()
v, repos := newFileDestinationVaultik(ctx, t, storeDir)
require.NoError(t, repos.Snapshots.Create(ctx, nil, &database.Snapshot{
ID: "host_first_2026-01-02T03:04:05Z",
Hostname: "host",
StartedAt: time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC),
}))
err := backUp(v, "first")
require.ErrorContains(t, err, markerFile)
assertUntouched(ctx, t, repos, storeDir)
}
// TestPruneRefusesDestinationWithoutMarker checks that prune fails and
// deletes no local snapshot record when the destination has no marker.
func TestPruneRefusesDestinationWithoutMarker(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
v, repos, _, storeDir := backUpThenUnplugMountPoint(ctx, t)
err := v.Prune(&vaultik.PruneOptions{Force: true})
require.ErrorContains(t, err, markerFile)
assertUntouched(ctx, t, repos, storeDir)
}
// TestPurgeRefusesDestinationWithoutMarker checks that snapshot purge
// fails and deletes no local snapshot record when the destination has no
// marker.
func TestPurgeRefusesDestinationWithoutMarker(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
v, repos, _, storeDir := backUpThenUnplugMountPoint(ctx, t)
err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
KeepLatest: true,
Force: true,
})
require.ErrorContains(t, err, markerFile)
assertUntouched(ctx, t, repos, storeDir)
}
// TestNukeRemoteRefusesDestinationWithoutMarker checks that remote nuke
// fails, deletes no local snapshot record, and neither reports the
// destination empty nor advises running nuke again when the destination
// has no marker.
func TestNukeRemoteRefusesDestinationWithoutMarker(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
v, repos, out, storeDir := backUpThenUnplugMountPoint(ctx, t)
err := v.NukeRemote(true)
require.ErrorContains(t, err, markerFile)
assert.NotContains(t, out.String(), "now empty")
assert.NotContains(t, out.String(), "vaultik remote nuke --force")
assertUntouched(ctx, t, repos, storeDir)
}
// TestRemoveSnapshotWarnsWhenDestinationHasNoMarker checks that snapshot
// remove warns that the metadata could not be removed from a destination
// without a marker, instead of reporting that it was.
func TestRemoveSnapshotWarnsWhenDestinationHasNoMarker(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
v, repos, out, _ := backUpThenUnplugMountPoint(ctx, t)
result, err := v.RemoveSnapshot(localSnapshotID(ctx, t, repos, "first"),
&vaultik.RemoveOptions{Force: true})
require.NoError(t, err)
assert.False(t, result.RemoteRemoved)
assert.Contains(t, out.String(),
"Could not remove snapshot metadata from remote")
assert.Contains(t, out.String(), markerFile)
assert.NotContains(t, out.String(),
"Removed snapshot metadata from remote storage")
}
// TestRemoveSnapshotOnlyOnDestinationFailsWithoutMarker checks that
// snapshot remove, for a snapshot that is only on the destination, fails
// saying the destination is not present when it has no marker, instead
// of saying the snapshot does not exist.
func TestRemoveSnapshotOnlyOnDestinationFailsWithoutMarker(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "mnt")
v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
require.NoError(t, backUp(v, "second"))
id := localSnapshotID(ctx, t, repos, "first")
_, err := v.RemoveSnapshot(id,
&vaultik.RemoveOptions{Force: true, LocalOnly: true})
require.NoError(t, err)
// Unplug the volume: an empty directory stays at its mount point.
require.NoError(t, os.Rename(storeDir, storeDir+"-unplugged"))
require.NoError(t, os.Mkdir(storeDir, 0o750))
_, err = v.RemoveSnapshot(id, &vaultik.RemoveOptions{Force: true})
require.ErrorContains(t, err, markerFile)
require.ErrorContains(t, err, "mount the volume")
assertUntouched(ctx, t, repos, storeDir)
}
// TestListSnapshotsWarnsWhenDestinationHasNoMarker checks that snapshot
// list warns and shows the local index alone when the destination has no
// marker, without reporting the local snapshot as missing from it.
func TestListSnapshotsWarnsWhenDestinationHasNoMarker(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
v, repos, out, _ := backUpThenUnplugMountPoint(ctx, t)
id := localSnapshotID(ctx, t, repos, "first")
require.NoError(t, v.ListSnapshots(false))
assert.Contains(t, out.String(), "Could not list backup destination store")
assert.Contains(t, out.String(), markerFile)
assert.Contains(t, out.String(), id)
assert.NotContains(t, out.String(), "not found in backup destination store")
}
// TestListSnapshotsAfterStorageURLChangeToEmptyDirectory checks that
// snapshot list, after storage_url is changed to an empty directory,
// warns only that the local index is bound to a different destination:
// the local snapshots are stored at the old one, so the new one's lack
// of a marker says nothing. With --json the local row is not on the new
// destination, so remote_present is false, not unknown.
func TestListSnapshotsAfterStorageURLChangeToEmptyDirectory(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
v, repos, out := backUpToFileDestination(ctx, t, t.TempDir())
id := localSnapshotID(ctx, t, repos, "first")
newDir := t.TempDir()
store, err := storage.NewFileStorer(newDir)
require.NoError(t, err)
v.Storage = store
v.Config.StorageURL = "file://" + newDir
require.NoError(t, v.ListSnapshots(false))
assert.Contains(t, out.String(), id)
assert.Contains(t, out.String(),
"local index is bound to a different backup destination")
assert.NotContains(t, out.String(), "Could not list backup destination store")
assert.NotContains(t, out.String(), markerFile)
out.Reset()
require.NoError(t, v.ListSnapshots(true))
rows := decodeListJSON(t, out.String())
require.Len(t, rows, 1)
require.NotNil(t, rows[0].RemotePresent)
assert.False(t, *rows[0].RemotePresent)
}
// TestBackupAfterNukeRemoteSucceeds checks that remote nuke leaves the
// destination ready for a new first backup, which writes the marker
// again.
func TestBackupAfterNukeRemoteSucceeds(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
storeDir := t.TempDir()
v, _, _ := backUpToFileDestination(context.Background(), t, storeDir)
require.NoError(t, v.NukeRemote(true))
assert.NoFileExists(t, filepath.Join(storeDir, markerFile))
require.NoError(t, backUp(v, "second"))
assert.FileExists(t, filepath.Join(storeDir, markerFile))
}
internal/vaultik/fault_injection_test.go
+22 -29
View File
@@ -192,7 +192,7 @@ func assertRestoreRejectsDamagedBlob(
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -238,7 +238,7 @@ func TestDeepVerifyCatchesLyingBackend(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
@@ -290,7 +290,7 @@ func TestInterruptedBlobUploadRecordsNoUploadedBlob(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
@@ -298,6 +298,10 @@ func TestInterruptedBlobUploadRecordsNoUploadedBlob(t *testing.T) {
writeFaultSourceTree(t, fs, dataDir)
// No upload succeeds, so nothing creates the destination directory.
// It must exist for the listing below to show that no blob survived.
require.NoError(t, os.Mkdir(storeDir, 0o750))
inner, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
@@ -361,7 +365,7 @@ func TestBackupRetryAfterInterruptedUploadIsRestorable(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -425,7 +429,7 @@ func TestBackupSurvivesMetadataExportInterruption(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
@@ -441,10 +445,6 @@ func TestBackupSurvivesMetadataExportInterruption(t *testing.T) {
repos := database.NewRepositories(db)
// snapshot create writes the marker; this backup runs its steps one
// by one, so the marker is written here.
require.NoError(t, inner.Put(ctx, markerFile, strings.NewReader("")))
// Back up and complete with a working backend.
sm := newFaultSnapshotManager(fs, inner, cfg, repos)
scanner := newFaultScanner(fs, inner, cfg, repos)
@@ -493,14 +493,8 @@ func TestBackupSurvivesMetadataExportInterruption(t *testing.T) {
"shallow verify must report the missing manifest")
// snapshot list must not crash on the partial snapshot.
var listOut strings.Builder
reader.UI = ui.NewWithColor(&listOut, false)
require.NoError(t, reader.ListSnapshots(false),
"snapshot list must tolerate a partially-exported snapshot")
assert.NotContains(t, listOut.String(),
"Could not list backup destination store",
"snapshot list must read the partial snapshot from the destination")
}
// Scenario 2, repair: the process dies during the metadata export of a
@@ -517,7 +511,7 @@ func TestBackupCompletesOnlyAfterMetadataExport(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -667,18 +661,17 @@ func faultScannerFactory(
) snapshot.ScannerFactory {
return func(params snapshot.ScannerParams) *snapshot.Scanner {
return snapshot.NewScanner(snapshot.ScannerConfig{
FS: params.Fs,
Storage: storer,
ChunkSize: faultChunkSize,
MaxBlobSize: faultMaxBlobSize,
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
Repositories: repos,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: params.Exclude,
SkipErrors: params.SkipErrors,
PreviousSnapshotID: params.PreviousSnapshotID,
FS: params.Fs,
Storage: storer,
ChunkSize: faultChunkSize,
MaxBlobSize: faultMaxBlobSize,
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
Repositories: repos,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: params.Exclude,
SkipErrors: params.SkipErrors,
})
}
}
@@ -693,7 +686,7 @@ func TestRestoreReportsDiskFull(t *testing.T) {
osFS := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/info.go
+4 -4
View File
@@ -457,9 +457,9 @@ func (v *Vaultik) scanRemoteBlobStorage(
return err
}
for _, blob := range allBlobs {
for _, size := range allBlobs {
result.TotalBlobCount++
result.TotalBlobSize += blob.Size
result.TotalBlobSize += size
}
// A blob named only by a manifest that could not be read, or by one
@@ -474,10 +474,10 @@ func (v *Vaultik) scanRemoteBlobStorage(
orphanedSize int64
)
for hash, blob := range allBlobs {
for hash, size := range allBlobs {
if _, referenced := referencedBlobs[hash]; !referenced {
orphanedCount++
orphanedSize += blob.Size
orphanedSize += size
}
}
internal/vaultik/integration_test.go
+2 -2
View File
@@ -771,7 +771,7 @@ func TestEndToEndFileStorage(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -964,7 +964,7 @@ func TestDedupOnlySnapshotRestores(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/missing_destination_test.go
+16 -73
View File
@@ -24,11 +24,13 @@ import (
// that is not plugged in, cannot be listed. It is not an empty store, so
// no command may conclude from it that the local snapshots are gone.
// newFileDestinationVaultik returns a Vaultik that backs up the
// snapshot named "first" to a file:// destination at storeDir.
func newFileDestinationVaultik(
// backUpToFileDestination backs up the snapshot named "first" to a
// file:// destination at storeDir, which need not exist yet. Everything
// the returned Vaultik prints after the backup goes to the returned
// buffer.
func backUpToFileDestination(
ctx context.Context, t *testing.T, storeDir string,
) (*vaultik.Vaultik, *database.Repositories) {
) (*vaultik.Vaultik, *database.Repositories, *bytes.Buffer) {
t.Helper()
osFs := afero.NewOsFs()
@@ -47,22 +49,8 @@ func newFileDestinationVaultik(
repos := database.NewRepositories(db)
cfg := changedFileConfig(dataDir, dbPath)
v := newBackupVaultik(ctx, cfg, store, repos, db, osFs)
return newBackupVaultik(ctx, cfg, store, repos, db, osFs), repos
}
// backUpToFileDestination creates the directory storeDir, as a user must
// before the first backup, and backs up the snapshot named "first" to a
// file:// destination there. Everything the returned Vaultik prints
// after the backup goes to the returned buffer.
func backUpToFileDestination(
ctx context.Context, t *testing.T, storeDir string,
) (*vaultik.Vaultik, *database.Repositories, *bytes.Buffer) {
t.Helper()
require.NoError(t, os.MkdirAll(storeDir, 0o750))
v, repos := newFileDestinationVaultik(ctx, t, storeDir)
require.NoError(t, backUp(v, "first"))
out := &bytes.Buffer{}
@@ -87,28 +75,21 @@ func backUpThenUnplug(
return v, repos, out
}
// TestBackupFailsWhenDestinationDirectoryMissing checks that a backup to
// a file:// destination whose directory does not exist fails before it
// records a snapshot, and does not create the directory.
func TestBackupFailsWhenDestinationDirectoryMissing(t *testing.T) {
// TestFirstBackupCreatesDestinationDirectory checks that a first backup
// to a destination directory that does not exist yet creates it, and
// that the destination can be listed afterwards.
func TestFirstBackupCreatesDestinationDirectory(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
volume := filepath.Join(t.TempDir(), "volume")
v, repos := newFileDestinationVaultik(ctx, t, filepath.Join(volume, "backup"))
storeDir := filepath.Join(t.TempDir(), "volume", "backup")
v, _, out := backUpToFileDestination(ctx, t, storeDir)
err := backUp(v, "first")
require.ErrorIs(t, err, fs.ErrNotExist)
require.ErrorContains(t, err, "create it, or mount the volume it is on")
require.NoError(t, v.ListSnapshots(false))
_, err = os.Stat(volume)
require.ErrorIs(t, err, fs.ErrNotExist,
"the backup must not create the destination directory")
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
require.NoError(t, err)
assert.Empty(t, snapshots)
assert.NotContains(t, out.String(), "Could not list backup destination store")
assert.NotContains(t, out.String(), "not found in backup destination store")
}
// TestListSnapshotsWarnsWhenDestinationMissing checks that snapshot list
@@ -188,41 +169,3 @@ func TestPurgeSaysListingFailedOnceWhenDestinationMissing(t *testing.T) {
assert.Equal(t, 1, strings.Count(err.Error(), "listing remote snapshots"),
err.Error())
}
// TestNukeRemoteKeepsLocalIndexWhenDestinationMissing checks that remote
// nuke fails on a destination it cannot list, leaves the local index
// unchanged, and neither reports the destination empty nor advises
// running nuke again.
func TestNukeRemoteKeepsLocalIndexWhenDestinationMissing(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
v, repos, out := backUpThenUnplug(ctx, t)
filesBefore, err := repos.Files.ListAll(ctx)
require.NoError(t, err)
require.NotEmpty(t, filesBefore)
blobsBefore, err := repos.Blobs.GetAll(ctx)
require.NoError(t, err)
require.NotEmpty(t, blobsBefore)
err = v.NukeRemote(true)
require.ErrorIs(t, err, fs.ErrNotExist)
require.ErrorContains(t, err, "listing remote snapshots")
assert.NotContains(t, out.String(), "now empty")
assert.NotContains(t, out.String(), "vaultik remote nuke --force")
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
require.NoError(t, err)
assert.Len(t, snapshots, 1, "nuke must delete no local snapshot record")
files, err := repos.Files.ListAll(ctx)
require.NoError(t, err)
assert.Len(t, files, len(filesBefore), "nuke must delete no local file record")
blobs, err := repos.Blobs.GetAll(ctx)
require.NoError(t, err)
assert.Len(t, blobs, len(blobsBefore), "nuke must delete no local blob record")
}
internal/vaultik/new_chunk_size_test.go
+1 -1
View File
@@ -39,7 +39,7 @@ func TestNewChunkSizeOfChangedFileStaysFixed(t *testing.T) {
appendRandomBytes(t, fs, files, changedPath, appendedFileSize)
store, err := storage.NewFileStorer(t.TempDir())
store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
internal/vaultik/nuke_remote_test.go
+2 -27
View File
@@ -104,32 +104,6 @@ func TestNukeRemoteFailsWhenADeleteFails(t *testing.T) {
}
}
// TestNukeRemoteKeepsLocalSnapshotWhoseMetadataIsNotDeleted checks that
// remote nuke keeps a snapshot in the local index while its metadata
// cannot be deleted from the destination store: dropped from the local
// index, it would be left there as a remote-only snapshot without its
// name.
func TestNukeRemoteKeepsLocalSnapshotWhoseMetadataIsNotDeleted(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
store := faultstore.New(v.Storage)
store.OnDelete = func(key string) bool {
return strings.HasPrefix(key, "metadata/")
}
v.Storage = store
require.Error(t, v.NukeRemote(true))
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
require.NoError(t, err)
assert.Len(t, snapshots, 1)
}
// TestNukeRemoteNamesWhatIsLeft checks that remote nuke, when an object
// it does not recognise cannot be deleted, does not report the store
// empty but names that object and fails.
@@ -180,7 +154,8 @@ func TestNukeRemoteRefusesAnotherDestinationWithoutRetryAdvice(t *testing.T) {
// TestNukeRemoteFailsWhenALocalSnapshotCannotBeRemoved checks that a
// snapshot remote nuke cannot remove from the local index fails the
// run, and that nuke then does not report the destination store empty.
// run: nuke then leaves that snapshot's metadata on the destination
// store.
func TestNukeRemoteFailsWhenALocalSnapshotCannotBeRemoved(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
internal/vaultik/prune.go
+21 -78
View File
@@ -5,10 +5,8 @@ import (
"errors"
"fmt"
"strings"
"time"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
)
// PruneOptions contains options for the prune command
@@ -44,10 +42,9 @@ const blobKeyParts = 4
// NukeRemote deletes every object under metadata/ and blobs/ in remote
// storage, whatever its name, along with any object an upload cut off
// part-way left under a temporary `.partial` name, and last the
// destination marker. It returns successfully only when a listing
// afterwards finds nothing left under metadata/ and blobs/, and the next
// backup then starts from scratch.
// part-way left under a temporary `.partial` name. It returns
// successfully only when a listing afterwards finds nothing left there,
// and the next backup then starts from scratch.
//
// Refuses to run unless force is true. The caller is responsible for
// confirming with the user.
@@ -57,19 +54,12 @@ func (v *Vaultik) NukeRemote(force bool) error {
}
// Checked before anything is deleted: running nuke again would fail
// the same way, so the advice below must not follow these errors.
// The listing also fails on a destination without the marker while
// the local index holds snapshots.
// the same way, so the advice below must not follow this error.
err := v.EnsureStorageBinding()
if err != nil {
return err
}
_, err = v.listAllRemoteSnapshotKeys()
if err != nil {
return err
}
err = v.emptyDestinationStore()
if err != nil {
v.UI.Warningf("Run '%s' again to delete what is left on the "+
@@ -115,13 +105,6 @@ func (v *Vaultik) emptyDestinationStore() error {
return fmt.Errorf("%d %w", len(left), errObjectsLeft)
}
// Last, once the local snapshot records are gone: the next backup
// then has none and writes the marker again.
err = v.Storage.Delete(v.ctx, destinationMarkerKey)
if err != nil {
return fmt.Errorf("deleting %s: %w", destinationMarkerKey, err)
}
return nil
}
@@ -165,10 +148,6 @@ type PruneBlobsResult struct {
BlobsDeleted int `json:"blobs_deleted"`
BlobsFailed int `json:"blobs_failed,omitempty"`
BytesFreed int64 `json:"bytes_freed"`
// BlobsTooNew counts the unreferenced blobs kept because they are
// newer than the prune grace period, or of unknown age. BlobsFound
// does not include them.
BlobsTooNew int `json:"blobs_too_new"`
}
// Prune removes orphaned data from the local index database AND
@@ -214,15 +193,9 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
return err
}
unreferencedBlobs, totalSize, tooNew := v.findUnreferencedBlobs(
allBlobs, allBlobsReferenced)
unreferencedBlobs, totalSize := v.findUnreferencedBlobs(allBlobs, allBlobsReferenced)
result := &PruneBlobsResult{
BlobsFound: len(unreferencedBlobs),
BlobsTooNew: tooNew,
}
v.reportBlobsTooNew(tooNew, opts)
result := &PruneBlobsResult{BlobsFound: len(unreferencedBlobs)}
if len(unreferencedBlobs) == 0 {
log.Info("No unreferenced blobs found")
@@ -356,12 +329,11 @@ func (v *Vaultik) listUniqueSnapshotIDs() ([]string, error) {
return snapshotIDs, nil
}
// listAllRemoteBlobs returns a map of all blob hashes in remote storage
// to their listing entries.
func (v *Vaultik) listAllRemoteBlobs() (map[string]storage.ObjectInfo, error) {
// listAllRemoteBlobs returns a map of all blob hashes to their sizes in remote storage
func (v *Vaultik) listAllRemoteBlobs() (map[string]int64, error) {
log.Info("Listing all blobs in storage")
allBlobs := make(map[string]storage.ObjectInfo)
allBlobs := make(map[string]int64)
blobObjectCh := v.Storage.ListStream(v.ctx, "blobs/")
for object := range blobObjectCh {
@@ -385,7 +357,7 @@ func (v *Vaultik) listAllRemoteBlobs() (map[string]storage.ObjectInfo, error) {
continue
}
allBlobs[parts[3]] = object
allBlobs[parts[3]] = object.Size
}
log.Info("Found blobs in storage", "count", len(allBlobs))
@@ -393,59 +365,30 @@ func (v *Vaultik) listAllRemoteBlobs() (map[string]storage.ObjectInfo, error) {
return allBlobs, nil
}
// findUnreferencedBlobs returns the hashes of the blobs no manifest
// references that are older than the prune grace period, and their total
// size. It also returns how many unreferenced blobs it left out for
// being newer than that, or of unknown age because the listing gave no
// time for them.
// findUnreferencedBlobs returns blob hashes not referenced by any
// manifest and their total size.
func (v *Vaultik) findUnreferencedBlobs(
allBlobs map[string]storage.ObjectInfo, referenced map[string]bool,
) ([]string, int64, int) {
allBlobs map[string]int64, referenced map[string]bool,
) ([]string, int64) {
var (
unreferenced []string
totalSize int64
tooNew int
)
cutoff := time.Now().UTC().Add(-v.Config.PruneGracePeriod)
for hash, blob := range allBlobs {
if referenced[hash] {
continue
for hash, size := range allBlobs {
if !referenced[hash] {
unreferenced = append(unreferenced, hash)
totalSize += size
}
if blob.ModTime.IsZero() || blob.ModTime.After(cutoff) {
tooNew++
continue
}
unreferenced = append(unreferenced, hash)
totalSize += blob.Size
}
return unreferenced, totalSize, tooNew
}
// reportBlobsTooNew says how many unreferenced blobs prune kept for being
// newer than the grace period or of unknown age. Under --json the
// document carries the count instead.
func (v *Vaultik) reportBlobsTooNew(tooNew int, opts *PruneOptions) {
if tooNew == 0 || opts.JSON {
return
}
v.UI.Infof("Kept %d unreferenced blob(s) newer than "+
"prune_grace_period (%s), or of unknown age: a backup still "+
"running may need them.",
tooNew, v.Config.PruneGracePeriod)
return unreferenced, totalSize
}
// deleteUnreferencedBlobs deletes the given blobs from storage and
// populates the result.
func (v *Vaultik) deleteUnreferencedBlobs(
unreferencedBlobs []string, allBlobs map[string]storage.ObjectInfo,
result *PruneBlobsResult,
unreferencedBlobs []string, allBlobs map[string]int64, result *PruneBlobsResult,
) {
log.Info("Deleting unreferenced blobs")
@@ -460,7 +403,7 @@ func (v *Vaultik) deleteUnreferencedBlobs(
}
result.BlobsDeleted++
result.BytesFreed += allBlobs[hash].Size
result.BytesFreed += allBlobs[hash]
if (i+1)%progressLogEvery == 0 || i == len(unreferencedBlobs)-1 {
log.Info("Deletion progress",
internal/vaultik/prune_grace_period_test.go
-166
View File
@@ -1,166 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"encoding/json"
"os"
"path/filepath"
"strings"
"testing"
"time"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/storage/faultstore"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestPruneDuringBackupKeepsItsBlobs runs a prune from another host
// sharing the destination store at the moment a backup has uploaded its
// blobs but not yet its manifest, so no manifest lists those blobs. The
// prune must leave them, and the backup must then restore.
func TestPruneDuringBackupKeepsItsBlobs(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
cfg := faultTestConfig()
testFiles := writeFaultSourceTree(t, fs, dataDir)
inner, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
otherHostCfg := faultTestConfig()
otherHostCfg.PruneGracePeriod = time.Hour
otherHost := newReaderVaultik(ctx, otherHostCfg, inner, nil, fs)
var (
pruned bool
pruneErr error
)
store := faultstore.New(inner)
store.OnPut = func(key string) faultstore.PutAction {
if strings.HasSuffix(key, "/manifest.json.zst") {
pruned = true
pruneErr = otherHost.PruneBlobs(&vaultik.PruneOptions{Force: true})
}
return faultstore.PutNormal
}
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
repos := database.NewRepositories(db)
id := fullFaultBackup(ctx, t, fs, store, cfg, repos, dataDir, dbPath, "shared")
require.NoError(t, db.Close())
require.True(t, pruned, "the prune must run before the manifest upload")
require.NoError(t, pruneErr)
v := newReaderVaultik(ctx, cfg, inner, nil, fs)
require.NoError(t, v.Restore(&vaultik.RestoreOptions{
SnapshotID: id,
TargetDir: restoreDir,
Verify: true,
}), "a prune during the backup must not delete the backup's blobs")
assertRestoredTree(t, fs, restoreDir, testFiles)
}
// TestPruneKeepsUnreferencedBlobWithNoTime checks that a blob no
// manifest lists, whose listing gives no modification time (as an S3
// listing entry without LastModified does), is kept and counted with
// the blobs too new to delete: its age is unknown.
func TestPruneKeepsUnreferencedBlobWithNoTime(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newListEnv(t)
// Written into the mock store's map directly rather than through
// Put, so its listing gives no time.
blobKey := "blobs/" + testBlobHashA[:2] + "/" + testBlobHashA[2:4] +
"/" + testBlobHashA
env.store.data[blobKey] = []byte("blob")
require.NoError(t, env.v.PruneBlobs(&vaultik.PruneOptions{JSON: true}))
assert.True(t, env.store.hasKey(blobKey),
"a blob of unknown age must be kept")
var result vaultik.PruneBlobsResult
require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &result))
assert.Equal(t, 0, result.BlobsDeleted)
assert.Equal(t, 1, result.BlobsTooNew)
}
// TestPruneDeletesUnreferencedBlobOlderThanGracePeriod checks that the
// grace period only delays deletion: a blob no manifest lists is deleted
// once it is older than the grace period, and kept and counted until
// then.
func TestPruneDeletesUnreferencedBlobOlderThanGracePeriod(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := t.TempDir()
store, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
oldKey := "blobs/" + testBlobHashA[:2] + "/" + testBlobHashA[2:4] +
"/" + testBlobHashA
newKey := "blobs/" + testBlobHashB[:2] + "/" + testBlobHashB[2:4] +
"/" + testBlobHashB
for _, key := range []string{oldKey, newKey} {
require.NoError(t, store.Put(ctx, key, strings.NewReader("blob")))
}
gracePeriod := time.Hour
beforeGracePeriod := time.Now().Add(-gracePeriod - time.Minute)
require.NoError(t, os.Chtimes(filepath.Join(storeDir, oldKey),
beforeGracePeriod, beforeGracePeriod))
stdout := &bytes.Buffer{}
v := &vaultik.Vaultik{
Config: &config.Config{PruneGracePeriod: gracePeriod},
Storage: store,
Stdout: stdout,
UI: ui.NewWithColor(stdout, false),
}
v.SetContext(ctx)
require.NoError(t, v.PruneBlobs(&vaultik.PruneOptions{JSON: true}))
_, err = store.Stat(ctx, oldKey)
require.ErrorIs(t, err, storage.ErrNotFound,
"a blob older than the grace period must be deleted")
_, err = store.Stat(ctx, newKey)
require.NoError(t, err, "a blob newer than the grace period must be kept")
var result vaultik.PruneBlobsResult
require.NoError(t, json.Unmarshal(stdout.Bytes(), &result))
assert.Equal(t, 1, result.BlobsDeleted)
assert.Equal(t, 1, result.BlobsTooNew)
}
internal/vaultik/purge_local_remote_consistency_test.go
-3
View File
@@ -35,9 +35,6 @@ func setupConsistencyTest(
repos := database.NewRepositories(db)
mockStorage := NewMockStorer()
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, mockStorage.Put(ctx, markerFile, strings.NewReader("")))
for _, id := range snapshotIDs {
parts := strings.Split(id, "_")
startedAt, err := time.Parse(time.RFC3339, parts[len(parts)-1])
internal/vaultik/purge_per_name_test.go
+1 -5
View File
@@ -45,9 +45,6 @@ func setupPurgeTest(
repos := database.NewRepositories(db)
mockStorage := NewMockStorer()
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, mockStorage.Put(ctx, markerFile, strings.NewReader("")))
// Insert each snapshot into the DB and create remote metadata stubs.
// Use timestamps parsed from snapshot IDs for realistic ordering.
for _, id := range snapshotIDs {
@@ -284,8 +281,7 @@ func TestPurgeOlderThan_TooLargeDeletesNothing(t *testing.T) {
OlderThan: "1000y",
Force: true,
})
require.EqualError(t, err,
`invalid duration: "1000y" is longer than about 292 years`)
require.Error(t, err)
err = v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
OlderThan: "292y",
internal/vaultik/remove_quiet_test.go
-4
View File
@@ -96,10 +96,6 @@ func TestRemoveSnapshot_QuietSuppressesReport(t *testing.T) {
store := newTestStorer()
addManifest(t, store, "snapshot-001", nil)
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, store.Put(context.Background(), markerFile,
bytes.NewReader(nil)))
tv := vaultik.NewForTesting(store)
tv.Repositories = newLocalIndex(t, "snapshot-001")
tv.UI.SetQuiet(true)
internal/vaultik/remove_snapshot_test.go
+4 -23
View File
@@ -26,14 +26,11 @@ import (
type testStorer struct {
mu sync.Mutex
data map[string][]byte
// putTimes holds when Put stored each object; ListStream reports it.
putTimes map[string]time.Time
}
func newTestStorer() *testStorer {
return &testStorer{
data: make(map[string][]byte),
putTimes: make(map[string]time.Time),
data: make(map[string][]byte),
}
}
@@ -47,7 +44,6 @@ func (s *testStorer) Put(_ context.Context, key string, reader io.Reader) error
}
s.data[key] = data
s.putTimes[key] = time.Now().UTC()
return nil
}
@@ -91,7 +87,6 @@ func (s *testStorer) Delete(_ context.Context, key string) error {
defer s.mu.Unlock()
delete(s.data, key)
delete(s.putTimes, key)
return nil
}
@@ -125,9 +120,8 @@ func (s *testStorer) ListStream(
for key, data := range s.data {
if prefix == "" || strings.HasPrefix(key, prefix) {
ch <- storage.ObjectInfo{
Key: key,
Size: int64(len(data)),
ModTime: s.putTimes[key],
Key: key,
Size: int64(len(data)),
}
}
}
@@ -310,10 +304,6 @@ func TestRemoveSnapshot_DefaultRemovesMetadataNotBlobs(t *testing.T) {
addBlob(t, store, blobUnique)
addBlob(t, store, blobShared)
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, store.Put(context.Background(), markerFile,
bytes.NewReader(nil)))
tv := vaultik.NewForTesting(store)
tv.Repositories = newLocalIndex(t, "snapshot-001", "snapshot-002")
@@ -383,10 +373,6 @@ func TestRemoveSnapshot_UnknownIDIsError(t *testing.T) {
store := newTestStorer()
addManifest(t, store, "snapshot-001", nil)
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, store.Put(context.Background(), markerFile,
bytes.NewReader(nil)))
tv := vaultik.NewForTesting(store)
tv.Repositories = newLocalIndex(t, "snapshot-001")
@@ -407,12 +393,7 @@ func TestRemoveSnapshot_NoMetadataOnDestination(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
// A backup wrote to this destination, so it carries the marker.
store := newTestStorer()
require.NoError(t, store.Put(context.Background(), markerFile,
bytes.NewReader(nil)))
tv := vaultik.NewForTesting(store)
tv := vaultik.NewForTesting(newTestStorer())
tv.Repositories = newLocalIndex(t, "snapshot-001")
result, err := tv.RemoveSnapshot("snapshot-001",
internal/vaultik/restore.go
+5 -42
View File
@@ -12,7 +12,6 @@ import (
"path/filepath"
"slices"
"strings"
"syscall"
"time"
"filippo.io/age"
@@ -220,7 +219,9 @@ func (v *Vaultik) finishRestore(
)
if os.Geteuid() != 0 {
v.warnIfOwnershipNotPreserved(files, opts.TargetDir)
v.UI.Warningf("Restore did not preserve file ownership: chown(2) " +
"requires root. Re-run as root (e.g. with sudo) if you need " +
"original UID/GID preserved.")
}
if result.FilesFailed > 0 {
@@ -246,43 +247,6 @@ func (v *Vaultik) finishRestore(
return unmatchedErr
}
// warnIfOwnershipNotPreserved warns once if some entry restored under
// targetDir has another owner or group on disk than the snapshot
// records. It is meant for a restore by a normal user, which changes no
// owner or group: a new entry is owned by that user, and its group is
// that user's, or the group of the directory it is created in on macOS
// and in a setgid directory on Linux. An entry that is not on disk, or
// whose filesystem reports no owner, is skipped.
func (v *Vaultik) warnIfOwnershipNotPreserved(
files []*database.File, targetDir string,
) {
for _, file := range files {
targetPath, err := containedRestorePath(
v.Fs, targetDir, file.Path.String())
if err != nil {
continue
}
info, err := lstatIfPossible(v.Fs, targetPath)
if err != nil {
continue
}
owner, ok := info.Sys().(*syscall.Stat_t)
if !ok {
continue
}
if owner.Uid != file.UID || owner.Gid != file.GID {
v.UI.Warningf("Restore did not preserve file ownership: chown(2) " +
"requires root. Re-run as root (e.g. with sudo) if you need " +
"original UID/GID preserved.")
return
}
}
}
// reportUnmatchedPaths warns, by name, about each requested path that
// matched nothing in the snapshot, and returns an error counting them,
// or nil when there are none.
@@ -1001,9 +965,8 @@ type restoreSession struct {
// root can chown a file to an arbitrary UID/GID — non-root chown
// always fails with EPERM. Attempting it anyway produces N
// guaranteed-failed syscalls + N noisy debug lines, so we skip
// the call entirely as non-root; warnIfOwnershipNotPreserved warns
// once at the end of the restore if that left any owner or group
// other than recorded.
// the call entirely as non-root and emit one warning at the end
// of the restore explaining that ownership was not preserved.
runningAsRoot bool
// directories holds every restored directory, for
// applyDirectoryMetadata to finish after the restore loop.
internal/vaultik/restore_another_machine_test.go
+1 -1
View File
@@ -42,7 +42,7 @@ func TestRestoreOnAnotherMachine(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/restore_interrupt_test.go
+1 -1
View File
@@ -65,7 +65,7 @@ func TestRestoreCleansTempDirOnInterrupt(t *testing.T) {
root := t.TempDir()
dataDir := filepath.Join(root, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(root, "remote")
restoreDir := filepath.Join(root, "restored")
dbPath := filepath.Join(root, "index.sqlite")
internal/vaultik/restore_locality_test.go
+1 -1
View File
@@ -201,7 +201,7 @@ func TestRestoreLocalityAndReadAt(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/restore_ownership_warning_test.go
-131
View File
@@ -1,131 +0,0 @@
package vaultik //nolint:testpackage // calls the unexported ownership check
import (
"bytes"
"context"
"os"
"strings"
"syscall"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/ui"
)
// These tests cover https://git.eeqj.de/sneak/vaultik/issues/316: a
// restore by a normal user warns that ownership was not preserved only
// when some restored entry has another owner or group on disk than the
// snapshot records.
const ownershipWarning = "did not preserve file ownership"
// TestOwnershipWarningSilentWhenEntriesMatch checks that a restore whose
// entries all end up with their recorded owner and group prints no
// warning.
func TestOwnershipWarningSilentWhenEntriesMatch(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
targetDir := t.TempDir()
owner := ownerOf(t, targetDir)
out := restoreAsNormalUser(t, targetDir, []*database.File{
{Path: "/a", Mode: plainFileMode, UID: owner.Uid, GID: owner.Gid},
{Path: "/b", Mode: plainFileMode, UID: owner.Uid, GID: owner.Gid},
})
assert.Empty(t, out)
}
// TestOwnershipWarningWhenOwnerDiffers checks that the warning is printed
// when an entry recorded with another owner is restored owned by the
// restoring user, even though its group matches the recorded one.
func TestOwnershipWarningWhenOwnerDiffers(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
targetDir := t.TempDir()
owner := ownerOf(t, targetDir)
out := restoreAsNormalUser(t, targetDir, []*database.File{
{Path: "/a", Mode: plainFileMode, UID: otherOwnerID, GID: owner.Gid},
})
assert.Equal(t, 1, strings.Count(out, ownershipWarning), out)
}
// TestOwnershipWarningWhenDirectoryGivesItsGroup checks that the warning
// is printed, once, when entries recorded with the restoring user's
// owner and group take another group from the setgid directory they are
// restored into, as every new entry takes its directory's group on
// macOS.
func TestOwnershipWarningWhenDirectoryGivesItsGroup(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
if os.Geteuid() != 0 {
t.Skip("giving a directory to another group needs root")
}
targetDir := t.TempDir()
user := ownerOf(t, targetDir)
require.NoError(t, os.Chown(targetDir, -1, int(otherOwnerID)))
require.NoError(t, os.Chmod(targetDir, os.ModeSetgid|writableTestMode))
out := restoreAsNormalUser(t, targetDir, []*database.File{
{Path: "/a", Mode: plainFileMode, UID: user.Uid, GID: user.Gid},
{Path: "/b", Mode: plainFileMode, UID: user.Uid, GID: user.Gid},
})
assert.Equal(t, 1, strings.Count(out, ownershipWarning), out)
}
// ownerOf returns the owner and group path has on disk.
func ownerOf(t *testing.T, path string) *syscall.Stat_t {
t.Helper()
info, err := os.Lstat(path)
require.NoError(t, err)
owner, ok := info.Sys().(*syscall.Stat_t)
require.True(t, ok)
return owner
}
// restoreAsNormalUser restores rows, all empty regular files, into
// targetDir without changing any owner or group, as restore does for a
// normal user, and returns what warnIfOwnershipNotPreserved prints.
func restoreAsNormalUser(
t *testing.T, targetDir string, rows []*database.File,
) string {
t.Helper()
ctx := context.Background()
rows, repos := makeFiles(ctx, t, rows)
var out bytes.Buffer
v := newContainmentVaultik(ctx, afero.NewOsFs())
v.UI = ui.NewWithColor(&out, false)
session := &restoreSession{
v: v,
ctx: ctx,
repos: repos,
opts: &RestoreOptions{TargetDir: targetDir},
result: &RestoreResult{},
}
for _, row := range rows {
require.NoError(t, session.restoreFile(row))
}
v.warnIfOwnershipNotPreserved(rows, targetDir)
return out.String()
}
internal/vaultik/restore_perms_test.go
+1 -1
View File
@@ -107,7 +107,7 @@ func backupOneFile(
require.NoError(t, afero.WriteFile(fs, srcPath, content, mode))
require.NoError(t, fs.Chmod(srcPath, mode))
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
storer, err := storage.NewFileStorer(storeDir)
internal/vaultik/restore_skip_errors_test.go
+2 -5
View File
@@ -231,8 +231,7 @@ func (f trailingByteFile) Close() error {
}
// TestRestoreMissingBlobAbortsWithoutSkipErrors checks that a deleted blob
// still ends the restore with an error when SkipErrors is not set, and
// that the error names the blob once.
// still ends the restore with an error when SkipErrors is not set.
func TestRestoreMissingBlobAbortsWithoutSkipErrors(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
@@ -248,8 +247,6 @@ func TestRestoreMissingBlobAbortsWithoutSkipErrors(t *testing.T) {
})
require.ErrorIs(t, err, storage.ErrNotFound)
assert.Equal(t, 1, strings.Count(err.Error(), "downloading blob"),
err.Error())
}
// TestRestoreChunkInNoBlobAbortsWithoutSkipErrors checks that a chunk held
@@ -348,7 +345,7 @@ func backupSingleChunkFiles(
require.NoError(t, afero.WriteFile(fs, path, files[path], 0o644))
}
storer, err := storage.NewFileStorer(t.TempDir())
storer, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
internal/vaultik/restore_snapshot_identity_test.go
+2 -2
View File
@@ -29,7 +29,7 @@ func TestRestoreAndDeepVerifyRejectSwappedDatabase(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
chunkSize := int64(64 * 1024)
@@ -100,7 +100,7 @@ func TestDeepVerifyRejectsSwappedDatabaseWithEmptyManifest(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
chunkSize := int64(64 * 1024)
internal/vaultik/restore_sweeper_integration_test.go
+1 -1
View File
@@ -186,7 +186,7 @@ func TestRestoreSweeperEvictsBlobs(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/restore_sweeper_test.go
+1 -1
View File
@@ -34,7 +34,7 @@ func TestRestoreFreesBlobsNoPendingFileNeeds(t *testing.T) {
dataDir := filepath.Join(tempDir, "source")
originalsDir := filepath.Join(dataDir, "originals")
copiesDir := filepath.Join(dataDir, "copies")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
originals := writeFilesWithCopies(t, fs, originalsDir, copiesDir, fileBytes)
internal/vaultik/restore_truncated_db_test.go
+1 -1
View File
@@ -33,7 +33,7 @@ func TestRestoreRejectsTruncatedMetadataDB(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/restore_unmatched_path_test.go
+3 -3
View File
@@ -32,7 +32,7 @@ func TestRestoreNamesUnmatchedPathAndRestoresTheMatchingOne(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -89,7 +89,7 @@ func TestRestoreNamesEveryPathWhenNothingMatches(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
linkDir := filepath.Join(tempDir, "srclink")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -152,7 +152,7 @@ func TestRestoreNamesUnmatchedPathWhenADamagedBlobStopsIt(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/reused_blob_verify_test.go
+1 -1
View File
@@ -28,7 +28,7 @@ func TestVerifyPassesWhenBackupReusesStoredBlob(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
secondDBPath := filepath.Join(tempDir, "second.sqlite")
chunkSize := int64(64 * 1024)
internal/vaultik/same_second_rewrite_test.go
+1 -1
View File
@@ -25,7 +25,7 @@ func TestBackupOfSameSecondRewriteRestoresNewContent(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
rewrittenPath := filepath.Join(dataDir, "small.txt")
internal/vaultik/shallow_verify_test.go
+5 -11
View File
@@ -27,7 +27,7 @@ import (
// then grows one stored blob so its size no longer matches the manifest.
// Shallow verify must then fail, count the grown blob as a size mismatch,
// and drop it from the verified count rather than continuing to report it
// as checked, and its error must not repeat the cli layer's prefix.
// as checked.
func TestShallowVerifyDetectsWrongBlobSize(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
@@ -36,7 +36,7 @@ func TestShallowVerifyDetectsWrongBlobSize(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
@@ -96,12 +96,6 @@ func TestShallowVerifyDetectsWrongBlobSize(t *testing.T) {
require.Equal(t, 1, bad.Mismatched)
require.Equal(t, healthy.BlobCount-1, bad.Verified,
"the wrong-sized blob must not be counted as verified")
// The cli layer prints this error after its own "Verification failed:".
err = newVerifier(io.Discard).VerifySnapshotWithOptions(
snapshotID, &vaultik.VerifyOptions{})
require.EqualError(t, err,
"problems found in storage: 1 blobs have the wrong size")
}
// TestShallowVerifyDetectsMissingDatabase backs up a real snapshot,
@@ -116,7 +110,7 @@ func TestShallowVerifyDetectsMissingDatabase(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
@@ -199,7 +193,7 @@ func TestShallowVerifyReportsStatErrorsApartFromMissing(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
@@ -288,7 +282,7 @@ func TestShallowVerifyQuietFailsOnStatErrorAlone(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
internal/vaultik/snapshot.go
+79 -263
View File
@@ -23,7 +23,6 @@ var (
errSnapshotNotInConfig = errors.New("snapshot not found in config")
errNoSnapshotsInConfig = errors.New("no snapshots configured")
errSnapshotVerifyFailed = errors.New("verification failed")
errProblemsInStorage = errors.New("problems found in storage")
errRemoveAllNeedsForce = errors.New("--all requires --force")
errSnapshotNotFound = errors.New("snapshot not found")
errSnapshotRemoveFailed = errors.New("snapshot(s) could not be removed")
@@ -39,18 +38,6 @@ var (
// caller can report it apart from a failed backup.
var ErrPostBackupPruneFailed = errors.New("post-backup prune failed")
// ErrFilesUnreadable is returned when --skip-errors skipped files or
// directories it could not read or list. The snapshot is complete and
// kept, so the caller can report it apart from a failed backup.
var ErrFilesUnreadable = errors.New("file(s) could not be read")
// ErrSourcePathEmpty is returned when --prune skipped the post-backup
// prune because the scan found nothing in a configured path of a
// snapshot, as in the mount point of a volume that is not mounted. The
// snapshots are complete and kept, so the caller can report it apart
// from a failed backup.
var ErrSourcePathEmpty = errors.New("source path(s) were empty")
// listRecentLimit caps how many snapshot rows are fetched from the
// local index for listing and purge operations.
const listRecentLimit = 10000
@@ -107,13 +94,6 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
return err
}
// Before PruneDatabase: it drops incomplete snapshots, which could
// leave the local index without one and so skip the marker check.
err = v.markDestination()
if err != nil {
return err
}
// Clean up incomplete snapshots FIRST, before any scanning.
// This is critical for data safety; PruneDatabase below does it.
hostname := v.Config.Hostname
@@ -136,15 +116,30 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
return fmt.Errorf("prune database: %w", err)
}
snapshotNames, err := v.snapshotNamesToCreate(opts.Snapshots)
if err != nil {
return err
// Determine which snapshots to process
snapshotNames := opts.Snapshots
if len(snapshotNames) == 0 {
snapshotNames = v.Config.SnapshotNames()
} else {
// Validate requested snapshot names exist
for _, name := range snapshotNames {
if _, ok := v.Config.Snapshots[name]; !ok {
return fmt.Errorf("%w: %q", errSnapshotNotInConfig, name)
}
}
}
filesUnreadable, emptyPaths, err := v.createNamedSnapshots(
opts, hostname, snapshotNames)
if err != nil {
return err
if len(snapshotNames) == 0 {
return errNoSnapshotsInConfig
}
// Process each named snapshot
for snapIdx, snapName := range snapshotNames {
err = v.createNamedSnapshot(
opts, hostname, snapName, snapIdx+1, len(snapshotNames))
if err != nil {
return err
}
}
// Print overall summary if multiple snapshots
@@ -153,84 +148,13 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
len(snapshotNames), v.UI.Duration(time.Since(overallStartTime)))
}
switch {
case opts.Prune && (filesUnreadable > 0 || len(emptyPaths) > 0):
return v.skipPostBackupPrune(filesUnreadable, emptyPaths)
case opts.Prune:
if opts.Prune {
err = v.runPostBackupPrune(snapshotNames, opts.KeepNewerThan)
if err != nil {
return fmt.Errorf("%w: %w", ErrPostBackupPruneFailed, err)
}
}
return v.finishCreateSnapshot(filesUnreadable)
}
// createNamedSnapshots creates each named snapshot in turn. It returns
// the number of entries --skip-errors skipped because it could not read
// or list them, and each configured path in which the scan found
// nothing, named with its snapshot.
func (v *Vaultik) createNamedSnapshots(
opts *SnapshotCreateOptions, hostname string, snapshotNames []string,
) (int, []string, error) {
filesUnreadable := 0
var emptyPaths []string
for snapIdx, snapName := range snapshotNames {
stats, err := v.createNamedSnapshot(
opts, hostname, snapName, snapIdx+1, len(snapshotNames))
if err != nil {
return 0, nil, err
}
filesUnreadable += stats.totalFilesUnreadable
for _, dir := range stats.emptyPaths {
emptyPaths = append(emptyPaths, dir+" of snapshot "+snapName)
}
}
return filesUnreadable, emptyPaths, nil
}
// skipPostBackupPrune says why the post-backup prune does not run, naming
// every cause, and returns the error the run ends with. An older snapshot
// may be the only one that still holds a file this run could not read,
// or what an empty path held. The previous snapshot is no guide: after
// one run with an empty path it is empty too.
func (v *Vaultik) skipPostBackupPrune(
filesUnreadable int, emptyPaths []string,
) error {
log.Warn("Skipping post-backup prune",
"files_unreadable", filesUnreadable, "empty_paths", emptyPaths)
if len(emptyPaths) > 0 {
v.UI.Warningf("Skipped the post-backup prune because nothing was "+
"found in %s; older snapshots are kept.",
strings.Join(emptyPaths, ", "))
}
if filesUnreadable > 0 {
v.UI.Warningf("Skipped the post-backup prune because %d file(s) "+
"could not be read; older snapshots are kept.", filesUnreadable)
return fmt.Errorf("%d %w", filesUnreadable, ErrFilesUnreadable)
}
return fmt.Errorf("%d %w", len(emptyPaths), ErrSourcePathEmpty)
}
// finishCreateSnapshot ends a run whose snapshots are all complete and
// kept. Like finishRestore, it returns an error when --skip-errors
// skipped anything it could not read or list; otherwise it prints the
// closing line. A file removed during the run is counted as failed in
// the summary but is not an error, with or without --skip-errors.
func (v *Vaultik) finishCreateSnapshot(filesUnreadable int) error {
if filesUnreadable > 0 {
return fmt.Errorf("%d %w", filesUnreadable, ErrFilesUnreadable)
}
// Terminus must obey the --cron invariant: silent on total
// success only. UI.Complete is dropped in cron/quiet mode (that's
// the success path), but if any warnings fired during the run we
@@ -246,28 +170,6 @@ func (v *Vaultik) finishCreateSnapshot(filesUnreadable int) error {
return nil
}
// snapshotNamesToCreate returns the requested snapshot names, each checked
// against the config, or every configured name when none was requested.
func (v *Vaultik) snapshotNamesToCreate(requested []string) ([]string, error) {
snapshotNames := requested
if len(snapshotNames) == 0 {
snapshotNames = v.Config.SnapshotNames()
} else {
// Validate requested snapshot names exist
for _, name := range snapshotNames {
if _, ok := v.Config.Snapshots[name]; !ok {
return nil, fmt.Errorf("%w: %q", errSnapshotNotInConfig, name)
}
}
}
if len(snapshotNames) == 0 {
return nil, errNoSnapshotsInConfig
}
return snapshotNames, nil
}
// runPostBackupPrune drops older snapshots of the given names and removes
// orphan blobs from remote storage. If keepNewerThan is set (e.g. "4w"),
// snapshots newer than that duration are kept. Otherwise only the latest
@@ -320,24 +222,16 @@ type snapshotStats struct {
totalBlobsUploaded int
uploadDuration time.Duration
// The part of totalFilesFailed that --skip-errors skipped because it
// could not be read or listed.
totalFilesUnreadable int
// The configured paths in which the scan found nothing.
emptyPaths []string
// The sizes of all blobs the snapshot references, set by
// finalizeSnapshotMetadata once snapshot_blobs is populated.
blobSize int64
blobUncompressedSize int64
}
// createNamedSnapshot creates a single named snapshot and returns the
// statistics of its scan.
// createNamedSnapshot creates a single named snapshot
func (v *Vaultik) createNamedSnapshot(
opts *SnapshotCreateOptions, hostname, snapName string, idx, total int,
) (*snapshotStats, error) {
) error {
snapshotStartTime := time.Now()
if total > 1 {
@@ -346,27 +240,21 @@ func (v *Vaultik) createNamedSnapshot(
resolvedDirs, err := v.resolveSnapshotPaths(snapName)
if err != nil {
return nil, err
}
previousSnapshotID, err := v.previousSnapshotID(snapName)
if err != nil {
return nil, err
return err
}
scanner := v.ScannerFactory(snapshot.ScannerParams{
EnableProgress: !opts.Cron,
UI: v.UI,
Fs: v.Fs,
Exclude: v.Config.GetExcludes(snapName),
SkipErrors: opts.SkipErrors,
PreviousSnapshotID: previousSnapshotID,
EnableProgress: !opts.Cron,
UI: v.UI,
Fs: v.Fs,
Exclude: v.Config.GetExcludes(snapName),
SkipErrors: opts.SkipErrors,
})
snapshotID, err := v.SnapshotManager.CreateSnapshotWithName(
v.ctx, hostname, snapName, v.Globals.Version, v.Globals.Commit)
if err != nil {
return nil, fmt.Errorf("creating snapshot: %w", err)
return fmt.Errorf("creating snapshot: %w", err)
}
log.Info("Beginning snapshot", "snapshot_id", snapshotID, "name", snapName)
@@ -374,12 +262,12 @@ func (v *Vaultik) createNamedSnapshot(
stats, err := v.scanAllDirectories(scanner, resolvedDirs, snapshotID)
if err != nil {
return nil, err
return err
}
err = v.finalizeSnapshotMetadata(snapshotID, stats)
if err != nil {
return nil, err
return err
}
log.Info("Snapshot complete",
@@ -392,30 +280,11 @@ func (v *Vaultik) createNamedSnapshot(
v.printSnapshotSummary(snapshotID, snapshotStartTime, stats)
return stats, nil
}
// previousSnapshotID returns the ID of the most recent completed snapshot
// named snapName in the local index, or "" when there is none.
func (v *Vaultik) previousSnapshotID(snapName string) (string, error) {
snapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, listRecentLimit)
if err != nil {
return "", fmt.Errorf("listing snapshots: %w", err)
}
for _, s := range snapshots {
if s.CompletedAt != nil &&
parseSnapshotName(s.ID.String(), s.Hostname.String()) == snapName {
return s.ID.String(), nil
}
}
return "", nil
return nil
}
// resolveSnapshotPaths resolves source directories to absolute paths
// with symlink resolution. A path that is a symlink whose target does
// not exist is an error.
// with symlink resolution.
func (v *Vaultik) resolveSnapshotPaths(snapName string) ([]string, error) {
snapConfig := v.Config.Snapshots[snapName]
resolvedDirs := make([]string, 0, len(snapConfig.Paths))
@@ -428,18 +297,12 @@ func (v *Vaultik) resolveSnapshotPaths(snapName string) ([]string, error) {
resolvedPath, err := filepath.EvalSymlinks(absPath)
if err != nil {
// A path that does not exist is left for the scan to report.
// One that exists is a symlink whose target is gone, as one
// into a volume that is not mounted: the scan would record
// only the link, and --prune would then drop the older
// snapshots that hold the files.
_, lstatErr := os.Lstat(absPath)
if !os.IsNotExist(err) || lstatErr == nil {
if os.IsNotExist(err) {
resolvedPath = absPath
} else {
return nil, fmt.Errorf(
"failed to resolve symlinks for %s: %w", absPath, err)
}
resolvedPath = absPath
}
resolvedDirs = append(resolvedDirs, resolvedPath)
@@ -485,7 +348,6 @@ func (v *Vaultik) scanAllDirectories(
stats.totalBlobs += result.BlobsCreated
stats.totalFilesSkipped += result.FilesSkipped
stats.totalFilesFailed += result.FilesFailed
stats.totalFilesUnreadable += result.FilesUnreadable
stats.totalBytesSkipped += result.BytesSkipped
stats.totalFilesDeleted += result.FilesDeleted
stats.totalBytesDeleted += result.BytesDeleted
@@ -493,10 +355,6 @@ func (v *Vaultik) scanAllDirectories(
stats.totalBytesUploaded += result.BytesUploaded
stats.uploadDuration += result.UploadDuration
if result.EntriesFound == 0 {
stats.emptyPaths = append(stats.emptyPaths, dir)
}
log.Info("Directory scan complete",
"path", dir,
"files", result.FilesScanned,
@@ -754,7 +612,7 @@ func selectSnapshotsToPurge(
case opts.OlderThan != "":
duration, err := parseDuration(opts.OlderThan)
if err != nil {
return nil, err
return nil, fmt.Errorf("invalid duration: %w", err)
}
cutoff := time.Now().UTC().Add(-duration)
@@ -1083,10 +941,8 @@ func (v *Vaultik) formatVerifyResult(
v.printVerifySummary(result, failure)
}
// Not errSnapshotVerifyFailed: the cli layer prints this after its own
// "Verification failed:".
if failure != "" {
return fmt.Errorf("%w: %s", errProblemsInStorage, failure)
return fmt.Errorf("%w: %s", errSnapshotVerifyFailed, failure)
}
return nil
@@ -1398,18 +1254,10 @@ func (v *Vaultik) RemoveSnapshot(
return v.removeSnapshotDryRun(result, snapshotID, opts)
}
if !v.confirmRemoveSnapshot(snapshotID, opts) {
if !opts.Force && !opts.JSON && !v.confirmRemoveSnapshot(snapshotID, opts) {
return result, nil
}
// Checked before the local record is deleted: it may be the last
// snapshot in the local index, and the check applies only while the
// local index holds one.
var markerErr error
if !opts.LocalOnly {
markerErr = v.checkDestinationMarker()
}
if inLocalIndex {
log.Info("Removing snapshot from local database", "snapshot_id", snapshotID)
@@ -1420,7 +1268,7 @@ func (v *Vaultik) RemoveSnapshot(
}
result.RemoteRemoved, err = v.removeSnapshotRemote(
snapshotID, inLocalIndex, markerErr, opts)
snapshotID, inLocalIndex, opts)
if err != nil {
return result, err
}
@@ -1457,9 +1305,7 @@ func (v *Vaultik) RemoveSnapshot(
// remove: no row and, unless LocalOnly is set, no metadata on the
// destination store either. The destination store is consulted only
// when the local index has no row, so a snapshot in the local index can
// still be removed from it while the destination store is unreachable,
// and only after checkDestinationMarker passes, so an unplugged volume's
// empty mount point is not taken for a store without the snapshot.
// still be removed from it while the destination store is unreachable.
func (v *Vaultik) findSnapshotToRemove(
snapshotID string, opts *RemoveOptions,
) (bool, error) {
@@ -1479,11 +1325,6 @@ func (v *Vaultik) findSnapshotToRemove(
errSnapshotNotFound, snapshotID)
}
err := v.checkDestinationMarker()
if err != nil {
return false, err
}
objects, err := v.remoteSnapshotObjects(snapshot.RemoteSnapshotKey(snapshotID))
if err != nil {
return false, fmt.Errorf("looking up snapshot on destination store: %w", err)
@@ -1522,15 +1363,11 @@ func (v *Vaultik) removeSnapshotDryRun(
}
// confirmRemoveSnapshot prompts for confirmation before removing a
// snapshot, unless --force or --json is set. Returns false (treating
// EOF/read errors as "no") unless the user answers "y". The prompt and
// its answer bypass the UI: they are an interactive exchange the
// operator must see, so --quiet does not silence them.
// snapshot. Returns false (treating EOF/read errors as "no") unless the
// user answers "y". The prompt and its answer bypass the UI: they are an
// interactive exchange the operator must see, so --quiet does not
// silence them.
func (v *Vaultik) confirmRemoveSnapshot(snapshotID string, opts *RemoveOptions) bool {
if opts.Force || opts.JSON {
return true
}
if opts.LocalOnly {
v.stdoutf("Remove snapshot '%s' from local database "+
"(remote untouched)? [y/N] ", snapshotID)
@@ -1560,17 +1397,15 @@ func (v *Vaultik) confirmRemoveSnapshot(snapshotID string, opts *RemoveOptions)
// removeSnapshotRemote strips the snapshot's metadata from the
// destination store. It returns true only when the delete finished
// without an error and removed at least one object; under LocalOnly it
// does nothing. markerErr is the result of checkDestinationMarker; when
// it is set, nothing is deleted and it is the failure. When the snapshot
// is only on the destination store, a failure is returned as an error,
// because that removal is all the command does. When the snapshot was in
// the local index, its removal there has already happened, so a failure
// is only a warning telling the user to run `vaultik snapshot remove`
// for the snapshot again once the destination store is reachable
// (`vaultik prune` never removes snapshot metadata).
// does nothing. When the snapshot is only on the destination store, a
// failure is returned as an error, because that removal is all the
// command does. When the snapshot was in the local index, its removal
// there has already happened, so a failure is only a warning telling the
// user to run `vaultik snapshot remove` for the snapshot again once the
// destination store is reachable (`vaultik prune` never removes snapshot
// metadata).
func (v *Vaultik) removeSnapshotRemote(
snapshotID string, inLocalIndex bool, markerErr error,
opts *RemoveOptions,
snapshotID string, inLocalIndex bool, opts *RemoveOptions,
) (bool, error) {
if opts.LocalOnly {
return false, nil
@@ -1579,14 +1414,9 @@ func (v *Vaultik) removeSnapshotRemote(
log.Info("Removing snapshot metadata from remote storage",
"snapshot_id", snapshotID)
var deleted int
err := markerErr
if err == nil {
deleted, err = v.deleteRemoteSnapshotByKey(
snapshot.RemoteSnapshotKey(snapshotID))
}
remoteKey := snapshot.RemoteSnapshotKey(snapshotID)
deleted, err := v.deleteRemoteSnapshotByKey(remoteKey)
if err != nil && !inLocalIndex {
return false, fmt.Errorf(
"removing snapshot metadata from destination store: %w", err)
@@ -1616,9 +1446,7 @@ func (v *Vaultik) removeSnapshotRemote(
// database from the local index, and (with --remote) every snapshot
// metadata directory in remote storage. Both sides are processed so a
// "remove --all" leaves nothing behind, even when the local DB and
// remote storage have diverged. Unless LocalOnly is set, it fails
// before it removes anything when the destination store cannot be
// listed or is not present by checkDestinationMarker.
// remote storage have diverged.
func (v *Vaultik) RemoveAllSnapshots(opts *RemoveOptions) (*RemoveResult, error) {
err := v.EnsureStorageBinding()
if err != nil {
@@ -1631,15 +1459,11 @@ func (v *Vaultik) RemoveAllSnapshots(opts *RemoveOptions) (*RemoveResult, error)
}
// remoteKeys is the set of metadata/<key>/ subdirectories on the
// destination store. Only for a local-only remove is a failure
// downgraded to a warning, so a permission-denied or unreachable
// remote can't block it.
// destination store; failures are downgraded to a warning so a
// permission-denied or unreachable remote can't block a local-only
// remove.
remoteKeys, remoteErr := v.listAllRemoteSnapshotKeys()
if remoteErr != nil {
if !opts.LocalOnly {
return nil, remoteErr
}
log.Warn("Could not list remote snapshots", "error", remoteErr)
v.UI.Warningf("Could not list remote snapshots: %v.", remoteErr)
}
@@ -1701,7 +1525,8 @@ func (v *Vaultik) localSnapshotIDs() ([]string, error) {
// listAllRemoteSnapshotKeys collects the hashed remote keys
// (subdirectories under metadata/) currently present in the
// destination store. Returns (nil, err) when the store cannot be
// listed, or is not present by checkDestinationMarker.
// listed; callers must treat that as "no remote info available," not
// fatal.
func (v *Vaultik) listAllRemoteSnapshotKeys() ([]string, error) {
log.Info("Listing all remote snapshots")
@@ -1750,11 +1575,6 @@ func (v *Vaultik) listAllRemoteSnapshotKeys() ([]string, error) {
}
}
err := v.checkDestinationMarker()
if err != nil {
return nil, err
}
return keys, nil
}
@@ -1885,12 +1705,10 @@ func (v *Vaultik) deleteIncompleteSnapshot(snapshotIDStr string, id any) bool {
return true
}
// removeAllLocalSnapshots removes each known local snapshot's remote
// metadata, unless --local-only, and then its local record, returning
// the number of snapshots it could not remove. The local record goes
// only once the metadata is deleted: dropped first, it would leave that
// metadata on the destination store as a remote-only snapshot whose name
// is lost.
// removeAllLocalSnapshots removes each known local snapshot (and, unless
// --local-only, its remote metadata), returning the number of snapshots
// it could not remove. A snapshot left in the local index keeps its
// remote metadata too, since it is not an orphan remote key.
func (v *Vaultik) removeAllLocalSnapshots(
localSnaps []string, opts *RemoveOptions, result *RemoveResult,
) int {
@@ -1899,19 +1717,6 @@ func (v *Vaultik) removeAllLocalSnapshots(
for _, snapshotID := range localSnaps {
log.Info("Removing snapshot", "snapshot_id", snapshotID)
if !opts.LocalOnly {
_, err := v.deleteRemoteSnapshotByKey(
snapshot.RemoteSnapshotKey(snapshotID))
if err != nil {
log.Warn("Failed to remove snapshot metadata from remote",
"snapshot_id", snapshotID, "error", err)
failures++
continue
}
}
err := v.deleteSnapshotFromLocalDB(snapshotID)
if err != nil {
log.Error("Failed to remove from local database",
@@ -1922,6 +1727,17 @@ func (v *Vaultik) removeAllLocalSnapshots(
continue
}
if !opts.LocalOnly {
_, err = v.deleteRemoteSnapshotByKey(
snapshot.RemoteSnapshotKey(snapshotID))
if err != nil {
log.Warn("Failed to remove snapshot metadata from remote",
"snapshot_id", snapshotID, "error", err)
failures++
}
}
result.SnapshotsRemoved = append(result.SnapshotsRemoved, snapshotID)
}
internal/vaultik/snapshot_deleted_count_test.go
-251
View File
@@ -1,251 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"fmt"
"os"
"path/filepath"
"testing"
"time"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// These tests cover https://git.eeqj.de/sneak/vaultik/issues/304: a
// backup counts a file as deleted only when the previous snapshot of
// the same name had it and it is gone, and never counts an excluded
// file.
// deletedCountEnv is a backup setup over the source directory src whose
// user-facing output is kept in out. Each test configures its snapshots
// with setSnapshot.
type deletedCountEnv struct {
v *vaultik.Vaultik
out *bytes.Buffer
src string
}
// newDeletedCountEnv writes files, keyed by path relative to src.
func newDeletedCountEnv(t *testing.T, files map[string][]byte) *deletedCountEnv {
t.Helper()
ctx := context.Background()
fs := afero.NewOsFs()
tempDir := t.TempDir()
srcDir := filepath.Join(tempDir, "src")
for rel, content := range files {
path := filepath.Join(srcDir, rel)
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
require.NoError(t, afero.WriteFile(fs, path, content, 0o644))
}
cfg := faultTestConfig()
cfg.IndexPath = filepath.Join(tempDir, "index.sqlite")
cfg.Snapshots = map[string]config.SnapshotConfig{}
store, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
db, err := database.New(ctx, cfg.IndexPath)
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
out := &bytes.Buffer{}
v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
v.UI = ui.NewWithColor(out, false)
return &deletedCountEnv{v: v, out: out, src: srcDir}
}
// setSnapshot configures the snapshot name to back up the path rel
// beneath src, with the given excludes.
func (e *deletedCountEnv) setSnapshot(name, rel string, exclude ...string) {
e.v.Config.Snapshots[name] = config.SnapshotConfig{
Paths: []string{filepath.Join(e.src, rel)},
Exclude: exclude,
}
}
// backUp runs a backup of the named snapshot and returns its output.
func (e *deletedCountEnv) backUp(t *testing.T, name string) string {
t.Helper()
e.out.Reset()
require.NoError(t, e.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Snapshots: []string{name},
}))
return e.out.String()
}
// A file this snapshot excludes is not counted as deleted: neither one
// that another snapshot backs up, nor one that the previous snapshot of
// this name had before the exclude was added.
func TestBackupDoesNotCountExcludedFileAsDeleted(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"top.txt": []byte("top"),
"cache/tmp.bin": []byte("cache"),
"photos/a.jpg": []byte("photo a"),
"photos/b.jpg": []byte("photo b"),
"photos/c.jpg": []byte("photo c"),
})
env.setSnapshot("photos", "photos")
env.setSnapshot("home", "", "/photos")
env.backUp(t, "photos")
assert.Contains(t, env.backUp(t, "home"), filesLine(2, 2, 0))
env.setSnapshot("home", "", "/photos", "/cache")
assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
}
// A file inside a directory that an exclude added after a backup
// matches is not counted as deleted, though the pattern matches only the
// directory and the directory is gone from disk.
func TestBackupDoesNotCountFileInExcludedDirectoryAsDeleted(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"top.txt": []byte("top"),
"user/.local/share/Trash/old.txt": []byte("old"),
})
env.setSnapshot("home", "")
assert.Contains(t, env.backUp(t, "home"), filesLine(2, 2, 0))
require.NoError(t, os.RemoveAll(
filepath.Join(env.src, "user/.local/share/Trash")))
env.setSnapshot("home", "", "*/.local/share/Trash")
assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
}
// A file whose directory was replaced by a regular file of the same name
// is counted as deleted.
func TestBackupCountsFileInDirectoryReplacedByFileAsDeleted(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"dir/inside.txt": []byte("inside"),
})
env.setSnapshot("home", "")
assert.Contains(t, env.backUp(t, "home"), filesLine(1, 1, 0))
dir := filepath.Join(env.src, "dir")
require.NoError(t, os.RemoveAll(dir))
require.NoError(t, os.WriteFile(dir, []byte("now a file"), 0o600))
assert.Contains(t, env.backUp(t, "home"),
"Files: 1 examined, 1 backed up, 0 unchanged, 1 deleted.")
}
// Under --skip-errors a file inside a directory that the walk cannot
// open is not counted as deleted: it is still on disk.
func TestBackupDoesNotCountFileInUnopenableDirectoryAsDeleted(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"open.txt": []byte("open"),
"locked/inside.txt": []byte("inside"),
})
env.setSnapshot("work", "")
assert.Contains(t, env.backUp(t, "work"), filesLine(2, 2, 0))
// A directory's mode does not lock out root, who runs the tests, so
// opening the directory is made to fail instead.
env.v.Fs = &openFailFs{
path: filepath.Join(env.src, "locked"),
err: os.ErrPermission,
}
env.out.Reset()
err := env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
SkipErrors: true,
Snapshots: []string{"work"},
})
require.ErrorIs(t, err, vaultik.ErrFilesUnreadable)
assert.Contains(t, env.out.String(),
"Files: 2 examined, 0 backed up, 1 unchanged, 1 failed.")
}
// A backup counts only files that the previous snapshot of its own name
// had, not one that a later snapshot of another name over the same path
// had and that is since removed.
func TestBackupIgnoresSnapshotOfAnotherName(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"kept.txt": []byte("kept"),
})
env.setSnapshot("home", "")
env.setSnapshot("other", "")
env.backUp(t, "home")
// Snapshot start times are kept in whole seconds: wait so that other's
// snapshot is strictly the most recent.
time.Sleep(time.Second)
extra := filepath.Join(env.src, "extra.txt")
require.NoError(t, os.WriteFile(extra, []byte("extra"), 0o600))
env.backUp(t, "other")
require.NoError(t, os.Remove(extra))
assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
}
// A file removed from disk is counted as deleted by the next backup of
// the snapshot that had it, and not by any later backup of that
// snapshot, nor by the first backup of another name over the same path.
func TestBackupCountsDeletedFileOnce(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
aContent := bytes.Repeat([]byte("a"), 1000)
bContent := bytes.Repeat([]byte("b"), 2000)
keptContent := bytes.Repeat([]byte("k"), 500)
env := newDeletedCountEnv(t, map[string][]byte{
"a.txt": aContent,
"b.txt": bContent,
"kept.txt": keptContent,
})
env.setSnapshot("home", "")
env.setSnapshot("other", "")
assert.Contains(t, env.backUp(t, "home"), filesLine(3, 3, 0))
require.NoError(t, os.Remove(filepath.Join(env.src, "a.txt")))
require.NoError(t, os.Remove(filepath.Join(env.src, "b.txt")))
summary := env.backUp(t, "home")
assert.Contains(t, summary,
"Files: 1 examined, 0 backed up, 1 unchanged, 2 deleted.")
assert.Contains(t, summary,
fmt.Sprintf("Data: %s total (%s backed up), %s deleted.",
env.v.UI.Size(int64(len(keptContent))), env.v.UI.Size(0),
env.v.UI.Size(int64(len(aContent)+len(bContent)))))
assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
assert.Contains(t, env.backUp(t, "other"), filesLine(1, 0, 1))
}
internal/vaultik/snapshot_failed_file_test.go
+4 -11
View File
@@ -49,19 +49,13 @@ func TestSnapshotSummaryCountsFileNotStoredAsFailed(t *testing.T) {
name string
openErr error
skipErrors bool
wantErr error // nil for none
}{
// What a normal user gets opening a file with mode 000.
{name: "unopenable under skip-errors",
openErr: os.ErrPermission, skipErrors: true,
wantErr: vaultik.ErrFilesUnreadable},
openErr: os.ErrPermission, skipErrors: true},
// What opening a file removed after phase 1 gives.
{name: "removed between the phases",
openErr: os.ErrNotExist, skipErrors: false},
// A removal is not an error, so --skip-errors does not make the
// run fail. See https://git.eeqj.de/sneak/vaultik/issues/310.
{name: "removed between the phases under skip-errors",
openErr: os.ErrNotExist, skipErrors: true},
}
for _, tt := range tests {
@@ -93,7 +87,7 @@ func TestSnapshotSummaryCountsFileNotStoredAsFailed(t *testing.T) {
"src": {Paths: []string{srcDir}},
}
store, err := storage.NewFileStorer(t.TempDir())
store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
db, err := database.New(ctx, cfg.IndexPath)
@@ -105,11 +99,10 @@ func TestSnapshotSummaryCountsFileNotStoredAsFailed(t *testing.T) {
v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
v.UI = ui.NewWithColor(out, false)
err = v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
require.NoError(t, v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
SkipErrors: tt.skipErrors,
Snapshots: []string{"src"},
})
require.ErrorIs(t, err, tt.wantErr)
}))
summary := out.String()
assert.Contains(t, summary,
internal/vaultik/snapshot_list_test.go
-3
View File
@@ -122,9 +122,6 @@ func newListEnv(t *testing.T) *listEnv {
store := newObservingStorer()
stdout := &bytes.Buffer{}
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, store.Put(ctx, markerFile, strings.NewReader("")))
v := &vaultik.Vaultik{
Config: &config.Config{
AgeSecretKey: "",
internal/vaultik/snapshot_prune_test.go
-234
View File
@@ -1,15 +1,8 @@
package vaultik_test
import (
"context"
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/vaultik"
)
@@ -32,230 +25,3 @@ func TestSnapshotCreateOptions_PruneFlag(t *testing.T) {
t.Error("Expected Prune to be false")
}
}
// A backup under --prune that finds nothing in a configured path, as in
// the mount point of a volume that is not mounted, does not prune: run
// after run, the snapshot that holds the files is kept with everything
// it stored, and the run fails. That holds whether the empty path is the
// snapshot's only path or one of two. See
// https://git.eeqj.de/sneak/vaultik/issues/388.
func TestBackupWithEmptySourcePathDoesNotPrune(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
// emptied is the path, relative to the source directory, that is
// emptied after the first backup.
const (
snapshotName = "media"
emptied = "music"
)
tests := []struct {
name string
paths []string // relative to the source directory
}{
{name: "only path", paths: []string{emptied}},
{name: "one of two paths", paths: []string{emptied, "docs"}},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
ctx := context.Background()
env := newDeletedCountEnv(t, map[string][]byte{
emptied + "/a.mp3": []byte("song a"),
emptied + "/b.mp3": []byte("song b"),
"docs/notes.txt": []byte("notes"),
})
paths := make([]string, 0, len(tt.paths))
for _, rel := range tt.paths {
paths = append(paths, filepath.Join(env.src, rel))
}
env.v.Config.Snapshots[snapshotName] = config.SnapshotConfig{
Paths: paths,
}
env.backUp(t, snapshotName)
firstID := localSnapshotID(ctx, t, env.v.Repositories, snapshotName)
stored, err := env.v.Storage.List(ctx, "")
require.NoError(t, err)
// A volume that is not mounted leaves its mount point behind
// as an empty directory.
emptiedDir := filepath.Join(env.src, emptied)
require.NoError(t, os.RemoveAll(emptiedDir))
require.NoError(t, os.Mkdir(emptiedDir, 0o750))
for range 2 {
env.out.Reset()
err := env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Prune: true,
Snapshots: []string{snapshotName},
})
require.ErrorIs(t, err, vaultik.ErrSourcePathEmpty)
assert.Contains(t, env.out.String(),
"Skipped the post-backup prune because nothing was found in ")
assert.Contains(t, env.out.String(),
emptied+" of snapshot "+snapshotName+";")
assert.NotContains(t, env.out.String(), "Running post-backup prune.")
}
snapshots, err := env.v.Repositories.Snapshots.ListRecent(
ctx, listRecentTestLimit)
require.NoError(t, err)
require.Len(t, snapshots, 3)
assert.Equal(t, firstID, snapshots[2].ID.String(),
"the snapshot that holds the files is kept")
for _, key := range stored {
_, err := env.v.Storage.Stat(ctx, key)
require.NoError(t, err, "%s is kept", key)
}
})
}
}
// A backup under --prune of a configured path that is a symlink whose
// target is gone, as one into a volume that is not mounted, fails before
// anything is pruned: the snapshot that holds the files is kept with
// everything it stored. See https://git.eeqj.de/sneak/vaultik/issues/388.
func TestBackupThroughSymlinkWhoseTargetIsGoneDoesNotPrune(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
const snapshotName = "photos"
ctx := context.Background()
env := newDeletedCountEnv(t, map[string][]byte{
"volume/a.jpg": []byte("photo a"),
"volume/b.jpg": []byte("photo b"),
})
target := filepath.Join(env.src, "volume")
link := filepath.Join(env.src, "photos")
require.NoError(t, os.Symlink(target, link))
env.setSnapshot(snapshotName, "photos")
env.backUp(t, snapshotName)
firstID := localSnapshotID(ctx, t, env.v.Repositories, snapshotName)
stored, err := env.v.Storage.List(ctx, "")
require.NoError(t, err)
// The volume is not mounted, so the symlink points at nothing.
require.NoError(t, os.RemoveAll(target))
env.out.Reset()
err = env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Prune: true,
Snapshots: []string{snapshotName},
})
require.ErrorIs(t, err, os.ErrNotExist)
assert.Contains(t, err.Error(), link)
assert.NotContains(t, env.out.String(), "Running post-backup prune.")
snapshots, err := env.v.Repositories.Snapshots.ListRecent(
ctx, listRecentTestLimit)
require.NoError(t, err)
require.Len(t, snapshots, 1)
assert.Equal(t, firstID, snapshots[0].ID.String(),
"the snapshot that holds the files is kept")
for _, key := range stored {
_, err := env.v.Storage.Stat(ctx, key)
require.NoError(t, err, "%s is kept", key)
}
}
// A backup under --skip-errors --prune that both skipped a file it could
// not read and found nothing in a configured path names the empty path
// too when it skips the prune. See
// https://git.eeqj.de/sneak/vaultik/issues/388.
func TestBackupWithEmptySourcePathAndUnreadableFileNamesBoth(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
const snapshotName = "media"
env := newDeletedCountEnv(t, map[string][]byte{
"docs/notes.txt": []byte("notes"),
})
require.NoError(t, os.Mkdir(filepath.Join(env.src, "music"), 0o750))
env.v.Config.Snapshots[snapshotName] = config.SnapshotConfig{
Paths: []string{
filepath.Join(env.src, "docs"),
filepath.Join(env.src, "music"),
},
}
// A mode does not lock out root, who runs the tests, so opening the
// file is made to fail instead.
env.v.Fs = &openFailFs{
path: filepath.Join(env.src, "docs", "notes.txt"),
err: os.ErrPermission,
}
err := env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Prune: true,
SkipErrors: true,
Snapshots: []string{snapshotName},
})
require.ErrorIs(t, err, vaultik.ErrFilesUnreadable)
assert.Contains(t, env.out.String(),
"Skipped the post-backup prune because 1 file(s) could not be read")
assert.Contains(t, env.out.String(),
"Skipped the post-backup prune because nothing was found in ")
assert.Contains(t, env.out.String(), "music of snapshot "+snapshotName+";")
assert.NotContains(t, env.out.String(), "Running post-backup prune.")
}
// A backup under --prune that finds something in each configured path
// prunes the previous snapshot, also when a path is a single file. See
// https://git.eeqj.de/sneak/vaultik/issues/388.
func TestBackupWithNoEmptySourcePathPrunes(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
const (
snapshotName = "album"
file = "pictures/one.jpg" // relative to the source directory
)
tests := []struct {
name string
path string // relative to the source directory
}{
{name: "directory", path: filepath.Dir(file)},
{name: "single file", path: file},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
ctx := context.Background()
env := newDeletedCountEnv(t, map[string][]byte{
file: []byte("picture"),
})
env.setSnapshot(snapshotName, tt.path)
env.backUp(t, snapshotName)
firstID := localSnapshotID(ctx, t, env.v.Repositories, snapshotName)
require.NoError(t, env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Prune: true,
Snapshots: []string{snapshotName},
}))
snapshots, err := env.v.Repositories.Snapshots.ListRecent(
ctx, listRecentTestLimit)
require.NoError(t, err)
require.Len(t, snapshots, 1, "the previous snapshot is pruned")
assert.NotEqual(t, firstID, snapshots[0].ID.String())
})
}
}
internal/vaultik/snapshot_skip_errors_test.go
+1 -209
View File
@@ -3,7 +3,6 @@ package vaultik_test
import (
"context"
"fmt"
"os"
"path/filepath"
"testing"
@@ -46,7 +45,7 @@ func TestSkipErrorsBackupStopsOnIndexErrorRecordingDirectory(t *testing.T) {
"tree": {Paths: []string{srcDir}},
}
store, err := storage.NewFileStorer(t.TempDir())
store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
db, err := database.New(ctx, cfg.IndexPath)
@@ -74,210 +73,3 @@ func TestSkipErrorsBackupStopsOnIndexErrorRecordingDirectory(t *testing.T) {
require.Len(t, snapshots, 1)
assert.Nil(t, snapshots[0].CompletedAt)
}
// A backup under --skip-errors that skips a file it cannot open, or a
// directory it cannot list, keeps the snapshot, counts what it skipped
// as failed and returns an error instead of finishing successfully. See
// https://git.eeqj.de/sneak/vaultik/issues/310.
func TestSkipErrorsBackupKeepsSnapshotAndFailsWhenItSkips(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
tests := []struct {
name string
skipped string // relative to the source directory
}{
{name: "file it cannot open", skipped: "skipdir/file.txt"},
{name: "directory it cannot list", skipped: "skipdir"},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"stored.txt": []byte("stored"),
"skipdir/file.txt": []byte("in skipdir"),
})
env.setSnapshot("work", "")
// A mode does not lock out root, who runs the tests, so
// opening the skipped path is made to fail instead.
env.v.Fs = &openFailFs{
path: filepath.Join(env.src, tt.skipped),
err: os.ErrPermission,
}
err := env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
SkipErrors: true,
Snapshots: []string{"work"},
})
require.ErrorIs(t, err, vaultik.ErrFilesUnreadable)
assert.Contains(t, env.out.String(),
"Files: 2 examined, 1 backed up, 0 unchanged, 1 failed.")
assert.NotContains(t, env.out.String(), "Finished successfully.")
snapshots, err := env.v.Repositories.Snapshots.ListRecent(
context.Background(), listRecentTestLimit)
require.NoError(t, err)
require.Len(t, snapshots, 1)
assert.NotNil(t, snapshots[0].CompletedAt, "the snapshot is kept")
})
}
}
// removeOnLookupFs is the real filesystem, except that path is removed
// just before it is looked up. The walk looks an entry up after listing
// its directory, so path is listed but gone when the walk reaches it.
type removeOnLookupFs struct {
afero.OsFs
path string
}
func (f *removeOnLookupFs) LstatIfPossible(
name string,
) (os.FileInfo, bool, error) {
if name == f.path {
_ = os.Remove(name)
}
return f.OsFs.LstatIfPossible(name)
}
// A file removed before the walk reaches it is counted once, as failed,
// like a file removed before its data is read, and the backup finishes
// successfully, with or without --skip-errors. See
// https://git.eeqj.de/sneak/vaultik/issues/310.
func TestBackupCountsFileRemovedBeforeWalkReachesItAsFailed(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
tests := []struct {
name string
skipErrors bool
}{
{name: "under skip-errors", skipErrors: true},
{name: "without skip-errors", skipErrors: false},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"stays.txt": []byte("stays"),
"removed.txt": []byte("removed"),
})
env.setSnapshot("walk", "")
// The previous snapshot has the file, so a removal the walk
// also counted as deleted would show.
env.backUp(t, "walk")
env.v.Fs = &removeOnLookupFs{
path: filepath.Join(env.src, "removed.txt"),
}
env.out.Reset()
require.NoError(t, env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
SkipErrors: tt.skipErrors,
Snapshots: []string{"walk"},
}))
assert.Contains(t, env.out.String(),
"Files: 2 examined, 0 backed up, 1 unchanged, 1 failed.")
assert.Contains(t, env.out.String(), "Finished successfully.")
})
}
}
// A file an exclude pattern matches is not counted when it is removed
// before the walk reaches it. See
// https://git.eeqj.de/sneak/vaultik/issues/310.
func TestBackupIgnoresExcludedFileRemovedBeforeWalkReachesIt(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"stays.txt": []byte("stays"),
"removed.tmp": []byte("removed"),
})
env.setSnapshot("walk", "", "*.tmp")
env.v.Fs = &removeOnLookupFs{
path: filepath.Join(env.src, "removed.tmp"),
}
require.NoError(t, env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
SkipErrors: true,
Snapshots: []string{"walk"},
}))
assert.Contains(t, env.out.String(), filesLine(1, 1, 0))
assert.Contains(t, env.out.String(), "Finished successfully.")
}
// A backup under --skip-errors --prune that skipped a file it could not
// read does not prune: the previous snapshot, the only one that holds
// the file, is kept, and the output says the prune was skipped. See
// https://git.eeqj.de/sneak/vaultik/issues/382.
func TestSkipErrorsBackupDoesNotPruneWhenItSkips(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"other.txt": []byte("other"),
"skipped.txt": []byte("skipped"),
})
env.setSnapshot("photos", "")
env.backUp(t, "photos")
// An unchanged file is not read again, so the file is changed before
// it becomes unreadable.
skipped := filepath.Join(env.src, "skipped.txt")
require.NoError(t, os.WriteFile(skipped, []byte("changed"), 0o600))
env.v.Fs = &openFailFs{path: skipped, err: os.ErrPermission}
env.out.Reset()
err := env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Prune: true,
SkipErrors: true,
Snapshots: []string{"photos"},
})
require.ErrorIs(t, err, vaultik.ErrFilesUnreadable)
assert.Contains(t, env.out.String(),
"Skipped the post-backup prune because 1 file(s) could not be read")
assert.NotContains(t, env.out.String(), "Running post-backup prune.")
snapshots, err := env.v.Repositories.Snapshots.ListRecent(
context.Background(), listRecentTestLimit)
require.NoError(t, err)
assert.Len(t, snapshots, 2, "the previous snapshot is kept")
}
// A file removed during a backup under --skip-errors --prune is not a
// skipped file, so the backup prunes as usual. See
// https://git.eeqj.de/sneak/vaultik/issues/382.
func TestSkipErrorsBackupPrunesWhenAFileIsRemovedDuringIt(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"other.txt": []byte("other"),
"removed.txt": []byte("removed"),
})
env.setSnapshot("photos", "")
env.backUp(t, "photos")
env.v.Fs = &removeOnLookupFs{path: filepath.Join(env.src, "removed.txt")}
require.NoError(t, env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Prune: true,
SkipErrors: true,
Snapshots: []string{"photos"},
}))
snapshots, err := env.v.Repositories.Snapshots.ListRecent(
context.Background(), listRecentTestLimit)
require.NoError(t, err)
assert.Len(t, snapshots, 1, "the previous snapshot is pruned")
}
internal/vaultik/snapshot_summary_test.go
+1 -117
View File
@@ -13,7 +13,6 @@ import (
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"golang.org/x/sys/unix"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
@@ -85,7 +84,7 @@ func newSummaryEnv(t *testing.T) *summaryEnv {
"split": {Paths: []string{dirOne, dirTwo}},
}
inner, err := storage.NewFileStorer(t.TempDir())
inner, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
store := faultstore.New(inner)
@@ -189,42 +188,6 @@ func (e *summaryEnv) dataLine(total, backedUp int64) string {
e.v.UI.Size(total), e.v.UI.Size(backedUp))
}
// enumeratedLine returns the line printed when the walk of a source path
// ends.
func (e *summaryEnv) enumeratedLine(
files int, total int64, toBackUp int, toBackUpSize int64,
) string {
return fmt.Sprintf(
"Enumerated %d snapshot source files (%s total), %d to back up (%s).",
files, e.v.UI.Size(total), toBackUp, e.v.UI.Size(toBackUpSize))
}
// snapshotPaths returns the paths the snapshot lists, sorted.
func (e *summaryEnv) snapshotPaths(t *testing.T, snapshotID string) []string {
t.Helper()
rows, err := e.db.Conn().QueryContext(context.Background(), `
SELECT f.path FROM snapshot_files sf JOIN files f ON f.id = sf.file_id
WHERE sf.snapshot_id = ? ORDER BY f.path`, snapshotID)
require.NoError(t, err)
defer func() { _ = rows.Close() }()
var paths []string
for rows.Next() {
var path string
require.NoError(t, rows.Scan(&path))
paths = append(paths, path)
}
require.NoError(t, rows.Err())
return paths
}
// A first backup stores copy.bin's chunks while backing up a.bin, so
// copy.bin's chunks are deduplicated within the run. Each file and byte
// is still counted once.
@@ -285,85 +248,6 @@ func TestSnapshotSummaryIncrementalRunWithDeduplicatedChunks(t *testing.T) {
assert.Equal(t, uncompressed, snap.BlobUncompressedSize)
}
// A backup of a tree with directories and a symlink, none of which
// changed since the last backup, backs up nothing, and the snapshot
// still lists every one of them. Both sides of the line that ends the
// walk count the same entries, the files and the symlink, and no
// directory's size. See https://git.eeqj.de/sneak/vaultik/issues/305.
func TestSnapshotSummaryUnchangedRunWithDirectoriesAndSymlink(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newSummaryEnv(t)
const linkTarget = "a.bin"
require.NoError(t, os.Symlink(linkTarget,
filepath.Join(filepath.Dir(env.aPath), "link")))
// A symlink's size is the length of its target.
total := env.totalSize + int64(len(linkTarget))
first := env.backUp(t, "first", false)
assert.Contains(t, first, env.enumeratedLine(4, total, 4, total))
assert.Contains(t, first, filesLine(4, 4, 0))
second := env.backUp(t, "second", false)
assert.Contains(t, second, env.enumeratedLine(4, total, 0, 0))
assert.Contains(t, second, filesLine(4, 0, 4))
assert.Contains(t, second, env.dataLine(total, 0))
assert.Equal(t,
env.snapshotPaths(t, env.snapshot(t, "first").ID.String()),
env.snapshotPaths(t, env.snapshot(t, "second").ID.String()))
}
// A directory whose mtime changed and a symlink whose target changed are
// recorded again by the next backup, which counts only the symlink as
// backed up.
func TestSnapshotSummaryChangedDirectoryAndSymlink(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newSummaryEnv(t)
// The local index keeps paths with symlinks resolved.
dir, err := filepath.EvalSymlinks(filepath.Dir(env.aPath))
require.NoError(t, err)
// The new link gets the old one's mtime, and a target, which need not
// exist, of the old target's length, a symlink's size: only the
// target differs.
linkTime := unix.NsecToTimeval(
time.Date(2029, time.March, 4, 5, 6, 7, 0, time.UTC).UnixNano())
link := filepath.Join(dir, "link")
require.NoError(t, os.Symlink("a.bin", link))
require.NoError(t, unix.Lutimes(link, []unix.Timeval{linkTime, linkTime}))
env.backUp(t, "first", false)
require.NoError(t, os.Remove(link))
require.NoError(t, os.Symlink("b.bin", link))
require.NoError(t, unix.Lutimes(link, []unix.Timeval{linkTime, linkTime}))
mtime := time.Date(2030, time.January, 2, 3, 4, 5, 0, time.UTC)
require.NoError(t, os.Chtimes(dir, mtime, mtime))
assert.Contains(t, env.backUp(t, "second", false), filesLine(4, 1, 3))
ctx := context.Background()
dirRow, err := env.repos.Files.GetByPath(ctx, dir)
require.NoError(t, err)
require.NotNil(t, dirRow)
assert.Equal(t, mtime.Unix(), dirRow.MTime.Unix())
linkRow, err := env.repos.Files.GetByPath(ctx, link)
require.NoError(t, err)
require.NotNil(t, linkRow)
assert.Equal(t, "b.bin", linkRow.LinkTarget.String())
}
// Under --cron the progress reporter is off; the upload figures must
// still reach the summary and the snapshots row. The snapshot has two
// paths, each backed up by its own scan.
internal/vaultik/two_path_snapshot_test.go
+1 -1
View File
@@ -28,7 +28,7 @@ func TestBackupWithoutCronOfTwoPathSnapshotRestoresBothPaths(t *testing.T) {
tempDir := t.TempDir()
firstDir := filepath.Join(tempDir, "first")
secondDir := filepath.Join(tempDir, "second")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/uncompressed_size_test.go
+1 -1
View File
@@ -36,7 +36,7 @@ func TestUncompressedSizeOfChangedFileStaysFixed(t *testing.T) {
appendRandomBytes(t, fs, files, changedPath, appendedFileSize)
store, err := storage.NewFileStorer(t.TempDir())
store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
internal/vaultik/verify.go
+2 -2
View File
@@ -680,7 +680,7 @@ func (v *Vaultik) verifyManifestAgainstDatabase(
func (v *Vaultik) verifyBlobExistenceFromDB(
blobs []snapshot.BlobInfo, result *VerifyResult,
) error {
log.Info("Verifying blob existence in storage", "blob_count", len(blobs))
log.Info("Verifying blob existence in S3", "blob_count", len(blobs))
for i, blob := range blobs {
// The hash is read from the snapshot database, which is not
@@ -700,7 +700,7 @@ func (v *Vaultik) verifyBlobExistenceFromDB(
result.Missing++
result.MissingSize += blob.CompressedSize
case err != nil:
return fmt.Errorf("could not check blob %s in storage: %w",
return fmt.Errorf("checking blob %s in storage: %w",
blob.Hash, err)
case stat.Size != blob.CompressedSize:
log.Warn("Blob has the wrong size in storage",
internal/vaultik/verify_quiet_test.go
+1 -1
View File
@@ -28,7 +28,7 @@ func TestVerify_QuietSuppressesReport(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)