sneak/vaultik
1
0
Fork 0
Code Issues 3 Pull Requests 1 Actions 245 Packages Projects Releases Wiki Activity

Compare commits

base: sneak/vaultik:3037bf9059514529b73a7b28db7e69f2a811c1e8
Branches Tags
sneak/vaultik:main 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:next
Branches Tags
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
21 Commits
3037bf9059 ... next
Author SHA1 Message Date
clawbot 6a57750a7b Keep unreferenced blobs newer than prune_grace_period (closes #387)
check / check (push) Waiting to run
Details
release / release (push) Waiting to run
Details 
A backup uploads its blobs before the manifest that lists them, and the
process lock covers one user on one machine, so a prune from another host
or user sharing the destination deleted a running backup's blobs.

Prune now deletes an unreferenced blob only once its listed time is older
than the new config key prune_grace_period (default 24h; a negative value
is refused). A newer blob, or one listed with no time, is kept and counted
(blobs_too_new). The rclone backend takes each object's time from the
listing (use_server_modtime).

Decision: a blob a backup reuses from an earlier run that stopped before
its manifest keeps its old time and is not protected; the docs and config
comments say so.

Model: opus-5-5
 2026-10-14 13:06:35 +02:00
clawbot 2590f49583 Record the defect-hunt fixes in TODO.md Completed Steps (closes #334)
check / check (push) Waiting to run
Details
release / release (push) Waiting to run
Details 
Adds a Completed Steps entry, newest first, for every issue from the
defect hunt (#288) that a merged
fix closed and that had none: the hunt's own issues, those filed while
fixing them, and the owner's ruling on
#239. Each entry says in one or
two sentences what was wrong and what changed; the detail is in each
fix's commit. Next Step now says the hunt's fixes have landed.

Judgement call: #332, closed as
covered by the fix for #296, is
named in that entry rather than given its own.
Judgement call: #351, a Docker
build fix filed while gating these fixes, gets an entry.

Model: opus-5-5
 2026-10-14 09:18:09 +02:00
clawbot 5b8d84e38a Do not prune after a backup that skipped unreadable files (closes #382)
check / check (push) Waiting to run
Details 
snapshot create --skip-errors --prune pruned even when files were
skipped, so by default it deleted the previous snapshot of that name,
the only one still holding a file that had become unreadable, along
with blobs only that snapshot referenced.

The prune is now skipped exactly when the run exits non-zero for
entries --skip-errors could not read or list: older snapshots are
kept, a warning says why, and the run still exits non-zero. A file
removed during the run does not count, so such a run still prunes.
The README's --prune text and the flag's help say so.

Model: opus-5-5
 2026-10-14 07:44:50 +02:00
clawbot 7a950ea2aa Exit non-zero when snapshot create --skip-errors skips anything it cannot read (closes #310)
check / check (push) Waiting to run
Details 
A backup under --skip-errors printed its skip errors, then "Finished
successfully.", and exited 0, so a cron wrapper could not tell it from
a complete backup.

Each skipped entry, including a directory the walk could not list, is
now counted as examined and failed. If --skip-errors skipped anything
it could not read or list, the run still keeps its snapshots and
prunes as before, then fails with "Backup completed, but N file(s)
could not be read". A file removed during the run, even before the
walk reaches it, counts once as failed and leaves the exit status
alone; without the flag it no longer stops the backup. Excluded
entries are never counted.

Model: opus-5-5
 2026-10-14 07:13:48 +02:00
clawbot 16b03dfda5 Keep the local index when remote nuke cannot list or find the destination (closes #292)
check / check (push) Waiting to run
Details 
`remote nuke` took a destination store it could not list, or one
without `vaultik-destination.txt` while the local index held
snapshots, as a warning: it then cleared the local snapshot records,
and for an unplugged volume's empty mount point reported the store
empty and exited zero. Nuke now fails on either before it removes
anything, without its advice to run it again, which would fail the
same way. The bulk remove it runs fails on either too; only a
local-only remove still goes on with a warning. Nuke also deletes each
snapshot's remote metadata before its local record, so a failed delete
keeps the snapshot in the local index rather than leaving it on the
store as a remote-only snapshot.

Model: opus-5-5
 2026-10-14 06:47:38 +02:00
clawbot 2125a9d451 Stop counting directories and unchanged symlinks as files to back up (closes #305)
check / check (push) Waiting to run
Details 
Every backup queued every directory and symlink for the second phase.
The line ending the walk counted directories, and their stat sizes, as
files to back up while its enumerated count left them out, and a
symlink was counted as backed up on every run, its target length as
data.

The walk now sets directories aside: they are recorded before the files
are backed up and never counted as files or data, and the walk's
progress estimate leaves out the directories the local index knows. A
symlink is checked against its record like a regular file, its target
included, so an unchanged one counts as unchanged.

Judgement call: every directory is still written to the local index on
every backup, as before; no report shows it.

Model: opus-5-5
 2026-10-14 06:46:45 +02:00
clawbot a0de8bfdb7 Refuse a backup destination an unplugged volume left empty (closes #239)
check / check (push) Waiting to run
Details 
Every backup writes vaultik-destination.txt at the destination root.
While the local index holds snapshots stored there, a destination
without it is not present: snapshot create refuses before writing,
prune and snapshot purge fail, and snapshot list and snapshot remove
act as for a destination that cannot be listed. snapshot create and
snapshot remove check it first. remote nuke deletes the marker last.
The file:// backend never creates its destination directory, which
protects a directory on a removable volume, not a mount point.

Tests back up into directories that exist; fixtures for a written
destination carry the marker.

Judgement call: the marker is rewritten on every backup.
Deviation: for the complexity limit, two blocks moved, unchanged, into
snapshotNamesToCreate and confirmRemoveSnapshot.

Model: opus-5-5
 2026-10-14 05:46:42 +02:00
clawbot 291c39174f Warn about restored ownership only when an entry's owner or group differs (closes #316)
check / check (push) Waiting to run
Details 
A restore by a normal user always warned that file ownership was not
preserved, even when every entry came out with its recorded owner and
group. The owner and group each restored entry has on disk are now
compared with the recorded ones, and the warning is printed once if any
differ. The comparison is made on disk because on macOS, and in a setgid
directory on Linux, a new entry takes the group of its directory, not
the user's.

Judgement call: an entry that is not on disk after the restore is not compared.
Unverified: not run on a Mac; the directory-group test runs only as root.

Model: opus-5-5
 2026-10-14 05:39:27 +02:00
clawbot 65036bba1b 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 04:29:36 +02:00
clawbot 54ad279dd6 Count a file as deleted only if the previous snapshot of its name had it (closes #304)
check / check (push) Waiting to run
Details 
A backup counted as deleted every file in the local index under the
source path that the walk did not find: files the snapshot excludes
but another snapshot backs up, and files removed long ago, which every
later backup, and the first backup of another name over the same
path, reported as deleted again.

The backup now counts only files that the latest completed snapshot of
the same name lists, the walk did not find, and are gone from disk,
including a file whose directory became a regular file. Excluded files
and files the walk could not reach under --skip-errors are not
counted.

Only the backup's output changes; the snapshots row stores no deleted
figure.

Model: opus-5-5
 2026-10-14 04:24:30 +02:00
clawbot d156a02c49 Name each prefix once in restore, verify and purge errors (closes #327)
check / check (push) Waiting to run
Details 
A missing blob during restore, a failed shallow verify and an invalid
purge duration each printed their prefix twice. FetchBlob now returns
the storage error as is, since restore and deep verify name the blob
themselves; purge returns the duration parser's error unchanged; and a
failed shallow verify wraps "problems found in storage" instead of
"verification failed", which the command already prints. Deep verify
words a storage error other than not found as a blob it could not
check, and its log line no longer says S3.

Already fixed for #314: the
deep verify size message naming S3 and other errors called missing;
tests now check both.
Not tested: the log line.

Model: opus-5-5
 2026-10-14 04:04:14 +02:00
clawbot aeac897805 Refuse credentials in a storage URL's endpoint or rclone remote name (closes #322)
check / check (push) Waiting to run
Details 
storage_url refused only the outer URL's userinfo and unknown query
parameters. Userinfo inside the s3 endpoint= value, and rclone's
remote,param=value parameters in the remote name, were accepted and
then printed by info, remote info and snapshot create. Both are now
refused without echoing the value: a host name never contains "@", and
an rclone remote name never contains a comma. An s3 or rclone query
that cannot be decoded (a ";" or a bad "%" escape) is refused too,
because decoding drops that part before it can be checked. The comma
is checked before url.Parse, whose error for such a name prints part of
it. The rclone remote name case has its own error pointing at rclone
config.

Model: opus-5-5
 2026-10-14 03:26:02 +02:00
clawbot d8f4f62f41 Run $EDITOR through the shell in config edit (closes #315)
check / check (push) Waiting to run
Details 
config edit used the whole of $EDITOR as the program name, so a value
with arguments such as "code --wait" or "emacsclient -t" failed with
"executable file not found". It now runs $EDITOR the way git does:
sh -c '<editor> "$@"' with the config path as a separate argument, so
the editor's own arguments and quoting work and a path with spaces
reaches it whole. A test runs config edit with an $EDITOR carrying an
argument on a config path that contains a space.

Model: opus-5-5
 2026-10-14 03:06:57 +02:00
clawbot 9fd88a34c7 Fail snapshot remove when a destination-only snapshot's metadata cannot be deleted (closes #340)
check / check (push) Waiting to run
Details 
When a snapshot was only on the destination store and deleting its
metadata there failed, snapshot remove warned and exited 0 having
removed nothing. That failure is now an error. A snapshot in the local
index keeps its behaviour: it is removed from the local index and the
failed delete on the destination store is a warning.

The README and the help text said the `vaultik prune` follow-up is
printed on every success; they now say it is printed only when metadata
was removed from the destination store, and never under --json. The
comments on RemoveSnapshot and removeSnapshotRemote describe both
cases; removeSnapshotRemote's also says it returns true only when the
delete finished without an error and removed at least one object.

Model: opus-5-5
 2026-10-14 02:20:01 +02:00
clawbot 5db2e920e5 Label the index cleanup totals as totals (closes #306)
check / check (push) Waiting to run
Details 
The summary printed by the local index cleanup before each backup gave,
in brackets after each removed count, the number of snapshots, files,
chunks or blobs left in the local index, worded "(N remain)", which
read as incomplete or orphaned rows left over: removing the only
incomplete snapshot printed "1 removed (1 remain)". Each line now
labels that figure as the total of its kind left in the local index.

Model: opus-5-5
 2026-10-14 02:03:51 +02:00
clawbot 66ea7f5f45 Free a cached blob once no file still to restore needs it (closes #324)
check / check (push) Waiting to run
Details 
A restore of selected paths, or one where files failed under
--skip-errors, kept the blobs those files share in the temporary cache
until it ended: the sweeper freed a blob only once every file in the
snapshot database that uses it had been restored, and files outside the
selection or that failed never are.

The sweeper now asks the restore plan, through pendingFileUsesBlob,
whether any pending file still uses a cached blob. The plan holds only
this run's files and drops each one once it is restored or has failed.

The new test backs up 16 KiB files so it stays quick; the locality
backup helper takes the file size for that.

Model: opus-5-5
 2026-10-14 01:47:48 +02:00
clawbot dd3667c8e9 Keep the whole startup error when it contains "): " (closes #320)
check / check (push) Waiting to run
Details 
A startup error was cut at its last "): " to drop the annotations fx
adds, so the blob_size_limit message, which itself contains
"(... size spread): ", lost everything but "need at least N bytes".
cleanStartupError now uses dig.RootCause, from the library fx is built
on, which removes exactly those annotations and returns the error
underneath unchanged.

The test starts a real fx app on a config whose blob_size_limit is below
the minimum. The old cases fed it plain strings that only looked like fx
output; such an error is now rightly left whole, so they are replaced.

go.uber.org/dig, already required through fx, becomes a direct
requirement in go.mod.

Model: opus-5-5
 2026-10-14 01:34:38 +02:00
clawbot 30285c7a8c Silence prune and snapshot removal status under --cron and --quiet (closes #294)
check / check (push) Waiting to run
Details 
PruneBlobs, CleanupLocalSnapshots, RemoveSnapshot, RemoveAllSnapshots
and snapshot purge wrote their status lines straight to stdout, so
`snapshot create --cron --prune` printed on every successful run and
--quiet did not silence `prune`, `snapshot purge`, `snapshot remove` or
`remote nuke`. Those lines now go through internal/ui, which drops them
under --cron and --quiet; warnings, errors and --json documents still
print.

The confirmation prompts still write straight to stdout, as the
`database delete` prompt does, together with what they ask to delete:
the snapshot list before the purge prompt, and the blob count and size
before the prune prompt. With --force those lines are status lines.

The two purge test fixtures gained the UI writer production always sets.

Model: opus-5-5
 2026-10-14 01:10:43 +02:00
clawbot 8d5e6f3399 Read the rclone config file named by RCLONE_CONFIG (closes #321)
check / check (push) Waiting to run
Details 
An rclone destination whose remote is defined only in the file
RCLONE_CONFIG names was reported as not found: rclone reads that
variable only as the value of its --config flag, which vaultik does not
have, so vaultik always used rclone's default config file.
NewRcloneStorer now sets rclone's config path from RCLONE_CONFIG when
the variable is set, as that flag would, including an empty value,
which rclone takes to mean no config file.

Model: opus-5-5
 2026-10-14 00:39:32 +02:00
clawbot abad8161bc Make **/ in an exclude pattern match zero directories (closes #338)
check / check (push) Waiting to run
Details 
The glob library needs a slash on both sides of **, so the anchored
pattern /**/x missed an x directly under the snapshot path, and
a/**/*.log missed a/x.log. As in gitignore, a leading **/ now makes any
pattern, anchored or not, match at every depth, and a pattern holding
/**/ is also compiled with each /**/ made a single slash. The library's
{a,b} alternatives cannot express this: with ** inside them in
mid-pattern they miss paths they should match.

Judgement call: the test for a/**/b uses a/**/*.log, because with a
plain name after the ** the glob library already matched a/b.

Model: opus-5-5
 2026-10-14 00:13:27 +02:00
clawbot 05a2c86d65 Make the size defaults and the chunk_size minimum 1000-based (closes #313)
check / check (push) Waiting to run
Details 
The chunk_size and blob_size_limit defaults and the chunk_size minimum
were 1024-based, while the size parser reads 10MB as 10,000,000 bytes and
the docs and info use 1000-based units. So chunk_size: 1MB was rejected,
writing out a documented default changed it, and info showed an 11 GB
blob limit. They are now 1000-based like the parser. The examples below
the 1MB minimum in config.example.yml and the config init template are
replaced, and both now state the minimum.

Judgement call: s3.part_size keeps its 5MiB to 5GiB bounds, which are
S3's own limits, and MiB and GiB stay listed as accepted spellings.

Model: opus-5-5
 2026-10-13 23:56:22 +02:00
85 changed files with 4237 additions and 646 deletions
Expand all files Collapse all files
ARCHITECTURE.md
+19 -5
View File
@@ -279,8 +279,8 @@ Key methods:
- `Scan(ctx, path, snapshotID)` → Main scan operation
Scan phases:
1. **Phase 0**: Detect deleted files from previous snapshots
2. **Phase 1**: Walk directory, identify files needing processing
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
3. **Phase 2**: Process files (chunk → pack → upload)
#### SnapshotManager
@@ -311,6 +311,8 @@ Repository interfaces:
```
CreateSnapshot(opts)
│
├─► markDestination() // Refuse a destination without the marker, then write it
│
├─► PruneDatabase() // Critical: avoid dedup errors
│
@@ -320,13 +322,13 @@ 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()
@@ -357,7 +359,7 @@ CreateSnapshot(opts)
## Deduplication Strategy
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
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
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.
@@ -367,6 +369,8 @@ CreateSnapshot(opts)
```
bucket/
├── vaultik-destination.txt # Marker written by every backup
│
├── blobs/
│ └── {hash[0:2]}/
│ └── {hash[2:4]}/
@@ -378,6 +382,16 @@ 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
+129 -32
View File
@@ -24,6 +24,10 @@ 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
@@ -92,6 +96,14 @@ 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
@@ -178,7 +190,7 @@ 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.
* `--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.
### locking
@@ -188,7 +200,22 @@ 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 or the destination store.
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.
Read-only commands — `info`, `snapshot list`, `snapshot verify`, and
`remote info` — do not take the lock and are never blocked, so they run
@@ -292,12 +319,21 @@ 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 from remote storage. By default keeps only the latest
snapshot per name; use `--keep-newer-than` for a rolling window.
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.
* `--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))
**`snapshot list`**: Show every snapshot known to this host — the union
of the local index and the backup destination store — with timestamps
@@ -323,18 +359,27 @@ read from the manifest.
Snapshots in the local index with no counterpart on the destination
store are reported below the table as drift, with the `vaultik prune`
invocation that reconciles them.
invocation that reconciles them. If the local index is bound to a
different destination than the configured one (after a change to
`storage_url`, or `s3.endpoint`, `s3.bucket` or `s3.prefix`), the
command says so instead and gives the same two ways out that `prune`
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.
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.
* `--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
on the destination store, or `null` if the destination could not be
listed). Warnings about an unlistable destination, unreadable
manifests, and a truncated listing all go to stderr through the
logger, so stdout stays a single parseable document.
listed). Warnings about an unlistable destination, a local index
bound to a different destination (with both destinations and the
same two ways out), unreadable manifests, and a truncated listing all
go to stderr through the logger, so stdout stays a single parseable
document.
**`snapshot verify`**: Verify snapshot integrity.
* Default (shallow): checks that every blob the manifest lists is present in
@@ -360,16 +405,21 @@ snapshot from the local index and strips the snapshot's metadata from
the backup destination store. Blobs are NOT touched — deleting blobs
requires reading every remaining remote manifest (the destination store
may hold snapshots this host doesn't know about), which is what
`vaultik prune` does. On success the command prints the exact `vaultik
prune` invocation to run as a follow-up. An ID that names no 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
`vaultik prune` does. The command prints the `vaultik prune` invocation
to run as a follow-up only when it removed the snapshot's metadata from
the destination store, and never under `--json`. An ID that names no
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 the destination 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). To wipe everything
on the destination in one go, use `vaultik remote nuke --force`.
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`.
* `--local-only`: Skip remote cleanup; only touch the local index
* `--dry-run`: Show what would be deleted without deleting
* `--force`: Skip confirmation prompt
@@ -397,15 +447,28 @@ 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. 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.
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.
* `--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.
@@ -425,11 +488,17 @@ 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, 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.
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.
* `--force`: Required to confirm destruction.
**`database delete`**: Delete the local SQLite state database file
@@ -454,7 +523,12 @@ 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 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.
**Rclone** (`rclone://remote/path`): Uses rclone's 70+ supported cloud
providers. Requires rclone to be configured separately (`rclone config`).
@@ -469,6 +543,14 @@ 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.
@@ -485,6 +567,7 @@ 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/
@@ -493,6 +576,16 @@ 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
@@ -544,7 +637,8 @@ 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
4. Delete any blob not in the referenced set that is older than
`prune_grace_period`
### chunking and deduplication
@@ -589,6 +683,7 @@ 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 |
@@ -712,8 +807,10 @@ the `NO_COLOR` environment variable is unset (https://no-color.org/).
reports and tables (`version`, `info`, `remote info`, `snapshot
verify`, `snapshot list`) but never the machine-consumed `config get`
value or the `--json` documents, which a script depends on. The
`database delete` confirmation prompt is also written this way and
always shown: it is an interactive exchange the operator must see.
confirmation prompts of `database delete`, `prune`, `snapshot purge`
and `snapshot remove`, each with what it asks to delete, are also
written this way and always shown: they are an interactive exchange
the operator must see.
`internal/ui` writes to stdout; it is the output the user asked for. The
exceptions are the startup banner and the error a failed command ends
TODO.md
+220 -4
View File
@@ -15,13 +15,229 @@ 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) 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.
[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`.
# Completed Steps
- 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
+14 -1
View File
@@ -302,7 +302,8 @@ storage_url: "rclone://myremote/path/to/backups"
# Average chunk size for content-defined chunking
# Smaller chunks = better deduplication but more metadata
# Supports: 10MB, 5M, 1GB, 500KB, 64MiB, etc.
# Minimum 1MB
# Supports: 10MB, 5M, 1GB, 64MiB, etc.
# Default: 10MB
#chunk_size: 10MB
@@ -327,6 +328,18 @@ 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
+2 -1
View File
@@ -228,7 +228,8 @@ 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 and local database
- Delete from S3, once older than `prune_grace_period`, and from the local
database
### 6. Incomplete Snapshot Cleanup
docs/REPOSTRUCTURE.md
+7 -2
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:
Vaultik stores all backup data in an S3-compatible object store. The repository consists of two main components, plus a marker file:
1. **Blobs** - The actual backup data (content-addressed, encrypted)
2. **Metadata** - Snapshot information and manifests (partially encrypted)
@@ -12,6 +12,7 @@ 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]>/
@@ -24,6 +25,10 @@ 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
@@ -161,7 +166,7 @@ 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. 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
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
## Restoration Requirements
go.mod
+1 -1
View File
@@ -22,6 +22,7 @@ require (
github.com/spf13/cobra v1.10.1
github.com/spf13/pflag v1.0.10
github.com/stretchr/testify v1.11.1
go.uber.org/dig v1.19.0
go.uber.org/fx v1.24.0
golang.org/x/sync v0.18.0
golang.org/x/sys v0.38.0
@@ -256,7 +257,6 @@ require (
go.opentelemetry.io/otel/metric v1.38.0 // indirect
go.opentelemetry.io/otel/trace v1.38.0 // indirect
go.shabbyrobe.org/gocovmerge v0.0.0-20230507111327-fa4f82cfbf4d // indirect
go.uber.org/dig v1.19.0 // indirect
go.uber.org/multierr v1.11.0 // indirect
go.uber.org/zap v1.27.0 // indirect
go.yaml.in/yaml/v2 v2.4.3 // indirect
internal/cli/app.go
+6 -10
View File
@@ -8,12 +8,12 @@ import (
"errors"
"fmt"
"path/filepath"
"strings"
"sync"
"time"
"github.com/adrg/xdg"
"github.com/spf13/cobra"
"go.uber.org/dig"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
@@ -146,16 +146,12 @@ func (e *startupError) Error() string {
// could not build arguments for function "Y" (file:line): failed to build U:
// received non-nil error from function "Z" (file:line): <real error>
//
// Users care about the real error, not the DI plumbing. We strip everything
// up through the last "): " (which is always the close-paren of an fx
// function-location annotation followed by the wrapped error).
// Users care about the real error, not the DI plumbing. dig.RootCause,
// from the library fx is built on, unwraps those layers and returns the
// real error whole. Cutting the text at "): " instead would also cut a
// real error that contains it, such as the blob_size_limit one.
func cleanStartupError(err error) error {
msg := err.Error()
if idx := strings.LastIndex(msg, "): "); idx >= 0 {
msg = msg[idx+3:]
}
return &startupError{msg: msg}
return &startupError{msg: dig.RootCause(err).Error()}
}
// RunApp starts the fx application, blocks until it is asked to stop, and
internal/cli/app_test.go
+47 -40
View File
@@ -2,58 +2,65 @@ package cli //nolint:testpackage // needs access to unexported cleanStartupError
import (
"errors"
"os"
"path/filepath"
"testing"
"go.uber.org/fx"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/pidlock"
)
// TestCleanStartupError starts a real fx app whose config has a
// blob_size_limit below the minimum. fx puts annotations naming the
// functions it was building in front of the config error; only those
// may be removed, although the config error itself contains "): ".
func TestCleanStartupError(t *testing.T) {
t.Parallel()
tests := []struct {
name string
in string
want string
}{
{
name: "real fx error chain",
in: `could not build arguments for function ` +
`"sneak.berlin/go/vaultik/internal/cli".newSnapshotCreateCommand.func1.1 ` +
`(/Users/user/dev/vaultik/internal/cli/snapshot.go:71): ` +
`failed to build *vaultik.Vaultik: ` +
`could not build arguments for function ` +
`"sneak.berlin/go/vaultik/internal/vaultik".New ` +
`(/Users/user/dev/vaultik/internal/vaultik/vaultik.go:59): ` +
`failed to build storage.Storer: ` +
`received non-nil error from function ` +
`"sneak.berlin/go/vaultik/internal/storage".NewStorer ` +
`(/Users/user/dev/vaultik/internal/storage/module.go:23): ` +
`creating base path: mkdir /Volumes/BACKUPS: permission denied`,
want: `creating base path: mkdir /Volumes/BACKUPS: permission denied`,
},
{
name: "no fx wrapping",
in: "plain error",
want: "plain error",
},
{
name: "single fx wrapping",
in: `received non-nil error from function "foo" (file.go:1): underlying problem`,
want: "underlying problem",
},
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte("snapshots:\n"+
" test:\n"+
" paths: [/tmp/vaultik-test-source]\n"+
"storage_url: file:///tmp/vaultik-test-storage\n"+
"chunk_size: 10MB\n"+
"blob_size_limit: 30MB\n"), 0o600)
if err != nil {
t.Fatalf("write config: %v", err)
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
app := fx.New(
fx.NopLogger,
fx.Supply(config.Path(path)),
config.Module,
fx.Invoke(func(*config.Config) {}),
)
//nolint:err113 // test constructs errors from table input
got := cleanStartupError(errors.New(tt.in)).Error()
if got != tt.want {
t.Errorf("got %q, want %q", got, tt.want)
}
})
err = app.Start(t.Context())
if err == nil {
t.Fatal("app started; want a blob_size_limit error")
}
want := "failed to load config: invalid config: blob_size_limit must " +
"be at least the largest chunk the chunker can emit (chunk_size " +
"times the FastCDC size spread): need at least 40000000 bytes"
got := cleanStartupError(err).Error()
if got != want {
t.Errorf("got %q, want %q", got, want)
}
}
// TestCleanStartupErrorNotFromFx checks that an error fx did not wrap is
// shown unchanged.
func TestCleanStartupErrorNotFromFx(t *testing.T) {
t.Parallel()
//nolint:err113 // a one-off error standing in for a startup failure
got := cleanStartupError(errors.New("plain error")).Error()
if got != "plain error" {
t.Errorf("got %q, want %q", got, "plain error")
}
}
internal/cli/config.go
+19 -2
View File
@@ -224,7 +224,7 @@ storage_url: ""
# Average chunk size for content-defined chunking (FastCDC).
# Smaller = better deduplication but more metadata overhead.
# Accepts: 1MB, 10M, 64KB, etc.
# Minimum 1MB. Accepts: 1MB, 10M, 64MiB, etc.
# Default: 10MB
# chunk_size: 10MB
@@ -239,6 +239,16 @@ 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
@@ -333,8 +343,15 @@ func newConfigEditCommand() *cobra.Command {
editor = "vi"
}
// Run $EDITOR through the shell, as git does, so a value
// with arguments such as "code --wait" works. The path
// goes in as an argument ("$@"), not into the command
// text, so a path with spaces or quotes arrives whole.
// sh -c takes the word after the command as $0, which
// is why editor appears twice.
//nolint:gosec // G204: launching the operator's own $EDITOR is the point
ed := exec.CommandContext(cmd.Context(), editor, path)
ed := exec.CommandContext(cmd.Context(),
"sh", "-c", editor+` "$@"`, editor, path)
ed.Stdin = os.Stdin
ed.Stdout = os.Stdout
ed.Stderr = os.Stderr
internal/cli/config_test.go
+24
View File
@@ -647,6 +647,30 @@ func TestWriteConfigSetTightensMode(t *testing.T) {
}
}
// TestConfigEditEditorWithArgument checks that an $EDITOR carrying an
// argument works and that a config path with a space reaches it whole.
// The "editor" is cp with the replacement file as its argument, so the
// config ends up with the replacement's content only if both arrived.
func TestConfigEditEditorWithArgument(t *testing.T) {
dir := t.TempDir()
path := seedFile(t, dir, "my config.yml", "compression_level: 3\n")
edited := seedFile(t, dir, "edited.yml", "compression_level: 9\n")
setRootFlags(t, RootFlags{ConfigPath: path})
t.Setenv("EDITOR", "cp '"+edited+"'")
mustExecute(t, newConfigEditCommand())
data, err := os.ReadFile(path) //nolint:gosec // G304: test-controlled path
if err != nil {
t.Fatalf("reading config back: %v", err)
}
if string(data) != "compression_level: 9\n" {
t.Errorf("config after edit = %q, want the edited content", data)
}
}
func splitPath(s string) []string {
return strings.Split(s, ".")
}
internal/cli/entry_prune_json_test.go
+7 -1
View File
@@ -101,7 +101,8 @@ 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. Returns the config path.
// counterpart on the destination store, and gives the destination the
// marker a backup writes. Returns the config path.
func writeHermeticPruneConfig(t *testing.T, seedStale bool) string {
t.Helper()
@@ -131,6 +132,11 @@ 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
+127
View File
@@ -0,0 +1,127 @@
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
import (
"os"
"path/filepath"
"strings"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// flagCron is used to build the argument vectors below.
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.
func plantUnreferencedBlob(t *testing.T, storeDir string) string {
t.Helper()
hash := strings.Repeat("b", 64)
path := filepath.Join(storeDir, "blobs", hash[:2], hash[2:4], hash)
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
}
// TestEntrySnapshotCreatePruneIsSilent checks that a successful
// `snapshot create --prune` under --cron or --quiet prints nothing on
// stdout or stderr, whether or not the prune finds a blob to delete.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotCreatePruneIsSilent(t *testing.T) {
for _, testCase := range []struct {
name string
args []string
plantBlob bool
}{
{
name: "cron, no blob to delete",
args: []string{cmdSnapshot, cmdCreate, flagCron, flagPrune},
},
{
name: "cron, blob to delete",
args: []string{cmdSnapshot, cmdCreate, flagCron, flagPrune},
plantBlob: true,
},
{
name: "cron with keep-newer-than",
args: []string{
cmdSnapshot, cmdCreate, flagCron, flagPrune,
flagKeepNewerThan, "4w",
},
plantBlob: true,
},
{
name: "quiet",
args: []string{flagQuiet, cmdSnapshot, cmdCreate, flagPrune},
plantBlob: true,
},
} {
t.Run(testCase.name, func(t *testing.T) {
configPath, storeDir := writeBackupConfig(t)
var blob string
if testCase.plantBlob {
blob = plantUnreferencedBlob(t, storeDir)
}
code, stdout, stderr := runEntry(t,
append([]string{flagConfig, configPath}, testCase.args...)...)
assert.Equal(t, 0, code)
assert.Empty(t, stdout)
assert.Empty(t, stderr)
if testCase.plantBlob {
assert.NoFileExists(t, blob, "the prune must delete the blob")
}
})
}
}
// TestEntryPruneQuietIsSilent checks that a successful `prune --force`
// under --quiet prints nothing on stdout or stderr, both when there is
// nothing to remove and when it removes a stale local snapshot record
// and an unreferenced blob.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntryPruneQuietIsSilent(t *testing.T) {
for _, testCase := range []struct {
name string
staleRecordAndBlob bool
}{
{name: "nothing to remove"},
{name: "stale record and blob to remove", staleRecordAndBlob: true},
} {
t.Run(testCase.name, func(t *testing.T) {
configPath := writeHermeticPruneConfig(t, testCase.staleRecordAndBlob)
var blob string
if testCase.staleRecordAndBlob {
// writeHermeticPruneConfig puts the store beside the config.
blob = plantUnreferencedBlob(t,
filepath.Join(filepath.Dir(configPath), "store"))
}
code, stdout, stderr := runEntry(t,
flagConfig, configPath, flagQuiet, cmdPrune, flagForce)
assert.Equal(t, 0, code)
assert.Empty(t, stdout)
assert.Empty(t, stderr)
if testCase.staleRecordAndBlob {
assert.NoFileExists(t, blob, "the prune must delete the blob")
}
})
}
}
internal/cli/entry_snapshot_create_skip_errors_test.go
+30
View File
@@ -0,0 +1,30 @@
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
+8 -1
View File
@@ -41,6 +41,11 @@ 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))
@@ -59,10 +64,12 @@ func TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails(t *testing.T)
require.NoError(t, err)
require.NoError(t, db.Close())
code, _, _ := runEntry(t, flagConfig, configPath,
code, _, stderr := 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
+6 -1
View File
@@ -20,7 +20,12 @@ 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.
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.
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
+18 -7
View File
@@ -115,6 +115,13 @@ on Linux), then /etc/vaultik/config.yml.`,
return
}
if errors.Is(err, vaultik.ErrFilesUnreadable) {
log.Error("Backup completed with unreadable files", "error", err)
ReportErrorf("Backup completed, but %v", err)
return
}
log.Error("Snapshot creation failed", "error", err)
ReportErrorf("Snapshot creation failed: %v", err)
})
@@ -125,7 +132,8 @@ 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")
"orphaned blobs older than prune_grace_period (not after a "+
"backup that skipped unreadable files)")
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) "+
@@ -270,8 +278,9 @@ By default, this removes the snapshot from the local index database and
strips the snapshot's metadata from the backup destination store. Blobs
are NOT touched: deleting them requires reading every remaining remote
manifest (the destination store may hold snapshots this host doesn't
know about), which is what 'vaultik prune' does. On success the command
prints the exact 'vaultik prune' invocation to run as a follow-up.
know about), which is what 'vaultik prune' does. The command prints the
'vaultik prune' invocation to run as a follow-up only when it removed the
snapshot's metadata from the destination store, and never under --json.
An ID that names no snapshot in the local index or on the destination
store is an error.
@@ -280,10 +289,12 @@ Use --local-only to skip the remote half (e.g. when you want to forget a
snapshot locally without touching the destination store); the snapshot
must then be in the local index.
If the remote is unreachable, the local-database removal still completes
and a warning is emitted; run 'vaultik snapshot remove <snapshot-id>' again
once the destination store is reachable to remove the snapshot's metadata
from it ('vaultik prune' does not).
If removing the snapshot's metadata from the destination store fails (for
example because the remote is unreachable), the local-database removal
still completes and a warning is emitted; run 'vaultik snapshot remove
<snapshot-id>' again once the destination 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 the entire destination store and start over, use 'vaultik remote
nuke --force' — it is the single supported entry point for that.`,
internal/config/config.go
+23 -4
View File
@@ -11,6 +11,7 @@ import (
"path/filepath"
"sort"
"strings"
"time"
"filippo.io/age"
"git.eeqj.de/sneak/smartconfig"
@@ -30,13 +31,16 @@ const appName = "vaultik"
//nolint:gosec // G101: marker for detecting a pasted secret key, not a credential
const secretKeyPrefix = "AGE-SECRET-KEY-"
// Defaults and validation bounds for tunable settings.
// Defaults and validation bounds for tunable settings. MB and GB are
// 1000-based, as the size parser reads them; the S3 part sizes are S3's own
// limits, which are 1024-based (MiB, GiB).
const (
defaultBlobSizeLimit = Size(10 * 1024 * 1024 * 1024) // 10GB
defaultChunkSize = Size(10 * 1024 * 1024) // 10MB
defaultBlobSizeLimit = Size(10 * 1000 * 1000 * 1000) // 10GB
defaultChunkSize = Size(10 * 1000 * 1000) // 10MB
defaultS3PartSize = Size(5 * 1024 * 1024) // 5MiB
defaultCompressionLevel = 3
minChunkSize = 1024 * 1024 // 1MB
defaultPruneGracePeriod = 24 * time.Hour
minChunkSize = 1000 * 1000 // 1MB
minCompressionLevel = 1
maxCompressionLevel = 19
// S3 accepts a multipart upload part from 5MiB to 5GiB.
@@ -65,6 +69,8 @@ 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")
@@ -185,6 +191,13 @@ 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:
@@ -286,6 +299,7 @@ func Parse(data []byte) (*Config, error) {
ChunkSize: defaultChunkSize,
IndexPath: filepath.Join(xdg.DataHome, appName, "index.sqlite"),
CompressionLevel: defaultCompressionLevel,
PruneGracePeriod: defaultPruneGracePeriod,
S3: S3Config{PartSize: defaultS3PartSize},
}
@@ -354,6 +368,7 @@ 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 {
@@ -403,6 +418,10 @@ func (c *Config) Validate() error {
return errBadS3PartSize
}
if c.PruneGracePeriod < 0 {
return errNegativePruneGracePeriod
}
return nil
}
internal/config/config_test.go
+143
View File
@@ -6,6 +6,7 @@ import (
"path/filepath"
"strings"
"testing"
"time"
"sneak.berlin/go/vaultik/internal/chunker"
"sneak.berlin/go/vaultik/internal/log"
@@ -337,6 +338,148 @@ func TestLoadS3PartSize(t *testing.T) {
})
}
// TestDocumentedSizeDefaults checks that the defaults are the documented
// chunk_size 10MB and blob_size_limit 10GB as the parser reads those values
// (1000-based), so writing a default out in the config file changes nothing.
func TestDocumentedSizeDefaults(t *testing.T) {
t.Parallel()
cfg, err := Parse([]byte("chunk_size: 10MB\nblob_size_limit: 10GB\n"))
if err != nil {
t.Fatalf("Parse() unexpected error: %v", err)
}
if cfg.ChunkSize != defaultChunkSize {
t.Errorf("chunk_size: 10MB is %d bytes, the default is %d",
cfg.ChunkSize, defaultChunkSize)
}
if cfg.BlobSizeLimit != defaultBlobSizeLimit {
t.Errorf("blob_size_limit: 10GB is %d bytes, the default is %d",
cfg.BlobSizeLimit, defaultBlobSizeLimit)
}
}
// TestDocumentedSizeExamples checks the 1MB minimum chunk_size and that
// every size the README, config.example.yml and the config init template
// list as an example is accepted.
func TestDocumentedSizeExamples(t *testing.T) {
t.Parallel()
const withoutSizes = "snapshots:\n" +
" test:\n" +
" paths: [/tmp/vaultik-test-source]\n" +
"storage_url: file:///tmp/vaultik-test-storage\n"
tests := []struct {
setting string
wantErr error
}{
{"chunk_size: 1MB", nil},
{"chunk_size: 999999", errChunkSizeTooSmall},
{"chunk_size: 5M", nil},
{"chunk_size: 10M", nil},
{"chunk_size: 10MB", nil},
{"chunk_size: 64MiB", nil},
{"chunk_size: 1GB", nil},
// Four times the default chunk_size, the documented minimum.
{"blob_size_limit: 40MB", nil},
{"blob_size_limit: 500MB", nil},
{"blob_size_limit: 1GB", nil},
{"blob_size_limit: 1GiB", nil},
{"blob_size_limit: 10G", nil},
{"blob_size_limit: 10GB", nil},
{"s3: {part_size: 5MiB}", nil},
{"s3: {part_size: 10MB}", nil},
{"s3: {part_size: 16MiB}", nil},
{"s3: {part_size: 100MiB}", nil},
{"s3: {part_size: 5GiB}", nil},
}
for _, tt := range tests {
t.Run(tt.setting, func(t *testing.T) {
t.Parallel()
cfg, err := Parse([]byte(withoutSizes + 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)
}
})
}
}
// 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
@@ -267,6 +267,45 @@ 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
@@ -212,6 +212,65 @@ 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
+8 -3
View File
@@ -8,6 +8,7 @@ import (
"io"
"strings"
"sync/atomic"
"time"
"github.com/aws/aws-sdk-go-v2/aws"
"github.com/aws/aws-sdk-go-v2/config"
@@ -302,7 +303,10 @@ func IsNotFound(err error) bool {
type ObjectInfo struct {
Key string
Size int64
Err error
// ModTime is the object's LastModified time. Only ListObjectsStream
// sets it.
ModTime time.Time
Err error
}
// ListObjectsStream lists objects with the given prefix and returns a channel.
@@ -343,8 +347,9 @@ func (c *Client) ListObjectsStream(
}
ch <- ObjectInfo{
Key: key,
Size: *obj.Size,
Key: key,
Size: *obj.Size,
ModTime: aws.ToTime(obj.LastModified),
}
}
}
internal/snapshot/exclude_test.go
+51
View File
@@ -578,3 +578,54 @@ func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
require.Equal(t, 1, result.FilesScanned,
"**/ file pattern should match at the top level and nested")
}
func TestExcludePatterns_AnchoredDoubleStarAtEveryDepth(t *testing.T) {
t.Parallel()
// As in gitignore, /**/ also matches directly under the source dir
fs := setupAnchoredTestFS(t)
scanner, repos, cleanup := createTestScanner(t, fs, []string{"/**/projectname"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// /**/projectname should exclude BOTH:
// - /backup/projectname/file.txt
// - /backup/otherproject/projectname/file.txt
// Total files: 4, excluded: 2
require.Equal(t, 2, result.FilesScanned,
"/**/ pattern should match at the top level and nested")
}
func TestExcludePatterns_DoubleStarInMiddleMatchesZeroDirectories(t *testing.T) {
t.Parallel()
// As in gitignore, a/**/b matches a/b as well as a/c/b. The last part
// is a glob: with a plain name the glob library already matched a/b.
fs := &afero.MemMapFs{}
files := []string{"/backup/a/x.log", "/backup/a/c/y.log", "/backup/a/c/kept.txt"}
for _, path := range files {
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0755))
require.NoError(t, afero.WriteFile(fs, path, []byte(path), 0644))
}
scanner, repos, cleanup := createTestScanner(t, fs, []string{"a/**/*.log"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// a/**/*.log should exclude /backup/a/x.log and /backup/a/c/y.log
// Total files: 3, excluded: 2
require.Equal(t, 1, result.FilesScanned,
"a/**/*.log should match a/x.log as well as a/c/y.log")
}
internal/snapshot/module.go
+15 -11
View File
@@ -16,6 +16,9 @@ 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.
@@ -44,17 +47,18 @@ 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,
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,
})
}
}
internal/snapshot/progress_test.go
+1 -2
View File
@@ -78,8 +78,7 @@ func TestProgressPercentWithSecondPathSmaller(t *testing.T) {
stats := progress.GetStats()
// Directories count toward the total size but produce no chunks, so
// the percentage ends just under 100%.
// With both paths counted, the percentage must not exceed 100%.
percent := float64(stats.BytesProcessed.Load()) /
float64(stats.TotalSize.Load()) * 100
if percent > 100 {
internal/snapshot/scanner.go
+286 -125
View File
@@ -58,6 +58,10 @@ 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
@@ -129,15 +133,20 @@ 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; 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, 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.
type ScanResult struct {
FilesScanned int
FilesSkipped int
@@ -154,6 +163,11 @@ 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
}
// NewScanner creates a new scanner instance
@@ -207,6 +221,7 @@ func NewScanner(cfg ScannerConfig) *Scanner {
compiledExclude: compiledExclude,
progress: progress,
skipErrors: cfg.SkipErrors,
previousSnapshotID: cfg.PreviousSnapshotID,
ui: uiw,
pendingChunkHashes: make(map[string]struct{}),
}
@@ -258,8 +273,9 @@ func (s *Scanner) Scan(
filesToProcess := scanResult.FilesToProcess
// Phase 1b: Detect deleted files by comparing DB against scanned files
err = s.detectDeletedFilesFromMap(ctx, knownFiles, existingFiles, result)
// Phase 1b: Detect deleted files by comparing the previous snapshot
// of this name against scanned files
err = s.detectDeletedFiles(ctx, path, existingFiles, result)
if err != nil {
return nil, fmt.Errorf("detecting deleted files: %w", err)
}
@@ -275,6 +291,11 @@ 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)
@@ -439,9 +460,8 @@ func (s *Scanner) summarizeScanPhase(
}
// loadKnownFiles loads the known files at and beneath path from the
// 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.
// database into a map for fast lookup. This avoids per-file database
// queries during the scan phase.
func (s *Scanner) loadKnownFiles(
ctx context.Context, path string,
) (map[string]*database.File, error) {
@@ -847,14 +867,15 @@ 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
UnchangedFileIDs []types.FileID // IDs of unchanged files to associate with snapshot
Directories []*FileToProcess // Every directory found, to record
}
// 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 and IDs of unchanged files for snapshot
// association.
// Returns files needing processing, IDs of unchanged files for snapshot
// association, and the directories found.
func (s *Scanner) scanPhase(
ctx context.Context,
path string,
@@ -862,8 +883,10 @@ 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)
estimatedTotal := int64(len(knownFiles))
// 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)
collector := &scanCollector{}
@@ -874,8 +897,28 @@ 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)
return s.handleWalkError(filePath, err, result)
}
// Check context cancellation
@@ -885,18 +928,9 @@ func (s *Scanner) scanPhase(
default:
}
// 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, collector, result)
filePath, info, existingFiles, knownFiles, collector, result)
if handled {
return err
}
@@ -910,9 +944,10 @@ func (s *Scanner) scanPhase(
existingFiles[filePath] = struct{}{}
// Check file against in-memory map (no DB query!)
file, needsProcessing := s.checkFileInMemory(filePath, info, knownFiles)
file := s.buildRegularFileEntry(filePath, info)
needsProcessing := s.checkFileInMemory(file, knownFiles)
filesScanned, changedCount := collector.recordRegularFile(
filesScanned, changedCount := collector.recordFile(
filePath, info, file, needsProcessing)
// Update result stats
@@ -936,27 +971,45 @@ 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. For a symlink
// whose target cannot be read it returns handleWalkError's result.
// 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.
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)
return true, s.handleWalkError(filePath, err, result)
}
existingFiles[filePath] = struct{}{}
collector.addToProcess(filePath, info, file)
s.updateScanEntryStats(result, true, info)
needsProcessing := s.checkFileInMemory(file, knownFiles)
collector.recordFile(filePath, info, file, needsProcessing)
s.updateScanEntryStats(result, needsProcessing, info)
return true, nil
}
@@ -966,7 +1019,7 @@ func (s *Scanner) recordSpecialEntry(
if info.IsDir() {
file := s.buildDirectoryEntry(filePath, info)
existingFiles[filePath] = struct{}{}
collector.addToProcess(filePath, info, file)
collector.addDirectory(filePath, info, file)
return true, nil
}
@@ -974,15 +1027,38 @@ func (s *Scanner) recordSpecialEntry(
return false, nil
}
// 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:
// skipped (with a UI notice) under --skip-errors, fatal otherwise.
func (s *Scanner) handleWalkError(filePath string, err error) error {
// 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 {
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
}
@@ -996,28 +1072,29 @@ type scanCollector struct {
mu sync.Mutex
filesToProcess []*FileToProcess
unchangedFileIDs []types.FileID // Just IDs - no new records needed
directories []*FileToProcess
filesScanned int64
}
// addToProcess queues a file entry for processing.
func (c *scanCollector) addToProcess(
// addDirectory sets a directory aside to be recorded. It is not counted
// as a file.
func (c *scanCollector) addDirectory(
path string, info os.FileInfo, file *database.File,
) {
c.mu.Lock()
defer c.mu.Unlock()
c.filesToProcess = append(c.filesToProcess, &FileToProcess{
c.directories = append(c.directories, &FileToProcess{
Path: path,
FileInfo: info,
File: file,
})
c.filesScanned++
}
// 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(
// 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(
path string, info os.FileInfo, file *database.File, needsProcessing bool,
) (int64, int) {
c.mu.Lock()
@@ -1120,7 +1197,28 @@ func (s *Scanner) printScanProgressLine(
}
}
// buildSymlinkEntry creates a File record for a symlink.
// 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.
func (s *Scanner) buildSymlinkEntry(
path string, info os.FileInfo,
) (*database.File, error) {
@@ -1136,7 +1234,6 @@ func (s *Scanner) buildSymlinkEntry(
}
return &database.File{
ID: types.NewFileID(),
Path: types.FilePath(path),
SourcePath: types.SourcePath(s.currentSourcePath),
MTime: info.ModTime(),
@@ -1168,6 +1265,22 @@ 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 {
@@ -1181,62 +1294,36 @@ func (s *Scanner) recordNonRegularFile(ctx context.Context, ftp *FileToProcess)
})
}
// checkFileInMemory checks if a file needs processing using the in-memory map
// 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.
// No database access is performed - this is purely CPU/memory work
func (s *Scanner) checkFileInMemory(
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,
}
file *database.File, knownFiles map[string]*database.File,
) bool {
existingFile, exists := knownFiles[file.Path.String()]
// New file - needs processing
if !exists {
return file, true
file.ID = types.NewFileID()
return true
}
file.ID = existingFile.ID
// No uploaded blob holds one of its chunks (see loadFilesToRechunk)
if _, rechunk := s.filesToRechunk[fileID]; rechunk {
return file, true
if _, rechunk := s.filesToRechunk[file.ID]; rechunk {
return true
}
// Check if file has changed
if existingFile.Size != file.Size ||
return existingFile.Size != file.Size ||
!existingFile.MTime.Equal(file.MTime) ||
existingFile.Mode != file.Mode ||
existingFile.UID != file.UID ||
existingFile.GID != file.GID {
return file, true
}
// File unchanged
return file, false
existingFile.GID != file.GID ||
existingFile.LinkTarget != file.LinkTarget
}
// batchAddFilesToSnapshot adds existing file IDs to the snapshot association table
@@ -1363,17 +1450,16 @@ func (s *Scanner) processPhase(
return s.finalizeProcessPhase(ctx, result)
}
// processFileWithErrorHandling records a directory or symlink, or wraps
// processFileWithErrorHandling records a 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 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() {
// 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 {
err := s.recordNonRegularFile(ctx, fileToProcess)
if err != nil {
return false, fmt.Errorf("processing file %s: %w", fileToProcess.Path, err)
@@ -1414,6 +1500,7 @@ func (s *Scanner) processFileWithErrorHandling(
s.ui.Path(fileToProcess.Path), err)
countFailedFile(fileToProcess, result)
result.FilesUnreadable++
return true, nil
}
@@ -1954,21 +2041,29 @@ func (s *Scanner) queueFileForBatchInsert(
})
}
// 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(
// 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(
ctx context.Context,
knownFiles map[string]*database.File,
path string,
existingFiles map[string]struct{},
result *ScanResult,
) error {
if len(knownFiles) == 0 {
if s.previousSnapshotID == "" {
return nil
}
// Check each known file against the enumerated set (no filesystem access needed)
for path, file := range knownFiles {
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 context cancellation periodically
select {
case <-ctx.Done():
@@ -1976,13 +2071,22 @@ func (s *Scanner) detectDeletedFilesFromMap(
default:
}
// 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)
filePath := file.Path.String()
_, exists := existingFiles[filePath]
if exists || s.excludedOrInExcludedDir(filePath, path) {
continue
}
// 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 {
@@ -1993,6 +2097,36 @@ func (s *Scanner) detectDeletedFilesFromMap(
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
@@ -2035,33 +2169,60 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
pattern = strings.TrimSuffix(pattern, "/")
// A leading "**/" demands a "/" before the name and so misses an
// entry directly under the source path. An unanchored pattern
// already matches at every depth, so drop the prefix: as in
// gitignore, "**/x" then also matches a top-level "x".
if !anchored {
pattern = strings.TrimPrefix(pattern, "**/")
// entry directly under the source path. It means "at every depth",
// which is what an unanchored pattern already does, so drop the
// prefix and match unanchored: as in gitignore, "**/x" and
// "/**/x" then also match a top-level "x".
if rest, found := strings.CutPrefix(pattern, "**/"); found {
pattern = rest
anchored = false
}
// Compile the glob pattern
// For patterns without path separators, we need to match them as components
// e.g., ".git" should match ".git" anywhere in the path
g, err := glob.Compile(pattern, '/')
if err != nil {
log.Warn("Invalid exclude pattern, skipping", "pattern", p, "error", err)
// Likewise "/**/" inside a pattern demands two slashes, so
// "a/**/*.log" misses "a/x.log". As in gitignore it stands for
// zero or more directories, so also compile the pattern with it
// made a single "/". The glob library's {a,b} is no help: with a
// "**" inside it in mid-pattern, it misses paths it should match.
for _, variant := range doubleStarVariants(pattern) {
// For patterns without path separators, we need to match them as components
// e.g., ".git" should match ".git" anywhere in the path
g, err := glob.Compile(variant, '/')
if err != nil {
log.Warn("Invalid exclude pattern, skipping", "pattern", p, "error", err)
continue
break
}
compiled = append(compiled, compiledPattern{
pattern: g,
anchored: anchored,
original: p,
})
}
compiled = append(compiled, compiledPattern{
pattern: g,
anchored: anchored,
original: p,
})
}
return compiled
}
// doubleStarVariants returns pattern once for every way of keeping each
// "/**/" in it or making it a single "/".
func doubleStarVariants(pattern string) []string {
const doubleStar = "/**/"
before, after, found := strings.Cut(pattern, doubleStar)
if !found {
return []string{pattern}
}
var variants []string
for _, rest := range doubleStarVariants(after) {
variants = append(variants, before+doubleStar+rest, before+"/"+rest)
}
return variants
}
// shouldExclude checks if a path should be excluded based on exclude patterns
// filePath is the full path to the file
// rootPath is the root of the backup source directory
internal/snapshot/scanner_estimate_test.go
+28
View File
@@ -0,0 +1,28 @@
//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
+35 -3
View File
@@ -8,6 +8,7 @@ import (
"reflect"
"sort"
"testing"
"time"
"sneak.berlin/go/vaultik/internal/storage"
)
@@ -19,15 +20,17 @@ import (
// constructor, so the contract is defined once.
//
// It exercises the public Storer interface: round-trip, stat, list with
// 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.
// 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.
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))
}
@@ -118,6 +121,35 @@ 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
+23 -6
View File
@@ -21,9 +21,13 @@ type FileStorer struct {
// NewFileStorer creates a new filesystem storage backend.
//
// Construction is intentionally cheap and does not touch the filesystem.
// 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.
// 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.
// 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.
@@ -231,8 +235,9 @@ 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(),
Key: relPath,
Size: info.Size(),
ModTime: info.ModTime(),
}
}
@@ -299,7 +304,19 @@ func (f *FileStorer) writeAtomic(
path := f.fullPath(key)
dir := filepath.Dir(path)
err := f.fs.MkdirAll(dir, storageDirPerm)
// 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)
if err != nil {
return fmt.Errorf("creating directories: %w", err)
}
internal/storage/file_backend_test.go
+40
View File
@@ -292,3 +292,43 @@ 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
+22 -2
View File
@@ -7,10 +7,12 @@ import (
"errors"
"fmt"
"io"
"os"
"strings"
"time"
"github.com/rclone/rclone/fs"
"github.com/rclone/rclone/fs/config"
"github.com/rclone/rclone/fs/config/configfile"
"github.com/rclone/rclone/fs/operations"
@@ -33,6 +35,15 @@ type RcloneStorer struct {
// The remote parameter is the rclone remote name (as configured via `rclone config`).
// The path parameter is the path within the remote.
func NewRcloneStorer(ctx context.Context, remote, path string) (*RcloneStorer, error) {
// rclone reads RCLONE_CONFIG only as the value of its --config flag,
// which vaultik does not have, so it is applied here as that flag would.
if configPath, ok := os.LookupEnv("RCLONE_CONFIG"); ok {
err := config.SetConfigPath(configPath)
if err != nil {
return nil, fmt.Errorf("using RCLONE_CONFIG %q: %w", configPath, err)
}
}
// Install the default config file handler
configfile.Install()
@@ -42,6 +53,14 @@ 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 {
@@ -200,8 +219,9 @@ func (r *RcloneStorer) ListStream(
if prefix == "" || strings.HasPrefix(key, prefix) {
ch <- ObjectInfo{
Key: key,
Size: obj.Size(),
Key: key,
Size: obj.Size(),
ModTime: obj.ModTime(ctx),
}
}
})
internal/storage/rclone_test.go
+114
View File
@@ -5,12 +5,19 @@ 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"
"sneak.berlin/go/vaultik/internal/storage"
)
@@ -390,3 +397,110 @@ func TestNewRcloneStorerUnknownRemote(t *testing.T) {
t.Errorf("NewRcloneStorer error = %v, want ErrRemoteNotFound", err)
}
}
// TestNewRcloneStorerReadsRcloneConfigEnv checks that a remote defined only
// in the file RCLONE_CONFIG names is found and written to, as rclone itself
// would.
func TestNewRcloneStorerReadsRcloneConfigEnv(t *testing.T) {
// rclone keeps the config file path in a process-global variable, which
// NewRcloneStorer leaves pointing at this test's file.
previous := config.GetConfigPath()
t.Cleanup(func() { _ = config.SetConfigPath(previous) })
confFile := filepath.Join(t.TempDir(), "rclone.conf")
err := os.WriteFile(confFile, []byte("[loc]\ntype = local\n"), 0o600)
if err != nil {
t.Fatalf("writing rclone config: %v", err)
}
t.Setenv("RCLONE_CONFIG", confFile)
dir := t.TempDir()
ctx := context.Background()
s, err := storage.NewRcloneStorer(ctx, "loc", dir)
if err != nil {
t.Fatalf("NewRcloneStorer: %v", err)
}
err = s.Put(ctx, testBlobKey, strings.NewReader("blob-bytes"))
if err != nil {
t.Fatalf("Put: %v", err)
}
_, err = os.Stat(filepath.Join(dir, testBlobKey))
if err != nil {
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
+4 -3
View File
@@ -89,9 +89,10 @@ 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,
Err: info.Err,
Key: info.Key,
Size: info.Size,
ModTime: info.ModTime,
Err: info.Err,
}
}
}()
internal/storage/storer.go
+9 -3
View File
@@ -14,6 +14,7 @@ import (
"context"
"errors"
"io"
"time"
)
// ErrNotFound is returned when an object does not exist.
@@ -27,7 +28,10 @@ type ProgressCallback func(bytesTransferred int64) error
type ObjectInfo struct {
Key string // Object key/path
Size int64 // Size in bytes
Err error // Error for streaming results (nil on success)
// 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)
}
// Info provides human-readable storage configuration.
@@ -41,7 +45,8 @@ type Info struct {
// directory for filesystem).
type Storer interface {
// Put stores data at the specified key.
// Parent directories are created automatically for filesystem backends.
// The filesystem backend fails when its destination directory does
// not exist, and creates the directories below it as needed.
Put(ctx context.Context, key string, data io.Reader) error
// PutWithProgress stores data with progress reporting.
@@ -66,7 +71,8 @@ type Storer interface {
// For large result sets, prefer ListStream.
List(ctx context.Context, prefix string) ([]string, error)
// ListStream returns a channel of ObjectInfo for large result sets.
// ListStream returns a channel of ObjectInfo, with each object's key,
// size and modification time, 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
+47 -6
View File
@@ -30,6 +30,12 @@ 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.
@@ -90,8 +96,9 @@ func parseFileURL(rawPath string) (*URL, error) {
}
// parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
// the userinfo and any query parameter other than endpoint, region and
// ssl, so a credential-bearing URL is never stored or echoed.
// 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.
func parseS3URL(rawURL string) (*URL, error) {
u, err := url.Parse(rawURL)
if err != nil {
@@ -107,13 +114,26 @@ func parseS3URL(rawURL string) (*URL, error) {
return nil, ErrMissingBucket
}
query := u.Query()
// 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
}
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,
@@ -125,9 +145,23 @@ func parseS3URL(rawURL string) (*URL, error) {
}
// parseRcloneURL parses an rclone://remote/path URL. rclone:// takes no
// query parameters, so credentials in the userinfo and any parameter at
// query parameters, so credentials in the userinfo, parameters in the
// remote name, a query that cannot be decoded and any query 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)
@@ -137,12 +171,19 @@ func parseRcloneURL(rawURL string) (*URL, error) {
return nil, ErrURLCredentials
}
remote := u.Host
remote = u.Host
if remote == "" {
return nil, ErrMissingRemote
}
err = rejectUnknownParams(u.Query())
// 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)
if err != nil {
return nil, err
}
internal/storage/url_parse_test.go
+119
View File
@@ -150,6 +150,19 @@ 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,
@@ -203,6 +216,112 @@ 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
+3 -2
View File
@@ -104,7 +104,8 @@ 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.
// blocked inside it. A storage error is returned as is: restore and deep
// verify name the blob in their own errors.
func (v *Vaultik) FetchBlob(
ctx context.Context, blobHash string,
) (io.ReadCloser, error) {
@@ -119,7 +120,7 @@ func (v *Vaultik) FetchBlob(
rc, err := v.Storage.Get(ctx, blobPath)
if err != nil {
return nil, fmt.Errorf("downloading blob %s: %w", shortHash(blobHash), err)
return nil, err
}
return newCloseOnCancelReader(ctx, rc), nil
internal/vaultik/blobcache.go
+3 -3
View File
@@ -39,9 +39,9 @@ type blobDiskCacheEntry struct {
// internally and will fall back to LRU eviction if curBytes exceeds
// maxBytes. Restore passes math.MaxInt64 as maxBytes and drives
// eviction itself via Delete() through restoreSweeper, which deletes
// each blob the moment every file that references its chunks has been
// written. LRU never fires under that configuration; it is kept as a
// safety net for callers that don't manage eviction themselves.
// each blob once no file still to be restored in this run needs it.
// LRU never fires under that configuration; it is kept as a safety net
// for callers that don't manage eviction themselves.
//
// Get/ReadAt/peak-Len counters are debugging instrumentation used by
// tests to assert that the restore code path uses ReadAt rather than
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
changedPath := filepath.Join(dataDir, "appended.bin")
internal/vaultik/deep_verify_test.go
+13 -6
View File
@@ -6,6 +6,7 @@ import (
"crypto/rand"
"io"
"os"
"path"
"path/filepath"
"testing"
@@ -34,7 +35,7 @@ func TestDeepVerifyAcceptsHealthyAndRejectsCorruptBlob(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(64 * 1024)
@@ -93,7 +94,7 @@ func TestDeepVerifyJSONCountsBlobs(t *testing.T) {
fs := afero.NewOsFs()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "remote")
storeDir := t.TempDir()
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
@@ -142,14 +143,15 @@ 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.
// 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.
func TestDeepVerifyJSONCountsWrongSizeBlob(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "remote")
storeDir := t.TempDir()
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
@@ -168,17 +170,20 @@ 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 with the storage error.
// deep verify stops and fails, saying it could not check the blob, with
// the storage error.
func TestDeepVerifyStopsOnBlobThatCannotBeChecked(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "remote")
storeDir := t.TempDir()
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
failing := statFailingStorer{Storer: storer, failKeys: []string{keys[0]}}
@@ -187,6 +192,8 @@ 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
@@ -0,0 +1,90 @@
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
@@ -0,0 +1,297 @@
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
+29 -22
View File
@@ -192,7 +192,7 @@ func assertRestoreRejectsDamagedBlob(
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
@@ -298,10 +298,6 @@ 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)
@@ -365,7 +361,7 @@ func TestBackupRetryAfterInterruptedUploadIsRestorable(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -429,7 +425,7 @@ func TestBackupSurvivesMetadataExportInterruption(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
@@ -445,6 +441,10 @@ 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)
@@ -493,8 +493,14 @@ 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
@@ -511,7 +517,7 @@ func TestBackupCompletesOnlyAfterMetadataExport(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -661,17 +667,18 @@ 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,
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,
})
}
}
@@ -686,7 +693,7 @@ func TestRestoreReportsDiskFull(t *testing.T) {
osFS := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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 _, size := range allBlobs {
for _, blob := range allBlobs {
result.TotalBlobCount++
result.TotalBlobSize += size
result.TotalBlobSize += blob.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, size := range allBlobs {
for hash, blob := range allBlobs {
if _, referenced := referencedBlobs[hash]; !referenced {
orphanedCount++
orphanedSize += size
orphanedSize += blob.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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/missing_destination_test.go
+73 -16
View File
@@ -24,13 +24,11 @@ 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.
// 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(
// newFileDestinationVaultik returns a Vaultik that backs up the
// snapshot named "first" to a file:// destination at storeDir.
func newFileDestinationVaultik(
ctx context.Context, t *testing.T, storeDir string,
) (*vaultik.Vaultik, *database.Repositories, *bytes.Buffer) {
) (*vaultik.Vaultik, *database.Repositories) {
t.Helper()
osFs := afero.NewOsFs()
@@ -49,8 +47,22 @@ func backUpToFileDestination(
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{}
@@ -75,21 +87,28 @@ func backUpThenUnplug(
return v, repos, out
}
// 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) {
// 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) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "volume", "backup")
v, _, out := backUpToFileDestination(ctx, t, storeDir)
volume := filepath.Join(t.TempDir(), "volume")
v, repos := newFileDestinationVaultik(ctx, t, filepath.Join(volume, "backup"))
require.NoError(t, v.ListSnapshots(false))
err := backUp(v, "first")
require.ErrorIs(t, err, fs.ErrNotExist)
require.ErrorContains(t, err, "create it, or mount the volume it is on")
assert.NotContains(t, out.String(), "Could not list backup destination store")
assert.NotContains(t, out.String(), "not found in backup destination store")
_, 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)
}
// TestListSnapshotsWarnsWhenDestinationMissing checks that snapshot list
@@ -169,3 +188,41 @@ 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(filepath.Join(tempDir, "remote"))
store, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
internal/vaultik/nuke_remote_test.go
+27 -2
View File
@@ -104,6 +104,32 @@ 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.
@@ -154,8 +180,7 @@ func TestNukeRemoteRefusesAnotherDestinationWithoutRetryAdvice(t *testing.T) {
// TestNukeRemoteFailsWhenALocalSnapshotCannotBeRemoved checks that a
// snapshot remote nuke cannot remove from the local index fails the
// run: nuke then leaves that snapshot's metadata on the destination
// store.
// run, and that nuke then does not report the destination store empty.
func TestNukeRemoteFailsWhenALocalSnapshotCannotBeRemoved(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
internal/vaultik/prune.go
+87 -25
View File
@@ -5,8 +5,10 @@ import (
"errors"
"fmt"
"strings"
"time"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
)
// PruneOptions contains options for the prune command
@@ -42,9 +44,10 @@ 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. It returns
// successfully only when a listing afterwards finds nothing left there,
// and the next backup then starts from scratch.
// 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.
//
// Refuses to run unless force is true. The caller is responsible for
// confirming with the user.
@@ -54,12 +57,19 @@ 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 this error.
// 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.
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 "+
@@ -105,6 +115,13 @@ 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
}
@@ -148,6 +165,10 @@ 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
@@ -193,9 +214,15 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
return err
}
unreferencedBlobs, totalSize := v.findUnreferencedBlobs(allBlobs, allBlobsReferenced)
unreferencedBlobs, totalSize, tooNew := v.findUnreferencedBlobs(
allBlobs, allBlobsReferenced)
result := &PruneBlobsResult{BlobsFound: len(unreferencedBlobs)}
result := &PruneBlobsResult{
BlobsFound: len(unreferencedBlobs),
BlobsTooNew: tooNew,
}
v.reportBlobsTooNew(tooNew, opts)
if len(unreferencedBlobs) == 0 {
log.Info("No unreferenced blobs found")
@@ -204,7 +231,7 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
return v.outputPruneBlobsJSON(result)
}
v.printlnStdout("No unreferenced blobs to remove.")
v.UI.Infof("No unreferenced blobs to remove.")
return nil
}
@@ -212,12 +239,17 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
log.Info("Found unreferenced blobs",
"count", len(unreferencedBlobs), "total_size", ubytes(totalSize))
if !opts.JSON {
v.stdoutf("Found %d unreferenced blob(s) totaling %s\n",
if opts.Force && !opts.JSON {
v.UI.Infof("Found %d unreferenced blob(s) totaling %s.",
len(unreferencedBlobs), ubytes(totalSize))
}
if !opts.Force && !opts.JSON {
// The count, the prompt and its answer bypass the UI: they are an
// interactive exchange the operator must see, so --quiet does not
// silence them.
v.stdoutf("Found %d unreferenced blob(s) totaling %s.\n",
len(unreferencedBlobs), ubytes(totalSize))
v.stdoutf("\nDelete %d unreferenced blob(s)? [y/N] ", len(unreferencedBlobs))
var confirm string
@@ -244,7 +276,7 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
return err
}
} else {
v.stdoutf("\nDeleted %d blob(s) totaling %s\n",
v.UI.Infof("Deleted %d blob(s) totaling %s.",
result.BlobsDeleted, ubytes(result.BytesFreed))
}
@@ -324,11 +356,12 @@ func (v *Vaultik) listUniqueSnapshotIDs() ([]string, error) {
return snapshotIDs, nil
}
// listAllRemoteBlobs returns a map of all blob hashes to their sizes in remote storage
func (v *Vaultik) listAllRemoteBlobs() (map[string]int64, error) {
// listAllRemoteBlobs returns a map of all blob hashes in remote storage
// to their listing entries.
func (v *Vaultik) listAllRemoteBlobs() (map[string]storage.ObjectInfo, error) {
log.Info("Listing all blobs in storage")
allBlobs := make(map[string]int64)
allBlobs := make(map[string]storage.ObjectInfo)
blobObjectCh := v.Storage.ListStream(v.ctx, "blobs/")
for object := range blobObjectCh {
@@ -352,7 +385,7 @@ func (v *Vaultik) listAllRemoteBlobs() (map[string]int64, error) {
continue
}
allBlobs[parts[3]] = object.Size
allBlobs[parts[3]] = object
}
log.Info("Found blobs in storage", "count", len(allBlobs))
@@ -360,30 +393,59 @@ func (v *Vaultik) listAllRemoteBlobs() (map[string]int64, error) {
return allBlobs, nil
}
// findUnreferencedBlobs returns blob hashes not referenced by any
// manifest and their total size.
// 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.
func (v *Vaultik) findUnreferencedBlobs(
allBlobs map[string]int64, referenced map[string]bool,
) ([]string, int64) {
allBlobs map[string]storage.ObjectInfo, referenced map[string]bool,
) ([]string, int64, int) {
var (
unreferenced []string
totalSize int64
tooNew int
)
for hash, size := range allBlobs {
if !referenced[hash] {
unreferenced = append(unreferenced, hash)
totalSize += size
cutoff := time.Now().UTC().Add(-v.Config.PruneGracePeriod)
for hash, blob := range allBlobs {
if referenced[hash] {
continue
}
if blob.ModTime.IsZero() || blob.ModTime.After(cutoff) {
tooNew++
continue
}
unreferenced = append(unreferenced, hash)
totalSize += blob.Size
}
return unreferenced, totalSize
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)
}
// deleteUnreferencedBlobs deletes the given blobs from storage and
// populates the result.
func (v *Vaultik) deleteUnreferencedBlobs(
unreferencedBlobs []string, allBlobs map[string]int64, result *PruneBlobsResult,
unreferencedBlobs []string, allBlobs map[string]storage.ObjectInfo,
result *PruneBlobsResult,
) {
log.Info("Deleting unreferenced blobs")
@@ -398,7 +460,7 @@ func (v *Vaultik) deleteUnreferencedBlobs(
}
result.BlobsDeleted++
result.BytesFreed += allBlobs[hash]
result.BytesFreed += allBlobs[hash].Size
if (i+1)%progressLogEvery == 0 || i == len(unreferencedBlobs)-1 {
log.Info("Deletion progress",
internal/vaultik/prune_count_test.go
+60
View File
@@ -1,13 +1,17 @@
package vaultik //nolint:testpackage // exercises unexported count helpers
import (
"bytes"
"context"
"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/snapshot"
"sneak.berlin/go/vaultik/internal/ui"
)
// TestTableCountForReportSurfacesReadFailure is the regression guard for
@@ -76,3 +80,59 @@ func TestCountDiffUnknownWhenEitherSideUnknown(t *testing.T) {
assert.Nil(t, countDiff(&before, nil), "unknown after yields unknown delta")
assert.Nil(t, countDiff(nil, nil))
}
// TestPruneDatabaseSummaryLabelsTotals removes the only incomplete
// snapshot from an index that also holds a complete one. The figure in
// brackets is every snapshot left in the local index, so the line must
// say so rather than read as incomplete snapshots that remain.
func TestPruneDatabaseSummaryLabelsTotals(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
db, err := database.New(ctx, ":memory:")
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
startedAt := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
completedAt := startedAt.Add(time.Minute)
require.NoError(t, repos.Snapshots.Create(ctx, nil, &database.Snapshot{
ID: "host_complete_2026-01-02T03:04:05Z",
Hostname: "host",
StartedAt: startedAt,
CompletedAt: &completedAt,
}))
require.NoError(t, repos.Snapshots.Create(ctx, nil, &database.Snapshot{
ID: "host_incomplete_2026-01-02T03:04:05Z",
Hostname: "host",
StartedAt: startedAt,
}))
var out bytes.Buffer
v := &Vaultik{
DB: db,
Repositories: repos,
SnapshotManager: snapshot.NewSnapshotManager(
snapshot.SnapshotManagerParams{Repos: repos}),
UI: ui.NewWithColor(&out, false),
}
v.SetContext(ctx)
result, err := v.PruneDatabase()
require.NoError(t, err)
require.Equal(t, int64(1), result.SnapshotsDeleted)
assert.Contains(t, out.String(), "Incomplete snapshots: 1 removed "+
"(total snapshots left in the local index: 1).")
assert.Contains(t, out.String(), "Orphaned files: 0 removed "+
"(total files left in the local index: 0).")
assert.Contains(t, out.String(), "Orphaned chunks: 0 removed "+
"(total chunks left in the local index: 0).")
assert.Contains(t, out.String(), "Orphaned blobs: 0 removed "+
"(total blobs left in the local index: 0).")
}
internal/vaultik/prune_grace_period_test.go
+166
View File
@@ -0,0 +1,166 @@
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
+8 -1
View File
@@ -14,6 +14,7 @@ import (
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/types"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
@@ -34,6 +35,9 @@ 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])
@@ -58,13 +62,16 @@ func setupConsistencyTest(
require.NoError(t, err)
}
stdout := &bytes.Buffer{}
v := &vaultik.Vaultik{
Storage: mockStorage,
Repositories: repos,
DB: db,
Stdout: &bytes.Buffer{},
Stdout: stdout,
Stderr: &bytes.Buffer{},
Stdin: &bytes.Buffer{},
UI: ui.NewWithColor(stdout, false),
}
v.SetContext(ctx)
internal/vaultik/purge_per_name_test.go
+7 -1
View File
@@ -14,6 +14,7 @@ import (
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/types"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
@@ -44,6 +45,9 @@ 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 {
@@ -86,6 +90,7 @@ func setupPurgeTest(
Stdout: stdout,
Stderr: stderr,
Stdin: stdin,
UI: ui.NewWithColor(stdout, false),
}
v.SetContext(ctx)
@@ -279,7 +284,8 @@ func TestPurgeOlderThan_TooLargeDeletesNothing(t *testing.T) {
OlderThan: "1000y",
Force: true,
})
require.Error(t, err)
require.EqualError(t, err,
`invalid duration: "1000y" is longer than about 292 years`)
err = v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
OlderThan: "292y",
internal/vaultik/remove_quiet_test.go
+152
View File
@@ -0,0 +1,152 @@
package vaultik_test
import (
"bytes"
"context"
"encoding/json"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestPurgeSnapshots_QuietSuppressesReport checks that `snapshot purge
// --keep-latest --force` under --quiet deletes the older snapshot and
// prints nothing.
func TestPurgeSnapshots_QuietSuppressesReport(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
v := setupPurgeTest(t, snapHostname, []string{snapHomeT0, snapHomeT1})
var out bytes.Buffer
v.Stdout = &out
v.UI = ui.NewWithColor(&out, false)
v.UI.SetQuiet(true)
require.NoError(t, v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
KeepLatest: true,
Force: true,
}))
assert.Equal(t, []string{snapHomeT1}, listRemainingSnapshots(t, v))
assert.Empty(t, out.String())
}
// TestPurgeSnapshots_QuietPromptListsSnapshots checks that `snapshot
// purge --keep-latest` without --force still lists the snapshots its
// prompt asks to delete under --quiet.
func TestPurgeSnapshots_QuietPromptListsSnapshots(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
v := setupPurgeTest(t, snapHostname, []string{snapHomeT0, snapHomeT1})
var out bytes.Buffer
v.Stdout = &out
v.UI = ui.NewWithColor(&out, false)
v.UI.SetQuiet(true)
// Stdin is empty, so the prompt reads no answer and cancels.
require.NoError(t, v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
KeepLatest: true,
}))
assert.Contains(t, out.String(), snapHomeT0)
assert.Contains(t, out.String(), "Delete 1 snapshot(s)? [y/N]")
assert.Len(t, listRemainingSnapshots(t, v), 2)
}
// TestPruneBlobs_QuietPromptShowsBlobTotal checks that `prune` without
// --force still states the count and total size of the blobs its prompt
// asks to delete under --quiet.
func TestPruneBlobs_QuietPromptShowsBlobTotal(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newListEnv(t)
env.v.UI.SetQuiet(true)
// The store holds no manifest, so nothing references this blob.
addBlob(t, env.store.testStorer, testBlobHashA)
// Stdin is empty, so the prompt reads no answer and cancels.
require.NoError(t, env.v.PruneBlobs(&vaultik.PruneOptions{}))
assert.Contains(t, env.stdout.String(),
"Found 1 unreferenced blob(s) totaling")
assert.Contains(t, env.stdout.String(),
"Delete 1 unreferenced blob(s)? [y/N]")
}
// TestRemoveSnapshot_QuietSuppressesReport checks that `snapshot remove`
// under --quiet prints nothing with --dry-run or with --force, and that
// the --json document still prints.
func TestRemoveSnapshot_QuietSuppressesReport(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
newQuietRemover := func() (*vaultik.TestVaultik, *testStorer) {
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)
return tv, store
}
tv, store := newQuietRemover()
_, err := tv.RemoveSnapshot("snapshot-001",
&vaultik.RemoveOptions{DryRun: true})
require.NoError(t, err)
assert.Empty(t, tv.Stdout.String(),
"--dry-run must print nothing under --quiet")
_, err = tv.RemoveSnapshot("snapshot-001",
&vaultik.RemoveOptions{Force: true})
require.NoError(t, err)
assert.False(t, store.hasKey(remoteKeyPath("snapshot-001")))
assert.Empty(t, tv.Stdout.String(),
"--force must print nothing under --quiet")
tv, _ = newQuietRemover()
_, err = tv.RemoveSnapshot("snapshot-001",
&vaultik.RemoveOptions{JSON: true})
require.NoError(t, err)
var result vaultik.RemoveResult
require.NoError(t, json.Unmarshal(tv.Stdout.Bytes(), &result),
"the --json document must still print under --quiet")
assert.True(t, result.RemoteRemoved)
}
// TestNukeRemote_QuietSuppressesReport checks that `remote nuke --force`
// under --quiet prints nothing while it removes a snapshot's metadata
// and its blobs.
func TestNukeRemote_QuietSuppressesReport(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, _, out := backUpToFileDestination(ctx, t, storeDir)
v.UI.SetQuiet(true)
require.NoError(t, v.NukeRemote(true))
assert.Empty(t, out.String())
}
internal/vaultik/remove_snapshot_test.go
+60 -6
View File
@@ -17,6 +17,7 @@ import (
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/storage/faultstore"
"sneak.berlin/go/vaultik/internal/types"
"sneak.berlin/go/vaultik/internal/vaultik"
)
@@ -25,11 +26,14 @@ 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),
data: make(map[string][]byte),
putTimes: make(map[string]time.Time),
}
}
@@ -43,6 +47,7 @@ func (s *testStorer) Put(_ context.Context, key string, reader io.Reader) error
}
s.data[key] = data
s.putTimes[key] = time.Now().UTC()
return nil
}
@@ -86,6 +91,7 @@ func (s *testStorer) Delete(_ context.Context, key string) error {
defer s.mu.Unlock()
delete(s.data, key)
delete(s.putTimes, key)
return nil
}
@@ -119,8 +125,9 @@ 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)),
Key: key,
Size: int64(len(data)),
ModTime: s.putTimes[key],
}
}
}
@@ -303,6 +310,10 @@ 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")
@@ -350,7 +361,7 @@ func TestRemoveSnapshot_DryRun(t *testing.T) {
assert.True(t, store.hasKey("blobs/aa/aa/"+blobA))
assert.True(t, store.hasKey(remoteKeyPath("snapshot-001")))
assert.Contains(t, tv.Stdout.String(), "[Dry run - no changes made]")
assert.Contains(t, tv.Stdout.String(), "Dry run: no changes made.")
}
// TestRemoveSnapshot_UnknownIDIsError checks that an ID naming no
@@ -372,6 +383,10 @@ 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")
@@ -392,7 +407,12 @@ func TestRemoveSnapshot_NoMetadataOnDestination(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
tv := vaultik.NewForTesting(newTestStorer())
// 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.Repositories = newLocalIndex(t, "snapshot-001")
result, err := tv.RemoveSnapshot("snapshot-001",
@@ -431,6 +451,40 @@ func TestRemoveSnapshot_NotInLocalIndex(t *testing.T) {
assert.Contains(t, out, "Removed snapshot metadata from remote storage")
}
// TestRemoveSnapshot_NotInLocalIndexDeleteFails checks that removing a
// snapshot only the destination store holds fails when its metadata
// cannot be deleted there, under --force and under --json: nothing was
// removed, so the command must not succeed.
func TestRemoveSnapshot_NotInLocalIndexDeleteFails(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
for name, opts := range map[string]vaultik.RemoveOptions{
"force": {Force: true},
"json": {JSON: true},
} {
t.Run(name, func(t *testing.T) {
t.Parallel()
store := newTestStorer()
addManifest(t, store, "snapshot-001", nil)
faulty := faultstore.New(store)
faulty.OnDelete = func(string) bool { return true }
tv := vaultik.NewForTesting(faulty)
tv.Repositories = newLocalIndex(t)
result, err := tv.RemoveSnapshot("snapshot-001", &opts)
require.ErrorIs(t, err, faultstore.ErrInjectedDelete)
assert.False(t, result.RemoteRemoved)
assert.True(t, store.hasKey(remoteKeyPath("snapshot-001")))
assert.Empty(t, tv.Stdout.String())
})
}
}
func TestRemoveAllSnapshots_RequiresForce(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
@@ -504,7 +558,7 @@ func TestRemoveAllSnapshots_DryRun(t *testing.T) {
assert.Equal(t, initialCount, store.keyCount())
assert.Contains(t, tv.Stdout.String(), "[Dry run - no changes made]")
assert.Contains(t, tv.Stdout.String(), "Dry run: no changes made.")
}
func TestRemoveAllSnapshots_NoSnapshots(t *testing.T) {
internal/vaultik/restore.go
+50 -15
View File
@@ -12,6 +12,7 @@ import (
"path/filepath"
"slices"
"strings"
"syscall"
"time"
"filippo.io/age"
@@ -219,9 +220,7 @@ func (v *Vaultik) finishRestore(
)
if os.Geteuid() != 0 {
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.")
v.warnIfOwnershipNotPreserved(files, opts.TargetDir)
}
if result.FilesFailed > 0 {
@@ -247,6 +246,43 @@ 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.
@@ -323,12 +359,6 @@ func (v *Vaultik) restoreAllFiles(
_ = blobCache.Close()
}()
// Per-restore sweep state: every blob_size_limit/100 bytes written,
// scan the cache and delete any blob whose remaining file references
// are all already restored.
sweeper := newRestoreSweeper(v.ctx, repos, blobCache,
v.Config.BlobSizeLimit.Int64()/sweepIntervalDivisor)
blobByHash, blobIDToHash, err := v.buildBlobIndexes(repos)
if err != nil {
return nil, err
@@ -340,6 +370,12 @@ func (v *Vaultik) restoreAllFiles(
return nil, fmt.Errorf("building restore plan: %w", err)
}
// Per-restore sweep state: every blob_size_limit/100 bytes written,
// scan the cache and delete any blob that no pending file in the
// plan references.
sweeper := newRestoreSweeper(plan, blobCache,
v.Config.BlobSizeLimit.Int64()/sweepIntervalDivisor)
// Ranging over files rather than the map reports them in a stable order.
for _, file := range files {
if planErr, ok := unplanned[file.ID]; ok {
@@ -427,10 +463,8 @@ func (v *Vaultik) runRestoreLoop(
continue
}
// Record the file as restored so the sweeper can free blobs
// once all referencing files are done, and drop it from the
// plan's indexes so future picks ignore it.
session.sweeper.fileRestored(fileID.String())
// Drop the file from the plan's indexes so future picks ignore
// it and the sweeper can free blobs no pending file needs.
plan.finishFile(fileID)
processed++
@@ -967,8 +1001,9 @@ 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 and emit one warning at the end
// of the restore explaining that ownership was not preserved.
// 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.
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/restore_interrupt_test.go
+3 -2
View File
@@ -65,7 +65,7 @@ func TestRestoreCleansTempDirOnInterrupt(t *testing.T) {
root := t.TempDir()
dataDir := filepath.Join(root, "source")
storeDir := filepath.Join(root, "remote")
storeDir := t.TempDir()
restoreDir := filepath.Join(root, "restored")
dbPath := filepath.Join(root, "index.sqlite")
@@ -74,7 +74,8 @@ func TestRestoreCleansTempDirOnInterrupt(t *testing.T) {
buildLocalityFixture(t, fs, dataDir)
cfg, storer, snapshotID := setupLocalityBackup(
context.Background(), t, fs, dataDir, storeDir, dbPath)
context.Background(), t, fs, dataDir, storeDir, dbPath,
localitySourceBytes)
// Point the "" temp paths (the blob cache directory and the
// snapshot-database directory) at a private directory so the test can
internal/vaultik/restore_locality_test.go
+16 -12
View File
@@ -63,6 +63,10 @@ type localityCopy struct {
data []byte
}
// localitySourceBytes is the size of each source file of the locality
// fixture.
const localitySourceBytes = 1024 * 1024
// buildLocalityFixture writes the adversarial source layout described
// in TestRestoreLocalityAndReadAt: 15 sources of 1 MiB each (which the
// backup packs into 3 blobs of 5 chunks) plus 9 interleaved-name copies
@@ -73,7 +77,6 @@ func buildLocalityFixture(
t.Helper()
const (
srcBytes = 1024 * 1024
srcCount = 15
blobsCount = 3
perBlob = srcCount / blobsCount
@@ -83,7 +86,7 @@ func buildLocalityFixture(
for i := range srcCount {
s := &localitySource{
path: fmt.Sprintf("src-%03d.bin", i+1),
data: randomBytes(t, srcBytes),
data: randomBytes(t, localitySourceBytes),
}
sources[i] = s
require.NoError(t, afero.WriteFile(
@@ -115,19 +118,20 @@ func buildLocalityFixture(
// setupLocalityBackup runs the backup half of the locality test: a
// snapshot of dataDir into a file storer with sizes tuned so 15 one-chunk
// files pack into 3 blobs. The index database is closed before returning
// so the restore half runs from remote bytes only.
// files of srcBytes pack into 3 blobs. The index database is closed
// before returning so the restore half runs from remote bytes only.
func setupLocalityBackup(
ctx context.Context, t *testing.T, fs afero.Fs,
dataDir, storeDir, dbPath string,
dataDir, storeDir, dbPath string, srcBytes int64,
) (*config.Config, *storage.FileStorer, string) {
t.Helper()
// chunkSize avg = 4 MiB makes minSize = 1 MiB, so a 1 MiB file
// becomes one chunk. maxBlobSize = 5 MiB packs exactly 5 chunks
// per blob, yielding 3 blobs from 15 source files.
chunkSize := int64(4 * 1024 * 1024)
maxBlobSize := int64(5 * 1024 * 1024)
// An average chunk size of four times srcBytes makes the minimum
// chunk srcBytes, so each source file becomes one chunk. A blob limit
// of five times srcBytes packs exactly 5 chunks per blob, yielding 3
// blobs from 15 source files.
chunkSize := 4 * srcBytes
maxBlobSize := 5 * srcBytes
storer, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
@@ -197,7 +201,7 @@ func TestRestoreLocalityAndReadAt(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -208,7 +212,7 @@ func TestRestoreLocalityAndReadAt(t *testing.T) {
ctx := context.Background()
cfg, storer, snapshotID := setupLocalityBackup(
ctx, t, fs, dataDir, storeDir, dbPath)
ctx, t, fs, dataDir, storeDir, dbPath, localitySourceBytes)
// Wrap the storer so we can count downloads per blob key.
counter := newCountingStorer(storer)
internal/vaultik/restore_ownership_warning_test.go
+131
View File
@@ -0,0 +1,131 @@
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
storer, err := storage.NewFileStorer(storeDir)
internal/vaultik/restore_plan.go
+8 -1
View File
@@ -31,7 +31,8 @@ var (
// with no further downloads.
// - blobFiles: for each blob, the set of pending files referencing
// it. Used to short-circuit "when this blob lands, which files
// become ready" without a global scan.
// become ready" without a global scan, and by the sweeper to tell
// whether a cached blob is still needed.
type restorePlan struct {
fileBlobs map[types.FileID]map[string]struct{}
blobFiles map[string]map[types.FileID]struct{}
@@ -237,6 +238,12 @@ func (p *restorePlan) filesReferencingBlob(blobHash string) []types.FileID {
return out
}
// pendingFileUsesBlob reports whether any pending file references the
// named blob, whether or not the blob is cached.
func (p *restorePlan) pendingFileUsesBlob(blobHash string) bool {
return len(p.blobFiles[blobHash]) > 0
}
// hasPending reports whether any unfinished files remain.
func (p *restorePlan) hasPending() bool {
return len(p.fileBlobs) > 0
internal/vaultik/restore_plan_test.go
+9 -9
View File
@@ -63,15 +63,6 @@ func TestRunRestoreLoopFailsOnAbandonedFiles(t *testing.T) {
t.Cleanup(func() { _ = cache.Close() })
v := &Vaultik{ctx: ctx}
session := &restoreSession{
v: v,
ctx: ctx,
repos: repos,
sweeper: newRestoreSweeper(ctx, repos, cache, 1),
result: &RestoreResult{},
}
// A file that is still pending but whose uncached-blob set is empty
// and which was never queued as ready: the loop can neither restore
// nor download it. This is the abandonment the guard must catch.
@@ -83,6 +74,15 @@ func TestRunRestoreLoopFailsOnAbandonedFiles(t *testing.T) {
cached: map[string]struct{}{},
}
v := &Vaultik{ctx: ctx}
session := &restoreSession{
v: v,
ctx: ctx,
repos: repos,
sweeper: newRestoreSweeper(plan, cache, 1),
result: &RestoreResult{},
}
err = v.runRestoreLoop(session, plan, map[types.FileID]*database.File{}, 0)
require.ErrorIs(t, err, errRestoreIncomplete)
}
internal/vaultik/restore_skip_errors_test.go
+5 -2
View File
@@ -231,7 +231,8 @@ func (f trailingByteFile) Close() error {
}
// TestRestoreMissingBlobAbortsWithoutSkipErrors checks that a deleted blob
// still ends the restore with an error when SkipErrors is not set.
// still ends the restore with an error when SkipErrors is not set, and
// that the error names the blob once.
func TestRestoreMissingBlobAbortsWithoutSkipErrors(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
@@ -247,6 +248,8 @@ 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
@@ -345,7 +348,7 @@ func backupSingleChunkFiles(
require.NoError(t, afero.WriteFile(fs, path, files[path], 0o644))
}
storer, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
storer, err := storage.NewFileStorer(t.TempDir())
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
chunkSize := int64(64 * 1024)
@@ -100,7 +100,7 @@ func TestDeepVerifyRejectsSwappedDatabaseWithEmptyManifest(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
chunkSize := int64(64 * 1024)
internal/vaultik/restore_sweeper.go
+14 -88
View File
@@ -1,46 +1,30 @@
package vaultik
import (
"context"
"fmt"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
)
// restoreSweeper frees cached blobs once all files that reference any of
// their chunks have been restored. It works as follows:
// restoreSweeper frees cached blobs once no file still to be restored in
// this run needs them. It works as follows:
//
// 1. Callers add a file's ID to an in-memory restored set via
// fileRestored once the file is fully written to disk.
// 2. After each chunk is restored, chunkRestored accumulates a running
// 1. After each chunk is restored, chunkRestored accumulates a running
// byte count.
// 3. When the accumulator crosses a threshold (one hundredth of the
// 2. When the accumulator crosses a threshold (one hundredth of the
// configured blob size — so a sweep runs about a hundred times per
// blob's worth of restored bytes), the sweeper iterates every key in
// the cache. For each cached blob it asks the DB which files
// reference any chunk in that blob, then compares that list against
// the in-memory restored set. If any referencing file is missing
// from the set the blob is kept; otherwise the cache entry is
// deleted.
// the cache and deletes each blob that the restore plan no longer
// needs.
//
// All DB reads happen against the snapshot's temporary metadata DB,
// which is local, indexed, and not under contention — the queries are
// cheap and run at most once per blob per sweep interval.
// The plan drops a file once it is restored or has failed, and holds
// only the files this run restores, so files outside the requested paths
// never keep a blob.
type restoreSweeper struct {
ctx context.Context //nolint:containedctx // ctx bound at construction by design
repos *database.Repositories
plan *restorePlan
cache *blobDiskCache
threshold int64
bytesAccum int64
restored map[string]struct{}
}
// newRestoreSweeper returns a sweeper that triggers eviction every
// `threshold` bytes restored. Callers should pass blob_size_limit/100.
func newRestoreSweeper(
ctx context.Context,
repos *database.Repositories,
plan *restorePlan,
cache *blobDiskCache,
threshold int64,
) *restoreSweeper {
@@ -49,21 +33,12 @@ func newRestoreSweeper(
}
return &restoreSweeper{
ctx: ctx,
repos: repos,
plan: plan,
cache: cache,
threshold: threshold,
restored: make(map[string]struct{}),
}
}
// fileRestored records a file as fully restored. After this call, any
// blob whose only remaining references come from files in the restored
// set may be evicted on the next sweep.
func (s *restoreSweeper) fileRestored(fileID string) {
s.restored[fileID] = struct{}{}
}
// chunkRestored accounts n bytes against the sweep threshold and runs a
// sweep if the threshold has been crossed since the last sweep.
func (s *restoreSweeper) chunkRestored(n int64) {
@@ -76,60 +51,11 @@ func (s *restoreSweeper) chunkRestored(n int64) {
s.sweep()
}
// sweep deletes any cached blob whose chunks are no longer referenced
// by an unrestored file. Per-blob DB failures are logged and the blob
// is kept — we'd rather hold a blob longer than risk a re-download.
// sweep deletes every cached blob that no pending file references.
func (s *restoreSweeper) sweep() {
for _, blobHash := range s.cache.Keys() {
needed, err := s.blobStillNeeded(blobHash)
if err != nil {
log.Debug("sweeper referencing-files query failed",
"blob_hash", blobHash[:16], "error", err)
continue
}
if !needed {
if !s.plan.pendingFileUsesBlob(blobHash) {
s.cache.Delete(blobHash)
}
}
}
// blobStillNeeded returns true if any file that references a chunk in
// this blob has not yet been restored. On any error the function
// returns true — keeping the blob is always the safe answer because we
// can't prove we're done with it.
func (s *restoreSweeper) blobStillNeeded(blobHash string) (bool, error) {
rows, err := s.repos.DB().Conn().QueryContext(s.ctx, `
SELECT DISTINCT fc.file_id
FROM file_chunks fc
JOIN blob_chunks bc ON bc.chunk_hash = fc.chunk_hash
JOIN blobs b ON b.id = bc.blob_id
WHERE b.blob_hash = ?
`, blobHash)
if err != nil {
return true, fmt.Errorf("querying referencing files: %w", err)
}
defer func() { _ = rows.Close() }()
for rows.Next() {
var fileID string
err := rows.Scan(&fileID)
if err != nil {
return true, fmt.Errorf("scanning file_id: %w", err)
}
if _, ok := s.restored[fileID]; !ok {
return true, nil
}
}
err = rows.Err()
if err != nil {
return true, err
}
return false, nil
}
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/restore_sweeper_test.go
+163
View File
@@ -0,0 +1,163 @@
package vaultik //nolint:testpackage // reads the restore blob cache's peak size
import (
"context"
"fmt"
"io"
"path/filepath"
"testing"
"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/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
)
// TestRestoreFreesBlobsNoPendingFileNeeds asserts that the restore cache
// frees a blob once no file still to be restored in this run needs it.
// Every original file has a copy with the same content, so every blob
// holds chunks of copies: a restore that leaves the copies out of its
// paths, or fails on them, must not keep the blobs for them.
func TestRestoreFreesBlobsNoPendingFileNeeds(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
// Small files keep the backup and both restores quick.
const fileBytes = 16 * 1024
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
originalsDir := filepath.Join(dataDir, "originals")
copiesDir := filepath.Join(dataDir, "copies")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
originals := writeFilesWithCopies(t, fs, originalsDir, copiesDir, fileBytes)
ctx := context.Background()
cfg, storer, snapshotID := setupLocalityBackup(
ctx, t, fs, dataDir, storeDir, dbPath, fileBytes)
t.Run("restore by path", func(t *testing.T) {
t.Parallel()
restoreDir := filepath.Join(tempDir, "by-path")
peak, err := restorePeakCachedBlobs(ctx, t, fs, cfg, storer,
&RestoreOptions{
SnapshotID: snapshotID,
TargetDir: restoreDir,
Paths: []string{originalsDir},
})
require.NoError(t, err)
requireRestoredFiles(t, fs, restoreDir, originals)
assert.LessOrEqualf(t, peak, 1,
"peak cached blobs was %d; blobs were kept for unselected files",
peak)
})
t.Run("restore with failed files", func(t *testing.T) {
t.Parallel()
restoreDir := filepath.Join(tempDir, "with-failures")
// A regular file where the copies directory belongs makes every
// copy fail to restore.
blocker := filepath.Join(restoreDir, copiesDir)
require.NoError(t, fs.MkdirAll(filepath.Dir(blocker), 0o755))
require.NoError(t, afero.WriteFile(fs, blocker, nil, 0o644))
peak, err := restorePeakCachedBlobs(ctx, t, fs, cfg, storer,
&RestoreOptions{
SnapshotID: snapshotID,
TargetDir: restoreDir,
SkipErrors: true,
})
require.ErrorIs(t, err, errFilesFailedRestore)
requireRestoredFiles(t, fs, restoreDir, originals)
assert.LessOrEqualf(t, peak, 1,
"peak cached blobs was %d; blobs were kept for failed files", peak)
})
}
// writeFilesWithCopies writes 15 random files of fileBytes into
// originalsDir and a copy of each into copiesDir. With
// setupLocalityBackup given the same size, each file is one chunk and the
// 15 chunks fill 3 blobs. Returns the originals' content by path.
func writeFilesWithCopies(
t *testing.T, fs afero.Fs, originalsDir, copiesDir string, fileBytes int,
) map[string][]byte {
t.Helper()
const fileCount = 15
require.NoError(t, fs.MkdirAll(originalsDir, 0o755))
require.NoError(t, fs.MkdirAll(copiesDir, 0o755))
originals := make(map[string][]byte, fileCount)
for i := range fileCount {
name := fmt.Sprintf("file-%02d.bin", i)
data := randomBytes(t, fileBytes)
original := filepath.Join(originalsDir, name)
originals[original] = data
require.NoError(t, afero.WriteFile(fs, original, data, 0o644))
require.NoError(t, afero.WriteFile(
fs, filepath.Join(copiesDir, name), data, 0o644))
}
return originals
}
// requireRestoredFiles requires every file in want to have been restored
// under restoreDir with its content intact.
func requireRestoredFiles(
t *testing.T, fs afero.Fs, restoreDir string, want map[string][]byte,
) {
t.Helper()
for path, data := range want {
got, err := afero.ReadFile(fs, filepath.Join(restoreDir, path))
require.NoErrorf(t, err, "file missing after restore: %s", path)
require.Equalf(t, data, got, "byte mismatch for %s", path)
}
}
// restorePeakCachedBlobs runs a restore and returns the most blobs its
// cache held at once, together with the restore's error.
func restorePeakCachedBlobs(
ctx context.Context, t *testing.T, fs afero.Fs,
cfg *config.Config, storer storage.Storer, opts *RestoreOptions,
) (int, error) {
t.Helper()
var cache *blobDiskCache
v := &Vaultik{
Config: cfg,
Storage: storer,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
restoreCacheObserver: func(c *blobDiskCache) {
cache = c
},
}
v.SetContext(ctx)
err := v.Restore(opts)
require.NotNil(t, cache, "restoreCacheObserver must fire during restore")
return cache.PeakLen(), err
}
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
rewrittenPath := filepath.Join(dataDir, "small.txt")
internal/vaultik/shallow_verify_test.go
+11 -5
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.
// as checked, and its error must not repeat the cli layer's prefix.
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
@@ -96,6 +96,12 @@ 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,
@@ -110,7 +116,7 @@ func TestShallowVerifyDetectsMissingDatabase(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
@@ -193,7 +199,7 @@ func TestShallowVerifyReportsStatErrorsApartFromMissing(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
@@ -282,7 +288,7 @@ func TestShallowVerifyQuietFailsOnStatErrorAlone(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
internal/vaultik/snapshot.go
+262 -107
View File
@@ -23,6 +23,7 @@ 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")
@@ -38,6 +39,11 @@ 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")
// listRecentLimit caps how many snapshot rows are fetched from the
// local index for listing and purge operations.
const listRecentLimit = 10000
@@ -94,6 +100,13 @@ 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
@@ -116,30 +129,22 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
return fmt.Errorf("prune database: %w", 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)
}
}
}
if len(snapshotNames) == 0 {
return errNoSnapshotsInConfig
snapshotNames, err := v.snapshotNamesToCreate(opts.Snapshots)
if err != nil {
return err
}
// Process each named snapshot
filesUnreadable := 0
for snapIdx, snapName := range snapshotNames {
err = v.createNamedSnapshot(
unreadable, err := v.createNamedSnapshot(
opts, hostname, snapName, snapIdx+1, len(snapshotNames))
if err != nil {
return err
}
filesUnreadable += unreadable
}
// Print overall summary if multiple snapshots
@@ -148,13 +153,34 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
len(snapshotNames), v.UI.Duration(time.Since(overallStartTime)))
}
if opts.Prune {
switch {
case opts.Prune && filesUnreadable > 0:
// An older snapshot may be the only one that still holds a file
// this run could not read.
log.Warn("Skipping post-backup prune",
"files_unreadable", filesUnreadable)
v.UI.Warningf("Skipped the post-backup prune because %d file(s) "+
"could not be read; older snapshots are kept.", filesUnreadable)
case opts.Prune:
err = v.runPostBackupPrune(snapshotNames, opts.KeepNewerThan)
if err != nil {
return fmt.Errorf("%w: %w", ErrPostBackupPruneFailed, err)
}
}
return v.finishCreateSnapshot(filesUnreadable)
}
// 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
@@ -170,6 +196,28 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) 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
@@ -222,16 +270,22 @@ 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 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
// createNamedSnapshot creates a single named snapshot and returns the
// number of entries --skip-errors skipped because it could not read or
// list them.
func (v *Vaultik) createNamedSnapshot(
opts *SnapshotCreateOptions, hostname, snapName string, idx, total int,
) error {
) (int, error) {
snapshotStartTime := time.Now()
if total > 1 {
@@ -240,21 +294,27 @@ func (v *Vaultik) createNamedSnapshot(
resolvedDirs, err := v.resolveSnapshotPaths(snapName)
if err != nil {
return err
return 0, err
}
previousSnapshotID, err := v.previousSnapshotID(snapName)
if err != nil {
return 0, err
}
scanner := v.ScannerFactory(snapshot.ScannerParams{
EnableProgress: !opts.Cron,
UI: v.UI,
Fs: v.Fs,
Exclude: v.Config.GetExcludes(snapName),
SkipErrors: opts.SkipErrors,
EnableProgress: !opts.Cron,
UI: v.UI,
Fs: v.Fs,
Exclude: v.Config.GetExcludes(snapName),
SkipErrors: opts.SkipErrors,
PreviousSnapshotID: previousSnapshotID,
})
snapshotID, err := v.SnapshotManager.CreateSnapshotWithName(
v.ctx, hostname, snapName, v.Globals.Version, v.Globals.Commit)
if err != nil {
return fmt.Errorf("creating snapshot: %w", err)
return 0, fmt.Errorf("creating snapshot: %w", err)
}
log.Info("Beginning snapshot", "snapshot_id", snapshotID, "name", snapName)
@@ -262,12 +322,12 @@ func (v *Vaultik) createNamedSnapshot(
stats, err := v.scanAllDirectories(scanner, resolvedDirs, snapshotID)
if err != nil {
return err
return 0, err
}
err = v.finalizeSnapshotMetadata(snapshotID, stats)
if err != nil {
return err
return 0, err
}
log.Info("Snapshot complete",
@@ -280,7 +340,25 @@ func (v *Vaultik) createNamedSnapshot(
v.printSnapshotSummary(snapshotID, snapshotStartTime, stats)
return nil
return stats.totalFilesUnreadable, 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
}
// resolveSnapshotPaths resolves source directories to absolute paths
@@ -348,6 +426,7 @@ 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
@@ -574,7 +653,7 @@ func (v *Vaultik) PurgeSnapshotsWithOptions(opts *SnapshotPurgeOptions) error {
if len(toDelete) == 0 {
if !opts.Quiet {
v.printlnStdout("No snapshots to delete")
v.UI.Infof("No snapshots to delete.")
}
return nil
@@ -612,7 +691,7 @@ func selectSnapshotsToPurge(
case opts.OlderThan != "":
duration, err := parseDuration(opts.OlderThan)
if err != nil {
return nil, fmt.Errorf("invalid duration: %w", err)
return nil, err
}
cutoff := time.Now().UTC().Add(-duration)
@@ -631,19 +710,19 @@ func selectSnapshotsToPurge(
func (v *Vaultik) confirmAndExecutePurge(
toDelete []SnapshotInfo, force, quiet bool,
) error {
if !quiet {
// Confirm unless --force is used. The list, the prompt and its answer
// bypass the UI: they are an interactive exchange the operator must
// see, so --quiet does not silence them.
if !force {
v.stdoutf("The following snapshots will be deleted:\n\n")
for _, snap := range toDelete {
v.stdoutf(" %s (%s, %s)\n",
snap.ID,
snap.Timestamp.Format("2006-01-02 15:04:05"),
snap.Timestamp.Format(time.DateTime),
ubytes(snap.CompressedSize))
}
}
// Confirm unless --force is used
if !force {
v.stdoutf("\nDelete %d snapshot(s)? [y/N] ", len(toDelete))
var confirm string
@@ -661,7 +740,16 @@ func (v *Vaultik) confirmAndExecutePurge(
return nil
}
} else if !quiet {
v.stdoutf("\nDeleting %d snapshot(s) (--force specified)\n", len(toDelete))
v.UI.Infof("The following snapshots will be deleted:")
for _, snap := range toDelete {
v.UI.Detailf("%s (%s, %s)",
v.UI.Snapshot(snap.ID.String()),
snap.Timestamp.Format(time.DateTime),
ubytes(snap.CompressedSize))
}
v.UI.Infof("Deleting %d snapshot(s) (--force specified).", len(toDelete))
}
// Delete snapshots (both local and remote)
@@ -694,9 +782,9 @@ func (v *Vaultik) confirmAndExecutePurge(
}
if !quiet {
v.stdoutf("Deleted %d snapshot(s)\n", len(toDelete))
v.printlnStdout(
"\nNote: Run 'vaultik prune' to clean up unreferenced remote blobs.")
v.UI.Infof("Deleted %d snapshot(s).", len(toDelete))
v.UI.Noticef("Run '%s' to clean up unreferenced remote blobs.",
pruneCommandHint)
}
return nil
@@ -932,8 +1020,10 @@ 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", errSnapshotVerifyFailed, failure)
return fmt.Errorf("%w: %s", errProblemsInStorage, failure)
}
return nil
@@ -1069,7 +1159,7 @@ func (v *Vaultik) CleanupLocalSnapshots(opts *PruneOptions) error {
log.Info("Removing stale local snapshot record", "snapshot_id", id)
if !opts.JSON {
v.stdoutf("Removing stale local record: %s\n", id)
v.UI.Infof("Removing stale local record: %s.", v.UI.Snapshot(id))
}
err = v.deleteSnapshotFromLocalDB(id)
@@ -1092,9 +1182,9 @@ func (v *Vaultik) CleanupLocalSnapshots(opts *PruneOptions) error {
}
if removed == 0 {
v.printlnStdout("No stale local snapshots found.")
v.UI.Infof("No stale local snapshots found.")
} else {
v.stdoutf("Removed %d stale local snapshot record(s).\n", removed)
v.UI.Infof("Removed %d stale local snapshot record(s).", removed)
}
return nil
@@ -1219,9 +1309,11 @@ const snapshotRemoveCommandHint = "vaultik snapshot remove"
// destination store. Blobs are NOT touched: removing a snapshot's
// blobs requires reading every remaining remote manifest (the remote
// may hold snapshots this host doesn't know about), which is what
// `vaultik prune` is for — the command prints the prune invocation to
// run as a follow-up. When the remote is unreachable the command still
// completes the local-DB removal and warns.
// `vaultik prune` is for — when metadata was removed from the
// destination store, the text output names the prune invocation to run
// as a follow-up. When removing the metadata fails, a snapshot in the
// local index is still removed from it, with a warning; a snapshot
// only on the destination store is an error.
func (v *Vaultik) RemoveSnapshot(
snapshotID string, opts *RemoveOptions,
) (*RemoveResult, error) {
@@ -1243,10 +1335,18 @@ func (v *Vaultik) RemoveSnapshot(
return v.removeSnapshotDryRun(result, snapshotID, opts)
}
if !opts.Force && !opts.JSON && !v.confirmRemoveSnapshot(snapshotID, opts) {
if !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)
@@ -1256,8 +1356,10 @@ func (v *Vaultik) RemoveSnapshot(
}
}
if !opts.LocalOnly {
result.RemoteRemoved = v.removeSnapshotRemote(snapshotID, opts)
result.RemoteRemoved, err = v.removeSnapshotRemote(
snapshotID, inLocalIndex, markerErr, opts)
if err != nil {
return result, err
}
if v.SnapshotManager != nil {
@@ -1273,14 +1375,15 @@ func (v *Vaultik) RemoveSnapshot(
}
if inLocalIndex {
v.stdoutf("Removed snapshot '%s' from local database\n", snapshotID)
v.UI.Infof("Removed snapshot '%s' from local database.",
v.UI.Snapshot(snapshotID))
}
if result.RemoteRemoved {
v.printlnStdout("Removed snapshot metadata from remote storage")
v.stdoutf("\nNote: The removed snapshot's blobs remain on the remote. "+
v.UI.Infof("Removed snapshot metadata from remote storage.")
v.UI.Noticef("The removed snapshot's blobs remain on the remote. "+
"Run '%s' to delete any blobs no longer referenced by any "+
"remaining remote snapshot.\n", pruneCommandHint)
"remaining remote snapshot.", pruneCommandHint)
}
return result, nil
@@ -1291,7 +1394,9 @@ 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.
// 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.
func (v *Vaultik) findSnapshotToRemove(
snapshotID string, opts *RemoveOptions,
) (bool, error) {
@@ -1311,6 +1416,11 @@ 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)
@@ -1336,22 +1446,28 @@ func (v *Vaultik) removeSnapshotDryRun(
return result, v.outputRemoveJSON(result)
}
v.stdoutf("Would remove snapshot: %s\n", snapshotID)
v.UI.Infof("Would remove snapshot: %s.", v.UI.Snapshot(snapshotID))
if !opts.LocalOnly {
v.printlnStdout("Would also remove snapshot metadata from " +
"remote storage (blobs untouched)")
v.UI.Infof("Would also remove snapshot metadata from " +
"remote storage (blobs untouched).")
}
v.printlnStdout("[Dry run - no changes made]")
v.UI.Noticef("Dry run: no changes made.")
return result, nil
}
// confirmRemoveSnapshot prompts for confirmation before removing a
// snapshot. Returns false (treating EOF/read errors as "no") unless the
// user answers "y".
// 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.
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)
@@ -1379,19 +1495,40 @@ func (v *Vaultik) confirmRemoveSnapshot(snapshotID string, opts *RemoveOptions)
}
// removeSnapshotRemote strips the snapshot's metadata from the
// destination store, warning and proceeding on failure: the local-DB
// removal has already happened, so the user is told the remote half
// didn't finish and to run `vaultik snapshot remove` for the snapshot
// again once the destination store is reachable (`vaultik prune` never
// removes snapshot metadata). Returns true when the remote removal
// succeeded and deleted something.
func (v *Vaultik) removeSnapshotRemote(snapshotID string, opts *RemoveOptions) bool {
// 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).
func (v *Vaultik) removeSnapshotRemote(
snapshotID string, inLocalIndex bool, markerErr error,
opts *RemoveOptions,
) (bool, error) {
if opts.LocalOnly {
return false, nil
}
log.Info("Removing snapshot metadata from remote storage",
"snapshot_id", snapshotID)
remoteKey := snapshot.RemoteSnapshotKey(snapshotID)
var deleted int
err := markerErr
if err == nil {
deleted, err = v.deleteRemoteSnapshotByKey(
snapshot.RemoteSnapshotKey(snapshotID))
}
if err != nil && !inLocalIndex {
return false, fmt.Errorf(
"removing snapshot metadata from destination store: %w", err)
}
deleted, err := v.deleteRemoteSnapshotByKey(remoteKey)
if err != nil {
log.Warn("Could not remove snapshot metadata from remote storage; "+
"run '"+snapshotRemoveCommandHint+"' with the snapshot's ID "+
@@ -1406,17 +1543,19 @@ func (v *Vaultik) removeSnapshotRemote(snapshotID string, opts *RemoveOptions) b
err, snapshotRemoveCommandHint, snapshotID)
}
return false
return false, nil
}
return deleted > 0
return deleted > 0, nil
}
// RemoveAllSnapshots removes every snapshot known to the local
// 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.
// 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.
func (v *Vaultik) RemoveAllSnapshots(opts *RemoveOptions) (*RemoveResult, error) {
err := v.EnsureStorageBinding()
if err != nil {
@@ -1429,11 +1568,15 @@ func (v *Vaultik) RemoveAllSnapshots(opts *RemoveOptions) (*RemoveResult, error)
}
// remoteKeys is the set of metadata/<key>/ subdirectories on the
// destination store; failures are downgraded to a warning so a
// permission-denied or unreachable remote can't block a local-only
// remove.
// 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.
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)
}
@@ -1456,7 +1599,7 @@ func (v *Vaultik) RemoveAllSnapshots(opts *RemoveOptions) (*RemoveResult, error)
if len(localSnaps) == 0 && len(orphanRemoteKeys) == 0 {
if !opts.JSON {
v.printlnStdout("No snapshots found")
v.UI.Infof("No snapshots found.")
}
return &RemoveResult{}, nil
@@ -1495,8 +1638,7 @@ 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; callers must treat that as "no remote info available," not
// fatal.
// listed, or is not present by checkDestinationMarker.
func (v *Vaultik) listAllRemoteSnapshotKeys() ([]string, error) {
log.Info("Listing all remote snapshots")
@@ -1545,6 +1687,11 @@ func (v *Vaultik) listAllRemoteSnapshotKeys() ([]string, error) {
}
}
err := v.checkDestinationMarker()
if err != nil {
return nil, err
}
return keys, nil
}
@@ -1561,27 +1708,27 @@ func (v *Vaultik) handleRemoveAllDryRun(
}
if !opts.JSON {
v.stdoutf("Would remove %d local snapshot(s):\n", len(localSnaps))
v.UI.Infof("Would remove %d local snapshot(s):", len(localSnaps))
for _, id := range localSnaps {
v.stdoutf(" %s\n", id)
v.UI.Detailf("%s", v.UI.Snapshot(id))
}
if !opts.LocalOnly {
if len(orphanRemoteKeys) > 0 {
v.stdoutf("Would also remove %d orphan remote snapshot key(s):\n",
v.UI.Infof("Would also remove %d orphan remote snapshot key(s):",
len(orphanRemoteKeys))
for _, key := range orphanRemoteKeys {
v.stdoutf(" %s\n", key)
v.UI.Detailf("%s", key)
}
} else {
v.printlnStdout("Would also remove snapshot metadata from " +
"remote storage (blobs untouched)")
v.UI.Infof("Would also remove snapshot metadata from " +
"remote storage (blobs untouched).")
}
}
v.printlnStdout("[Dry run - no changes made]")
v.UI.Noticef("Dry run: no changes made.")
}
if opts.JSON {
@@ -1630,10 +1777,10 @@ func (v *Vaultik) executeRemoveAll(
return result, v.outputRemoveJSON(result)
}
v.stdoutf("Removed %d snapshot(s)\n", len(result.SnapshotsRemoved))
v.UI.Infof("Removed %d snapshot(s).", len(result.SnapshotsRemoved))
if !opts.LocalOnly && result.RemoteRemoved {
v.printlnStdout("Removed snapshot metadata from remote storage")
v.UI.Infof("Removed snapshot metadata from remote storage.")
}
return result, nil
@@ -1675,10 +1822,12 @@ func (v *Vaultik) deleteIncompleteSnapshot(snapshotIDStr string, id any) bool {
return true
}
// 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.
// 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.
func (v *Vaultik) removeAllLocalSnapshots(
localSnaps []string, opts *RemoveOptions, result *RemoveResult,
) int {
@@ -1687,6 +1836,19 @@ 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",
@@ -1697,17 +1859,6 @@ 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)
}
@@ -1890,13 +2041,17 @@ func (v *Vaultik) PruneDatabase() (*PruneResult, error) {
snapshotsRemain := countDiff(snapshotCountBefore, &result.SnapshotsDeleted)
v.UI.Completef("Pruned local index database.")
v.UI.Detailf("Incomplete snapshots: %s removed (%s remain).",
v.UI.Detailf("Incomplete snapshots: %s removed "+
"(total snapshots left in the local index: %s).",
countText(&result.SnapshotsDeleted), countText(snapshotsRemain))
v.UI.Detailf("Orphaned files: %s removed (%s remain).",
v.UI.Detailf("Orphaned files: %s removed "+
"(total files left in the local index: %s).",
countText(result.FilesDeleted), countText(fileCountAfter))
v.UI.Detailf("Orphaned chunks: %s removed (%s remain).",
v.UI.Detailf("Orphaned chunks: %s removed "+
"(total chunks left in the local index: %s).",
countText(result.ChunksDeleted), countText(chunkCountAfter))
v.UI.Detailf("Orphaned blobs: %s removed (%s remain).",
v.UI.Detailf("Orphaned blobs: %s removed "+
"(total blobs left in the local index: %s).",
countText(result.BlobsDeleted), countText(blobCountAfter))
return result, nil
internal/vaultik/snapshot_deleted_count_test.go
+251
View File
@@ -0,0 +1,251 @@
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
+11 -4
View File
@@ -49,13 +49,19 @@ 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},
openErr: os.ErrPermission, skipErrors: true,
wantErr: vaultik.ErrFilesUnreadable},
// 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 {
@@ -87,7 +93,7 @@ func TestSnapshotSummaryCountsFileNotStoredAsFailed(t *testing.T) {
"src": {Paths: []string{srcDir}},
}
store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
store, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
db, err := database.New(ctx, cfg.IndexPath)
@@ -99,10 +105,11 @@ func TestSnapshotSummaryCountsFileNotStoredAsFailed(t *testing.T) {
v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
v.UI = ui.NewWithColor(out, false)
require.NoError(t, v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
err = 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.go
+33 -4
View File
@@ -61,7 +61,9 @@ const tabPadding = 3
// attempt is made to recover or fabricate the human ID.
//
// Snapshots in the local index with no counterpart on the destination
// store are reported as drift below the table.
// store are reported as drift below the table, unless the local index
// is bound to a different destination than the configured one: that is
// reported instead.
//
// If remote listing fails (unmounted volume, permission denied,
// network), we degrade to local-only with a warning. List never fails
@@ -103,7 +105,26 @@ func (v *Vaultik) ListSnapshots(jsonOutput bool) error {
return snapshots[i].Timestamp.After(snapshots[j].Timestamp)
})
stored, configured, err := v.storageBinding()
if err != nil {
return err
}
// A local index bound to another destination describes that one, so
// its records are expected to be missing here, and prune refuses to
// run. The binding is reported instead of advising prune.
boundElsewhere := stored != "" && stored != configured
if jsonOutput {
// stdout holds only the document, so this goes to the logger.
if boundElsewhere {
log.Warn("Local index is bound to a different backup "+
"destination; to proceed, revert storage_url (or the s3.* "+
"endpoint, bucket and prefix) to the bound destination, "+
"or run 'vaultik database delete'",
"bound_to", stored, "configured", configured)
}
if remoteErr == nil {
v.reportJSONListingLimits(listing)
}
@@ -125,8 +146,13 @@ func (v *Vaultik) ListSnapshots(jsonOutput bool) error {
}
}
if boundElsewhere {
v.UI.Warningf("%v\n%s", errStorageBindingMismatch,
buildBindingMismatchMessage(stored, configured))
}
if remoteErr == nil {
v.reportListDrift(snapshots, listing)
v.reportListDrift(snapshots, listing, boundElsewhere)
}
return nil
@@ -432,7 +458,9 @@ func (v *Vaultik) snapshotInfoFromLocal(ls *database.Snapshot) SnapshotInfo {
// reportListDrift prints the reconciliation notes the merged table
// cannot express on its own: local records with no counterpart on the
// destination store, plus counts of remote snapshots that were
// unreadable or omitted.
// unreadable or omitted. Local records are not reported when
// boundElsewhere is set: ListSnapshots has already said why they are
// missing.
//
// This is what remains of the old reportRemoteDrift, and it no longer
// touches the destination store. Its remote-only half collapsed into
@@ -441,6 +469,7 @@ func (v *Vaultik) snapshotInfoFromLocal(ls *database.Snapshot) SnapshotInfo {
// so `snapshot list` lists the destination exactly once per invocation.
func (v *Vaultik) reportListDrift(
snapshots []SnapshotInfo, listing *remoteSnapshotListing,
boundElsewhere bool,
) {
var localOnly []string
@@ -450,7 +479,7 @@ func (v *Vaultik) reportListDrift(
}
}
if len(localOnly) > 0 {
if len(localOnly) > 0 && !boundElsewhere {
v.UI.Warningf("%d local snapshot record(s) not found in backup "+
"destination store:", len(localOnly))
internal/vaultik/snapshot_list_test.go
+71
View File
@@ -122,6 +122,9 @@ 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: "",
@@ -421,6 +424,74 @@ func TestListSnapshots_LocalOnlyReportedAsDrift(t *testing.T) {
assert.NotContains(t, out, "snapshot cleanup")
}
// TestListSnapshots_BoundElsewhereDoesNotAdvisePrune covers a changed
// storage_url: the local index is still bound to the old destination,
// so its records are missing from the new one. prune refuses to run in
// that state, so the listing must give the choices prune gives instead
// of advising it.
func TestListSnapshots_BoundElsewhereDoesNotAdvisePrune(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
const (
oldURL = "file:///mnt/backups/old"
newURL = "file:///mnt/backups/new"
)
env := newListEnv(t)
env.v.Config.StorageURL = newURL
require.NoError(t, env.v.Repositories.LocalMeta.Set(context.Background(),
database.LocalMetaKeyStorageURL, oldURL))
env.addLocal(t, listLocalID, time.Date(2026, 3, 1, 10, 0, 0, 0, time.UTC))
err := env.v.ListSnapshots(false)
require.NoError(t, err)
out := env.stdout.String()
assert.Contains(t, out, listLocalID)
assert.Contains(t, out,
"local index is bound to a different backup destination")
assert.Contains(t, out, oldURL)
assert.Contains(t, out, newURL)
assert.Contains(t, out, "revert storage_url")
assert.Contains(t, out, "vaultik database delete")
assert.NotContains(t, out, "vaultik prune")
}
// TestListSnapshots_JSONReportsBoundElsewhere is the --json side of the
// test above. Every local row comes out with remote_present false, which
// a script reads as stale local records unless it is told, on stderr,
// that the local index is bound to a different destination.
//
//nolint:paralleltest // captureProcessStderr replaces os.Stderr
func TestListSnapshots_JSONReportsBoundElsewhere(t *testing.T) {
const (
oldURL = "file:///mnt/backups/old"
newURL = "file:///mnt/backups/new"
)
env := newListEnv(t)
env.v.Config.StorageURL = newURL
require.NoError(t, env.v.Repositories.LocalMeta.Set(context.Background(),
database.LocalMetaKeyStorageURL, oldURL))
env.addLocal(t, listLocalID, time.Date(2026, 3, 1, 10, 0, 0, 0, time.UTC))
stderr := captureProcessStderr(t, func() {
require.NoError(t, env.v.ListSnapshots(true))
})
rows := decodeListJSON(t, env.stdout.String())
require.Len(t, rows, 1)
assert.Equal(t, listLocalID, rows[0].ID)
assert.Contains(t, stderr, "bound to a different backup destination")
assert.Contains(t, stderr, oldURL)
assert.Contains(t, stderr, newURL)
assert.Contains(t, stderr, "revert storage_url")
assert.Contains(t, stderr, "vaultik database delete")
}
// TestListSnapshots_UnreachableRemoteDegrades covers the promise in the
// doc comment: an unreachable destination is a warning plus local-only
// output, never a failure.
internal/vaultik/snapshot_skip_errors_test.go
+209 -1
View File
@@ -3,6 +3,7 @@ package vaultik_test
import (
"context"
"fmt"
"os"
"path/filepath"
"testing"
@@ -45,7 +46,7 @@ func TestSkipErrorsBackupStopsOnIndexErrorRecordingDirectory(t *testing.T) {
"tree": {Paths: []string{srcDir}},
}
store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
store, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
db, err := database.New(ctx, cfg.IndexPath)
@@ -73,3 +74,210 @@ 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
+117 -1
View File
@@ -13,6 +13,7 @@ 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"
@@ -84,7 +85,7 @@ func newSummaryEnv(t *testing.T) *summaryEnv {
"split": {Paths: []string{dirOne, dirTwo}},
}
inner, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
inner, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
store := faultstore.New(inner)
@@ -188,6 +189,42 @@ 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.
@@ -248,6 +285,85 @@ 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/storage_bind.go
+23 -10
View File
@@ -45,17 +45,9 @@ func (v *Vaultik) EnsureStorageBinding() error {
return nil
}
configured := v.Config.StorageURL
if configured == "" {
// The s3.* form: bind on its endpoint, bucket and prefix,
// written the way storage_url would name the same destination.
s3 := v.Config.S3
configured = "s3://" + s3.Bucket + "/" + s3.Prefix + "?endpoint=" + s3.Endpoint
}
stored, err := v.Repositories.LocalMeta.Get(v.ctx, database.LocalMetaKeyStorageURL)
stored, configured, err := v.storageBinding()
if err != nil {
return fmt.Errorf("reading local storage binding: %w", err)
return err
}
if stored == "" {
@@ -78,6 +70,27 @@ func (v *Vaultik) EnsureStorageBinding() error {
errStorageBindingMismatch, buildBindingMismatchMessage(stored, configured))
}
// storageBinding returns the destination the local index is bound to
// ("" when no binding is recorded yet), then the configured destination
// written the same way. It records nothing, so a read-only command can
// call it.
func (v *Vaultik) storageBinding() (string, string, error) {
configured := v.Config.StorageURL
if configured == "" {
// The s3.* form: bind on its endpoint, bucket and prefix,
// written the way storage_url would name the same destination.
s3 := v.Config.S3
configured = "s3://" + s3.Bucket + "/" + s3.Prefix + "?endpoint=" + s3.Endpoint
}
stored, err := v.Repositories.LocalMeta.Get(v.ctx, database.LocalMetaKeyStorageURL)
if err != nil {
return "", "", fmt.Errorf("reading local storage binding: %w", err)
}
return stored, configured, nil
}
// buildBindingMismatchMessage assembles the multi-line explanation
// shown when the local index is bound to a different destination than
// the currently-configured one (the first line lives in the
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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
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(filepath.Join(tempDir, "remote"))
store, err := storage.NewFileStorer(t.TempDir())
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 S3", "blob_count", len(blobs))
log.Info("Verifying blob existence in storage", "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("checking blob %s in storage: %w",
return fmt.Errorf("could not check 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 := filepath.Join(tempDir, "remote")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)