sneak/vaultik
1
0
Fork 0
Code Issues 6 Pull Requests 3 Actions 242 Packages Projects Releases Wiki Activity

Compare commits

base: sneak/vaultik:issue-239-destination-marker
Branches Tags
sneak/vaultik:main sneak/vaultik:issue-305-unchanged-dirs-symlinks sneak/vaultik:issue-310-skip-errors-exit-status sneak/vaultik:issue-239-destination-marker sneak/vaultik:next sneak/vaultik:issue-316-ownership-warning sneak/vaultik:issue-337-purge-keeps-metadata
..
compare: sneak/vaultik:a92646f7a61a4a69300bfd89a9db139b1d59e2c4
Branches Tags
sneak/vaultik:issue-305-unchanged-dirs-symlinks sneak/vaultik:issue-310-skip-errors-exit-status sneak/vaultik:issue-239-destination-marker sneak/vaultik:next sneak/vaultik:issue-316-ownership-warning sneak/vaultik:issue-337-purge-keeps-metadata sneak/vaultik:main
1 Commits
issue-239-destination-marker .. a92646f7a6
Author SHA1 Message Date
sneak a92646f7a6 Stop restore --verify re-reporting files that failed to restore (closes #323)
check / check (push) Waiting to run
Details 
With --skip-errors, a file that failed to restore was verified anyway,
failed again because it was never written, and was added to the same
failure list as the restore failure. restore --verify then listed it
twice and called every entry a checksum mismatch.

Verification now skips the files that failed to restore and keeps its
own failures in a separate list, so failed restores and failed
verifications are reported apart, each path once. The restore still
exits non-zero. The tests cover a restore with skipped files where
nothing fails verification, and one where another restored file also
fails it.

Judgement call: the second test has its own trailing-byte file-system
wrapper; the one in restore_perms_test.go is in the internal test package.

Model: opus-5-5
 2026-10-13 14:19:39 +00:00
101 changed files with 1001 additions and 5628 deletions
Expand all files Collapse all files
ARCHITECTURE.md
+4 -17
View File
@@ -279,8 +279,8 @@ Key methods:
- `Scan(ctx, path, snapshotID)` → Main scan operation
Scan phases:
1. **Phase 1**: Walk directory, identify files needing processing
2. **Phase 1b**: Count as deleted the files that the previous snapshot of the same name lists, the walk did not find, and are gone from disk; a file that is excluded, or inside an excluded directory, is not counted
1. **Phase 0**: Detect deleted files from previous snapshots
2. **Phase 1**: Walk directory, identify files needing processing
3. **Phase 2**: Process files (chunk → pack → upload)
#### SnapshotManager
@@ -311,8 +311,6 @@ Repository interfaces:
```
CreateSnapshot(opts)
│
├─► markDestination() // Refuse a destination without the marker, then write it
│
├─► PruneDatabase() // Critical: avoid dedup errors
│
@@ -322,13 +320,13 @@ CreateSnapshot(opts)
│ │
│ ├─► scanner.Scan(ctx, path, snapshotID)
│ │ │
│ │ ├─► Phase 0: detectDeletedFiles()
│ │ │
│ │ ├─► Phase 1: scanPhase()
│ │ │ Walk directory
│ │ │ Check file metadata changes
│ │ │ Build list of files to process
│ │ │
│ │ ├─► Phase 1b: detectDeletedFiles()
│ │ │
│ │ └─► Phase 2: processPhase()
│ │ For each file:
│ │ chunker.ChunkReaderStreaming()
@@ -369,8 +367,6 @@ CreateSnapshot(opts)
```
bucket/
├── vaultik-destination.txt # Marker written by every backup
│
├── blobs/
│ └── {hash[0:2]}/
│ └── {hash[2:4]}/
@@ -382,15 +378,6 @@ bucket/
└── manifest.json.zst # Blob list (for pruning/verification)
```
While the local index holds snapshots, a destination without
`vaultik-destination.txt` is treated as not present
(`checkDestinationMarker` in `internal/vaultik/destination_marker.go`):
`snapshot create` refuses to write to it, and listing it fails as for a
destination that cannot be listed. An unplugged volume's empty mount point
is therefore never taken 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
Dockerfile
+3 -24
View File
@@ -5,16 +5,7 @@
FROM golangci/golangci-lint:v2.14.0@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f AS lint
WORKDIR /src
COPY go.mod go.sum ./
# Without the time limit a stalled connection to the module proxy holds
# this step, and every build on the host sharing it, until the kernel
# drops the connection, which can take an hour. The limit is well above
# the three minutes a working download can take on a busy build host.
RUN for attempt in 1 2 3; do \
timeout 300 go mod download && exit 0; \
echo "go mod download attempt $attempt failed or ran over 300s" >&2; \
done; \
echo "module download failed: giving up after 3 attempts" >&2; \
exit 1
RUN go mod download
COPY . .
# `golangci-lint run` silently ignores an unknown top-level key in
# .golangci.yml, such as a misspelt `linters:`; `config verify` fails on it.
@@ -27,13 +18,7 @@ RUN golangci-lint run --config .golangci.yml ./...
FROM golang:1.26.1@sha256:cd78d88e00afadbedd272f977d375a6247455f3a4b1178f8ae8bbcb201743a8a AS test
WORKDIR /src
COPY go.mod go.sum ./
# Limited and retried as in the lint phase above.
RUN for attempt in 1 2 3; do \
timeout 300 go mod download && exit 0; \
echo "go mod download attempt $attempt failed or ran over 300s" >&2; \
done; \
echo "module download failed: giving up after 3 attempts" >&2; \
exit 1
RUN go mod download
COPY . .
RUN go test -timeout 90s -race -cover ./... || \
{ echo "--- Rerunning with -v for details ---"; \
@@ -51,13 +36,7 @@ RUN apk add --no-cache git
RUN git config --system --add safe.directory /src
WORKDIR /src
COPY go.mod go.sum ./
# Limited and retried as in the lint phase above.
RUN for attempt in 1 2 3; do \
timeout 300 go mod download && exit 0; \
echo "go mod download attempt $attempt failed or ran over 300s" >&2; \
done; \
echo "module download failed: giving up after 3 attempts" >&2; \
exit 1
RUN go mod download
COPY . .
# The VERSION build arg when one is given, otherwise
README.md
+30 -90
View File
@@ -24,10 +24,6 @@ grep 'public key' vaultik_backup_private_key.txt
vaultik config set age_recipients.0 age1YOUR_PUBLIC_KEY_HERE
vaultik config set storage_url "file:///Volumes/usbstick/mybackup"
# create the destination directory; vaultik never creates it, so a backup
# to a volume that is not plugged in fails instead of filling the disk
mkdir /Volumes/usbstick/mybackup
# macOS only: grant your terminal app Full Disk Access first
# (System Settings → Privacy & Security → Full Disk Access), otherwise
# the backup will abort with a permission error on protected directories
@@ -275,17 +271,8 @@ existing file. Created with mode `0600` since it will contain credentials.
**`config set`**: Set a scalar config value by dotted YAML path
(e.g. `vaultik config set compression_level 9`,
`vaultik config set storage_url "file:///mnt/backups"`). Comments and
formatting in the file are preserved. Missing keys along the path are
created: as a list when the next path element is a number (so
`vaultik config set age_recipients.0 age1...` works on a file without
`age_recipients`), otherwise as a map. If the config loads, a change
after which it would not, such as `vaultik config set compression_level 99`,
is refused and the file is left unchanged. A config that does not load,
such as the one `config init` writes before `storage_url` is set or one
with a `${ENV:...}` reference to a variable not set in this shell, is
checked one setting at a time: only a change after which the changed
setting cannot be read, such as one giving it the wrong type (a single
value where a list belongs or a word where a number belongs), is refused.
formatting in the file are preserved; intermediate maps are created as
needed.
**`snapshot create`**: Perform incremental backup of configured snapshots.
* Optional snapshot names argument to create specific snapshots (default: all)
@@ -302,17 +289,12 @@ value where a list belongs or a word where a number belongs), is refused.
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
and three sizes per snapshot (compressed remote size; total
uncompressed chunk size; size of the chunks that snapshot stored that
were not stored before). Both chunk sizes are recorded when the
snapshot's backup runs.
uncompressed chunk size; size of chunks newly referenced by that
snapshot).
Listing the destination store does **not** require the age secret key,
so it works in vaultik's intended configuration, where the backed-up
@@ -325,33 +307,24 @@ only the hash, so hostname and snapshot name exist solely in the local
index and in the encrypted per-snapshot database. Snapshots found only
on the destination store are therefore listed as
`<remote only:<abbreviated remote key>>` and show `<remote only>` in
the uncompressed and "new chunk" columns, which come only from the
local index. Their timestamp and compressed size are real,
the uncompressed and "new chunk" columns, which can only be computed
from the local index. Their timestamp and compressed size are real,
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. 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`.
invocation that reconciles them.
If the destination store cannot be listed (unmounted volume,
permission denied, network down), the command warns, falls back to the
local index alone, and still exits zero. It does the same when the
local index holds snapshots and the destination has no
`vaultik-destination.txt`, as when a volume mounted at the destination
is unplugged and leaves its empty mount point behind.
local index alone, and still exits zero.
* `--json`: Output in JSON format. Each entry carries `locally_tracked`
(whether the snapshot is in the local index), `remote_key` (the full
64-character storage key), and `remote_present` (whether it was seen
on the destination store, or `null` if the destination could not be
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.
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.
**`snapshot verify`**: Verify snapshot integrity.
* Default (shallow): checks that every blob the manifest lists is present in
@@ -377,21 +350,16 @@ 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. 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
`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
cleanup (files, chunks, blobs the snapshot was the last referrer for)
runs automatically. If removing the snapshot's metadata from the
destination store fails (for example because the store is unreachable,
or the local index holds snapshots and the destination has no
`vaultik-destination.txt`), the local-DB removal still completes and a
warning is emitted; run `vaultik snapshot remove <snapshot-id>` again
once the store is reachable to remove the snapshot's metadata from it
(`vaultik prune` does not). For a snapshot that is only on the
destination store, that failure is an error. To wipe everything on the
destination in one go, use `vaultik remote nuke --force`.
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`.
* `--local-only`: Skip remote cleanup; only touch the local index
* `--dry-run`: Show what would be deleted without deleting
* `--force`: Skip confirmation prompt
@@ -404,9 +372,7 @@ destination in one go, use `vaultik remote nuke --force`.
store — its remote key (or an unambiguous leading part of it) as shown
by `snapshot list`. See
[restoring on another machine](#restoring-on-another-machine).
* Optional path arguments to restore specific files/directories (default: all).
A path that matches nothing in the snapshot is named in a warning, and the
command exits non-zero after restoring the paths that match.
* Optional path arguments to restore specific files/directories (default: all)
* Preserves file permissions, timestamps, ownership (ownership requires root),
symlinks, and empty directories
* `--verify`: After restoring, verify every restored file's chunk hashes
@@ -422,16 +388,10 @@ 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 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.
manual entry point for the same work.
* `--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.
`--force` does.
**`info`**: Display system configuration, storage settings, encryption
recipients, and local database statistics.
@@ -450,13 +410,10 @@ under `blobs/` whose name is not a blob hash is not counted as a blob,
since `prune` never deletes it.
* `--json`: Output as JSON
**`remote nuke`**: Delete every object under `metadata/` and `blobs/` on
the backup destination store, whatever its name, and then
`vaultik-destination.txt`, leaving the bucket prefix empty. Destructive
and irreversible. This is the single supported way to wipe the entire
destination store. 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.
**`remote nuke`**: Delete every snapshot's metadata and every blob from the
backup destination store, leaving the bucket prefix empty. Destructive and
irreversible. This is the single supported way to wipe the entire
destination store.
* `--force`: Required to confirm destruction.
**`database delete`**: Delete the local SQLite state database file
@@ -481,12 +438,7 @@ object store. Credentials are read from `s3.access_key_id` and
a local or mounted filesystem. Useful for testing or backing up to a NAS. The
path must be absolute; a relative one is refused when the config loads.
Percent-escapes in the path are decoded, so `my%20stick` and `my stick` name
the same directory. The directory must exist before the first backup: vaultik
never creates it. A directory on a removable volume is gone while the volume is
not mounted, so a backup then fails instead of writing to the disk under the
mount point. The mount point itself stays behind when the volume is unplugged:
there only `vaultik-destination.txt` stops such a backup, and only while the
local index holds snapshots.
the same directory.
**Rclone** (`rclone://remote/path`): Uses rclone's 70+ supported cloud
providers. Requires rclone to be configured separately (`rclone config`).
@@ -517,7 +469,6 @@ For an implementation-level view of the internals — the data model, the
```
<bucket>/<prefix>/
├── vaultik-destination.txt # Marker written by every backup
├── blobs/
│ └── <aa>/<bb>/<full_blob_hash>
└── metadata/
@@ -526,15 +477,6 @@ For an implementation-level view of the internals — the data model, the
└── manifest.json.zst # Unencrypted blob list (for pruning)
```
* `vaultik-destination.txt` holds one fixed line of text, with no host
name, path or time. While the local index holds snapshots, a
destination without it is treated as not present: `snapshot create`
refuses to write to it, `prune` and `snapshot purge` 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
@@ -754,10 +696,8 @@ 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
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.
`database delete` confirmation prompt is also written this way and
always shown: it is 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
cmd/vaultik/dockermoddownload_test.go
-45
View File
@@ -1,45 +0,0 @@
package main_test
import (
"strings"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// TestDockerfileBoundsEveryModuleDownload fails unless every
// `go mod download` in the Dockerfile runs under a time limit, is tried
// a fixed number of times, and then fails the build with a message that
// names the module download (issue #351). Like the version tests, this
// parses the Dockerfile; that a stalled download really is cut off and
// retried was checked by hand.
func TestDockerfileBoundsEveryModuleDownload(t *testing.T) {
t.Parallel()
var downloads []string
for _, instruction := range instructions(t, productDockerfile) {
if strings.Contains(instruction, "go mod download") {
downloads = append(downloads, instruction)
}
}
require.NotEmpty(t, downloads, "%s must download modules",
productDockerfile)
for _, download := range downloads {
assert.Contains(t, download, "timeout 300 go mod download",
"%s: a module download must have a time limit: %s",
productDockerfile, download)
assert.Contains(t, download, "for attempt in 1 2 3",
"%s: a module download must be retried: %s",
productDockerfile, download)
assert.Contains(t, download, "module download failed",
"%s: a module download that never succeeds must say so: %s",
productDockerfile, download)
assert.True(t, strings.HasSuffix(download, "exit 1"),
"%s: a module download that never succeeds must fail the"+
" build: %s", productDockerfile, download)
}
}
config.example.yml
+1 -2
View File
@@ -302,8 +302,7 @@ storage_url: "rclone://myremote/path/to/backups"
# Average chunk size for content-defined chunking
# Smaller chunks = better deduplication but more metadata
# Minimum 1MB
# Supports: 10MB, 5M, 1GB, 64MiB, etc.
# Supports: 10MB, 5M, 1GB, 500KB, 64MiB, etc.
# Default: 10MB
#chunk_size: 10MB
docs/DATAMODEL.md
+2 -4
View File
@@ -90,7 +90,7 @@ Stores information about packed, compressed, and encrypted blob files.
- `created_ts` (INTEGER NOT NULL) - Creation timestamp
- `finished_ts` (INTEGER) - Finalization timestamp (NULL if in progress)
- `uncompressed_size` (INTEGER NOT NULL DEFAULT 0) - Total size of chunks before compression
- `compressed_size` (INTEGER NOT NULL DEFAULT 0) - Size after compression and encryption. Once uploaded, the size of the object in storage: when the blob was already stored, under another compression level or other recipients, this can differ from the size of the local copy
- `compressed_size` (INTEGER NOT NULL DEFAULT 0) - Size after compression and encryption
- `uploaded_ts` (INTEGER) - Upload completion timestamp (NULL if not uploaded)
**Purpose:** Tracks blob lifecycle from creation through upload. The UUID primary key allows immediate association of chunks with blobs.
@@ -119,10 +119,8 @@ Tracks backup snapshots.
- `completed_at` (INTEGER) - Completion timestamp (NULL if in progress)
- `file_count` (INTEGER) - Number of files in snapshot
- `chunk_count` (INTEGER) - Number of chunks this snapshot stored that were not stored before
- `new_chunk_size` (INTEGER) - Total size of those chunks before compression; `snapshot list` shows it as NEW CHUNK SIZE
- `blob_count` (INTEGER) - Number of blobs this snapshot created
- `total_size` (INTEGER) - Total size of all files
- `uncompressed_chunk_size` (INTEGER) - Total size before compression of the distinct chunks the snapshot's files reference, recorded when its backup ran; `snapshot list` shows it as UNCOMPRESSED SIZE
- `blob_size` (INTEGER) - Total compressed size of all referenced blobs
- `blob_uncompressed_size` (INTEGER) - Total uncompressed size of all referenced blobs
- `compression_ratio` (REAL) - Compression ratio achieved
@@ -185,7 +183,7 @@ Tracks blob upload metrics.
- `UPDATE blobs SET blob_hash = ?, finished_ts = ?` - Finalize blob after packing
4. **Upload**
- `UPDATE blobs SET uploaded_ts = ?, compressed_size = ?` - Mark blob as uploaded, with the size of the object in storage (the upload is skipped when the blob is already stored)
- `UPDATE blobs SET uploaded_ts = ?` - Mark blob as uploaded
- `INSERT INTO uploads` - Record upload metrics with snapshot_id
- `INSERT INTO snapshot_blobs` - Associate blob with snapshot
docs/REPOSTRUCTURE.md
+1 -6
View File
@@ -4,7 +4,7 @@ This document describes the structure and organization of data stored in the S3
## Overview
Vaultik stores all backup data in an S3-compatible object store. The repository consists of two main components, plus a marker file:
Vaultik stores all backup data in an S3-compatible object store. The repository consists of two main components:
1. **Blobs** - The actual backup data (content-addressed, encrypted)
2. **Metadata** - Snapshot information and manifests (partially encrypted)
@@ -12,7 +12,6 @@ Vaultik stores all backup data in an S3-compatible object store. The repository
```
<bucket>/<prefix>/
├── vaultik-destination.txt
├── blobs/
│ └── <hash[0:2]>/
│ └── <hash[2:4]>/
@@ -25,10 +24,6 @@ Vaultik stores all backup data in an S3-compatible object store. The repository
The metadata subdirectory is named with the **remote key**, a one-way hash of the snapshot ID, not with the human-readable snapshot ID itself. See [Remote Key Derivation](#remote-key-derivation).
## Marker File (`vaultik-destination.txt`)
Every backup writes this file at the root before it uploads anything. It holds one fixed line of plain text and names no host, path or time. While the local index holds snapshots, a destination without it is treated as not present: `snapshot create` refuses to write to it, and `prune`, `snapshot purge`, `snapshot remove` and `snapshot list` 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
go.mod
+1 -1
View File
@@ -22,7 +22,6 @@ 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
@@ -257,6 +256,7 @@ 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
+10 -6
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"
@@ -146,12 +146,16 @@ 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. 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.
// 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).
func cleanStartupError(err error) error {
return &startupError{msg: dig.RootCause(err).Error()}
msg := err.Error()
if idx := strings.LastIndex(msg, "): "); idx >= 0 {
msg = msg[idx+3:]
}
return &startupError{msg: msg}
}
// RunApp starts the fx application, blocks until it is asked to stop, and
internal/cli/app_test.go
+40 -47
View File
@@ -2,65 +2,58 @@ 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()
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)
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",
},
}
app := fx.New(
fx.NopLogger,
fx.Supply(config.Path(path)),
config.Module,
fx.Invoke(func(*config.Config) {}),
)
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
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")
//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)
}
})
}
}
internal/cli/config.go
+27 -129
View File
@@ -8,7 +8,6 @@ import (
"os/exec"
"path/filepath"
"reflect"
"slices"
"strconv"
"strings"
"unicode/utf8"
@@ -45,9 +44,6 @@ var (
errNeedNumericIndex = errors.New("key is a list; use a numeric index")
errIndexOutOfRange = errors.New("index out of range")
errNotMapOrList = errors.New("key is not a map or list")
errWouldNotLoad = errors.New(
"vaultik would not load the config after this change, " +
"so the file was not changed")
)
const defaultConfigTemplate = `# vaultik configuration
@@ -224,7 +220,7 @@ storage_url: ""
# Average chunk size for content-defined chunking (FastCDC).
# Smaller = better deduplication but more metadata overhead.
# Minimum 1MB. Accepts: 1MB, 10M, 64MiB, etc.
# Accepts: 1MB, 10M, 64KB, etc.
# Default: 10MB
# chunk_size: 10MB
@@ -333,15 +329,8 @@ 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 $EDITOR is the point
ed := exec.CommandContext(cmd.Context(),
"sh", "-c", editor+` "$@"`, editor, path)
ed := exec.CommandContext(cmd.Context(), editor, path)
ed.Stdin = os.Stdin
ed.Stdout = os.Stdout
ed.Stderr = os.Stderr
@@ -402,17 +391,8 @@ func newConfigSetCommand() *cobra.Command {
Use: "set <key> <value>",
Short: "Set a config value by dotted path (e.g. compression_level 5)",
Long: `Sets a scalar config value addressed by dotted YAML path and writes
the file back, preserving comments and formatting. Missing keys along
the path are created: as a list when the next path element is a
number, otherwise as a map.
If the config loads, a change after which it would not, such as
compression_level 99, is refused and the file is left unchanged. A
config that does not load, such as the one config init writes before
storage_url is set or one with a ${ENV:...} reference to a variable
not set here, is checked one setting at a time: only a change after
which the changed setting cannot be read, such as one giving it the
wrong type, is refused.
the file back, preserving comments and formatting. Intermediate maps
are created as needed.
Examples:
vaultik config set storage_url "file:///mnt/backups"
@@ -442,14 +422,7 @@ func writeConfigSet(out *ui.Writer, path, key, value string) error {
return err
}
oldData, err := marshalConfigYAML(root)
if err != nil {
return fmt.Errorf("marshaling config: %w", err)
}
keys := strings.Split(key, ".")
err = yamlPathSet(root, keys, value)
err = yamlPathSet(root, strings.Split(key, "."), value)
if err != nil {
return err
}
@@ -459,21 +432,6 @@ func writeConfigSet(out *ui.Writer, path, key, value string) error {
return fmt.Errorf("marshaling config: %w", err)
}
setting, err := yamlPathOnly(root, keys)
if err != nil {
return err
}
settingData, err := marshalConfigYAML(setting)
if err != nil {
return fmt.Errorf("marshaling config: %w", err)
}
err = checkConfigChange(oldData, data, settingData)
if err != nil {
return fmt.Errorf("%w: %w", errWouldNotLoad, err)
}
err = os.WriteFile(path, data, configFileMode)
if err != nil {
return fmt.Errorf("writing config file: %w", err)
@@ -495,58 +453,6 @@ func writeConfigSet(out *ui.Writer, path, key, value string) error {
return nil
}
// checkConfigChange returns the reason vaultik would not load newData, the
// config after a change, if the change brings that failure in. If oldData,
// the config before it, loads, the new one must load too. A config that
// does not load, such as one still being filled in or one with a ${...}
// reference that cannot be filled in here, is checked one setting at a
// time: settingData, the changed setting on its own, must decode into the
// config type.
func checkConfigChange(oldData, newData, settingData []byte) error {
oldCfg, err := config.Parse(oldData)
if err == nil && oldCfg.Validate() == nil {
newCfg, err := config.Parse(newData)
if err != nil {
return err
}
return newCfg.Validate()
}
_, err = config.Parse(settingData)
return err
}
// yamlPathOnly returns a document holding only the value at the dotted key
// path in root, inside the maps and lists that lead to it there.
func yamlPathOnly(root *yaml.Node, keys []string) (*yaml.Node, error) {
node, err := yamlPathGet(root, keys)
if err != nil {
return nil, err
}
for i, key := range slices.Backward(keys) {
parent, err := yamlPathGet(root, keys[:i])
if err != nil {
return nil, err
}
if parent.Kind == yaml.SequenceNode {
node = &yaml.Node{
Kind: yaml.SequenceNode, Content: []*yaml.Node{node},
}
} else {
keyNode := &yaml.Node{Kind: yaml.ScalarNode, Value: key}
node = &yaml.Node{
Kind: yaml.MappingNode, Content: []*yaml.Node{keyNode, node},
}
}
}
return &yaml.Node{Kind: yaml.DocumentNode, Content: []*yaml.Node{node}}, nil
}
// marshalConfigYAML renders a config document tree with 2-space indentation,
// matching defaultConfigTemplate. yaml.Marshal defaults to 4 spaces, which
// would reindent the whole file on the first `config set` despite the promise
@@ -653,8 +559,8 @@ func yamlPathGet(root *yaml.Node, keys []string) (*yaml.Node, error) {
return node, nil
}
// yamlPathSet navigates a dotted key path, creating missing keys as needed,
// and sets the final key to the given scalar value. Numeric path
// yamlPathSet navigates a dotted key path, creating intermediate maps as
// needed, and sets the final key to the given scalar value. Numeric path
// components index into sequences; an index equal to the sequence length
// appends a new element (e.g. "age_recipients.1" on a 1-element list).
func yamlPathSet(root *yaml.Node, keys []string, value string) error {
@@ -667,12 +573,12 @@ func yamlPathSet(root *yaml.Node, keys []string, value string) error {
node = node.Content[0]
}
for i := range keys {
for i, key := range keys {
last := i == len(keys)-1
switch node.Kind {
case yaml.MappingNode:
node = yamlSetInMapping(node, keys, i, value, last)
node = yamlSetInMapping(node, key, value, last)
case yaml.SequenceNode:
next, err := yamlSetInSequence(node, keys, i, value, last)
if err != nil {
@@ -741,16 +647,14 @@ func yamlField(typ reflect.Type, key string) (reflect.StructField, bool) {
return reflect.StructField{}, false
}
// yamlSetInMapping resolves (creating if needed) the value node for the
// path element keys[i] within a mapping node, setting it to value when it
// is the final path element, and returns the node to descend into.
func yamlSetInMapping(
node *yaml.Node, keys []string, i int, value string, last bool,
) *yaml.Node {
// yamlSetInMapping resolves (creating if needed) the value node for key
// within a mapping node, setting it to value when it is the final path
// element, and returns the node to descend into.
func yamlSetInMapping(node *yaml.Node, key, value string, last bool) *yaml.Node {
var valueNode *yaml.Node
for j := 0; j+1 < len(node.Content); j += 2 {
if node.Content[j].Value == keys[i] {
if node.Content[j].Value == key {
valueNode = node.Content[j+1]
break
@@ -758,8 +662,13 @@ func yamlSetInMapping(
}
if valueNode == nil {
keyNode := &yaml.Node{Kind: yaml.ScalarNode, Value: keys[i]}
valueNode = newPathNode(keys, i, value)
keyNode := &yaml.Node{Kind: yaml.ScalarNode, Value: key}
valueNode = &yaml.Node{Kind: yaml.MappingNode}
if last {
valueNode = &yaml.Node{Kind: yaml.ScalarNode, Value: value}
}
node.Content = append(node.Content, keyNode, valueNode)
} else if last {
setScalar(valueNode, value)
@@ -787,7 +696,12 @@ func yamlSetInSequence(
}
if idx == len(node.Content) {
node.Content = append(node.Content, newPathNode(keys, i, value))
newNode := &yaml.Node{Kind: yaml.MappingNode}
if last {
newNode = &yaml.Node{Kind: yaml.ScalarNode, Value: value}
}
node.Content = append(node.Content, newNode)
} else if last {
setScalar(node.Content[idx], value)
}
@@ -795,22 +709,6 @@ func yamlSetInSequence(
return node.Content[idx], nil
}
// newPathNode returns the node to create for the missing path element
// keys[i]: the value when it is the final path element, otherwise an empty
// list when the next path element is a number and an empty map when not.
func newPathNode(keys []string, i int, value string) *yaml.Node {
if i == len(keys)-1 {
return &yaml.Node{Kind: yaml.ScalarNode, Value: value}
}
_, err := strconv.Atoi(keys[i+1])
if err == nil {
return &yaml.Node{Kind: yaml.SequenceNode}
}
return &yaml.Node{Kind: yaml.MappingNode}
}
// setScalar overwrites a node in place with a plain scalar value.
func setScalar(n *yaml.Node, value string) {
n.Kind = yaml.ScalarNode
internal/cli/config_test.go
+5 -235
View File
@@ -58,17 +58,14 @@ func TestDefaultConfigTemplateParses(t *testing.T) {
}
}
// testRecipient is a valid age public key.
const testRecipient = "age1278m9q7dp3chsh2dcy82qk27v047zywyvtxwnj4cvt0z65jw6a7q5dqhfj"
// TestConfigSetRecipientOnFreshConfig follows the README quickstart: on the
// file `config init` writes, `config set age_recipients.0` and
// `config set storage_url` give a config that loads with that recipient.
// Neither is refused, although the config does not load until both are set;
// once it loads, a recipient that is not a valid key is.
func TestConfigSetRecipientOnFreshConfig(t *testing.T) {
t.Parallel()
const recipient = "age1278m9q7dp3chsh2dcy82qk27v047zywyvtxwnj4cvt0z65jw6a7q5dqhfj"
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(defaultConfigTemplate), configFileMode)
@@ -78,7 +75,7 @@ func TestConfigSetRecipientOnFreshConfig(t *testing.T) {
out := ui.NewWithColor(&bytes.Buffer{}, false)
err = writeConfigSet(out, path, "age_recipients.0", testRecipient)
err = writeConfigSet(out, path, "age_recipients.0", recipient)
if err != nil {
t.Fatalf("config set age_recipients.0: %v", err)
}
@@ -93,211 +90,8 @@ func TestConfigSetRecipientOnFreshConfig(t *testing.T) {
t.Fatalf("config.Load: %v", err)
}
if len(cfg.AgeRecipients) != 1 || cfg.AgeRecipients[0] != testRecipient {
t.Errorf("age_recipients = %v, want [%s]", cfg.AgeRecipients, testRecipient)
}
err = writeConfigSet(out, path, "age_recipients.0", "notakey")
if err == nil || !strings.Contains(err.Error(), "not a valid recipient") {
t.Errorf("config set age_recipients.0 notakey gives error %v, "+
"want one saying it is not a valid recipient", err)
}
_, err = config.Load(path)
if err != nil {
t.Errorf("config.Load after the refused change: %v", err)
}
}
// configWithoutRecipients loads, but has no age_recipients key and no
// snapshot named work.
const configWithoutRecipients = `storage_url: file:///mnt/backups
snapshots:
home:
paths:
- "~"
`
// configWithUnsetReference loads only where VAULTIK_TEST_UNSET_SECRET is
// set, as a backup job's environment might set it. No test sets it.
const configWithUnsetReference = configWithoutRecipients + `s3:
secret_access_key: ${ENV:VAULTIK_TEST_UNSET_SECRET}
`
// configWithLevelReference returns configWithoutRecipients with a ${FILE:...}
// reference on compression_level to a file holding 9, so that the config
// loads once the reference is filled in.
func configWithLevelReference(t *testing.T) string {
t.Helper()
levelPath := filepath.Join(t.TempDir(), "level")
err := os.WriteFile(levelPath, []byte("9"), configFileMode)
if err != nil {
t.Fatalf("write level: %v", err)
}
return configWithoutRecipients +
"compression_level: ${FILE:" + levelPath + "}\n"
}
// TestConfigSetIndexUnderMissingKey checks that a list index under a key
// the file does not have creates a list, and that the result loads.
func TestConfigSetIndexUnderMissingKey(t *testing.T) {
t.Parallel()
tests := []struct {
key string
value string
field func(cfg *config.Config) []string
}{
{"age_recipients.0", testRecipient,
func(cfg *config.Config) []string { return cfg.AgeRecipients }},
{"snapshots.work.paths.0", "/srv/work",
func(cfg *config.Config) []string { return cfg.Snapshots["work"].Paths }},
}
for _, tt := range tests {
t.Run(tt.key, func(t *testing.T) {
t.Parallel()
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(configWithoutRecipients), configFileMode)
if err != nil {
t.Fatalf("write config: %v", err)
}
err = writeConfigSet(ui.NewWithColor(&bytes.Buffer{}, false),
path, tt.key, tt.value)
if err != nil {
t.Fatalf("config set %s: %v", tt.key, err)
}
cfg, err := config.Load(path)
if err != nil {
t.Fatalf("config.Load: %v", err)
}
got := tt.field(cfg)
if len(got) != 1 || got[0] != tt.value {
t.Errorf("%s gives %v, want [%s]", tt.key, got, tt.value)
}
})
}
}
// TestConfigSetKeepsFileThatWouldNotLoad checks that config set refuses a
// change after which the config would not load, with an error giving the
// reason, and leaves the file as it was. On the file `config init` writes,
// which does not load until storage_url is set, and on one that cannot be
// read here, only a value of the wrong type is refused.
func TestConfigSetKeepsFileThatWouldNotLoad(t *testing.T) {
t.Parallel()
levelReference := configWithLevelReference(t)
tests := []struct {
config string
key string
value string
reason string
}{
// Index 1 of the empty list the missing key gives.
{configWithoutRecipients, "age_recipients.1", testRecipient,
"index out of range"},
// A list set to a single value.
{configWithoutRecipients, "snapshots.home.paths", "/srv",
"into []string"},
{configWithoutRecipients, "chunk_size", "fast",
"invalid size format"},
// Values of the right type that fail validation.
{configWithoutRecipients, "compression_level", "99",
"compression_level must be between 1 and 19"},
{configWithoutRecipients, "chunk_size", "1KB",
"chunk_size must be at least 1MB"},
// With its reference filled in, the config loads.
{levelReference, "blob_size_limit", "1MB",
"blob_size_limit must be at least"},
// The type check on a config that does not load yet.
{defaultConfigTemplate, "snapshots.apps.paths", "/srv",
"into []string"},
// The type check on a config that cannot be read here.
{configWithUnsetReference, "snapshots.home.paths", "/x",
"cannot unmarshal !!str `/x`"},
}
for _, tt := range tests {
t.Run(tt.key+" "+tt.value, func(t *testing.T) {
t.Parallel()
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(tt.config), configFileMode)
if err != nil {
t.Fatalf("write config: %v", err)
}
err = writeConfigSet(ui.NewWithColor(&bytes.Buffer{}, false),
path, tt.key, tt.value)
if err == nil || !strings.Contains(err.Error(), tt.reason) {
t.Errorf("config set %s %s gives error %v, want one saying %q",
tt.key, tt.value, err, tt.reason)
}
data, err := os.ReadFile(path) //nolint:gosec // G304: test-controlled path
if err != nil {
t.Fatalf("read config: %v", err)
}
if string(data) != tt.config {
t.Errorf("config set %s changed the file to:\n%s",
tt.key, data)
}
})
}
}
// TestConfigSetRefusesOnlyItsOwnFailure checks that setting another key
// works on a config with a ${...} reference on compression_level, which
// loads because loading fills the reference in, on one whose
// compression_level already fails to load, and on one with a reference
// that cannot be filled in here.
func TestConfigSetRefusesOnlyItsOwnFailure(t *testing.T) {
t.Parallel()
configs := map[string]string{
"reference": configWithLevelReference(t),
"failing": configWithoutRecipients + "compression_level: fast\n",
"unset reference": configWithUnsetReference,
}
for name, configYAML := range configs {
t.Run(name, func(t *testing.T) {
t.Parallel()
path := filepath.Join(t.TempDir(), "config.yml")
err := os.WriteFile(path, []byte(configYAML), configFileMode)
if err != nil {
t.Fatalf("write config: %v", err)
}
err = writeConfigSet(ui.NewWithColor(&bytes.Buffer{}, false),
path, "hostname", "myhost")
if err != nil {
t.Fatalf("config set hostname: %v", err)
}
data, err := os.ReadFile(path) //nolint:gosec // G304: test-controlled path
if err != nil {
t.Fatalf("read config: %v", err)
}
if !strings.Contains(string(data), "hostname: myhost") {
t.Errorf("config set hostname wrote:\n%s", data)
}
})
if len(cfg.AgeRecipients) != 1 || cfg.AgeRecipients[0] != recipient {
t.Errorf("age_recipients = %v, want [%s]", cfg.AgeRecipients, recipient)
}
}
@@ -647,30 +441,6 @@ 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
+1 -7
View File
@@ -101,8 +101,7 @@ func TestEntryPruneJSONStdoutIsExactlyOneDocument(t *testing.T) {
// writeHermeticPruneConfig builds a config over a temp directory with an
// empty destination directory and, if seedStale is set, creates the
// index database up front with one snapshot record that has no
// counterpart on the destination store, and gives the destination the
// marker a backup writes. Returns the config path.
// counterpart on the destination store. Returns the config path.
func writeHermeticPruneConfig(t *testing.T, seedStale bool) string {
t.Helper()
@@ -132,11 +131,6 @@ func writeHermeticPruneConfig(t *testing.T, seedStale bool) string {
if seedStale {
seedStaleSnapshotRecord(t, indexPath)
// While the local index holds a snapshot, prune fails on a
// destination without the marker a backup writes.
require.NoError(t, os.WriteFile(
filepath.Join(storeDir, "vaultik-destination.txt"), nil, 0o600))
}
return configPath
internal/cli/entry_prune_quiet_test.go
-123
View File
@@ -1,123 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
import (
"os"
"path/filepath"
"strings"
"testing"
"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, 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))
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_purge_test.go
-75
View File
@@ -1,75 +0,0 @@
package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
import (
"context"
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/snapshot"
)
// Words and flags of `snapshot purge` used to build argument vectors
// below.
const (
cmdPurge = "purge"
flagOlderThan = "--older-than"
flagForce = "--force"
)
// TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails makes
// the local index refuse to delete an old snapshot and checks that
// `snapshot purge` exits non-zero and leaves that snapshot's metadata on
// the destination store. It used to log the error, delete the metadata
// and exit 0.
//
// `snapshot create --prune` runs the same purge, but cannot be driven
// this way: the refusal also breaks the backup's metadata export, which
// deletes the other snapshots from its copy of the local index.
//
//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
func TestEntrySnapshotPurgeKeepsMetadataWhenLocalIndexDeleteFails(t *testing.T) {
configPath := writeHermeticPruneConfig(t, false)
dir := filepath.Dir(configPath)
indexPath := filepath.Join(dir, "index.sqlite")
// seedStaleSnapshotRecord writes an old snapshot to the local index
// only; the manifest planted here puts it on the destination store
// 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))
manifestPath := filepath.Join(manifestDir, "manifest.json.zst")
require.NoError(t, os.WriteFile(manifestPath, []byte("stub"), 0o600))
ctx := context.Background()
db, err := database.New(ctx, indexPath)
require.NoError(t, err)
_, err = db.Conn().ExecContext(ctx, `
CREATE TRIGGER refuse_snapshot_delete BEFORE DELETE ON snapshots
BEGIN SELECT RAISE(ABORT, 'simulated index error'); END`)
require.NoError(t, err)
require.NoError(t, db.Close())
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/snapshot.go
+6 -9
View File
@@ -270,9 +270,8 @@ 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. 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.
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.
@@ -281,12 +280,10 @@ 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 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.
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).
To wipe the entire destination store and start over, use 'vaultik remote
nuke --force' — it is the single supported entry point for that.`,
internal/cli/snapshot_restore.go
-2
View File
@@ -30,8 +30,6 @@ This command will restore files from the specified snapshot to the
target directory.
If no paths are specified, all files are restored.
If paths are specified, only matching files/directories are restored.
A path that matches nothing in the snapshot is named in a warning, and
the command exits non-zero after restoring the paths that match.
The snapshot may be named by its ID or, when restoring on a host with no
local index, by the remote key that 'snapshot list' prints for a
internal/config/config.go
+28 -47
View File
@@ -4,7 +4,6 @@
package config
import (
"bytes"
"errors"
"fmt"
"os"
@@ -30,15 +29,13 @@ 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. 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).
// Defaults and validation bounds for tunable settings.
const (
defaultBlobSizeLimit = Size(10 * 1000 * 1000 * 1000) // 10GB
defaultChunkSize = Size(10 * 1000 * 1000) // 10MB
defaultBlobSizeLimit = Size(10 * 1024 * 1024 * 1024) // 10GB
defaultChunkSize = Size(10 * 1024 * 1024) // 10MB
defaultS3PartSize = Size(5 * 1024 * 1024) // 5MiB
defaultCompressionLevel = 3
minChunkSize = 1000 * 1000 // 1MB
minChunkSize = 1024 * 1024 // 1MB
minCompressionLevel = 1
maxCompressionLevel = 19
// S3 accepts a multipart upload part from 5MiB to 5GiB.
@@ -236,48 +233,14 @@ func New(path Path) (*Config, error) {
return cfg, nil
}
// Load reads the configuration file at path, parses it with Parse, warns
// when others can read the file, and validates the configuration.
// Returns an error if the file cannot be read, parsed, or if validation
// fails.
// Load reads and parses the configuration file from the specified path.
// It applies default values for optional fields, performs environment variable
// substitution using smartconfig, and validates the configuration.
// The configuration file should be in YAML format. Returns an error if the file
// cannot be read, parsed, or if validation fails.
func Load(path string) (*Config, error) {
data, err := os.ReadFile(path) //nolint:gosec // G304: config path is operator-supplied
if err != nil {
return nil, fmt.Errorf("failed to load config file: %w", err)
}
cfg, err := Parse(data)
if err != nil {
return nil, err
}
// Check config file permissions (warn if world or group readable)
//nolint:gosec // G703: config path is operator-supplied by design
info, statErr := os.Stat(path)
if statErr == nil {
mode := info.Mode().Perm()
if mode&0044 != 0 { // group or world readable
log.Warn(cfg.readableByOthersWarning(),
"path", path,
"mode", fmt.Sprintf("%04o", mode),
"recommendation", "chmod 600 "+path)
}
}
err = cfg.Validate()
if err != nil {
return nil, fmt.Errorf("invalid config: %w", err)
}
return cfg, nil
}
// Parse reads YAML config data as Load does, without validating it. It
// applies default values for optional fields, fills in ${...} references
// using smartconfig, and expands ~ in paths.
func Parse(data []byte) (*Config, error) {
// Load config using smartconfig for interpolation
sc, err := smartconfig.NewFromReader(bytes.NewReader(data))
sc, err := smartconfig.NewFromConfigPath(path)
if err != nil {
return nil, fmt.Errorf("failed to load config file: %w", err)
}
@@ -339,6 +302,24 @@ func Parse(data []byte) (*Config, error) {
cfg.S3.Region = "us-east-1"
}
// Check config file permissions (warn if world or group readable)
//nolint:gosec // G703: config path is operator-supplied by design
info, statErr := os.Stat(path)
if statErr == nil {
mode := info.Mode().Perm()
if mode&0044 != 0 { // group or world readable
log.Warn(cfg.readableByOthersWarning(),
"path", path,
"mode", fmt.Sprintf("%04o", mode),
"recommendation", "chmod 600 "+path)
}
}
err = cfg.Validate()
if err != nil {
return nil, fmt.Errorf("invalid config: %w", err)
}
return cfg, nil
}
internal/config/config_test.go
-75
View File
@@ -337,81 +337,6 @@ 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)
}
})
}
}
// 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/blob_chunks.go
+6 -1
View File
@@ -58,7 +58,12 @@ func (r *BlobChunkRepository) GetByBlobID(
return nil, fmt.Errorf("querying blob chunks: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var blobChunks []*BlobChunk
internal/database/blobs.go
+12 -10
View File
@@ -83,7 +83,12 @@ func (r *BlobRepository) GetAll(ctx context.Context) (map[string]*Blob, error) {
return nil, fmt.Errorf("querying blobs: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
out := make(map[string]*Blob)
@@ -154,16 +159,13 @@ func (r *BlobRepository) UpdateFinished(
return nil
}
// UpdateUploaded marks a blob as uploaded and records the size of the
// stored object as its compressed size. That size can differ from the
// local copy's when an identical blob was already stored with another
// compression level or other recipients.
// UpdateUploaded marks a blob as uploaded
func (r *BlobRepository) UpdateUploaded(
ctx context.Context, tx *sql.Tx, id string, storedSize int64,
ctx context.Context, tx *sql.Tx, id string,
) error {
query := `
UPDATE blobs
SET uploaded_ts = ?, compressed_size = ?
UPDATE blobs
SET uploaded_ts = ?
WHERE id = ?
`
@@ -171,9 +173,9 @@ func (r *BlobRepository) UpdateUploaded(
var err error
if tx != nil {
_, err = tx.ExecContext(ctx, query, now, storedSize, id)
_, err = tx.ExecContext(ctx, query, now, id)
} else {
_, err = r.db.ExecWithLog(ctx, query, now, storedSize, id)
_, err = r.db.ExecWithLog(ctx, query, now, id)
}
if err != nil {
internal/database/blobs_test.go
+2 -6
View File
@@ -122,8 +122,8 @@ func TestBlobRepositoryUpdates(t *testing.T) {
t.Errorf("expected compressed size 500, got %d", updated.CompressedSize)
}
// Test UpdateUploaded, with a stored object larger than the local copy
err = repo.UpdateUploaded(ctx, nil, blob.ID.String(), 600)
// Test UpdateUploaded
err = repo.UpdateUploaded(ctx, nil, blob.ID.String())
if err != nil {
t.Fatalf("failed to update blob as uploaded: %v", err)
}
@@ -141,10 +141,6 @@ func TestBlobRepositoryUpdates(t *testing.T) {
if uploaded.UploadedTS.Before(now.Add(-1 * time.Second)) {
t.Error("uploaded timestamp should be around test time")
}
if uploaded.CompressedSize != 600 {
t.Errorf("expected the stored size 600, got %d", uploaded.CompressedSize)
}
}
func TestBlobRepositoryDuplicate(t *testing.T) {
internal/database/chunk_files.go
+18 -3
View File
@@ -61,7 +61,12 @@ func (r *ChunkFileRepository) GetByChunkHash(
return nil, fmt.Errorf("querying chunk files: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanChunkFiles(rows)
}
@@ -82,7 +87,12 @@ func (r *ChunkFileRepository) GetByFilePath(
return nil, fmt.Errorf("querying chunk files: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanChunkFiles(rows)
}
@@ -102,7 +112,12 @@ func (r *ChunkFileRepository) GetByFileID(
return nil, fmt.Errorf("querying chunk files: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanChunkFiles(rows)
}
internal/database/chunks.go
+12 -2
View File
@@ -107,7 +107,12 @@ func (r *ChunkRepository) GetByHashes(
return nil, fmt.Errorf("querying chunks: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var chunks []*Chunk
@@ -147,7 +152,12 @@ func (r *ChunkRepository) ListUnpacked(
return nil, fmt.Errorf("querying unpacked chunks: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var chunks []*Chunk
internal/database/chunks_ext.go
+6 -1
View File
@@ -38,7 +38,12 @@ func (r *ChunkRepository) list(ctx context.Context, query string) ([]*Chunk, err
return nil, fmt.Errorf("querying chunks: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var chunks []*Chunk
internal/database/errors.go
+12
View File
@@ -0,0 +1,12 @@
package database
import (
"fmt"
"os"
)
// Fatalf prints an error message to stderr and exits with status 1
func Fatalf(format string, args ...any) {
fmt.Fprintf(os.Stderr, "FATAL: "+format+"\n", args...)
os.Exit(1)
}
internal/database/file_chunks.go
+18 -3
View File
@@ -62,7 +62,12 @@ func (r *FileChunkRepository) GetByPath(
return nil, fmt.Errorf("querying file chunks: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanFileChunks(rows)
}
@@ -83,7 +88,12 @@ func (r *FileChunkRepository) GetByFileID(
return nil, fmt.Errorf("querying file chunks: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanFileChunks(rows)
}
@@ -107,7 +117,12 @@ func (r *FileChunkRepository) GetByPathTx(
return nil, fmt.Errorf("querying file chunks: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
fileChunks, err := r.scanFileChunks(rows)
LogSQL("GetByPathTx", "Complete", path, "count", len(fileChunks))
internal/database/files.go
+22 -41
View File
@@ -175,7 +175,12 @@ func (r *FileRepository) ListModifiedSince(
return nil, fmt.Errorf("querying files: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var files []*File
@@ -251,46 +256,12 @@ func (r *FileRepository) ListUnderPath(
return nil, fmt.Errorf("querying files: %w", err)
}
defer func() { _ = rows.Close() }()
var files []*File
for rows.Next() {
file, err := r.scanFileRows(rows)
defer func() {
err := rows.Close()
if err != nil {
return nil, fmt.Errorf("scanning file: %w", err)
Fatalf("failed to close rows: %v", err)
}
files = append(files, file)
}
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
@@ -333,7 +304,12 @@ func (r *FileRepository) ListIDsWithChunksNotInUploadedBlobs(
return nil, fmt.Errorf("querying files: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var ids []types.FileID
@@ -364,7 +340,12 @@ func (r *FileRepository) ListAll(ctx context.Context) ([]*File, error) {
return nil, fmt.Errorf("querying files: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var files []*File
internal/database/files_test.go
-59
View File
@@ -212,65 +212,6 @@ func TestFileRepositoryListUnderPath(t *testing.T) {
}
}
// ListUnderPathInSnapshot leaves out files outside path and files the
// snapshot does not list, though another snapshot lists them.
func TestFileRepositoryListUnderPathInSnapshot(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
files := database.NewFileRepository(db)
snapshots := database.NewSnapshotRepository(db)
listed := map[string][]string{
"one": {"/src/a.txt", "/src2/c.txt"},
"two": {"/src/b.txt"},
}
for snapshotID, paths := range listed {
err := snapshots.Create(ctx, nil, &database.Snapshot{
ID: types.SnapshotID(snapshotID),
Hostname: "host",
StartedAt: time.Now(),
})
if err != nil {
t.Fatalf("failed to create snapshot %s: %v", snapshotID, err)
}
for _, path := range paths {
err := files.Create(ctx, nil, &database.File{
Path: types.FilePath(path),
MTime: time.Now().Truncate(time.Second),
Mode: 0644,
})
if err != nil {
t.Fatalf("failed to create %s: %v", path, err)
}
err = snapshots.AddFile(ctx, nil, snapshotID, path)
if err != nil {
t.Fatalf("failed to add %s to %s: %v", path, snapshotID, err)
}
}
}
found, err := files.ListUnderPathInSnapshot(ctx, "/src", "one")
if err != nil {
t.Fatalf("failed to list files: %v", err)
}
got := make([]string, 0, len(found))
for _, f := range found {
got = append(got, f.Path.String())
}
if !slices.Equal(got, []string{"/src/a.txt"}) {
t.Errorf("got %q, want only /src/a.txt", got)
}
}
func TestFileRepositorySymlink(t *testing.T) {
t.Parallel()
internal/database/repositories.go
+18 -23
View File
@@ -3,7 +3,6 @@ package database
import (
"context"
"database/sql"
"errors"
"fmt"
)
@@ -61,24 +60,22 @@ func (r *Repositories) WithTx(ctx context.Context, fn TxFunc) error {
defer func() {
if p := recover(); p != nil {
// The panic is the failure to report, so a rollback error
// is dropped.
_ = tx.Rollback()
rollbackErr := tx.Rollback()
if rollbackErr != nil {
Fatalf("failed to rollback transaction: %v", rollbackErr)
}
panic(p)
} else if err != nil {
rollbackErr := tx.Rollback()
if rollbackErr != nil {
Fatalf("failed to rollback transaction: %v", rollbackErr)
}
}
}()
err = fn(ctx, tx)
if err != nil {
// Once ctx is cancelled, database/sql rolls the transaction
// back itself and Rollback returns sql.ErrTxDone.
rollbackErr := tx.Rollback()
if rollbackErr != nil && !errors.Is(rollbackErr, sql.ErrTxDone) {
return fmt.Errorf("%w; rolling back transaction: %w",
err, rollbackErr)
}
return err
}
@@ -106,24 +103,22 @@ func (r *Repositories) WithReadTx(ctx context.Context, fn TxFunc) error {
defer func() {
if p := recover(); p != nil {
// The panic is the failure to report, so a rollback error
// is dropped.
_ = tx.Rollback()
rollbackErr := tx.Rollback()
if rollbackErr != nil {
Fatalf("failed to rollback transaction: %v", rollbackErr)
}
panic(p)
} else if err != nil {
rollbackErr := tx.Rollback()
if rollbackErr != nil {
Fatalf("failed to rollback transaction: %v", rollbackErr)
}
}
}()
err = fn(ctx, tx)
if err != nil {
// Once ctx is cancelled, database/sql rolls the transaction
// back itself and Rollback returns sql.ErrTxDone.
rollbackErr := tx.Rollback()
if rollbackErr != nil && !errors.Is(rollbackErr, sql.ErrTxDone) {
return fmt.Errorf("%w; rolling back transaction: %w",
err, rollbackErr)
}
return err
}
internal/database/repositories_test.go
-158
View File
@@ -4,7 +4,6 @@ import (
"context"
"database/sql"
"errors"
"strings"
"testing"
"time"
@@ -236,125 +235,6 @@ func TestRepositoriesTransactionRollback(t *testing.T) {
}
}
// When the context is cancelled during the body, database/sql rolls the
// transaction back itself, so WithTx's own rollback finds it already
// done. WithTx must return the body's error alone, without that rollback.
func TestRepositoriesTransactionContextCancelled(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
repos := database.NewRepositories(db)
err := repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
file := &database.File{
Path: "/test/cancelled_file.txt",
MTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
GID: 1000,
}
err := repos.Files.Create(ctx, tx, file)
if err != nil {
return err
}
cancel()
// database/sql rolls back from a goroutine of its own; wait
// until it has, so the test does not depend on that race.
for {
_, err = tx.ExecContext(context.WithoutCancel(ctx), "SELECT 1")
if errors.Is(err, sql.ErrTxDone) {
return ctx.Err()
}
time.Sleep(time.Millisecond)
}
})
if !errors.Is(err, context.Canceled) {
t.Fatalf("expected context.Canceled, got: %v", err)
}
if errors.Is(err, sql.ErrTxDone) {
t.Fatalf("the already-done rollback was reported: %v", err)
}
file, err := repos.Files.GetByPath(
context.Background(), "/test/cancelled_file.txt",
)
if err != nil {
t.Fatalf("error checking for file: %v", err)
}
if file != nil {
t.Error("file should not exist after the cancelled transaction")
}
}
// A body that ends the transaction itself with ROLLBACK makes WithTx's
// own rollback fail. WithTx must return that failure together with the
// body's error.
func TestRepositoriesTransactionRollbackFails(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repos := database.NewRepositories(db)
err := repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
_, err := tx.ExecContext(ctx, "ROLLBACK")
if err != nil {
return err
}
return errIntentionalRollback
})
if !errors.Is(err, errIntentionalRollback) {
t.Fatalf("expected the body's error, got: %v", err)
}
if !strings.Contains(err.Error(), "rolling back transaction") {
t.Errorf("expected the failed rollback in the error, got: %v", err)
}
}
// When the body ends the transaction itself with ROLLBACK and then
// panics, WithTx's own rollback fails; the panic must still reach the
// caller.
func TestRepositoriesTransactionPanicRollbackFails(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repos := database.NewRepositories(db)
defer func() {
if recover() == nil {
t.Error("expected the body's panic to reach the caller")
}
}()
_ = repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
_, err := tx.ExecContext(ctx, "ROLLBACK")
if err != nil {
return err
}
panic(errIntentionalRollback)
})
}
func TestRepositoriesReadTransaction(t *testing.T) {
t.Parallel()
@@ -411,41 +291,3 @@ func TestRepositoriesReadTransaction(t *testing.T) {
t.Error("expected to retrieve file in read transaction")
}
}
// When the context is cancelled during a read transaction's body,
// database/sql rolls the transaction back itself, so WithReadTx's own
// rollback finds it already done. WithReadTx must return the body's error
// alone, without that rollback.
func TestRepositoriesReadTransactionContextCancelled(t *testing.T) {
t.Parallel()
db, cleanup := setupTestDB(t)
defer cleanup()
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
repos := database.NewRepositories(db)
err := repos.WithReadTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
cancel()
// database/sql rolls back from a goroutine of its own; wait
// until it has, so the test does not depend on that race.
for {
_, err := tx.ExecContext(context.WithoutCancel(ctx), "SELECT 1")
if errors.Is(err, sql.ErrTxDone) {
return ctx.Err()
}
time.Sleep(time.Millisecond)
}
})
if !errors.Is(err, context.Canceled) {
t.Fatalf("expected context.Canceled, got: %v", err)
}
if errors.Is(err, sql.ErrTxDone) {
t.Fatalf("the already-done rollback was reported: %v", err)
}
}
internal/database/schema/001.sql
-2
View File
@@ -86,10 +86,8 @@ CREATE TABLE IF NOT EXISTS snapshots (
completed_at INTEGER,
file_count INTEGER NOT NULL DEFAULT 0,
chunk_count INTEGER NOT NULL DEFAULT 0,
new_chunk_size INTEGER NOT NULL DEFAULT 0,
blob_count INTEGER NOT NULL DEFAULT 0,
total_size INTEGER NOT NULL DEFAULT 0,
uncompressed_chunk_size INTEGER NOT NULL DEFAULT 0,
blob_size INTEGER NOT NULL DEFAULT 0,
blob_uncompressed_size INTEGER NOT NULL DEFAULT 0,
compression_ratio REAL NOT NULL DEFAULT 1.0,
internal/database/snapshots.go
+79 -41
View File
@@ -120,11 +120,7 @@ func (r *SnapshotRepository) UpdateCounts(
return nil
}
// UpdateExtendedStats updates extended statistics for a snapshot. It also
// records the total plaintext size of the distinct chunks the snapshot's
// files reference. Only the snapshot's own backup can take that total: a
// file's row is shared by every snapshot that lists it, and a later
// backup of a changed file rewrites the row with the new chunks.
// UpdateExtendedStats updates extended statistics for a snapshot
func (r *SnapshotRepository) UpdateExtendedStats(
ctx context.Context,
tx *sql.Tx,
@@ -133,7 +129,6 @@ func (r *SnapshotRepository) UpdateExtendedStats(
compressionLevel int,
uploadBytes int64,
uploadDurationMs int64,
newChunkSize int64,
) error {
compressionRatio, err := r.extendedCompressionRatio(
ctx, tx, snapshotID, blobUncompressedSize,
@@ -148,29 +143,18 @@ func (r *SnapshotRepository) UpdateExtendedStats(
compression_ratio = ?,
compression_level = ?,
upload_bytes = ?,
upload_duration_ms = ?,
new_chunk_size = ?,
uncompressed_chunk_size = (
SELECT COALESCE(SUM(c.size), 0)
FROM (
SELECT DISTINCT fc.chunk_hash
FROM snapshot_files sf
JOIN file_chunks fc ON sf.file_id = fc.file_id
WHERE sf.snapshot_id = snapshots.id
) sc
JOIN chunks c ON sc.chunk_hash = c.chunk_hash
)
upload_duration_ms = ?
WHERE id = ?
`
if tx != nil {
_, err = tx.ExecContext(ctx, query,
blobUncompressedSize, compressionRatio, compressionLevel,
uploadBytes, uploadDurationMs, newChunkSize, snapshotID)
uploadBytes, uploadDurationMs, snapshotID)
} else {
_, err = r.db.ExecWithLog(ctx, query,
blobUncompressedSize, compressionRatio, compressionLevel,
uploadBytes, uploadDurationMs, newChunkSize, snapshotID)
uploadBytes, uploadDurationMs, snapshotID)
}
if err != nil {
@@ -255,7 +239,12 @@ func (r *SnapshotRepository) GetOnlySnapshot(ctx context.Context) (*Snapshot, er
return nil, fmt.Errorf("querying snapshots: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
snapshots, err := r.scanSnapshotRows(rows)
if err != nil {
@@ -290,7 +279,12 @@ func (r *SnapshotRepository) ListRecent(
return nil, fmt.Errorf("querying snapshots: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanSnapshotRows(rows)
}
@@ -505,7 +499,12 @@ func (r *SnapshotRepository) GetBlobHashes(
return nil, fmt.Errorf("querying blob hashes: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
var blobs []string
@@ -569,42 +568,71 @@ func (r *SnapshotRepository) GetSnapshotBlobSizes(
return compressed, uncompressed, nil
}
// GetSnapshotUncompressedChunkSize returns the total plaintext size of the
// distinct chunks the snapshot's files reference, as the snapshot's backup
// recorded it (see UpdateExtendedStats).
// GetSnapshotUncompressedChunkSize returns the sum of plaintext sizes of all unique
// chunks referenced by a snapshot (via snapshot_files → file_chunks → chunks).
func (r *SnapshotRepository) GetSnapshotUncompressedChunkSize(
ctx context.Context, snapshotID string,
) (int64, error) {
query := `SELECT uncompressed_chunk_size FROM snapshots WHERE id = ?`
query := `
SELECT COALESCE(SUM(c.size), 0)
FROM (
SELECT DISTINCT fc.chunk_hash
FROM snapshot_files sf
JOIN file_chunks fc ON sf.file_id = fc.file_id
WHERE sf.snapshot_id = ?
) sc
JOIN chunks c ON sc.chunk_hash = c.chunk_hash
`
var uncompressedChunkSize int64
var totalSize int64
err := r.db.conn.QueryRowContext(ctx, query, snapshotID).Scan(&uncompressedChunkSize)
err := r.db.conn.QueryRowContext(ctx, query, snapshotID).Scan(&totalSize)
if err != nil {
return 0, fmt.Errorf("querying uncompressed chunk size: %w", err)
}
return uncompressedChunkSize, nil
return totalSize, nil
}
// GetSnapshotNewChunkSize returns the total plaintext size of the chunks the
// snapshot's backup stored that were not stored before, as the backup
// recorded it. It is not derived from the snapshot's files: a file's row is
// shared by every snapshot that lists it and is rewritten when the file
// changes, so it shows only the file's latest chunks.
// GetSnapshotNewChunkSize returns the sum of plaintext sizes of chunks that are
// referenced by this snapshot but not by any earlier completed snapshot known to
// the local database. The result is the marginal uncompressed data this snapshot
// added to the dedup pool — i.e., the delta from prior snapshots.
func (r *SnapshotRepository) GetSnapshotNewChunkSize(
ctx context.Context, snapshotID string,
) (int64, error) {
query := `SELECT new_chunk_size FROM snapshots WHERE id = ?`
query := `
WITH this_snap_chunks AS (
SELECT DISTINCT fc.chunk_hash
FROM snapshot_files sf
JOIN file_chunks fc ON sf.file_id = fc.file_id
WHERE sf.snapshot_id = ?
),
prior_chunks AS (
SELECT DISTINCT fc.chunk_hash
FROM snapshots s
JOIN snapshot_files sf ON sf.snapshot_id = s.id
JOIN file_chunks fc ON fc.file_id = sf.file_id
WHERE s.completed_at IS NOT NULL
AND s.id != ?
AND s.started_at < (SELECT started_at FROM snapshots WHERE id = ?)
)
SELECT COALESCE(SUM(c.size), 0)
FROM chunks c
JOIN this_snap_chunks t ON c.chunk_hash = t.chunk_hash
WHERE c.chunk_hash NOT IN (SELECT chunk_hash FROM prior_chunks)
`
var newChunkSize int64
var totalSize int64
err := r.db.conn.QueryRowContext(ctx, query, snapshotID).Scan(&newChunkSize)
err := r.db.conn.QueryRowContext(
ctx, query, snapshotID, snapshotID, snapshotID,
).Scan(&totalSize)
if err != nil {
return 0, fmt.Errorf("querying new chunk size: %w", err)
}
return newChunkSize, nil
return totalSize, nil
}
// GetIncompleteSnapshots returns all snapshots that haven't been completed
@@ -625,7 +653,12 @@ func (r *SnapshotRepository) GetIncompleteSnapshots(
return nil, fmt.Errorf("querying incomplete snapshots: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
return r.scanSnapshotRows(rows)
}
@@ -648,7 +681,12 @@ func (r *SnapshotRepository) GetIncompleteByHostname(
return nil, fmt.Errorf("querying incomplete snapshots: %w", err)
}
defer func() { _ = rows.Close() }()
defer func() {
err := rows.Close()
if err != nil {
Fatalf("failed to close rows: %v", err)
}
}()
// Same column set as every other multi-row snapshot query, so the
// shared scanner applies — including its timestamp normalization.
internal/log/tty_handler.go
+10 -7
View File
@@ -10,8 +10,6 @@ import (
"sync"
"time"
"unicode"
"github.com/dustin/go-humanize"
)
// groupSeparator joins an open group path to an attribute key. This
@@ -306,13 +304,18 @@ func formatDuration(d time.Duration) string {
}
}
// formatBytes formats a byte count with humanize.Bytes, as every command
// prints one. humanize.Bytes takes no negative count, so one is printed
// as it is.
// formatBytes formats bytes in a human-readable way
func formatBytes(b int64) string {
if b < 0 {
const unit = 1024
if b < unit {
return fmt.Sprintf("%d B", b)
}
return humanize.Bytes(uint64(b))
div, exp := int64(unit), 0
for n := b / unit; n >= unit; n /= unit {
div *= unit
exp++
}
return fmt.Sprintf("%.1f %cB", float64(b)/float64(div), "KMGTPE"[exp])
}
internal/log/tty_handler_test.go
+4 -5
View File
@@ -200,8 +200,7 @@ func TestTTYHandlerWithGroupQualifiesKeys(t *testing.T) {
func TestTTYHandlerByteFormattingSurvivesGrouping(t *testing.T) {
t.Parallel()
// Printed as "1.0 MB", in powers of 1000 like every other byte count.
const oneMegabyte = 1_000_000
const oneAndAHalfKiB = 1536
for name, testCase := range map[string]struct {
derive func(*slog.Logger) *slog.Logger
@@ -224,13 +223,13 @@ func TestTTYHandlerByteFormattingSurvivesGrouping(t *testing.T) {
var buf bytes.Buffer
logger := slog.New(log.NewTTYHandler(&buf, debugHandlerOptions()))
testCase.derive(logger).Info("uploaded", "bytes", oneMegabyte)
testCase.derive(logger).Info("uploaded", "bytes", oneAndAHalfKiB)
line := ansiEscape.ReplaceAllString(buf.String(), "")
assert.Contains(t, line, testCase.key+"=1.0 MB",
assert.Contains(t, line, testCase.key+"=1.5 KB",
"a byte count must be human-readable however it is qualified")
assert.NotContains(t, line, strconv.Itoa(oneMegabyte),
assert.NotContains(t, line, strconv.Itoa(oneAndAHalfKiB),
"the raw number must not survive the formatting")
})
}
internal/s3/client.go
+2 -29
View File
@@ -18,13 +18,6 @@ import (
"github.com/aws/smithy-go/logging"
)
// ErrNoContinuationToken is returned by ListObjects and ListObjectsStream
// when the server marks a page of a listing truncated but sends no
// continuation token to fetch the rest with, as a server answering V2
// listings V1-style does.
var ErrNoContinuationToken = errors.New(
"server marked the listing truncated but sent no continuation token")
// Client wraps the AWS S3 client for vaultik operations.
// It provides a simplified interface for S3 operations with automatic
// prefix handling and connection management. All operations are performed
@@ -221,7 +214,7 @@ func (c *Client) ListObjects(ctx context.Context, prefix string) ([]string, erro
})
for paginator.HasMorePages() {
page, err := nextListPage(ctx, paginator)
page, err := paginator.NextPage(ctx)
if err != nil {
return nil, err
}
@@ -242,26 +235,6 @@ func (c *Client) ListObjects(ctx context.Context, prefix string) ([]string, erro
return keys, nil
}
// nextListPage fetches the next page of a listing. The SDK paginator takes
// a page marked truncated without a continuation token for the last page
// and stops without an error, so such a page is ErrNoContinuationToken
// here instead.
func nextListPage(
ctx context.Context, paginator *s3.ListObjectsV2Paginator,
) (*s3.ListObjectsV2Output, error) {
page, err := paginator.NextPage(ctx)
if err != nil {
return nil, err
}
truncated := aws.ToBool(page.IsTruncated)
if truncated && aws.ToString(page.NextContinuationToken) == "" {
return nil, ErrNoContinuationToken
}
return page, nil
}
// HeadObject checks if an object exists in S3.
// Returns true if the object exists, false otherwise.
// The key is automatically prefixed with the configured prefix.
@@ -327,7 +300,7 @@ func (c *Client) ListObjectsStream(
})
for paginator.HasMorePages() {
page, err := nextListPage(ctx, paginator)
page, err := paginator.NextPage(ctx)
if err != nil {
ch <- ObjectInfo{Err: err}
internal/snapshot/blob_temp_file_test.go
-62
View File
@@ -1,62 +0,0 @@
//nolint:testpackage // exercises the unexported cleanupBlobTempFile
package snapshot
import (
"errors"
"os"
"testing"
"github.com/spf13/afero"
"sneak.berlin/go/vaultik/internal/blob"
)
// A blob temp file that cannot be closed or removed must make the cleanup
// return an error, not end the process.
func TestCleanupBlobTempFileReturnsErrors(t *testing.T) {
t.Parallel()
fs := afero.NewOsFs()
s := &Scanner{fs: fs}
tests := []struct {
name string
// prepare runs before the cleanup and makes its close or remove
// fail.
prepare func(tempFile afero.File) error
want error
}{
{
name: "close fails",
prepare: func(tempFile afero.File) error { return tempFile.Close() },
want: os.ErrClosed,
},
{
name: "remove fails",
prepare: func(tempFile afero.File) error {
return fs.Remove(tempFile.Name())
},
want: os.ErrNotExist,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
tempFile, err := afero.TempFile(fs, t.TempDir(), "blob-*.tmp")
if err != nil {
t.Fatal(err)
}
err = tt.prepare(tempFile)
if err != nil {
t.Fatal(err)
}
err = s.cleanupBlobTempFile(&blob.WithReader{TempFile: tempFile})
if !errors.Is(err, tt.want) {
t.Fatalf("expected an error wrapping %v, got: %v", tt.want, err)
}
})
}
}
internal/snapshot/exclude_test.go
-51
View File
@@ -578,54 +578,3 @@ 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
+11 -15
View File
@@ -16,9 +16,6 @@ type ScannerParams struct {
Fs afero.Fs
Exclude []string // Exclude patterns (combined global + snapshot-specific)
SkipErrors bool // Skip file read errors (log loudly but continue)
// PreviousSnapshotID is the most recent completed snapshot of the
// same name, "" for none.
PreviousSnapshotID string
}
// Module exports backup functionality as an fx module.
@@ -47,18 +44,17 @@ func provideScannerFactory(
}
return NewScanner(ScannerConfig{
FS: params.Fs,
ChunkSize: cfg.ChunkSize.Int64(),
Repositories: repos,
Storage: storer,
MaxBlobSize: cfg.BlobSizeLimit.Int64(),
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: excludes,
SkipErrors: params.SkipErrors,
PreviousSnapshotID: params.PreviousSnapshotID,
FS: params.Fs,
ChunkSize: cfg.ChunkSize.Int64(),
Repositories: repos,
Storage: storer,
MaxBlobSize: cfg.BlobSizeLimit.Int64(),
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: excludes,
SkipErrors: params.SkipErrors,
})
}
}
internal/snapshot/scanner.go
+59 -157
View File
@@ -58,10 +58,6 @@ type Scanner struct {
compressionLevel int
ageRecipient string
snapshotID string // Current snapshot being processed
// previousSnapshotID is the most recent completed snapshot of the
// same name, "" for none. Only a file it lists can be counted as
// deleted.
previousSnapshotID string
// currentSourcePath is the source directory being scanned, stored with
// each file record.
currentSourcePath string
@@ -133,18 +129,13 @@ 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.
// includes them and BytesScanned does not.
type ScanResult struct {
FilesScanned int
FilesSkipped int
@@ -154,7 +145,6 @@ type ScanResult struct {
BytesSkipped int64
BytesDeleted int64
ChunksCreated int
NewChunkSize int64
BlobsCreated int
BlobsUploaded int
BytesUploaded int64
@@ -214,7 +204,6 @@ func NewScanner(cfg ScannerConfig) *Scanner {
compiledExclude: compiledExclude,
progress: progress,
skipErrors: cfg.SkipErrors,
previousSnapshotID: cfg.PreviousSnapshotID,
ui: uiw,
pendingChunkHashes: make(map[string]struct{}),
}
@@ -266,9 +255,8 @@ func (s *Scanner) Scan(
filesToProcess := scanResult.FilesToProcess
// Phase 1b: Detect deleted files by comparing the previous snapshot
// of this name against scanned files
err = s.detectDeletedFiles(ctx, path, existingFiles, result)
// Phase 1b: Detect deleted files by comparing DB against scanned files
err = s.detectDeletedFilesFromMap(ctx, knownFiles, existingFiles, result)
if err != nil {
return nil, fmt.Errorf("detecting deleted files: %w", err)
}
@@ -448,8 +436,9 @@ func (s *Scanner) summarizeScanPhase(
}
// loadKnownFiles loads the known files at and beneath path from the
// database into a map for fast lookup. This avoids per-file database
// queries during the scan phase.
// database into a map for fast lookup. Every loaded file the scan does
// not find is counted as deleted. This avoids per-file database queries
// during the scan phase.
func (s *Scanner) loadKnownFiles(
ctx context.Context, path string,
) (map[string]*database.File, error) {
@@ -1525,8 +1514,7 @@ func (s *Scanner) finalizeProcessPhase(ctx context.Context, result *ScanResult)
// snapshot references has uploaded_ts set, so deduplication and
// interrupted-run repair treat these blobs as trustworthy.
err = s.repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
err := s.repos.Blobs.UpdateUploaded(
ctx, tx, b.ID, b.Compressed)
err := s.repos.Blobs.UpdateUploaded(ctx, tx, b.ID)
if err != nil {
return fmt.Errorf("marking blob uploaded: %w", err)
}
@@ -1562,28 +1550,23 @@ func (s *Scanner) handleBlobReady(
blobPath := fmt.Sprintf("blobs/%s/%s/%s",
finishedBlob.Hash[:2], finishedBlob.Hash[2:4], finishedBlob.Hash)
storedSize, blobExists, err := s.uploadBlobIfNeeded(
blobExists, err := s.uploadBlobIfNeeded(
ctx, blobPath, blobWithReader, startTime, result)
if err != nil {
cleanupErr := s.cleanupBlobTempFile(blobWithReader)
s.cleanupBlobTempFile(blobWithReader)
return errors.Join(
fmt.Errorf("uploading blob %s: %w", finishedBlob.Hash, err), cleanupErr)
return fmt.Errorf("uploading blob %s: %w", finishedBlob.Hash, err)
}
err = s.recordBlobMetadata(
ctx, finishedBlob, storedSize, blobExists, startTime)
err = s.recordBlobMetadata(ctx, finishedBlob, blobExists, startTime)
if err != nil {
cleanupErr := s.cleanupBlobTempFile(blobWithReader)
s.cleanupBlobTempFile(blobWithReader)
return errors.Join(err, cleanupErr)
}
err = s.cleanupBlobTempFile(blobWithReader)
if err != nil {
return err
}
s.cleanupBlobTempFile(blobWithReader)
// Chunks from this blob are now committed to DB - remove from pending set
s.removePendingChunkHashes(blobWithReader.InsertedChunkHashes)
@@ -1597,22 +1580,20 @@ func (s *Scanner) handleBlobReady(
}
// uploadBlobIfNeeded uploads the blob to storage if it doesn't already
// exist. It returns the size of the object in storage, which for an
// existing object can differ from the local copy's, and whether it
// already existed.
// exist, returns whether it existed
func (s *Scanner) uploadBlobIfNeeded(
ctx context.Context,
blobPath string,
blobWithReader *blob.WithReader,
startTime time.Time,
result *ScanResult,
) (int64, bool, error) {
) (bool, error) {
finishedBlob := blobWithReader.FinishedBlob
// Check if blob already exists (deduplication after restart)
destination := s.storage.Info().Location
stored, err := s.storage.Stat(ctx, blobPath)
_, err := s.storage.Stat(ctx, blobPath)
if err == nil {
log.Info("Blob already exists in storage, skipping upload",
"hash", finishedBlob.Hash,
@@ -1621,7 +1602,7 @@ func (s *Scanner) uploadBlobIfNeeded(
s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed),
s.ui.Path(destination))
return stored.Size, true, nil
return true, nil
}
s.ui.Beginf("Uploading blob %s (%s) to %s.",
@@ -1635,7 +1616,7 @@ func (s *Scanner) uploadBlobIfNeeded(
if err != nil {
log.Error("Failed to upload blob", "hash", finishedBlob.Hash, "error", err)
return 0, false, fmt.Errorf("uploading blob to storage: %w", err)
return false, fmt.Errorf("uploading blob to storage: %w", err)
}
uploadDuration := time.Since(startTime)
@@ -1666,7 +1647,7 @@ func (s *Scanner) uploadBlobIfNeeded(
stats.BytesUploaded.Add(finishedBlob.Compressed)
}
return finishedBlob.Compressed, false, nil
return false, nil
}
// makeUploadProgressCallback creates a progress callback for blob uploads.
@@ -1736,7 +1717,6 @@ func (s *Scanner) makeUploadProgressCallback(
func (s *Scanner) recordBlobMetadata(
ctx context.Context,
finishedBlob *blob.FinishedBlob,
storedSize int64,
blobExists bool,
startTime time.Time,
) error {
@@ -1748,8 +1728,7 @@ func (s *Scanner) recordBlobMetadata(
uploadDuration := time.Since(startTime)
return s.repos.WithTx(ctx, func(txCtx context.Context, tx *sql.Tx) error {
err := s.repos.Blobs.UpdateUploaded(
txCtx, tx, finishedBlob.ID, storedSize)
err := s.repos.Blobs.UpdateUploaded(txCtx, tx, finishedBlob.ID)
if err != nil {
return fmt.Errorf("updating blob upload timestamp: %w", err)
}
@@ -1780,22 +1759,20 @@ func (s *Scanner) recordBlobMetadata(
}
// cleanupBlobTempFile closes and removes the blob's temporary file
func (s *Scanner) cleanupBlobTempFile(blobWithReader *blob.WithReader) error {
func (s *Scanner) cleanupBlobTempFile(blobWithReader *blob.WithReader) {
if blobWithReader.TempFile != nil {
tempName := blobWithReader.TempFile.Name()
err := blobWithReader.TempFile.Close()
if err != nil {
return fmt.Errorf("closing blob temp file: %w", err)
log.Fatal("Failed to close temp file", "file", tempName, "error", err)
}
err = s.fs.Remove(tempName)
if err != nil {
return fmt.Errorf("removing blob temp file: %w", err)
log.Fatal("Failed to remove temp file", "file", tempName, "error", err)
}
}
return nil
}
// streamingChunkInfo tracks chunk metadata collected during streaming
@@ -1889,12 +1866,11 @@ func (s *Scanner) processFileStreaming(
return nil
}
// updateChunkStats counts a chunk that was not already stored, and its
// size. The scan result's file counts, BytesScanned and BytesSkipped are
// not touched here: the scan phase counts each file once.
// updateChunkStats counts a chunk that was not already stored. The scan
// result's file counts, BytesScanned and BytesSkipped are not touched
// here: the scan phase counts each file once.
func (s *Scanner) updateChunkStats(chunkSize int64, result *ScanResult) {
result.ChunksCreated++
result.NewChunkSize += chunkSize
if s.progress != nil {
s.progress.GetStats().ChunksCreated.Add(1)
@@ -1962,29 +1938,21 @@ func (s *Scanner) queueFileForBatchInsert(
})
}
// detectDeletedFiles counts as deleted each file at or beneath path that
// the previous snapshot of this name lists, the walk did not find, and
// is gone from disk. A file that is excluded, or inside an excluded
// directory, is not counted: the walk skips it whether or not it is
// still on disk.
func (s *Scanner) detectDeletedFiles(
// detectDeletedFilesFromMap finds files that existed in previous snapshots
// but no longer exist. Uses pre-loaded maps to avoid any filesystem or
// database access.
func (s *Scanner) detectDeletedFilesFromMap(
ctx context.Context,
path string,
knownFiles map[string]*database.File,
existingFiles map[string]struct{},
result *ScanResult,
) error {
if s.previousSnapshotID == "" {
if len(knownFiles) == 0 {
return nil
}
previousFiles, err := s.repos.Files.ListUnderPathInSnapshot(
ctx, path, s.previousSnapshotID)
if err != nil {
return fmt.Errorf("listing files of snapshot %s: %w",
s.previousSnapshotID, err)
}
for _, file := range previousFiles {
// Check each known file against the enumerated set (no filesystem access needed)
for path, file := range knownFiles {
// Check context cancellation periodically
select {
case <-ctx.Done():
@@ -1992,22 +1960,13 @@ func (s *Scanner) detectDeletedFiles(
default:
}
filePath := file.Path.String()
_, exists := existingFiles[filePath]
if exists || s.excludedOrInExcludedDir(filePath, path) {
continue
// Check if the file exists in our enumerated set
if _, exists := existingFiles[path]; !exists {
// File has been deleted
result.FilesDeleted++
result.BytesDeleted += file.Size
log.Debug("Detected deleted file", "path", path, "size", file.Size)
}
// Under --skip-errors the walk also misses what it cannot reach,
// such as the files in a directory it cannot open.
if !s.goneFromDisk(filePath) {
continue
}
result.FilesDeleted++
result.BytesDeleted += file.Size
log.Debug("Detected deleted file", "path", filePath, "size", file.Size)
}
if result.FilesDeleted > 0 {
@@ -2018,36 +1977,6 @@ func (s *Scanner) detectDeletedFiles(
return nil
}
// excludedOrInExcludedDir reports whether filePath, which is at or
// beneath rootPath, or any directory between rootPath and it, matches an
// exclude pattern. A pattern such as */.local/share/Trash matches the
// directory but not the files inside it, which the walk skips too.
func (s *Scanner) excludedOrInExcludedDir(filePath, rootPath string) bool {
for p := filePath; len(p) > len(rootPath); p = filepath.Dir(p) {
if s.shouldExclude(p, rootPath) {
return true
}
}
return false
}
// goneFromDisk reports whether looking filePath up on disk finds that
// it does not exist. Like the walk, it does not follow a symlink, so a
// symlink whose target is gone is still on disk. A file whose directory
// was replaced by a regular file is gone too, though the lookup reports
// "not a directory".
func (s *Scanner) goneFromDisk(filePath string) bool {
var err error
if lstater, ok := s.fs.(afero.Lstater); ok {
_, _, err = lstater.LstatIfPossible(filePath)
} else {
_, err = s.fs.Stat(filePath)
}
return errors.Is(err, os.ErrNotExist) || errors.Is(err, syscall.ENOTDIR)
}
// wrapPermissionError augments permission errors with platform-specific
// remediation instructions. On macOS, TCC-protected directories (Calendars,
// Reminders, Photos, etc.) return EPERM unless the running application has
@@ -2090,60 +2019,33 @@ 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. 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
// 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, "**/")
}
// 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)
// 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)
break
}
compiled = append(compiled, compiledPattern{
pattern: g,
anchored: anchored,
original: p,
})
continue
}
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/snapshot.go
-2
View File
@@ -199,7 +199,6 @@ func (sm *SnapshotManager) UpdateSnapshotStatsExtended(
stats.CompressionLevel,
stats.BytesUploaded,
stats.UploadDurationMs,
stats.NewChunkSize,
)
})
}
@@ -907,7 +906,6 @@ type ExtendedBackupStats struct {
BlobUncompressedSize int64 // Total uncompressed size of all referenced blobs
CompressionLevel int // Compression level used for this snapshot
UploadDurationMs int64 // Total milliseconds spent uploading to S3
NewChunkSize int64 // Total size of the chunks counted in ChunksCreated
}
// deleteOtherSnapshots deletes all snapshots except the current one
internal/storage/faultstore/faultstore.go
+9 -23
View File
@@ -1,16 +1,15 @@
// Package faultstore provides a storage.Storer wrapper that injects
// faults on demand, so tests can reproduce the failure modes a real
// backend exhibits: an upload that fails partway, a backend that reports
// success while storing nothing, reads that return corrupt or truncated
// bytes, and a delete the backend refuses. It is the seam called for by
// the fault-injection tests (sneak/vaultik issue 72) and is meant to be
// reused by future tests rather than re-implemented per case.
// success while storing nothing, and reads that return corrupt or
// truncated bytes. It is the seam called for by the fault-injection
// tests (sneak/vaultik issue 72) and is meant to be reused by future
// tests rather than re-implemented per case.
//
// The wrapper delegates every method to the inner Storer. Three hooks
// change that: OnPut decides the fate of each write, OnGet decides how
// each read's bytes are returned, and OnDelete decides whether each
// delete fails. All are keyed by the object key, so a test can fault
// only blobs, only metadata, or a single object.
// The wrapper delegates every method to the inner Storer. Two hooks
// change that: OnPut decides the fate of each write, and OnGet decides
// how each read's bytes are returned. Both are keyed by the object key,
// so a test can fault only blobs, only metadata, or a single object.
package faultstore
import (
@@ -26,10 +25,6 @@ import (
// ErrInjectedUpload is returned by a Put the OnPut hook chose to fail.
var ErrInjectedUpload = errors.New("faultstore: injected upload failure")
// ErrInjectedDelete is returned by a Delete the OnDelete hook chose to
// fail.
var ErrInjectedDelete = errors.New("faultstore: injected delete failure")
// PutAction is the disposition OnPut assigns to a write.
type PutAction int
@@ -71,11 +66,6 @@ type Storer struct {
// OnGet, when set, is consulted for every Get with the object key
// and damages the returned bytes accordingly.
OnGet func(key string) GetFault
// OnDelete, when set, is consulted before every Delete with the
// object key. Returning true fails the delete and leaves the object
// in place.
OnDelete func(key string) bool
}
// New wraps inner. inner must be non-nil.
@@ -164,12 +154,8 @@ func (f *Storer) Stat(ctx context.Context, key string) (*storage.ObjectInfo, err
return f.inner.Stat(ctx, key)
}
// Delete removes the object unless OnDelete fails the delete.
// Delete delegates unchanged.
func (f *Storer) Delete(ctx context.Context, key string) error {
if f.OnDelete != nil && f.OnDelete(key) {
return fmt.Errorf("%w for %q", ErrInjectedDelete, key)
}
return f.inner.Delete(ctx, key)
}
internal/storage/file.go
+17 -83
View File
@@ -21,13 +21,9 @@ type FileStorer struct {
// NewFileStorer creates a new filesystem storage backend.
//
// Construction is intentionally cheap and does not touch the filesystem.
// The backend never creates basePath: the user does, so that when
// basePath is a directory on an unplugged volume, a write fails instead
// of landing on the disk under the mount point. This does not hold when
// basePath is the mount point itself, which stays behind when its volume
// is unplugged.
// Put and PutWithProgress fail on a missing basePath and create the
// directories below it as needed.
// The basePath is recorded; the directory is created lazily on first
// write. Write operations (Put/PutWithProgress) call MkdirAll for the
// per-blob parent directory, which also covers basePath on first use.
// Get and Stat report a key under a missing basePath as ErrNotFound.
// List and ListStream fail on a missing basePath, because listing it as
// an empty store would make `prune` drop every local snapshot record.
@@ -124,10 +120,9 @@ func (f *FileStorer) Delete(_ context.Context, key string) error {
return nil
}
// List returns all keys with the given prefix, reading through symlinked
// directories. It fails when the destination directory is missing, or
// when the prefix or a directory above it is a symlink whose target is
// missing; a prefix that is truly missing is an empty listing.
// List returns all keys with the given prefix. It fails when the
// destination directory is missing; a missing prefix under it is an
// empty listing.
func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) {
var keys []string
@@ -138,7 +133,8 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
basePath := f.fullPath(prefix)
exists, err := f.prefixExists(prefix)
// Check if the prefix exists
exists, err := afero.Exists(f.fs, basePath)
if err != nil {
return nil, fmt.Errorf("checking path: %w", err)
}
@@ -147,7 +143,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
return keys, nil // Empty list for non-existent prefix
}
err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
err = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
if err != nil {
return err
}
@@ -180,9 +176,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
}
// ListStream returns a channel of ObjectInfo for large result sets. Like
// List, it reads through symlinked directories and sends an error when
// the destination directory is missing, or when the prefix or a directory
// above it is a symlink whose target is missing.
// List, it sends an error when the destination directory is missing.
func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan ObjectInfo {
ch := make(chan ObjectInfo)
@@ -198,7 +192,8 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
basePath := f.fullPath(prefix)
exists, err := f.prefixExists(prefix)
// Check if the prefix exists
exists, err := afero.Exists(f.fs, basePath)
if err != nil {
ch <- ObjectInfo{Err: fmt.Errorf("checking path: %w", err)}
@@ -209,7 +204,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
return // Empty channel for non-existent prefix
}
_ = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
_ = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
// Check context cancellation
select {
case <-ctx.Done():
@@ -248,12 +243,11 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
}
// DeletePartialUploads removes every file under prefix whose name ends in
// tempSuffix. Like List, it reads through symlinked directories and fails
// on one whose target is missing. A missing prefix has none to remove.
// tempSuffix. A missing prefix has none to remove.
func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) error {
basePath := f.fullPath(prefix)
exists, err := f.prefixExists(prefix)
exists, err := afero.Exists(f.fs, basePath)
if err != nil {
return fmt.Errorf("checking path: %w", err)
}
@@ -262,7 +256,7 @@ func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) er
return nil
}
err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
err = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
if err != nil {
return err
}
@@ -303,19 +297,7 @@ func (f *FileStorer) writeAtomic(
path := f.fullPath(key)
dir := filepath.Dir(path)
// Checked on every write, so a destination that disappears part-way
// through a backup fails it rather than being recreated by MkdirAll.
_, err := f.fs.Stat(f.basePath)
if os.IsNotExist(err) {
return fmt.Errorf("destination directory does not exist; "+
"create it, or mount the volume it is on: %w", err)
}
if err != nil {
return fmt.Errorf("checking destination directory: %w", err)
}
err = f.fs.MkdirAll(dir, storageDirPerm)
err := f.fs.MkdirAll(dir, storageDirPerm)
if err != nil {
return fmt.Errorf("creating directories: %w", err)
}
@@ -370,54 +352,6 @@ func (f *FileStorer) writeAtomic(
return nil
}
// walk is afero.Walk, except that it reads through a symlinked directory
// the way Get and Stat do, where afero.Walk reports the link as one file.
// afero.Walk uses Lstat, which does not follow a link, whenever the
// filesystem has one; the struct below carries only the afero.Fs methods,
// so the walk uses Stat instead. A link back up the tree is followed until
// the operating system refuses the path for too many levels of links, and
// the walk then fails.
func (f *FileStorer) walk(root string, fn filepath.WalkFunc) error {
return afero.Walk(struct{ afero.Fs }{f.fs}, root, fn)
}
// prefixExists reports whether prefix exists under the destination
// directory. It checks each directory on the way down to prefix in turn,
// and the first one Stat cannot find decides: if it is not there at all,
// prefix is missing; if it is a symlink whose target is missing, such as
// a link to a volume that is not mounted, prefixExists fails, since
// listing it as empty would let prune delete every blob.
func (f *FileStorer) prefixExists(prefix string) (bool, error) {
lstater, canLstat := f.fs.(afero.Lstater)
path := f.basePath
for name := range strings.SplitSeq(prefix, "/") {
path = filepath.Join(path, name)
_, err := f.fs.Stat(path)
if err == nil {
continue
}
if !os.IsNotExist(err) {
return false, err
}
// Lstat does not follow a symlink at path, so it finds the link
// that Stat could not follow.
if canLstat {
_, _, lstatErr := lstater.LstatIfPossible(path)
if lstatErr == nil {
return false, err
}
}
return false, nil
}
return true, nil
}
// fullPath returns the full filesystem path for a key.
func (f *FileStorer) fullPath(key string) string {
return filepath.Join(f.basePath, key)
internal/storage/file_backend_test.go
-272
View File
@@ -4,10 +4,7 @@ import (
"context"
"errors"
"io/fs"
"os"
"path/filepath"
"reflect"
"strings"
"testing"
"sneak.berlin/go/vaultik/internal/storage"
@@ -63,272 +60,3 @@ func TestFileStorerListMissingDestination(t *testing.T) {
t.Errorf("ListStream error = %v, want a not-exist error", streamErr)
}
}
// The two directories at the top of a destination, either of which the
// tests below replace with a symlink.
const (
metadataDir = "metadata"
blobsDir = "blobs"
)
// moveBehindSymlink moves base/dir to a directory elsewhere and puts a
// symlink to it in its place.
func moveBehindSymlink(t *testing.T, base, dir string) {
t.Helper()
linkPath := filepath.Join(base, dir)
movedPath := filepath.Join(t.TempDir(), dir)
err := os.Rename(linkPath, movedPath)
if err != nil {
t.Fatalf("moving %s away: %v", dir, err)
}
err = os.Symlink(movedPath, linkPath)
if err != nil {
t.Fatalf("linking %s: %v", dir, err)
}
}
// TestFileStorerListsThroughSymlinkedDirectory checks that List and
// ListStream read through a symlinked metadata/ or blobs/ directory, as Get
// and Stat do, instead of listing the link as one key. Listing the whole
// destination meets the link part-way through the walk; listing its prefix
// starts the walk at the link. A prefix missing behind the link lists as
// empty.
func TestFileStorerListsThroughSymlinkedDirectory(t *testing.T) {
t.Parallel()
for _, dir := range []string{metadataDir, blobsDir} {
t.Run(dir, func(t *testing.T) {
t.Parallel()
base := t.TempDir()
key := dir + "/aa/bb/object"
s, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
err = s.Put(context.Background(), key, strings.NewReader("data"))
if err != nil {
t.Fatalf("Put: %v", err)
}
moveBehindSymlink(t, base, dir)
want := []string{key}
for _, prefix := range []string{"", dir + "/"} {
got := listSorted(t, s, prefix)
if !reflect.DeepEqual(got, want) {
t.Errorf("List(%q) = %v, want %v", prefix, got, want)
}
got = listStreamKeys(t, s, prefix)
if !reflect.DeepEqual(got, want) {
t.Errorf("ListStream(%q) = %v, want %v", prefix, got, want)
}
}
absent := dir + "/absent/"
if got := listSorted(t, s, absent); len(got) != 0 {
t.Errorf("List(%q) = %v, want empty", absent, got)
}
if got := listStreamKeys(t, s, absent); len(got) != 0 {
t.Errorf("ListStream(%q) = %v, want empty", absent, got)
}
})
}
}
// TestFileStorerListFailsOnSymlinkWithMissingTarget checks that List and
// ListStream fail on a symlinked metadata/ or blobs/ directory whose target
// is missing, such as a link to a volume that is not mounted, as they do on
// a missing destination directory, instead of listing it as empty. That
// holds for a prefix below the link too.
func TestFileStorerListFailsOnSymlinkWithMissingTarget(t *testing.T) {
t.Parallel()
ctx := context.Background()
for _, dir := range []string{metadataDir, blobsDir} {
t.Run(dir, func(t *testing.T) {
t.Parallel()
base := t.TempDir()
s, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
unmounted := filepath.Join(t.TempDir(), "unmounted")
err = os.Symlink(unmounted, filepath.Join(base, dir))
if err != nil {
t.Fatalf("Symlink: %v", err)
}
for _, prefix := range []string{"", dir + "/", dir + "/aa/"} {
keys, err := s.List(ctx, prefix)
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("List(%q) = %v, %v; want a not-exist error",
prefix, keys, err)
}
var streamErr error
for object := range s.ListStream(ctx, prefix) {
if object.Err != nil {
streamErr = object.Err
}
}
if !errors.Is(streamErr, fs.ErrNotExist) {
t.Errorf("ListStream(%q) error = %v, want a not-exist error",
prefix, streamErr)
}
}
})
}
}
// TestFileStorerListFailsOnSymlinkLoop checks that a symlink pointing back
// at the destination makes List and ListStream fail instead of walking it
// forever.
func TestFileStorerListFailsOnSymlinkLoop(t *testing.T) {
t.Parallel()
ctx := context.Background()
base := t.TempDir()
s, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
err = s.Put(ctx, testBlobKey, strings.NewReader("data"))
if err != nil {
t.Fatalf("Put: %v", err)
}
err = os.Symlink(base, filepath.Join(base, "blobs", "loop"))
if err != nil {
t.Fatalf("Symlink: %v", err)
}
keys, err := s.List(ctx, "blobs/")
if err == nil {
t.Errorf("List = %d keys and no error, want an error", len(keys))
}
var streamErr error
for object := range s.ListStream(ctx, "blobs/") {
if object.Err != nil {
streamErr = object.Err
}
}
if streamErr == nil {
t.Error("ListStream sent no error, want one")
}
}
// TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory checks that
// DeletePartialUploads, which remote nuke uses, removes a leftover temp
// file behind a symlinked metadata/ or blobs/ directory and keeps the
// object at the real key.
func TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory(t *testing.T) {
t.Parallel()
ctx := context.Background()
for _, dir := range []string{metadataDir, blobsDir} {
t.Run(dir, func(t *testing.T) {
t.Parallel()
base := t.TempDir()
key := dir + "/aa/bb/object"
s, err := storage.NewFileStorer(base)
if err != nil {
t.Fatalf("NewFileStorer: %v", err)
}
err = s.Put(ctx, key, strings.NewReader("data"))
if err != nil {
t.Fatalf("Put: %v", err)
}
leftover := filepath.Join(base, key+"-123456.partial")
err = os.WriteFile(leftover, []byte("half"), 0o600)
if err != nil {
t.Fatalf("writing leftover temp file: %v", err)
}
moveBehindSymlink(t, base, dir)
err = s.DeletePartialUploads(ctx, dir+"/")
if err != nil {
t.Fatalf("DeletePartialUploads: %v", err)
}
// leftover runs through the link.
_, err = os.Stat(leftover)
if !os.IsNotExist(err) {
t.Errorf("leftover temp file was not removed: %v", err)
}
_, err = s.Stat(ctx, key)
if err != nil {
t.Errorf("Stat of the real key: %v", err)
}
})
}
}
// 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
-11
View File
@@ -7,12 +7,10 @@ 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"
@@ -35,15 +33,6 @@ 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()
internal/storage/rclone_test.go
-39
View File
@@ -11,7 +11,6 @@ import (
"testing"
"github.com/rclone/rclone/fs"
"github.com/rclone/rclone/fs/config"
"github.com/rclone/rclone/fs/config/configmap"
"sneak.berlin/go/vaultik/internal/storage"
)
@@ -391,41 +390,3 @@ 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)
}
}
internal/storage/s3_test.go
+3 -69
View File
@@ -4,7 +4,6 @@ import (
"bytes"
"context"
"errors"
"io"
"net/http"
"net/http/httptest"
"slices"
@@ -23,16 +22,13 @@ import (
// s3TestBucket is the bucket created for each in-process S3 server.
const s3TestBucket = "test-bucket"
// Credentials for the tests' S3 clients. The test servers accept any.
// Credentials for the tests that build a storer from a config.Config. The
// in-process S3 server accepts any.
const (
s3TestAccessKeyID = "key"
s3TestSecretAccessKey = "secret"
)
// s3TestRegion is the region of the S3 clients built here with
// s3.NewClient. The test servers ignore it.
const s3TestRegion = "us-east-1"
// newS3Storer builds an s3:// backend backed by a fresh in-process
// S3 server. It reuses the same in-memory S3 harness (gofakes3 + s3mem
// over httptest) that internal/s3 and the not-found regression test use,
@@ -59,7 +55,7 @@ func newS3Storer(t *testing.T) storage.Storer {
Bucket: s3TestBucket,
AccessKeyID: "test",
SecretAccessKey: "test",
Region: s3TestRegion,
Region: "us-east-1",
})
if err != nil {
t.Fatalf("new client: %v", err)
@@ -97,68 +93,6 @@ func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
}
}
// TestS3ListingCutShortIsAnError checks that List and ListStream fail on a
// listing page marked truncated that carries no continuation token, as a
// server answering V2 listings V1-style sends it. Taken as the last page,
// it would hide every later key, and prune would treat the blobs of the
// snapshots listed there as unreferenced.
func TestS3ListingCutShortIsAnError(t *testing.T) {
t.Parallel()
const (
prefix = "metadata/"
truncatedPage = `<?xml version="1.0" encoding="UTF-8"?>
<ListBucketResult xmlns="http://s3.amazonaws.com/doc/2006-03-01/">
<Name>test-bucket</Name>
<Prefix>metadata/</Prefix>
<KeyCount>1</KeyCount>
<MaxKeys>1</MaxKeys>
<IsTruncated>true</IsTruncated>
<Contents>
<Key>metadata/snap/manifest.json.zst</Key>
<Size>8</Size>
</Contents>
</ListBucketResult>`
)
srv := httptest.NewServer(http.HandlerFunc(
func(w http.ResponseWriter, _ *http.Request) {
_, _ = io.WriteString(w, truncatedPage)
}))
t.Cleanup(srv.Close)
client, err := s3.NewClient(context.Background(), s3.Config{
Endpoint: srv.URL,
Bucket: s3TestBucket,
AccessKeyID: s3TestAccessKeyID,
SecretAccessKey: s3TestSecretAccessKey,
Region: s3TestRegion,
})
if err != nil {
t.Fatalf("new client: %v", err)
}
storer := storage.NewS3Storer(client)
ctx := context.Background()
keys, err := storer.List(ctx, prefix)
if !errors.Is(err, s3.ErrNoContinuationToken) {
t.Errorf("List = %q, %v; want ErrNoContinuationToken", keys, err)
}
var streamErr error
for obj := range storer.ListStream(ctx, prefix) {
if obj.Err != nil {
streamErr = obj.Err
}
}
if !errors.Is(streamErr, s3.ErrNoContinuationToken) {
t.Errorf("ListStream error = %v, want ErrNoContinuationToken", streamErr)
}
}
// TestS3URLPrefixKeyLayout pins the bucket keys an s3:// URL reads and
// writes: the README's remote storage layout, with the prefix joined to
// each key by one "/". s3://b/p and s3://b/p/ must be the same
internal/storage/storer.go
+1 -2
View File
@@ -41,8 +41,7 @@ type Info struct {
// directory for filesystem).
type Storer interface {
// Put stores data at the specified key.
// The filesystem backend fails when its destination directory does
// not exist, and creates the directories below it as needed.
// Parent directories are created automatically for filesystem backends.
Put(ctx context.Context, key string, data io.Reader) error
// PutWithProgress stores data with progress reporting.
internal/storage/url.go
+6 -47
View File
@@ -30,12 +30,6 @@ var (
"storage URL must not carry credentials; " +
"set s3.access_key_id and s3.secret_access_key in the config instead")
ErrURLUnknownParam = errors.New("unknown query parameter in storage URL")
ErrURLBadQuery = errors.New(
"storage URL query cannot be decoded; " +
"check it for a ; or a % not followed by two hex digits")
ErrRcloneRemoteParams = errors.New(
"rclone URL must not carry parameters in the remote name; " +
"set them on the remote with rclone config instead")
)
// URL represents a parsed storage URL.
@@ -96,9 +90,8 @@ func parseFileURL(rawPath string) (*URL, error) {
}
// parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
// the userinfo or in the endpoint parameter's userinfo, a query that
// cannot be decoded, and any query parameter other than endpoint, region
// and ssl, so a credential-bearing URL is never stored or echoed.
// the userinfo and any query parameter other than endpoint, region and
// ssl, so a credential-bearing URL is never stored or echoed.
func parseS3URL(rawURL string) (*URL, error) {
u, err := url.Parse(rawURL)
if err != nil {
@@ -114,26 +107,13 @@ func parseS3URL(rawURL string) (*URL, error) {
return nil, ErrMissingBucket
}
// u.Query() would silently drop a part it cannot decode, endpoint
// included. The decode error is not wrapped: it can quote the value.
query, err := url.ParseQuery(u.RawQuery)
if err != nil {
return nil, ErrURLBadQuery
}
query := u.Query()
err = rejectUnknownParams(query, "endpoint", "region", "ssl")
if err != nil {
return nil, err
}
// A host name never contains "@", so one in an endpoint, with or
// without a scheme, can only introduce userinfo.
for _, endpoint := range query["endpoint"] {
if strings.Contains(endpoint, "@") {
return nil, ErrURLCredentials
}
}
return &URL{
Scheme: schemeS3,
Bucket: bucket,
@@ -145,23 +125,9 @@ func parseS3URL(rawURL string) (*URL, error) {
}
// parseRcloneURL parses an rclone://remote/path URL. rclone:// takes no
// query parameters, so credentials in the userinfo, parameters in the
// remote name, a query that cannot be decoded and any query parameter at
// query parameters, so credentials in the userinfo and any parameter at
// all are rejected rather than silently ignored.
func parseRcloneURL(rawURL string) (*URL, error) {
// The remote name runs up to the first "/", "?" or "#". It never
// contains a comma; one starts rclone's remote,param=value form,
// whose values can be credentials. This is checked before url.Parse,
// whose error for such a name can print part of it.
remote := strings.TrimPrefix(rawURL, "rclone://")
if end := strings.IndexAny(remote, "/?#"); end >= 0 {
remote = remote[:end]
}
if strings.Contains(remote, ",") {
return nil, ErrRcloneRemoteParams
}
u, err := url.Parse(rawURL)
if err != nil {
return nil, wrapParseError(err)
@@ -171,19 +137,12 @@ func parseRcloneURL(rawURL string) (*URL, error) {
return nil, ErrURLCredentials
}
remote = u.Host
remote := u.Host
if remote == "" {
return nil, ErrMissingRemote
}
// As in parseS3URL: u.Query() would drop a part it cannot decode, and
// the decode error can quote the value.
query, err := url.ParseQuery(u.RawQuery)
if err != nil {
return nil, ErrURLBadQuery
}
err = rejectUnknownParams(query)
err = rejectUnknownParams(u.Query())
if err != nil {
return nil, err
}
internal/storage/url_parse_test.go
-119
View File
@@ -150,19 +150,6 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
wantErr: storage.ErrURLCredentials,
secrets: []string{key, secret, "mybucket"},
},
{
name: "s3 userinfo in endpoint",
raw: "s3://mybucket?endpoint=https://" +
key + ":" + secret + "@minio.example.com",
wantErr: storage.ErrURLCredentials,
secrets: []string{key, secret},
},
{
name: "s3 userinfo in endpoint without scheme",
raw: "s3://mybucket?endpoint=" + key + ":" + secret + "@minio.example.com",
wantErr: storage.ErrURLCredentials,
secrets: []string{key, secret},
},
{
name: "s3 unknown query param",
raw: "s3://mybucket?access_key=" + key + "&secret=" + secret,
@@ -216,112 +203,6 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
}
}
// TestParseStorageURLRejectsRcloneRemoteParams checks that an rclone
// remote name carrying parameters (rclone's "remote,param=value" form,
// which can hold a credential) is rejected without echoing the value,
// including the URLs that url.Parse itself refuses.
func TestParseStorageURLRejectsRcloneRemoteParams(t *testing.T) {
t.Parallel()
cases := []struct {
name string
raw string
secrets []string // must not appear in the error message
}{
{
name: "configured remote",
raw: "rclone://gdrive,client_secret=topsecret/backups",
secrets: []string{"topsecret"},
},
{
name: "remote defined inline",
raw: "rclone://:s3,access_key_id=KEY,secret_access_key=SECRET/bucket",
secrets: []string{"KEY", "SECRET"},
},
{
name: "colon in a parameter value",
raw: "rclone://gdrive,client_secret=ab:cd/backups",
secrets: []string{"cd"},
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
if !errors.Is(err, storage.ErrRcloneRemoteParams) {
t.Fatalf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, storage.ErrRcloneRemoteParams)
}
for _, secret := range tc.secrets {
if strings.Contains(err.Error(), secret) {
t.Errorf("error message leaked %q: %v", secret, err.Error())
}
}
})
}
}
// TestParseStorageURLRejectsUndecodableQuery checks that an s3 or rclone
// URL whose query cannot be decoded is rejected, not read with that part
// of the query left out, and that the error does not echo it.
func TestParseStorageURLRejectsUndecodableQuery(t *testing.T) {
t.Parallel()
const (
key = "AKIAKEY"
secret = "topsecret"
)
cases := []struct {
name string
raw string
}{
{
name: "semicolon",
raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
"@minio.example.com:9000;region=us-east-1",
},
{
name: "bad percent escape",
raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
"%zz@minio.example.com:9000",
},
{
name: "rclone semicolon",
raw: "rclone://gdrive/backups?token=" + secret + ";x=1",
},
{
name: "rclone bad percent escape",
raw: "rclone://gdrive/backups?token=" + secret + "%zz",
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
_, err := storage.ParseStorageURL(tc.raw)
if err == nil {
t.Fatalf("ParseStorageURL(%q) returned no error", tc.raw)
}
if !errors.Is(err, storage.ErrURLBadQuery) {
t.Errorf("ParseStorageURL(%q) error = %v, want %v",
tc.raw, err, storage.ErrURLBadQuery)
}
for _, s := range []string{key, secret, "minio.example.com"} {
if strings.Contains(err.Error(), s) {
t.Errorf("error message leaked %q: %v", s, err.Error())
}
}
})
}
}
// TestParseStorageURLParseFailureHidesURL checks that when url.Parse
// itself fails, the wrapped error carries only the inner cause, not the
// *url.Error whose text embeds the raw (possibly credential-bearing) URL.
internal/vaultik/blob_fetch.go
+2 -3
View File
@@ -104,8 +104,7 @@ func (v *Vaultik) FetchAndDecryptBlob(
// FetchBlob downloads a blob and returns a reader for the encrypted data.
// The reader is closed as soon as ctx is cancelled, which ends a read
// blocked inside it. A storage error is returned as is: restore and deep
// verify name the blob in their own errors.
// blocked inside it.
func (v *Vaultik) FetchBlob(
ctx context.Context, blobHash string,
) (io.ReadCloser, error) {
@@ -120,7 +119,7 @@ func (v *Vaultik) FetchBlob(
rc, err := v.Storage.Get(ctx, blobPath)
if err != nil {
return nil, err
return nil, fmt.Errorf("downloading blob %s: %w", shortHash(blobHash), err)
}
return newCloseOnCancelReader(ctx, rc), nil
internal/vaultik/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 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.
// 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.
//
// 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 := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
changedPath := filepath.Join(dataDir, "appended.bin")
@@ -184,7 +184,7 @@ func TestBackupAfterInterruptedRunRestoresChangedFile(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
changedPath := filepath.Join(dataDir, "appended.bin")
internal/vaultik/deep_verify_test.go
+1 -180
View File
@@ -1,20 +1,15 @@
package vaultik_test
import (
"bytes"
"context"
"crypto/rand"
"io"
"os"
"path"
"path/filepath"
"testing"
"github.com/spf13/afero"
"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"
"sneak.berlin/go/vaultik/internal/vaultik"
)
@@ -35,7 +30,7 @@ func TestDeepVerifyAcceptsHealthyAndRejectsCorruptBlob(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(64 * 1024)
@@ -82,180 +77,6 @@ func TestDeepVerifyAcceptsHealthyAndRejectsCorruptBlob(t *testing.T) {
"deep verify should fail on a corrupted blob")
}
// TestDeepVerifyJSONCountsBlobs checks the verified and missing counts
// that deep verify reports under --json: on a healthy snapshot, with a
// damaged blob, and with missing blobs. Deep verify stops at the first
// damaged blob, so the blobs read before it are the ones verified; when
// blobs are missing it reads no blob contents, but counts every missing
// blob.
func TestDeepVerifyJSONCountsBlobs(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
ctx := context.Background()
storeDir := t.TempDir()
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
healthy, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.NoError(t, err)
require.Equal(t, "ok", healthy.Status)
require.Len(t, keys, healthy.BlobCount)
require.Equal(t, healthy.BlobCount, healthy.Verified)
require.Zero(t, healthy.Missing)
// Damage the last blob read, keeping its length, so every blob before
// it is read and passes first.
lastPath := filepath.Join(storeDir, keys[len(keys)-1])
blob, err := afero.ReadFile(fs, lastPath)
require.NoError(t, err)
blob[len(blob)/2] ^= 0xff
require.NoError(t, afero.WriteFile(fs, lastPath, blob, 0o600))
got, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Equal(t, healthy.BlobCount-1, got.Verified)
require.Zero(t, got.Missing)
// Delete the first blob and the damaged last one: both must be
// counted as missing, not only the first one found.
var deletedSize int64
for _, key := range []string{keys[0], keys[len(keys)-1]} {
info, statErr := storer.Stat(ctx, key)
require.NoError(t, statErr)
deletedSize += info.Size
require.NoError(t, storer.Delete(ctx, key))
}
got, err = deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Equal(t, 2, got.Missing)
require.Equal(t, deletedSize, got.MissingSize)
require.Zero(t, got.Verified)
}
// TestDeepVerifyJSONCountsWrongSizeBlob checks that under --deep --json a
// blob of the wrong size is counted in mismatched and fails the run, and
// that the check goes on past it to count a missing blob after it. The
// store is on disk, so the message must not call it S3.
func TestDeepVerifyJSONCountsWrongSizeBlob(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
ctx := context.Background()
storeDir := t.TempDir()
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
// Make the first blob checked longer, and delete the last one.
firstPath := filepath.Join(storeDir, keys[0])
blob, err := afero.ReadFile(fs, firstPath)
require.NoError(t, err)
blob = append(blob, []byte("extra")...)
require.NoError(t, afero.WriteFile(fs, firstPath, blob, 0o600))
require.NoError(t, storer.Delete(ctx, keys[len(keys)-1]))
got, err := deepVerifyJSON(ctx, t, cfg, storer, snapshotID)
require.Error(t, err)
require.Equal(t, "failed", got.Status)
require.Equal(t, 1, got.Mismatched)
require.Equal(t, 1, got.Missing)
require.Zero(t, got.Verified)
require.Contains(t, got.ErrorMessage, "with the wrong size")
require.NotContains(t, got.ErrorMessage, "S3")
}
// TestDeepVerifyStopsOnBlobThatCannotBeChecked checks that a blob that is
// present in storage but cannot be checked is not counted as missing:
// deep verify stops and fails, saying it could not check the blob, with
// the storage error.
func TestDeepVerifyStopsOnBlobThatCannotBeChecked(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := t.TempDir()
cfg, storer, snapshotID, keys := backUpSeveralBlobs(ctx, t, storeDir)
failing := statFailingStorer{Storer: storer, failKeys: []string{keys[0]}}
got, err := deepVerifyJSON(ctx, t, cfg, failing, snapshotID)
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())
}
// backUpSeveralBlobs backs up random data, which does not compress or
// deduplicate, so it fills at least three blobs in a store on disk at
// storeDir. It returns the blobs' storage keys sorted, which is hash
// order, the order deep verify reads them in.
func backUpSeveralBlobs(
ctx context.Context, t *testing.T, storeDir string,
) (*config.Config, *storage.FileStorer, string, []string) {
t.Helper()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
maxBlobSize := int64(128 * 1024)
data := make([]byte, maxBlobSize*4)
_, err := rand.Read(data)
require.NoError(t, err)
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
require.NoError(t, afero.WriteFile(fs,
filepath.Join(dataDir, "data.bin"), data, 0o644))
cfg, storer, snapshotID := runFileStorageBackup(
ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
keys := storedBlobKeys(t, storeDir)
require.GreaterOrEqual(t, len(keys), 3)
return cfg, storer, snapshotID, keys
}
// deepVerifyJSON runs deep verify with --json on snapshotID and returns
// the decoded result and the error RunDeepVerify returned.
func deepVerifyJSON(
ctx context.Context, t *testing.T,
cfg *config.Config, storer storage.Storer, snapshotID string,
) (vaultik.VerifyResult, error) {
t.Helper()
var out bytes.Buffer
v := &vaultik.Vaultik{
Config: cfg,
Storage: storer,
Fs: afero.NewOsFs(),
Stdout: &out,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
err := v.RunDeepVerify(snapshotID,
&vaultik.VerifyOptions{Deep: true, JSON: true})
return decodeVerifyResult(t, out.Bytes()), err
}
// corruptOneBlob flips a middle byte of the first blob file found under
// blobsDir, leaving the file length unchanged.
func corruptOneBlob(t *testing.T, fs afero.Fs, blobsDir string) {
internal/vaultik/destination_marker.go
-74
View File
@@ -1,74 +0,0 @@
package vaultik
import (
"errors"
"fmt"
"strings"
"sneak.berlin/go/vaultik/internal/storage"
)
// destinationMarkerKey is the object every backup writes at the root of
// the backup destination store. While the local index holds a snapshot,
// 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 and the backup destination store has no marker.
var errDestinationNotPresent = errors.New("backup destination store is not present")
// checkDestinationMarker returns errDestinationNotPresent when the local
// index holds a snapshot and the backup destination 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.
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
}
_, 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
-239
View File
@@ -1,239 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"os"
"path/filepath"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/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)
}
// 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")
}
// 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/destination_validation_test.go
+1 -2
View File
@@ -161,14 +161,13 @@ func TestVerifyManifestBlobsRejectsShortHash(t *testing.T) {
Blobs: []snapshot.BlobInfo{{Hash: "abc", CompressedSize: 1}},
}
verified, missing, mismatched, missingSize, unchecked, err :=
verified, missing, mismatched, missingSize, err :=
v.verifyManifestBlobs(manifest, &VerifyOptions{JSON: true})
require.ErrorIs(t, err, errInvalidBlobHash)
require.Zero(t, verified)
require.Zero(t, missing)
require.Zero(t, mismatched)
require.Zero(t, missingSize)
require.Empty(t, unchecked)
}
// TestVerifyBlobChunksRejectsNegativeLength proves a blob_chunks row with a
internal/vaultik/fault_injection_test.go
+22 -29
View File
@@ -192,7 +192,7 @@ func assertRestoreRejectsDamagedBlob(
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -238,7 +238,7 @@ func TestDeepVerifyCatchesLyingBackend(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
@@ -290,7 +290,7 @@ func TestInterruptedBlobUploadRecordsNoUploadedBlob(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
@@ -298,6 +298,10 @@ func TestInterruptedBlobUploadRecordsNoUploadedBlob(t *testing.T) {
writeFaultSourceTree(t, fs, dataDir)
// No upload succeeds, so nothing creates the destination directory.
// It must exist for the listing below to show that no blob survived.
require.NoError(t, os.Mkdir(storeDir, 0o750))
inner, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
@@ -361,7 +365,7 @@ func TestBackupRetryAfterInterruptedUploadIsRestorable(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -425,7 +429,7 @@ func TestBackupSurvivesMetadataExportInterruption(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
@@ -441,10 +445,6 @@ func TestBackupSurvivesMetadataExportInterruption(t *testing.T) {
repos := database.NewRepositories(db)
// snapshot create writes the marker; this backup runs its steps one
// by one, so the marker is written here.
require.NoError(t, inner.Put(ctx, markerFile, strings.NewReader("")))
// Back up and complete with a working backend.
sm := newFaultSnapshotManager(fs, inner, cfg, repos)
scanner := newFaultScanner(fs, inner, cfg, repos)
@@ -493,14 +493,8 @@ func TestBackupSurvivesMetadataExportInterruption(t *testing.T) {
"shallow verify must report the missing manifest")
// snapshot list must not crash on the partial snapshot.
var listOut strings.Builder
reader.UI = ui.NewWithColor(&listOut, false)
require.NoError(t, reader.ListSnapshots(false),
"snapshot list must tolerate a partially-exported snapshot")
assert.NotContains(t, listOut.String(),
"Could not list backup destination store",
"snapshot list must read the partial snapshot from the destination")
}
// Scenario 2, repair: the process dies during the metadata export of a
@@ -517,7 +511,7 @@ func TestBackupCompletesOnlyAfterMetadataExport(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -667,18 +661,17 @@ func faultScannerFactory(
) snapshot.ScannerFactory {
return func(params snapshot.ScannerParams) *snapshot.Scanner {
return snapshot.NewScanner(snapshot.ScannerConfig{
FS: params.Fs,
Storage: storer,
ChunkSize: faultChunkSize,
MaxBlobSize: faultMaxBlobSize,
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
Repositories: repos,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: params.Exclude,
SkipErrors: params.SkipErrors,
PreviousSnapshotID: params.PreviousSnapshotID,
FS: params.Fs,
Storage: storer,
ChunkSize: faultChunkSize,
MaxBlobSize: faultMaxBlobSize,
CompressionLevel: cfg.CompressionLevel,
AgeRecipients: cfg.AgeRecipients,
Repositories: repos,
EnableProgress: params.EnableProgress,
UI: params.UI,
Exclude: params.Exclude,
SkipErrors: params.SkipErrors,
})
}
}
@@ -693,7 +686,7 @@ func TestRestoreReportsDiskFull(t *testing.T) {
osFS := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/helpers.go
+16
View File
@@ -89,6 +89,22 @@ type SnapshotInfo struct {
RemotePresent *bool `json:"remote_present"`
}
// formatBytes formats bytes in a human-readable format
func formatBytes(bytes int64) string {
const unit = 1024
if bytes < unit {
return fmt.Sprintf("%d B", bytes)
}
div, exp := int64(unit), 0
for n := bytes / unit; n >= unit; n /= unit {
div *= unit
exp++
}
return fmt.Sprintf("%.1f %cB", float64(bytes)/float64(div), "KMGTPE"[exp])
}
// parseSnapshotTimestamp extracts the timestamp from a snapshot ID
// Format: hostname_snapshotname_2026-01-12T14:41:15Z
func parseSnapshotTimestamp(snapshotID string) (time.Time, error) {
internal/vaultik/integration_test.go
+2 -2
View File
@@ -771,7 +771,7 @@ func TestEndToEndFileStorage(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -964,7 +964,7 @@ func TestDedupOnlySnapshotRestores(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/missing_destination_test.go
+16 -35
View File
@@ -24,11 +24,13 @@ import (
// that is not plugged in, cannot be listed. It is not an empty store, so
// no command may conclude from it that the local snapshots are gone.
// newFileDestinationVaultik returns a Vaultik that backs up the
// snapshot named "first" to a file:// destination at storeDir.
func newFileDestinationVaultik(
// backUpToFileDestination backs up the snapshot named "first" to a
// file:// destination at storeDir, which need not exist yet. Everything
// the returned Vaultik prints after the backup goes to the returned
// buffer.
func backUpToFileDestination(
ctx context.Context, t *testing.T, storeDir string,
) (*vaultik.Vaultik, *database.Repositories) {
) (*vaultik.Vaultik, *database.Repositories, *bytes.Buffer) {
t.Helper()
osFs := afero.NewOsFs()
@@ -47,22 +49,8 @@ func newFileDestinationVaultik(
repos := database.NewRepositories(db)
cfg := changedFileConfig(dataDir, dbPath)
v := newBackupVaultik(ctx, cfg, store, repos, db, osFs)
return newBackupVaultik(ctx, cfg, store, repos, db, osFs), repos
}
// backUpToFileDestination creates the directory storeDir, as a user must
// before the first backup, and backs up the snapshot named "first" to a
// file:// destination there. Everything the returned Vaultik prints
// after the backup goes to the returned buffer.
func backUpToFileDestination(
ctx context.Context, t *testing.T, storeDir string,
) (*vaultik.Vaultik, *database.Repositories, *bytes.Buffer) {
t.Helper()
require.NoError(t, os.MkdirAll(storeDir, 0o750))
v, repos := newFileDestinationVaultik(ctx, t, storeDir)
require.NoError(t, backUp(v, "first"))
out := &bytes.Buffer{}
@@ -87,28 +75,21 @@ func backUpThenUnplug(
return v, repos, out
}
// TestBackupFailsWhenDestinationDirectoryMissing checks that a backup to
// a file:// destination whose directory does not exist fails before it
// records a snapshot, and does not create the directory.
func TestBackupFailsWhenDestinationDirectoryMissing(t *testing.T) {
// TestFirstBackupCreatesDestinationDirectory checks that a first backup
// to a destination directory that does not exist yet creates it, and
// that the destination can be listed afterwards.
func TestFirstBackupCreatesDestinationDirectory(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
volume := filepath.Join(t.TempDir(), "volume")
v, repos := newFileDestinationVaultik(ctx, t, filepath.Join(volume, "backup"))
storeDir := filepath.Join(t.TempDir(), "volume", "backup")
v, _, out := backUpToFileDestination(ctx, t, storeDir)
err := backUp(v, "first")
require.ErrorIs(t, err, fs.ErrNotExist)
require.ErrorContains(t, err, "create it, or mount the volume it is on")
require.NoError(t, v.ListSnapshots(false))
_, err = os.Stat(volume)
require.ErrorIs(t, err, fs.ErrNotExist,
"the backup must not create the destination directory")
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
require.NoError(t, err)
assert.Empty(t, snapshots)
assert.NotContains(t, out.String(), "Could not list backup destination store")
assert.NotContains(t, out.String(), "not found in backup destination store")
}
// TestListSnapshotsWarnsWhenDestinationMissing checks that snapshot list
internal/vaultik/new_chunk_size_test.go
-133
View File
@@ -1,133 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"maps"
"path/filepath"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/chunker"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestNewChunkSizeOfChangedFileStaysFixed covers
// https://git.eeqj.de/sneak/vaultik/issues/311. A backup whose only change
// is a modified file lists the size of the chunks that change added as its
// NEW CHUNK SIZE, and a later backup that changes the file again leaves
// every earlier snapshot's figure as it was. The file's row in the local
// index is shared by all three snapshots and rewritten by each backup.
func TestNewChunkSizeOfChangedFileStaysFixed(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
dbPath := filepath.Join(tempDir, "index.sqlite")
changedPath := filepath.Join(dataDir, "changed.bin")
ctx := context.Background()
files := writeFaultSourceTree(t, fs, dataDir)
cfg := changedFileConfig(dataDir, dbPath)
appendRandomBytes(t, fs, files, changedPath, appendedFileSize)
store, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
require.NoError(t, backUp(v, "first"))
firstFiles := maps.Clone(files)
firstID := localSnapshotID(ctx, t, repos, "first")
appendRandomBytes(t, fs, files, changedPath, faultChunkSize)
require.NoError(t, backUp(v, "second"))
secondID := localSnapshotID(ctx, t, repos, "second")
secondAdded := sizeOfNewChunks(t, files, firstFiles)
require.Positive(t, secondAdded)
assert.Equal(t, secondAdded, listedNewChunkSizes(t, v)[secondID],
"the second snapshot must count the chunks the change added")
appendRandomBytes(t, fs, files, changedPath, faultChunkSize)
require.NoError(t, backUp(v, "third"))
sizes := listedNewChunkSizes(t, v)
assert.Equal(t, sizeOfNewChunks(t, firstFiles, nil), sizes[firstID],
"a later backup must not change the first snapshot's figure")
assert.Equal(t, secondAdded, sizes[secondID],
"a later backup must not change the second snapshot's figure")
}
// sizeOfNewChunks returns the total size of the distinct chunks of the
// files in after that no file in before has, cut the way the backup cuts
// them.
func sizeOfNewChunks(t *testing.T, after, before map[string][]byte) int64 {
t.Helper()
known := make(map[string]bool)
for _, chunk := range chunksOf(t, before) {
known[chunk.Hash] = true
}
var total int64
for _, chunk := range chunksOf(t, after) {
if !known[chunk.Hash] {
known[chunk.Hash] = true
total += chunk.Size
}
}
return total
}
// chunksOf returns the chunks of every file in files.
func chunksOf(t *testing.T, files map[string][]byte) []chunker.Chunk {
t.Helper()
c := chunker.NewChunker(faultChunkSize)
var all []chunker.Chunk
for _, content := range files {
chunks, err := c.ChunkReader(bytes.NewReader(content))
require.NoError(t, err)
all = append(all, chunks...)
}
return all
}
// listedNewChunkSizes runs `snapshot list --json` and returns each listed
// snapshot's new_chunk_size by snapshot ID.
func listedNewChunkSizes(t *testing.T, v *vaultik.Vaultik) map[string]int64 {
t.Helper()
var out bytes.Buffer
v.Stdout = &out
require.NoError(t, v.ListSnapshots(true))
sizes := make(map[string]int64)
for _, row := range decodeListJSON(t, out.String()) {
sizes[row.ID] = row.NewChunkSize
}
return sizes
}
internal/vaultik/nuke_remote_test.go
+2 -114
View File
@@ -5,28 +5,25 @@ import (
"io/fs"
"os"
"path/filepath"
"strings"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage/faultstore"
)
// TestNukeRemoteLeavesNoFiles checks that remote nuke leaves no file
// under a file:// destination, including the `.partial` files uploads
// killed part-way leave next to a snapshot's metadata and next to where a
// blob would have been, a snapshot's database whose manifest was never
// uploaded, and a file under blobs/ whose name is not a blob hash.
// blob would have been.
func TestNukeRemoteLeavesNoFiles(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, repos, out := backUpToFileDestination(ctx, t, storeDir)
v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
require.NoError(t, err)
@@ -39,9 +36,6 @@ func TestNukeRemoteLeavesNoFiles(t *testing.T) {
"db.zst.age-123456.partial"),
filepath.Join(storeDir, "blobs", hash[:2], hash[2:4],
hash+"-123456.partial"),
filepath.Join(storeDir, "metadata",
snapshot.RemoteSnapshotKey("no-manifest"), "db.zst.age"),
filepath.Join(storeDir, "blobs", "0b", "01", ".DS_Store"),
}
for _, leftover := range leftovers {
@@ -67,110 +61,4 @@ func TestNukeRemoteLeavesNoFiles(t *testing.T) {
})
require.NoError(t, err)
assert.Empty(t, files)
// Nuke deletes the blobs itself, so advice to run prune is wrong.
assert.Contains(t, out.String(), "Backup destination store is now empty.")
assert.NotContains(t, out.String(), "vaultik prune")
}
// TestNukeRemoteFailsWhenADeleteFails checks that remote nuke returns an
// error when a snapshot's metadata or a blob cannot be deleted, does not
// report the store empty, and advises running nuke again: prune deletes
// no metadata.
func TestNukeRemoteFailsWhenADeleteFails(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
for _, refusedPrefix := range []string{"metadata/", "blobs/"} {
t.Run(refusedPrefix, func(t *testing.T) {
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, _, out := backUpToFileDestination(ctx, t, storeDir)
store := faultstore.New(v.Storage)
store.OnDelete = func(key string) bool {
return strings.HasPrefix(key, refusedPrefix)
}
v.Storage = store
require.Error(t, v.NukeRemote(true))
assert.NotContains(t, out.String(), "now empty")
assert.Contains(t, out.String(), "vaultik remote nuke --force")
assert.NotContains(t, out.String(), "vaultik prune")
})
}
}
// 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.
func TestNukeRemoteNamesWhatIsLeft(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, _, out := backUpToFileDestination(ctx, t, storeDir)
const leftKey = "blobs/0b/01/.DS_Store"
leftPath := filepath.Join(storeDir, filepath.FromSlash(leftKey))
require.NoError(t, os.MkdirAll(filepath.Dir(leftPath), 0o750))
require.NoError(t, os.WriteFile(leftPath, []byte("finder"), 0o600))
store := faultstore.New(v.Storage)
store.OnDelete = func(key string) bool { return key == leftKey }
v.Storage = store
require.Error(t, v.NukeRemote(true))
assert.Contains(t, out.String(), leftKey)
assert.NotContains(t, out.String(), "now empty")
assert.Contains(t, out.String(), "vaultik remote nuke --force")
}
// TestNukeRemoteRefusesAnotherDestinationWithoutRetryAdvice checks that
// remote nuke, when the local index belongs to a different destination
// than the configured one, fails without advising to run nuke again:
// that run would fail the same way.
func TestNukeRemoteRefusesAnotherDestinationWithoutRetryAdvice(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.Config.StorageURL = "file://" + filepath.Join(t.TempDir(), "elsewhere")
err := v.NukeRemote(true)
require.ErrorContains(t, err, "bound to a different backup destination")
assert.NotContains(t, out.String(), "vaultik remote nuke --force")
}
// 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.
func TestNukeRemoteFailsWhenALocalSnapshotCannotBeRemoved(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, _, out := backUpToFileDestination(ctx, t, storeDir)
_, err := v.DB.Conn().ExecContext(ctx, `
CREATE TRIGGER refuse_snapshot_delete BEFORE DELETE ON snapshots
BEGIN SELECT RAISE(ABORT, 'simulated index error'); END`)
require.NoError(t, err)
require.Error(t, v.NukeRemote(true))
assert.NotContains(t, out.String(), "now empty")
assert.Contains(t, out.String(), "vaultik remote nuke --force")
}
internal/vaultik/prune.go
+26 -115
View File
@@ -19,19 +19,6 @@ type PruneOptions struct {
var errNukeRequiresForce = errors.New(
"nuke requires --force (this deletes ALL remote snapshots and blobs)")
// errBlobDeleteFailed reports unreferenced blobs prune could not delete.
var errBlobDeleteFailed = errors.New("blob(s) could not be deleted")
// errObjectsLeft reports objects remote nuke still finds on the backup
// destination store after deleting.
var errObjectsLeft = errors.New(
"object(s) still on the backup destination store")
// nukeCommandHint is the command suggested when a remote nuke could not
// delete everything: running it again deletes what is left, which
// `vaultik prune` does not do for snapshot metadata.
const nukeCommandHint = "vaultik remote nuke --force"
// metadataDirName is the top-level remote directory holding snapshot
// metadata.
const metadataDirName = "metadata"
@@ -40,12 +27,10 @@ const metadataDirName = "metadata"
// (blobs/<aa>/<bb>/<hash>).
const blobKeyParts = 4
// NukeRemote deletes every object under metadata/ and blobs/ in remote
// storage, whatever its name, along with any object an upload cut off
// part-way left under a temporary `.partial` name, and last the
// destination marker. It returns successfully only when a listing
// afterwards finds nothing left under metadata/ and blobs/, and the next
// backup then starts from scratch.
// NukeRemote deletes every snapshot's metadata and every blob from remote
// storage, along with any object an upload cut off part-way left under a
// temporary `.partial` name. After this returns successfully the bucket
// prefix is empty and the next backup starts from scratch.
//
// Refuses to run unless force is true. The caller is responsible for
// confirming with the user.
@@ -54,30 +39,6 @@ func (v *Vaultik) NukeRemote(force bool) error {
return errNukeRequiresForce
}
// Checked before anything is deleted: running nuke again would fail
// the same way, so the advice below must not follow this error.
err := v.EnsureStorageBinding()
if err != nil {
return err
}
err = v.emptyDestinationStore()
if err != nil {
v.UI.Warningf("Run '%s' again to delete what is left on the "+
"backup destination store.", nukeCommandHint)
return err
}
v.UI.Completef("Backup destination store is now empty.")
return nil
}
// emptyDestinationStore does the deleting for NukeRemote and stops at
// the first step that fails. It also fails when objects are still
// listed at the end, naming each one.
func (v *Vaultik) emptyDestinationStore() error {
v.UI.Beginf("Removing all snapshot metadata from backup destination store.")
_, err := v.RemoveAllSnapshots(&RemoveOptions{Force: true})
@@ -85,69 +46,27 @@ func (v *Vaultik) emptyDestinationStore() error {
return fmt.Errorf("removing all snapshots: %w", err)
}
v.UI.Beginf("Removing everything still present in backup destination store.")
v.UI.Beginf("Removing any blobs still present in backup destination store.")
var left []string
for _, prefix := range []string{"metadata/", "blobs/"} {
keys, err := v.deleteEverythingUnder(prefix)
if err != nil {
return err
}
left = append(left, keys...)
}
for _, key := range left {
v.UI.Warningf("Still on the backup destination store: %s", key)
}
if len(left) > 0 {
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)
err = v.PruneBlobs(&PruneOptions{Force: true})
if err != nil {
return fmt.Errorf("deleting %s: %w", destinationMarkerKey, err)
return fmt.Errorf("pruning blobs: %w", err)
}
// The file and rclone listings skip `.partial` objects, so the two
// steps above never delete them.
for _, prefix := range []string{"metadata/", "blobs/"} {
err = v.Storage.DeletePartialUploads(v.ctx, prefix)
if err != nil {
return fmt.Errorf("deleting partial uploads: %w", err)
}
}
v.UI.Completef("Backup destination store is now empty.")
return nil
}
// deleteEverythingUnder deletes every object under prefix, whatever its
// name, and returns the keys a listing afterwards still finds. A delete
// that fails is logged and the others still run; that object then
// shows up in the listing afterwards.
func (v *Vaultik) deleteEverythingUnder(prefix string) ([]string, error) {
keys, err := v.Storage.List(v.ctx, prefix)
if err != nil {
return nil, fmt.Errorf("listing %s: %w", prefix, err)
}
for _, key := range keys {
err = v.Storage.Delete(v.ctx, key)
if err != nil {
log.Error("Failed to delete object", "key", key, "error", err)
}
}
// The file and rclone listings skip `.partial` objects, so the
// deletes above never reach them.
err = v.Storage.DeletePartialUploads(v.ctx, prefix)
if err != nil {
return nil, fmt.Errorf("deleting partial uploads: %w", err)
}
left, err := v.Storage.List(v.ctx, prefix)
if err != nil {
return nil, fmt.Errorf("listing %s: %w", prefix, err)
}
return left, nil
}
// PruneBlobsResult contains the result of a blob prune operation
//
//nolint:tagliatelle // snake_case is the established JSON output format
@@ -212,7 +131,7 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
return v.outputPruneBlobsJSON(result)
}
v.UI.Infof("No unreferenced blobs to remove.")
v.printlnStdout("No unreferenced blobs to remove.")
return nil
}
@@ -220,17 +139,12 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
log.Info("Found unreferenced blobs",
"count", len(unreferencedBlobs), "total_size", ubytes(totalSize))
if opts.Force && !opts.JSON {
v.UI.Infof("Found %d unreferenced blob(s) totaling %s.",
if !opts.JSON {
v.stdoutf("Found %d unreferenced blob(s) totaling %s\n",
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
@@ -252,17 +166,14 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
v.deleteUnreferencedBlobs(unreferencedBlobs, allBlobs, result)
if opts.JSON {
err = v.outputPruneBlobsJSON(result)
if err != nil {
return err
}
} else {
v.UI.Infof("Deleted %d blob(s) totaling %s.",
result.BlobsDeleted, ubytes(result.BytesFreed))
return v.outputPruneBlobsJSON(result)
}
v.stdoutf("\nDeleted %d blob(s) totaling %s\n",
result.BlobsDeleted, ubytes(result.BytesFreed))
if result.BlobsFailed > 0 {
return fmt.Errorf("%d %w", result.BlobsFailed, errBlobDeleteFailed)
v.stdoutf("Failed to delete %d blob(s)\n", result.BlobsFailed)
}
return nil
internal/vaultik/prune_count_test.go
-60
View File
@@ -1,17 +1,13 @@
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
@@ -80,59 +76,3 @@ 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_delete_failure_test.go
-98
View File
@@ -1,98 +0,0 @@
package vaultik_test
import (
"context"
"encoding/json"
"os"
"path/filepath"
"strings"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage/faultstore"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// refuseBlobDeletes is an OnDelete hook that fails every blob delete.
func refuseBlobDeletes(key string) bool {
return strings.HasPrefix(key, "blobs/")
}
// TestPruneBlobs_FailedDeleteReturnsError checks that prune returns an
// error, so the command exits non-zero, when an unreferenced blob cannot
// be deleted.
func TestPruneBlobs_FailedDeleteReturnsError(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newListEnv(t)
// The store holds no manifest, so nothing references this blob.
addBlob(t, env.store.testStorer, testBlobHashA)
store := faultstore.New(env.store)
store.OnDelete = refuseBlobDeletes
env.v.Storage = store
err := env.v.PruneBlobs(&vaultik.PruneOptions{Force: true})
require.ErrorContains(t, err, "1 blob(s) could not be deleted")
}
// TestPruneBlobs_JSONFailedDeleteReturnsError checks that prune --json
// prints its document and then returns an error when an unreferenced
// blob cannot be deleted.
func TestPruneBlobs_JSONFailedDeleteReturnsError(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newListEnv(t)
addBlob(t, env.store.testStorer, testBlobHashA)
store := faultstore.New(env.store)
store.OnDelete = refuseBlobDeletes
env.v.Storage = store
err := env.v.PruneBlobs(&vaultik.PruneOptions{JSON: true})
require.Error(t, err, "prune must fail when a blob cannot be deleted")
var result vaultik.PruneBlobsResult
require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &result),
"stdout must hold the JSON document, got:\n%s", env.stdout.String())
assert.Equal(t, 1, result.BlobsFailed)
assert.Equal(t, 0, result.BlobsDeleted)
}
// TestCreateSnapshotPrune_FailedBlobDeleteReturnsError checks that the
// prune step of snapshot create --prune fails the run when an
// unreferenced blob cannot be deleted.
func TestCreateSnapshotPrune_FailedBlobDeleteReturnsError(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, _, _ := backUpToFileDestination(ctx, t, storeDir)
// No snapshot references this blob, so the prune step deletes it.
orphan := filepath.Join(storeDir, "blobs", testBlobHashA[:2],
testBlobHashA[2:4], testBlobHashA)
require.NoError(t, os.MkdirAll(filepath.Dir(orphan), 0o750))
require.NoError(t, os.WriteFile(orphan, []byte("orphan"), 0o600))
store := faultstore.New(v.Storage)
store.OnDelete = refuseBlobDeletes
v.Storage = store
err := v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Cron: true,
Prune: true,
})
require.ErrorContains(t, err, "1 blob(s) could not be deleted")
assert.FileExists(t, orphan)
}
internal/vaultik/purge_local_remote_consistency_test.go
+1 -8
View File
@@ -14,7 +14,6 @@ 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"
)
@@ -35,9 +34,6 @@ func setupConsistencyTest(
repos := database.NewRepositories(db)
mockStorage := NewMockStorer()
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, mockStorage.Put(ctx, markerFile, strings.NewReader("")))
for _, id := range snapshotIDs {
parts := strings.Split(id, "_")
startedAt, err := time.Parse(time.RFC3339, parts[len(parts)-1])
@@ -62,16 +58,13 @@ func setupConsistencyTest(
require.NoError(t, err)
}
stdout := &bytes.Buffer{}
v := &vaultik.Vaultik{
Storage: mockStorage,
Repositories: repos,
DB: db,
Stdout: stdout,
Stdout: &bytes.Buffer{},
Stderr: &bytes.Buffer{},
Stdin: &bytes.Buffer{},
UI: ui.NewWithColor(stdout, false),
}
v.SetContext(ctx)
internal/vaultik/purge_per_name_test.go
+1 -7
View File
@@ -14,7 +14,6 @@ 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"
)
@@ -45,9 +44,6 @@ func setupPurgeTest(
repos := database.NewRepositories(db)
mockStorage := NewMockStorer()
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, mockStorage.Put(ctx, markerFile, strings.NewReader("")))
// Insert each snapshot into the DB and create remote metadata stubs.
// Use timestamps parsed from snapshot IDs for realistic ordering.
for _, id := range snapshotIDs {
@@ -90,7 +86,6 @@ func setupPurgeTest(
Stdout: stdout,
Stderr: stderr,
Stdin: stdin,
UI: ui.NewWithColor(stdout, false),
}
v.SetContext(ctx)
@@ -284,8 +279,7 @@ func TestPurgeOlderThan_TooLargeDeletesNothing(t *testing.T) {
OlderThan: "1000y",
Force: true,
})
require.EqualError(t, err,
`invalid duration: "1000y" is longer than about 292 years`)
require.Error(t, err)
err = v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
OlderThan: "292y",
internal/vaultik/remove_quiet_test.go
-152
View File
@@ -1,152 +0,0 @@
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
+4 -53
View File
@@ -17,7 +17,6 @@ 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"
)
@@ -304,10 +303,6 @@ func TestRemoveSnapshot_DefaultRemovesMetadataNotBlobs(t *testing.T) {
addBlob(t, store, blobUnique)
addBlob(t, store, blobShared)
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, store.Put(context.Background(), markerFile,
bytes.NewReader(nil)))
tv := vaultik.NewForTesting(store)
tv.Repositories = newLocalIndex(t, "snapshot-001", "snapshot-002")
@@ -355,7 +350,7 @@ 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
@@ -377,10 +372,6 @@ func TestRemoveSnapshot_UnknownIDIsError(t *testing.T) {
store := newTestStorer()
addManifest(t, store, "snapshot-001", nil)
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, store.Put(context.Background(), markerFile,
bytes.NewReader(nil)))
tv := vaultik.NewForTesting(store)
tv.Repositories = newLocalIndex(t, "snapshot-001")
@@ -401,12 +392,7 @@ func TestRemoveSnapshot_NoMetadataOnDestination(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
// A backup wrote to this destination, so it carries the marker.
store := newTestStorer()
require.NoError(t, store.Put(context.Background(), markerFile,
bytes.NewReader(nil)))
tv := vaultik.NewForTesting(store)
tv := vaultik.NewForTesting(newTestStorer())
tv.Repositories = newLocalIndex(t, "snapshot-001")
result, err := tv.RemoveSnapshot("snapshot-001",
@@ -445,40 +431,6 @@ 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()
@@ -524,8 +476,7 @@ func TestRemoveAllSnapshots_WithForce(t *testing.T) {
out := tv.Stdout.String()
assert.Contains(t, out, "Removed 2 snapshot(s)")
assert.Contains(t, out, "Removed snapshot metadata from remote storage")
// Remote nuke, the only caller, deletes the blobs next itself.
assert.NotContains(t, out, "vaultik prune")
assert.Contains(t, out, "vaultik prune")
}
func TestRemoveAllSnapshots_DryRun(t *testing.T) {
@@ -552,7 +503,7 @@ 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
+35 -77
View File
@@ -27,7 +27,6 @@ import (
// Sentinel errors for restore failures.
var (
errFilesFailedRestore = errors.New("file(s) failed to restore")
errPathsNotInSnapshot = errors.New("requested path(s) not in the snapshot")
errFilesFailedVerify = errors.New("files failed verification")
errDecryptionKeyRequired = errors.New(
"decryption key required for restore\n\n" +
@@ -151,20 +150,16 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
repos := database.NewRepositories(tempDB)
// Step 2: Get list of files to restore
files, unmatched, err := v.getFilesToRestore(v.ctx, repos, opts.Paths)
files, err := v.getFilesToRestore(v.ctx, repos, opts.Paths)
if err != nil {
return fmt.Errorf("getting files to restore: %w", err)
}
// Named before anything is restored, so the names are shown even
// when the restore stops on an error.
unmatchedErr := v.reportUnmatchedPaths(unmatched)
if len(files) == 0 {
log.Warn("No files found to restore")
v.UI.Warningf("No files found to restore.")
return unmatchedErr
return nil
}
log.Info("Found files to restore", "count", len(files))
@@ -190,20 +185,6 @@ func (v *Vaultik) Restore(opts *RestoreOptions) error {
result.Duration = time.Since(startTime)
return v.finishRestore(repos, files, unmatchedErr, opts, result)
}
// finishRestore prints the restore summary and the post-restore
// warnings, runs optional verification, and converts any failed-file
// count into an error. Otherwise it returns unmatchedErr, the error for
// the requested paths that matched nothing (nil when there are none).
func (v *Vaultik) finishRestore(
repos *database.Repositories,
files []*database.File,
unmatchedErr error,
opts *RestoreOptions,
result *RestoreResult,
) error {
log.Info("Restore complete",
"files_restored", result.FilesRestored,
"bytes_restored", ubytes(result.BytesRestored),
@@ -218,6 +199,17 @@ func (v *Vaultik) finishRestore(
v.UI.Duration(result.Duration),
)
return v.finishRestore(repos, files, opts, result)
}
// finishRestore emits the post-restore warnings, runs optional
// verification, and converts any failed-file count into an error.
func (v *Vaultik) finishRestore(
repos *database.Repositories,
files []*database.File,
opts *RestoreOptions,
result *RestoreResult,
) error {
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 " +
@@ -244,23 +236,7 @@ func (v *Vaultik) finishRestore(
return fmt.Errorf("%d %w", result.FilesFailed, errFilesFailedRestore)
}
return unmatchedErr
}
// 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.
func (v *Vaultik) reportUnmatchedPaths(unmatched []string) error {
if len(unmatched) == 0 {
return nil
}
for _, path := range unmatched {
log.Warn("Requested path matches nothing in the snapshot", "path", path)
v.UI.Warningf("%s matches nothing in the snapshot.", v.UI.Path(path))
}
return fmt.Errorf("%d %w", len(unmatched), errPathsNotInSnapshot)
return nil
}
// restoreIdentities parses the configured age secret key once into every
@@ -323,33 +299,22 @@ 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
}
plan, unplanned, err := newRestorePlan(
v.ctx, repos, files, chunkToBlobMap, blobIDToHash)
plan, err := newRestorePlan(v.ctx, repos, files, chunkToBlobMap, blobIDToHash)
if err != nil {
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 {
err = v.handleRestoreFileError(plan, opts, result, file, file.ID, planErr)
if err != nil {
return nil, err
}
}
}
filesByID, totalBytesExpected := indexRestoreFiles(files)
v.UI.Beginf("Restoring %s files (%s) to %s.",
@@ -427,8 +392,10 @@ func (v *Vaultik) runRestoreLoop(
continue
}
// Drop the file from the plan's indexes so future picks ignore
// it and the sweeper can free blobs no pending file needs.
// 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())
plan.finishFile(fileID)
processed++
@@ -739,8 +706,6 @@ func (v *Vaultik) downloadSnapshotDB(
return nil, "", fmt.Errorf("downloading %s: %w", dbKey, err)
}
reader = newCloseOnCancelReader(v.ctx, reader)
defer func() { _ = reader.Close() }()
// Decrypt and decompress straight from the storage stream, then stream
@@ -862,34 +827,27 @@ func (v *Vaultik) materializeSnapshotDB(
return db, tempDir, nil
}
// getFilesToRestore returns the list of files to restore based on path
// filters, and the filters, as given, that matched no file.
// getFilesToRestore returns the list of files to restore based on path filters
func (v *Vaultik) getFilesToRestore(
ctx context.Context, repos *database.Repositories, pathFilters []string,
) ([]*database.File, []string, error) {
) ([]*database.File, error) {
// If no filters, get all files
if len(pathFilters) == 0 {
files, err := repos.Files.ListAll(ctx)
return files, nil, err
return repos.Files.ListAll(ctx)
}
// Get files matching the path filters
var (
result []*database.File
unmatched []string
)
var result []*database.File
seen := make(map[string]bool)
for _, filter := range pathFilters {
files, err := repos.Files.ListUnderPath(ctx, filepath.Clean(filter))
if err != nil {
return nil, nil, fmt.Errorf("listing files under %s: %w", filter, err)
}
// Normalize the filter path
filter = filepath.Clean(filter)
if len(files) == 0 {
unmatched = append(unmatched, filter)
files, err := repos.Files.ListUnderPath(ctx, filter)
if err != nil {
return nil, fmt.Errorf("listing files under %s: %w", filter, err)
}
for _, file := range files {
@@ -900,7 +858,7 @@ func (v *Vaultik) getFilesToRestore(
}
}
return result, unmatched, nil
return result, nil
}
// buildChunkToBlobMap creates a mapping from chunk hash to blob information
internal/vaultik/restore_another_machine_test.go
+1 -1
View File
@@ -42,7 +42,7 @@ func TestRestoreOnAnotherMachine(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/restore_interrupt_test.go
+58 -81
View File
@@ -65,7 +65,7 @@ func TestRestoreCleansTempDirOnInterrupt(t *testing.T) {
root := t.TempDir()
dataDir := filepath.Join(root, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(root, "remote")
restoreDir := filepath.Join(root, "restored")
dbPath := filepath.Join(root, "index.sqlite")
@@ -74,8 +74,7 @@ func TestRestoreCleansTempDirOnInterrupt(t *testing.T) {
buildLocalityFixture(t, fs, dataDir)
cfg, storer, snapshotID := setupLocalityBackup(
context.Background(), t, fs, dataDir, storeDir, dbPath,
localitySourceBytes)
context.Background(), t, fs, dataDir, storeDir, dbPath)
// Point the "" temp paths (the blob cache directory and the
// snapshot-database directory) at a private directory so the test can
@@ -208,37 +207,30 @@ func TestRestoreSkipErrorsCancelDuringBlobDownload(t *testing.T) {
"the cancel was reported as a failed file")
}
// stallingStorer wraps a Storer so that each download of a key chosen by
// stalls hands over the first half of the object and then stalls,
// ignoring the context, as a file:// read on a hung USB stick or network
// share does. Only closing the returned reader ends the stall.
type stallingStorer struct {
// stallingBlobStorer wraps a Storer so that every blob download hands
// over the first half of the blob and then stalls, ignoring the context,
// as a file:// blob on a hung USB stick or network share does. Only
// closing the returned reader ends the stall.
type stallingBlobStorer struct {
storage.Storer
stalls func(key string) bool
once sync.Once
stalled chan struct{}
}
func newStallingStorer(
inner storage.Storer, stalls func(key string) bool,
) *stallingStorer {
return &stallingStorer{
Storer: inner,
stalls: stalls,
stalled: make(chan struct{}),
}
func newStallingBlobStorer(inner storage.Storer) *stallingBlobStorer {
return &stallingBlobStorer{Storer: inner, stalled: make(chan struct{})}
}
func (s *stallingStorer) Get(
func (s *stallingBlobStorer) Get(
ctx context.Context, key string,
) (io.ReadCloser, error) {
rc, err := s.Storer.Get(ctx, key)
if err != nil || !s.stalls(key) {
if err != nil || !strings.HasPrefix(key, "blobs/") {
return rc, err
}
object, err := io.ReadAll(rc)
blob, err := io.ReadAll(rc)
_ = rc.Close()
if err != nil {
@@ -250,7 +242,7 @@ func (s *stallingStorer) Get(
pr, pw := io.Pipe()
go func() {
_, _ = pw.Write(object[:len(object)/2])
_, _ = pw.Write(blob[:len(blob)/2])
s.once.Do(func() { close(s.stalled) })
}()
@@ -258,26 +250,17 @@ func (s *stallingStorer) Get(
return pr, nil
}
// TestInterruptDuringStalledReadCleansTempDir stops a restore and a deep
// verify while a read of a blob or of the snapshot database is stalled
// on a source that ignores the context. Stopping must end that read, so
// the operation unwinds and removes its decrypted scratch files well
// within the shutdown timeout (issues #325 and #356).
// TestInterruptDuringStalledBlobReadCleansTempDir stops a restore and a
// deep verify while a blob read is stalled on a source that ignores the
// context. Stopping must end that read, so the operation unwinds and
// removes its decrypted scratch files well within the shutdown timeout
// (issue #325).
//
// Not parallel: it points TMPDIR at a private directory (via t.Setenv)
// so it can assert on exactly the scratch files the operation created.
func TestInterruptDuringStalledReadCleansTempDir(t *testing.T) {
func TestInterruptDuringStalledBlobReadCleansTempDir(t *testing.T) {
log.Initialize(log.Config{})
stalledReads := map[string]func(key string) bool{
"blob": func(key string) bool {
return strings.HasPrefix(key, "blobs/")
},
"snapshot database": func(key string) bool {
return strings.HasSuffix(key, "/db.zst.age")
},
}
operations := map[string]func(v *Vaultik, snapshotID, targetDir string) error{
"restore": func(v *Vaultik, snapshotID, targetDir string) error {
return v.Restore(&RestoreOptions{
@@ -290,58 +273,52 @@ func TestInterruptDuringStalledReadCleansTempDir(t *testing.T) {
},
}
for readName, stalls := range stalledReads {
for opName, op := range operations {
t.Run(readName+" read during "+opName, func(t *testing.T) {
fs := afero.NewOsFs()
root := t.TempDir()
for name, op := range operations {
t.Run(name, func(t *testing.T) {
fs := afero.NewOsFs()
root := t.TempDir()
// Random content, so the blob stays large enough to stall
// part-way through its compressed, encrypted body.
cfg, storer, snapshotID, _ := backupOneFile(context.Background(),
t, fs, root, "a.bin", randomBytes(t, 256*1024), 0o644)
// Random content, so the blob stays large enough to stall
// part-way through its compressed, encrypted body.
cfg, storer, snapshotID, _ := backupOneFile(context.Background(),
t, fs, root, "a.bin", randomBytes(t, 256*1024), 0o644)
scratch := filepath.Join(root, "scratch")
require.NoError(t, fs.MkdirAll(scratch, 0o755))
t.Setenv("TMPDIR", scratch)
scratch := filepath.Join(root, "scratch")
require.NoError(t, fs.MkdirAll(scratch, 0o755))
t.Setenv("TMPDIR", scratch)
stalling := newStallingStorer(storer, stalls)
stalling := newStallingBlobStorer(storer)
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
v := newRestoreVaultik(ctx, cfg, stalling, fs)
v.cancel = cancel
v := newRestoreVaultik(ctx, cfg, stalling, fs)
v.cancel = cancel
var opErr error
var opErr error
stop := v.StartOperation(func() {
opErr = op(v, snapshotID, filepath.Join(root, "restored"))
})
select {
case <-stalling.stalled:
case <-time.After(30 * time.Second):
t.Fatal("the operation never reached the stalled read")
}
// The snapshot database's temp directory is created just
// after its read starts, so it can appear after the stall.
require.Eventually(t, func() bool {
return len(scratchEntries(t, scratch)) > 0
}, 10*time.Second, 10*time.Millisecond,
"expected decrypted scratch files to exist mid-read")
stopCtx, stopCancel := context.WithTimeout(
context.Background(), 10*time.Second)
defer stopCancel()
require.True(t, stop(stopCtx),
"stop timed out; the stalled read was not interrupted")
require.ErrorIs(t, opErr, context.Canceled)
require.Empty(t, scratchEntries(t, scratch),
"decrypted scratch files remained after the interrupt")
stop := v.StartOperation(func() {
opErr = op(v, snapshotID, filepath.Join(root, "restored"))
})
}
select {
case <-stalling.stalled:
case <-time.After(30 * time.Second):
t.Fatal("the operation never reached a blob read")
}
require.NotEmpty(t, scratchEntries(t, scratch),
"expected decrypted scratch files to exist mid-read")
stopCtx, stopCancel := context.WithTimeout(
context.Background(), 10*time.Second)
defer stopCancel()
require.True(t, stop(stopCtx),
"stop timed out; the stalled blob read was not interrupted")
require.ErrorIs(t, opErr, context.Canceled)
require.Empty(t, scratchEntries(t, scratch),
"decrypted scratch files remained after the interrupt")
})
}
}
internal/vaultik/restore_locality_test.go
+12 -16
View File
@@ -63,10 +63,6 @@ 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
@@ -77,6 +73,7 @@ func buildLocalityFixture(
t.Helper()
const (
srcBytes = 1024 * 1024
srcCount = 15
blobsCount = 3
perBlob = srcCount / blobsCount
@@ -86,7 +83,7 @@ func buildLocalityFixture(
for i := range srcCount {
s := &localitySource{
path: fmt.Sprintf("src-%03d.bin", i+1),
data: randomBytes(t, localitySourceBytes),
data: randomBytes(t, srcBytes),
}
sources[i] = s
require.NoError(t, afero.WriteFile(
@@ -118,20 +115,19 @@ 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 of srcBytes pack into 3 blobs. The index database is closed
// before returning so the restore half runs from remote bytes only.
// files 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, srcBytes int64,
dataDir, storeDir, dbPath string,
) (*config.Config, *storage.FileStorer, string) {
t.Helper()
// 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
// 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)
storer, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
@@ -201,7 +197,7 @@ func TestRestoreLocalityAndReadAt(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
@@ -212,7 +208,7 @@ func TestRestoreLocalityAndReadAt(t *testing.T) {
ctx := context.Background()
cfg, storer, snapshotID := setupLocalityBackup(
ctx, t, fs, dataDir, storeDir, dbPath, localitySourceBytes)
ctx, t, fs, dataDir, storeDir, dbPath)
// Wrap the storer so we can count downloads per blob key.
counter := newCountingStorer(storer)
internal/vaultik/restore_malformed_db_test.go
+4 -6
View File
@@ -61,8 +61,8 @@ func craftedFile(
}
// TestRestoreShortChunkHashInNoBlob proves a file whose short chunk hash
// has no blob_chunks row is left out of the restore plan with an error,
// and fails the chunk write with an error.
// has no blob_chunks row fails restore planning and the chunk write with
// an error.
func TestRestoreShortChunkHashInNoBlob(t *testing.T) {
t.Parallel()
@@ -77,11 +77,9 @@ func TestRestoreShortChunkHashInNoBlob(t *testing.T) {
chunkToBlobMap, err := v.buildChunkToBlobMap(ctx, repos)
require.NoError(t, err)
plan, unplanned, err := newRestorePlan(ctx, repos, []*database.File{file},
_, err = newRestorePlan(ctx, repos, []*database.File{file},
chunkToBlobMap, map[string]string{})
require.NoError(t, err)
require.ErrorIs(t, unplanned[file.ID], errPlanChunkMissing)
require.False(t, plan.hasPending())
require.ErrorIs(t, err, errPlanChunkMissing)
fileChunks, err := repos.FileChunks.GetByFileID(ctx, file.ID)
require.NoError(t, err)
internal/vaultik/restore_perms_test.go
+1 -1
View File
@@ -107,7 +107,7 @@ func backupOneFile(
require.NoError(t, afero.WriteFile(fs, srcPath, content, mode))
require.NoError(t, fs.Chmod(srcPath, mode))
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
storer, err := storage.NewFileStorer(storeDir)
internal/vaultik/restore_plan.go
+9 -25
View File
@@ -31,8 +31,7 @@ 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, and by the sweeper to tell
// whether a cached blob is still needed.
// become ready" without a global scan.
type restorePlan struct {
fileBlobs map[types.FileID]map[string]struct{}
blobFiles map[string]map[types.FileID]struct{}
@@ -42,25 +41,20 @@ type restorePlan struct {
// newRestorePlan builds the file→blob index for the given files. Files
// whose chunks reference no blobs (symlinks, directories) start in the
// ready queue immediately. A file with a chunk that no blob holds cannot
// be restored: it is left out of the plan and returned, by ID, with the
// reason.
// ready queue immediately.
func newRestorePlan(
ctx context.Context,
repos *database.Repositories,
files []*database.File,
chunkToBlobMap map[string]*database.BlobChunk,
blobIDToHash map[string]string,
) (*restorePlan, map[types.FileID]error, error) {
) (*restorePlan, error) {
p := &restorePlan{
fileBlobs: make(map[types.FileID]map[string]struct{}, len(files)),
blobFiles: make(map[string]map[types.FileID]struct{}),
ready: make([]types.FileID, 0, len(files)),
cached: make(map[string]struct{}),
}
unplanned := make(map[types.FileID]error)
nextFile:
for _, f := range files {
if f.IsSymlink() || f.Mode&uint32(os.ModeDir) != 0 {
// No chunks to fetch — restore can run immediately.
@@ -72,7 +66,7 @@ nextFile:
fileChunks, err := repos.FileChunks.GetByFileID(ctx, f.ID)
if err != nil {
return nil, nil, fmt.Errorf("planning %s: %w", f.Path, err)
return nil, fmt.Errorf("planning %s: %w", f.Path, err)
}
blobs := make(map[string]struct{})
@@ -80,18 +74,14 @@ nextFile:
for _, fc := range fileChunks {
bc, ok := chunkToBlobMap[fc.ChunkHash.String()]
if !ok {
unplanned[f.ID] = fmt.Errorf("%w: %s",
errPlanChunkMissing, shortHash(fc.ChunkHash.String()))
continue nextFile
return nil, fmt.Errorf("planning %s: %w: %s",
f.Path, errPlanChunkMissing, shortHash(fc.ChunkHash.String()))
}
hash, ok := blobIDToHash[bc.BlobID.String()]
if !ok {
unplanned[f.ID] = fmt.Errorf("%w: %s",
errPlanBlobIDMissing, bc.BlobID)
continue nextFile
return nil, fmt.Errorf("planning %s: %w: %s",
f.Path, errPlanBlobIDMissing, bc.BlobID)
}
blobs[hash] = struct{}{}
@@ -113,7 +103,7 @@ nextFile:
}
}
return p, unplanned, nil
return p, nil
}
// markBlobCached records that the named blob is now resident in the
@@ -238,12 +228,6 @@ 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
@@ -63,6 +63,15 @@ 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.
@@ -74,15 +83,6 @@ 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
+18 -108
View File
@@ -30,8 +30,7 @@ const (
)
// missingBlobBackup is a snapshot of single-chunk files spread over two
// blobs, with one of those blobs lost: deleted from the store, or missing
// from the snapshot metadata.
// blobs, with one of those blobs deleted from the store.
type missingBlobBackup struct {
fs afero.Fs
cfg *config.Config
@@ -40,39 +39,20 @@ type missingBlobBackup struct {
restoreDir string
// files holds the original content by source path.
files map[string][]byte
// lost holds the source paths whose chunk is in the lost blob.
// lost holds the source paths whose chunk is in the deleted blob.
lost map[string]bool
}
// TestRestoreSkipErrorsSkipsFilesOfMissingBlob restores with SkipErrors
// after one blob of a two-blob snapshot was deleted from the store.
// after one blob of a two-blob snapshot was deleted. Every file stored in
// that blob must be reported as failed and left absent, every other file
// must be restored intact, and Restore must still return an error.
func TestRestoreSkipErrorsSkipsFilesOfMissingBlob(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
assertRestoreSkipsLostFiles(ctx, t, backupThenDeleteOneBlob(ctx, t))
}
// TestRestoreSkipErrorsSkipsFilesWithChunkInNoBlob restores with
// SkipErrors a snapshot whose metadata lists chunks that no blob holds, as
// earlier backup defects left behind.
func TestRestoreSkipErrorsSkipsFilesWithChunkInNoBlob(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
assertRestoreSkipsLostFiles(ctx, t, backupThenDropOneBlobFromMetadata(ctx, t))
}
// assertRestoreSkipsLostFiles restores backup with SkipErrors. Every file
// stored in the lost blob must be reported as failed and left absent,
// every other file must be restored intact, and Restore must still return
// an error.
func assertRestoreSkipsLostFiles(
ctx context.Context, t *testing.T, backup *missingBlobBackup,
) {
t.Helper()
backup := backupThenDeleteOneBlob(ctx, t)
var out bytes.Buffer
@@ -94,14 +74,14 @@ func assertRestoreSkipsLostFiles(
if backup.lost[path] {
assert.Containsf(t, out.String(), path,
"%s needs the lost blob and must be reported", path)
"%s needs the deleted blob and must be reported", path)
assert.NoFileExists(t, restored)
continue
}
got, err := afero.ReadFile(backup.fs, restored)
require.NoErrorf(t, err, "%s does not need the lost blob", path)
require.NoErrorf(t, err, "%s does not need the deleted blob", path)
assert.Equalf(t, content, got, "%s restored with wrong content", path)
}
}
@@ -231,8 +211,7 @@ func (f trailingByteFile) Close() error {
}
// TestRestoreMissingBlobAbortsWithoutSkipErrors checks that a deleted blob
// still ends the restore with an error when SkipErrors is not set, and
// that the error names the blob once.
// still ends the restore with an error when SkipErrors is not set.
func TestRestoreMissingBlobAbortsWithoutSkipErrors(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
@@ -248,32 +227,6 @@ func TestRestoreMissingBlobAbortsWithoutSkipErrors(t *testing.T) {
})
require.ErrorIs(t, err, storage.ErrNotFound)
assert.Equal(t, 1, strings.Count(err.Error(), "downloading blob"),
err.Error())
}
// TestRestoreChunkInNoBlobAbortsWithoutSkipErrors checks that a chunk held
// by no blob still ends the restore, before any file is written, when
// SkipErrors is not set.
func TestRestoreChunkInNoBlobAbortsWithoutSkipErrors(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
backup := backupThenDropOneBlobFromMetadata(ctx, t)
v := newReaderVaultik(ctx, backup.cfg, backup.storer, nil, backup.fs)
err := v.Restore(&vaultik.RestoreOptions{
SnapshotID: backup.snapshotID,
TargetDir: backup.restoreDir,
})
require.ErrorContains(t, err, "chunk missing from blob map")
for path := range backup.files {
assert.NoFileExists(t, filepath.Join(backup.restoreDir, path))
}
}
// backupThenDeleteOneBlob backs up missingBlobFileCount single-chunk
@@ -283,54 +236,6 @@ func backupThenDeleteOneBlob(
) *missingBlobBackup {
t.Helper()
backup, db, lostBlob := backupSingleChunkFiles(ctx, t)
require.NoError(t, db.Close())
require.NoError(t, backup.storer.Delete(ctx, fmt.Sprintf(
"blobs/%s/%s/%s", lostBlob[:2], lostBlob[2:4], lostBlob)))
return backup
}
// backupThenDropOneBlobFromMetadata backs up missingBlobFileCount
// single-chunk files, then removes the blob holding the first of them from
// the snapshot and exports the snapshot metadata again. The exported
// metadata then lists chunks that no blob holds.
func backupThenDropOneBlobFromMetadata(
ctx context.Context, t *testing.T,
) *missingBlobBackup {
t.Helper()
backup, db, lostBlob := backupSingleChunkFiles(ctx, t)
// The uploads row refers to the blob row, so it would keep the export
// from deleting it.
for _, query := range []string{
"DELETE FROM snapshot_blobs WHERE blob_hash = ?",
"DELETE FROM uploads WHERE blob_hash = ?",
} {
_, err := db.Conn().ExecContext(ctx, query, lostBlob)
require.NoError(t, err)
}
sm := newFaultSnapshotManager(
backup.fs, backup.storer, backup.cfg, database.NewRepositories(db))
require.NoError(t,
sm.ExportSnapshotMetadata(ctx, db.Path(), backup.snapshotID))
require.NoError(t, db.Close())
return backup
}
// backupSingleChunkFiles backs up missingBlobFileCount single-chunk files.
// It returns the backup, with lost naming the files stored in the same
// blob as the first of them, the still open local index, and the hash of
// that blob.
func backupSingleChunkFiles(
ctx context.Context, t *testing.T,
) (*missingBlobBackup, *database.DB, string) {
t.Helper()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
@@ -348,7 +253,7 @@ func backupSingleChunkFiles(
require.NoError(t, afero.WriteFile(fs, path, files[path], 0o644))
}
storer, err := storage.NewFileStorer(t.TempDir())
storer, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
@@ -364,11 +269,16 @@ func backupSingleChunkFiles(
blobOfFile[path] = blobHashOfSingleChunkFile(ctx, t, repos, path)
}
lostBlob := blobOfFile[filepath.Join(dataDir, "file-00.bin")]
require.NoError(t, db.Close())
deleted := blobOfFile[filepath.Join(dataDir, "file-00.bin")]
require.NoError(t, storer.Delete(ctx, fmt.Sprintf(
"blobs/%s/%s/%s", deleted[:2], deleted[2:4], deleted)))
lost := make(map[string]bool)
for path, hash := range blobOfFile {
if hash == lostBlob {
if hash == deleted {
lost[path] = true
}
}
@@ -384,7 +294,7 @@ func backupSingleChunkFiles(
restoreDir: filepath.Join(tempDir, "restored"),
files: files,
lost: lost,
}, db, lostBlob
}
}
// blobHashOfSingleChunkFile returns the hash of the blob holding the one
internal/vaultik/restore_snapshot_identity_test.go
+2 -2
View File
@@ -29,7 +29,7 @@ func TestRestoreAndDeepVerifyRejectSwappedDatabase(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
chunkSize := int64(64 * 1024)
@@ -100,7 +100,7 @@ func TestDeepVerifyRejectsSwappedDatabaseWithEmptyManifest(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
chunkSize := int64(64 * 1024)
internal/vaultik/restore_sweeper.go
+88 -14
View File
@@ -1,30 +1,46 @@
package vaultik
// restoreSweeper frees cached blobs once no file still to be restored in
// this run needs them. It works as follows:
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:
//
// 1. After each chunk is restored, chunkRestored accumulates a running
// 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
// byte count.
// 2. When the accumulator crosses a threshold (one hundredth of the
// 3. 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 and deletes each blob that the restore plan no longer
// needs.
// 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 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.
// 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.
type restoreSweeper struct {
plan *restorePlan
ctx context.Context //nolint:containedctx // ctx bound at construction by design
repos *database.Repositories
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(
plan *restorePlan,
ctx context.Context,
repos *database.Repositories,
cache *blobDiskCache,
threshold int64,
) *restoreSweeper {
@@ -33,12 +49,21 @@ func newRestoreSweeper(
}
return &restoreSweeper{
plan: plan,
ctx: ctx,
repos: repos,
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) {
@@ -51,11 +76,60 @@ func (s *restoreSweeper) chunkRestored(n int64) {
s.sweep()
}
// sweep deletes every cached blob that no pending file references.
// 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.
func (s *restoreSweeper) sweep() {
for _, blobHash := range s.cache.Keys() {
if !s.plan.pendingFileUsesBlob(blobHash) {
needed, err := s.blobStillNeeded(blobHash)
if err != nil {
log.Debug("sweeper referencing-files query failed",
"blob_hash", blobHash[:16], "error", err)
continue
}
if !needed {
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 := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/restore_sweeper_test.go
-163
View File
@@ -1,163 +0,0 @@
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 := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/restore_unmatched_path_test.go
-202
View File
@@ -1,202 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"os"
"path/filepath"
"strings"
"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/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"
)
// These tests cover https://git.eeqj.de/sneak/vaultik/issues/309: a path
// given to restore that matches nothing in the snapshot is named in a
// warning and makes the restore fail, after the paths that do match are
// restored.
func TestRestoreNamesUnmatchedPathAndRestoresTheMatchingOne(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()
files := writeFaultSourceTree(t, fs, dataDir)
store, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
id := fullFaultBackup(ctx, t, fs, store, cfg,
database.NewRepositories(db), dataDir, dbPath, "unmatched")
require.NoError(t, db.Close())
matched := filepath.Join(dataDir, "small.txt")
unmatched := filepath.Join(dataDir, "typo.txt")
var out bytes.Buffer
v := newReaderVaultik(ctx, cfg, store, nil, fs)
v.UI = ui.NewWithColor(&out, false)
err = v.Restore(&vaultik.RestoreOptions{
SnapshotID: id,
TargetDir: restoreDir,
Paths: []string{matched, unmatched},
})
require.Error(t, err, "a path that matches nothing must fail the restore")
assert.Contains(t, out.String(), unmatched,
"the path that matches nothing must be named")
assert.NotContains(t, out.String(), matched,
"the path that matches must not be reported")
got, err := afero.ReadFile(fs, filepath.Join(restoreDir, matched))
require.NoError(t, err, "the path that matches must still be restored")
assert.Equal(t, files[matched], got)
}
// When no requested path matches, nothing is restored and each path is
// named. One path is relative. The other goes through the symlink that
// is the snapshot's configured path, while the entries are stored under
// the directory the symlink points to.
func TestRestoreNamesEveryPathWhenNothingMatches(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
const snapshotName = "linked"
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
linkDir := filepath.Join(tempDir, "srclink")
storeDir := t.TempDir()
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
ctx := context.Background()
writeFaultSourceTree(t, fs, dataDir)
require.NoError(t, os.Symlink(dataDir, linkDir))
cfg := faultTestConfig()
cfg.IndexPath = dbPath
cfg.ChunkSize = config.Size(faultChunkSize)
cfg.Snapshots = map[string]config.SnapshotConfig{
snapshotName: {Paths: []string{linkDir}},
}
store, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
repos := database.NewRepositories(db)
v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
require.NoError(t, backUp(v, snapshotName))
id := localSnapshotID(ctx, t, repos, snapshotName)
require.NoError(t, db.Close())
throughLink := filepath.Join(linkDir, "sub")
relative := strings.TrimPrefix(filepath.Join(dataDir, "small.txt"), "/")
var out bytes.Buffer
reader := newReaderVaultik(ctx, cfg, store, nil, fs)
reader.UI = ui.NewWithColor(&out, false)
err = reader.Restore(&vaultik.RestoreOptions{
SnapshotID: id,
TargetDir: restoreDir,
Paths: []string{throughLink, relative},
})
require.Error(t, err, "a restore that matches nothing must fail")
assert.Contains(t, out.String(), throughLink,
"the path through the symlink must be named")
assert.Contains(t, out.String(), relative,
"the relative path must be named")
_, err = fs.Stat(restoreDir)
assert.True(t, os.IsNotExist(err), "nothing must be restored")
}
// Without --skip-errors a damaged blob stops the restore part way. The
// path that matches nothing must still be named.
func TestRestoreNamesUnmatchedPathWhenADamagedBlobStopsIt(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()
writeFaultSourceTree(t, fs, dataDir)
inner, err := storage.NewFileStorer(storeDir)
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
id := fullFaultBackup(ctx, t, fs, inner, cfg,
database.NewRepositories(db), dataDir, dbPath, "damaged")
require.NoError(t, db.Close())
damaged := faultstore.New(inner)
damaged.OnGet = func(key string) faultstore.GetFault {
if strings.HasPrefix(key, "blobs/") {
return faultstore.GetCorrupt
}
return faultstore.GetNormal
}
matched := filepath.Join(dataDir, "small.txt")
unmatched := filepath.Join(dataDir, "typo.txt")
var out bytes.Buffer
v := newReaderVaultik(ctx, cfg, damaged, nil, fs)
v.UI = ui.NewWithColor(&out, false)
err = v.Restore(&vaultik.RestoreOptions{
SnapshotID: id,
TargetDir: restoreDir,
Paths: []string{matched, unmatched},
})
require.Error(t, err, "a damaged blob must stop the restore")
assert.Contains(t, err.Error(), "blob",
"the restore must stop on the damaged blob")
assert.Contains(t, out.String(), unmatched,
"the path that matches nothing must be named")
}
internal/vaultik/reused_blob_verify_test.go
-83
View File
@@ -1,83 +0,0 @@
package vaultik_test
import (
"context"
"io"
"path/filepath"
"testing"
"filippo.io/age"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestVerifyPassesWhenBackupReusesStoredBlob backs up a file, then backs it
// up again from an empty local index, as after `database delete`, with an
// extra age recipient. The second backup builds the same blob, finds it
// already stored and skips the upload, but its own copy is larger, because
// age writes a header entry for each recipient. The second snapshot must
// record the size of the stored object, so shallow and deep verify pass.
func TestVerifyPassesWhenBackupReusesStoredBlob(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
secondDBPath := filepath.Join(tempDir, "second.sqlite")
chunkSize := int64(64 * 1024)
maxBlobSize := int64(512 * 1024)
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
require.NoError(t, afero.WriteFile(fs,
filepath.Join(dataDir, "data.bin"),
bytesPattern("reuse-", int(chunkSize*3)), 0o644))
ctx := context.Background()
runFileStorageBackup(ctx, t, fs, dataDir, storeDir,
filepath.Join(tempDir, "first.sqlite"), chunkSize, maxBlobSize)
env := setupDedupBackupEnv(
ctx, t, fs, storeDir, secondDBPath, chunkSize, maxBlobSize)
defer func() { _ = env.db.Close() }()
extra, err := age.GenerateX25519Identity()
require.NoError(t, err)
env.cfg.AgeRecipients = append(env.cfg.AgeRecipients,
extra.Recipient().String())
snapshotID, result := runDedupSnapshot(ctx, t, env.sm, env.makeScanner(),
env.cfg.Hostname, "second", dataDir, secondDBPath)
require.Positive(t, result.BlobsCreated)
require.Zero(t, result.BlobsUploaded,
"the second backup should find every blob already stored")
require.NoError(t, env.db.Close())
verifier := &vaultik.Vaultik{
Config: env.cfg,
Storage: env.storer,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
verifier.SetContext(ctx)
require.NoError(t,
verifier.VerifySnapshotWithOptions(snapshotID, &vaultik.VerifyOptions{}),
"shallow verify should pass")
require.NoError(t,
verifier.VerifySnapshotWithOptions(snapshotID,
&vaultik.VerifyOptions{Deep: true}),
"deep verify should pass")
}
internal/vaultik/same_second_rewrite_test.go
+1 -1
View File
@@ -25,7 +25,7 @@ func TestBackupOfSameSecondRewriteRestoresNewContent(t *testing.T) {
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
rewrittenPath := filepath.Join(dataDir, "small.txt")
internal/vaultik/shallow_verify_test.go
+3 -232
View File
@@ -4,20 +4,15 @@ import (
"bytes"
"context"
"encoding/json"
"errors"
"fmt"
"io"
"os"
"path"
"path/filepath"
"slices"
"testing"
"github.com/spf13/afero"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
@@ -27,7 +22,7 @@ import (
// then grows one stored blob so its size no longer matches the manifest.
// Shallow verify must then fail, count the grown blob as a size mismatch,
// and drop it from the verified count rather than continuing to report it
// as checked, and its error must not repeat the cli layer's prefix.
// as checked.
func TestShallowVerifyDetectsWrongBlobSize(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
@@ -36,7 +31,7 @@ func TestShallowVerifyDetectsWrongBlobSize(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
@@ -96,12 +91,6 @@ func TestShallowVerifyDetectsWrongBlobSize(t *testing.T) {
require.Equal(t, 1, bad.Mismatched)
require.Equal(t, healthy.BlobCount-1, bad.Verified,
"the wrong-sized blob must not be counted as verified")
// The cli layer prints this error after its own "Verification failed:".
err = newVerifier(io.Discard).VerifySnapshotWithOptions(
snapshotID, &vaultik.VerifyOptions{})
require.EqualError(t, err,
"problems found in storage: 1 blobs have the wrong size")
}
// TestShallowVerifyDetectsMissingDatabase backs up a real snapshot,
@@ -116,7 +105,7 @@ func TestShallowVerifyDetectsMissingDatabase(t *testing.T) {
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
@@ -162,224 +151,6 @@ func TestShallowVerifyDetectsMissingDatabase(t *testing.T) {
"shallow verify must fail when db.zst.age is absent")
}
// errStatDenied stands in for any storage error other than not-found: a
// permission error, an S3 403, a dropped connection.
var errStatDenied = errors.New("injected stat failure")
// statFailingStorer fails Stat with errStatDenied for the keys in
// failKeys and passes every other call to the wrapped Storer.
type statFailingStorer struct {
storage.Storer
failKeys []string
}
func (s statFailingStorer) Stat(
ctx context.Context, key string,
) (*storage.ObjectInfo, error) {
if slices.Contains(s.failKeys, key) {
return nil, fmt.Errorf("stat %q: %w", key, errStatDenied)
}
return s.Storer.Stat(ctx, key)
}
// TestShallowVerifyReportsStatErrorsApartFromMissing backs up a real
// snapshot, deletes one blob, and makes storage fail Stat with an error
// other than not-found for a second blob and for the encrypted database.
// Only the deleted blob may be counted as missing. The second blob and
// the database must be reported as could not be checked, with the error
// storage returned, and verify must fail, in the text output and under
// --json.
func TestShallowVerifyReportsStatErrorsApartFromMissing(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
maxBlobSize := int64(128 * 1024)
// Random content, so the snapshot spans several blobs.
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
appendRandomBytes(t, fs, map[string][]byte{},
filepath.Join(dataDir, "data.bin"), maxBlobSize*4)
ctx := context.Background()
cfg, storer, snapshotID := runFileStorageBackup(
ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
blobKeys := storedBlobKeys(t, storeDir)
require.GreaterOrEqual(t, len(blobKeys), 2, "expected at least two blobs")
missingKey, uncheckedKey := blobKeys[0], blobKeys[1]
missingHash, uncheckedHash := path.Base(missingKey), path.Base(uncheckedKey)
require.NoError(t, os.Remove(filepath.Join(storeDir, missingKey)))
dbKey := "metadata/" + snapshot.RemoteSnapshotKey(snapshotID) + "/db.zst.age"
failing := statFailingStorer{
Storer: storer,
failKeys: []string{uncheckedKey, dbKey},
}
newVerifier := func(out io.Writer) *vaultik.Vaultik {
v := &vaultik.Vaultik{
Config: cfg,
Storage: failing,
Fs: fs,
Stdout: out,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
return v
}
var out bytes.Buffer
err := newVerifier(&out).VerifySnapshotWithOptions(
snapshotID, &vaultik.VerifyOptions{JSON: true})
require.Error(t, err)
result := decodeVerifyResult(t, out.Bytes())
require.Equal(t, "failed", result.Status)
require.Equal(t, 1, result.Missing, "only the deleted blob is missing")
require.Equal(t, result.BlobCount-2, result.Verified)
require.Len(t, result.Unchecked, 1)
require.Equal(t, uncheckedHash, result.Unchecked[0].Hash)
require.Contains(t, result.Unchecked[0].Error, errStatDenied.Error())
require.False(t, result.DatabaseMissing,
"a database that could not be checked is not missing")
require.Contains(t, result.DatabaseCheckError, errStatDenied.Error())
out.Reset()
err = newVerifier(&out).VerifySnapshotWithOptions(
snapshotID, &vaultik.VerifyOptions{})
require.Error(t, err)
text := out.String()
require.Contains(t, text, "Missing: "+missingHash)
require.NotContains(t, text, "Missing: "+uncheckedHash)
require.Contains(t, text, "Could not check: "+uncheckedHash)
require.Contains(t, text, "Encrypted database: could not be checked")
require.Contains(t, text, errStatDenied.Error())
require.Contains(t, text, "FAILED")
}
// TestShallowVerifyQuietFailsOnStatErrorAlone backs up a healthy snapshot,
// then makes storage fail Stat, with an error other than not-found, for
// one blob alone and then for the encrypted database alone. Each run must
// fail verify, and under --quiet, which drops the report, the error
// storage returned must still reach stderr.
//
//nolint:paralleltest // captureProcessStderr replaces os.Stderr
func TestShallowVerifyQuietFailsOnStatErrorAlone(t *testing.T) {
log.Initialize(log.Config{})
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "source")
storeDir := t.TempDir()
dbPath := filepath.Join(tempDir, "index.sqlite")
chunkSize := int64(32 * 1024)
maxBlobSize := int64(128 * 1024)
require.NoError(t, fs.MkdirAll(dataDir, 0o755))
require.NoError(t, afero.WriteFile(fs,
filepath.Join(dataDir, "data.bin"),
bytesPattern("shallow-quiet-", int(maxBlobSize*2)), 0o644))
ctx := context.Background()
cfg, storer, snapshotID := runFileStorageBackup(
ctx, t, fs, dataDir, storeDir, dbPath, chunkSize, maxBlobSize)
newQuietVerifier := func(s storage.Storer) *vaultik.Vaultik {
v := &vaultik.Vaultik{
Config: cfg,
Storage: s,
Fs: fs,
Stdout: io.Discard,
Stderr: io.Discard,
UI: ui.NewWithColor(io.Discard, false),
}
v.SetContext(ctx)
v.UI.SetQuiet(true)
return v
}
require.NoError(t,
newQuietVerifier(storer).VerifySnapshotWithOptions(
snapshotID, &vaultik.VerifyOptions{}),
"shallow verify should pass on a healthy snapshot")
blobKeys := storedBlobKeys(t, storeDir)
require.NotEmpty(t, blobKeys)
dbKey := "metadata/" + snapshot.RemoteSnapshotKey(snapshotID) + "/db.zst.age"
for _, failKey := range []string{blobKeys[0], dbKey} {
v := newQuietVerifier(statFailingStorer{
Storer: storer,
failKeys: []string{failKey},
})
var err error
stderr := captureProcessStderr(t, func() {
err = v.VerifySnapshotWithOptions(
snapshotID, &vaultik.VerifyOptions{})
})
require.Error(t, err,
"verify must fail when %s could not be checked", failKey)
require.Contains(t, stderr, errStatDenied.Error(),
"under --quiet the error for %s must still reach stderr", failKey)
}
}
// storedBlobKeys returns the storage key of every blob file under
// storeDir, sorted.
func storedBlobKeys(t *testing.T, storeDir string) []string {
t.Helper()
var keys []string
err := filepath.Walk(filepath.Join(storeDir, "blobs"),
func(p string, info os.FileInfo, err error) error {
if err != nil {
return err
}
if info.IsDir() {
return nil
}
rel, err := filepath.Rel(storeDir, p)
if err != nil {
return err
}
keys = append(keys, filepath.ToSlash(rel))
return nil
})
require.NoError(t, err)
return keys
}
// growOneBlob appends bytes to the first blob file found under blobsDir,
// changing its on-disk size so it no longer matches the manifest.
func growOneBlob(t *testing.T, fs afero.Fs, blobsDir string) {
internal/vaultik/snapshot.go
+123 -283
View File
@@ -14,7 +14,6 @@ import (
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/types"
)
@@ -23,10 +22,8 @@ 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")
errInvalidTableName = errors.New("invalid table name")
errNoAgeRecipients = errors.New(
"creating a snapshot needs at least one public key in " +
@@ -95,13 +92,6 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
return err
}
// Before PruneDatabase: it drops incomplete snapshots, which could
// leave the local index without one and so skip the marker check.
err = v.markDestination()
if err != nil {
return err
}
// Clean up incomplete snapshots FIRST, before any scanning.
// This is critical for data safety; PruneDatabase below does it.
hostname := v.Config.Hostname
@@ -124,9 +114,21 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
return fmt.Errorf("prune database: %w", err)
}
snapshotNames, err := v.snapshotNamesToCreate(opts.Snapshots)
if err != nil {
return err
// Determine which snapshots to process
snapshotNames := opts.Snapshots
if len(snapshotNames) == 0 {
snapshotNames = v.Config.SnapshotNames()
} else {
// Validate requested snapshot names exist
for _, name := range snapshotNames {
if _, ok := v.Config.Snapshots[name]; !ok {
return fmt.Errorf("%w: %q", errSnapshotNotInConfig, name)
}
}
}
if len(snapshotNames) == 0 {
return errNoSnapshotsInConfig
}
// Process each named snapshot
@@ -166,28 +168,6 @@ 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
@@ -229,7 +209,6 @@ type snapshotStats struct {
totalFiles int
totalBytes int64
totalChunks int
newChunkSize int64
totalBlobs int
totalBytesSkipped int64
totalFilesSkipped int
@@ -261,18 +240,12 @@ func (v *Vaultik) createNamedSnapshot(
return err
}
previousSnapshotID, err := v.previousSnapshotID(snapName)
if err != nil {
return err
}
scanner := v.ScannerFactory(snapshot.ScannerParams{
EnableProgress: !opts.Cron,
UI: v.UI,
Fs: v.Fs,
Exclude: v.Config.GetExcludes(snapName),
SkipErrors: opts.SkipErrors,
PreviousSnapshotID: previousSnapshotID,
EnableProgress: !opts.Cron,
UI: v.UI,
Fs: v.Fs,
Exclude: v.Config.GetExcludes(snapName),
SkipErrors: opts.SkipErrors,
})
snapshotID, err := v.SnapshotManager.CreateSnapshotWithName(
@@ -307,24 +280,6 @@ func (v *Vaultik) createNamedSnapshot(
return 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
// with symlink resolution.
func (v *Vaultik) resolveSnapshotPaths(snapName string) ([]string, error) {
@@ -386,7 +341,6 @@ func (v *Vaultik) scanAllDirectories(
stats.totalFiles += result.FilesScanned
stats.totalBytes += result.BytesScanned
stats.totalChunks += result.ChunksCreated
stats.newChunkSize += result.NewChunkSize
stats.totalBlobs += result.BlobsCreated
stats.totalFilesSkipped += result.FilesSkipped
stats.totalFilesFailed += result.FilesFailed
@@ -449,7 +403,6 @@ func (v *Vaultik) finalizeSnapshotMetadata(
BlobUncompressedSize: stats.blobUncompressedSize,
CompressionLevel: v.Config.CompressionLevel,
UploadDurationMs: stats.uploadDuration.Milliseconds(),
NewChunkSize: stats.newChunkSize,
}
err = v.SnapshotManager.UpdateSnapshotStatsExtended(v.ctx, snapshotID, extStats)
@@ -616,7 +569,7 @@ func (v *Vaultik) PurgeSnapshotsWithOptions(opts *SnapshotPurgeOptions) error {
if len(toDelete) == 0 {
if !opts.Quiet {
v.UI.Infof("No snapshots to delete.")
v.printlnStdout("No snapshots to delete")
}
return nil
@@ -654,7 +607,7 @@ func selectSnapshotsToPurge(
case opts.OlderThan != "":
duration, err := parseDuration(opts.OlderThan)
if err != nil {
return nil, err
return nil, fmt.Errorf("invalid duration: %w", err)
}
cutoff := time.Now().UTC().Add(-duration)
@@ -673,19 +626,19 @@ func selectSnapshotsToPurge(
func (v *Vaultik) confirmAndExecutePurge(
toDelete []SnapshotInfo, force, quiet bool,
) error {
// 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 {
if !quiet {
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(time.DateTime),
ubytes(snap.CompressedSize))
snap.Timestamp.Format("2006-01-02 15:04:05"),
formatBytes(snap.CompressedSize))
}
}
// Confirm unless --force is used
if !force {
v.stdoutf("\nDelete %d snapshot(s)? [y/N] ", len(toDelete))
var confirm string
@@ -703,16 +656,7 @@ func (v *Vaultik) confirmAndExecutePurge(
return nil
}
} else if !quiet {
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))
v.stdoutf("\nDeleting %d snapshot(s) (--force specified)\n", len(toDelete))
}
// Delete snapshots (both local and remote)
@@ -720,11 +664,10 @@ func (v *Vaultik) confirmAndExecutePurge(
snapshotID := snap.ID.String()
log.Info("Deleting snapshot", "id", snapshotID)
// Stop before the remote delete, so a snapshot still in the local
// index keeps its metadata on the destination store.
err := v.deleteSnapshotFromLocalDB(snapshotID)
if err != nil {
return fmt.Errorf("deleting snapshot %s from local index: %w", snapshotID, err)
log.Error("Failed to delete from local database",
"snapshot_id", snapshotID, "error", err)
}
_, err = v.deleteRemoteSnapshotByKey(snapshot.RemoteSnapshotKey(snapshotID))
@@ -745,9 +688,9 @@ func (v *Vaultik) confirmAndExecutePurge(
}
if !quiet {
v.UI.Infof("Deleted %d snapshot(s).", len(toDelete))
v.UI.Noticef("Run '%s' to clean up unreferenced remote blobs.",
pruneCommandHint)
v.stdoutf("Deleted %d snapshot(s)\n", len(toDelete))
v.printlnStdout(
"\nNote: Run 'vaultik prune' to clean up unreferenced remote blobs.")
}
return nil
@@ -831,10 +774,18 @@ func (v *Vaultik) VerifySnapshotWithOptions(
v.stdoutf("Checking blob presence and sizes...\n")
}
v.checkSnapshotDatabase(remoteKey, result)
// A snapshot is only restorable if its encrypted database is present
// alongside the blobs. Shallow verify checks that the object exists; it
// does not decrypt it (that is deep verify's job).
dbPath := fmt.Sprintf("metadata/%s/db.zst.age", remoteKey)
result.Verified, result.Missing, result.Mismatched, result.MissingSize,
result.Unchecked, err = v.verifyManifestBlobs(manifest, opts)
_, dbErr := v.Storage.Stat(v.ctx, dbPath)
if dbErr != nil {
result.DatabaseMissing = true
}
result.Verified, result.Missing, result.Mismatched, result.MissingSize, err =
v.verifyManifestBlobs(manifest, opts)
if err != nil {
if opts.JSON {
result.Status = verifyStatusFailed
@@ -871,46 +822,25 @@ func (v *Vaultik) printVerifyHeader(snapshotID string, opts *VerifyOptions) {
}
}
// checkSnapshotDatabase records in result whether the snapshot's
// encrypted database is missing or could not be checked. A snapshot is
// only restorable if its database is present alongside the blobs.
// Shallow verify checks that the object exists; it does not decrypt it
// (that is deep verify's job).
func (v *Vaultik) checkSnapshotDatabase(remoteKey string, result *VerifyResult) {
dbPath := fmt.Sprintf("metadata/%s/db.zst.age", remoteKey)
_, err := v.Storage.Stat(v.ctx, dbPath)
switch {
case errors.Is(err, storage.ErrNotFound):
result.DatabaseMissing = true
case err != nil:
result.DatabaseCheckError = err.Error()
}
}
// verifyManifestBlobs checks that each blob in the manifest is present in
// storage with the size the manifest records, returning the counts of
// blobs that were present with the right size, absent, and present but the
// wrong size, the total bytes of the absent blobs, and the blobs it could
// not check because storage returned an error other than not-found. It
// does not read blob contents; deep verification (RunDeepVerify) does
// that. The size comparison matches the deep path (see
// verifyBlobExistenceFromDB).
// wrong size, plus the total bytes of the absent blobs. It does not read
// blob contents; deep verification (RunDeepVerify) does that. The size
// comparison matches the deep path (see verifyBlobExistenceFromDB).
func (v *Vaultik) verifyManifestBlobs(
manifest *snapshot.Manifest, opts *VerifyOptions,
) (int, int, int, int64, []UncheckedBlob, error) {
) (int, int, int, int64, error) {
var (
verified, missing, mismatched int
missingSize int64
unchecked []UncheckedBlob
)
for _, blob := range manifest.Blobs {
// The manifest is unauthenticated, so its blob hashes are checked
// before being spliced into a storage path.
if !isBlobHash(blob.Hash) {
return 0, 0, 0, 0, nil, fmt.Errorf("%w: %s",
return 0, 0, 0, 0, fmt.Errorf("%w: %s",
errInvalidBlobHash, shortHash(blob.Hash))
}
@@ -919,7 +849,7 @@ func (v *Vaultik) verifyManifestBlobs(
stat, err := v.Storage.Stat(v.ctx, blobPath)
switch {
case errors.Is(err, storage.ErrNotFound):
case err != nil:
if !opts.JSON && !v.UI.Quiet() {
v.stdoutf(" Missing: %s (%s)\n",
blob.Hash, ubytes(blob.CompressedSize))
@@ -927,13 +857,6 @@ func (v *Vaultik) verifyManifestBlobs(
missing++
missingSize += blob.CompressedSize
case err != nil:
if !opts.JSON && !v.UI.Quiet() {
v.stdoutf(" Could not check: %s (%v)\n", blob.Hash, err)
}
unchecked = append(unchecked,
UncheckedBlob{Hash: blob.Hash, Error: err.Error()})
case stat.Size != blob.CompressedSize:
if !opts.JSON && !v.UI.Quiet() {
v.stdoutf(" Wrong size: %s (store has %s, manifest lists %s)\n",
@@ -946,7 +869,7 @@ func (v *Vaultik) verifyManifestBlobs(
}
}
return verified, missing, mismatched, missingSize, unchecked, nil
return verified, missing, mismatched, missingSize, nil
}
// formatVerifyResult outputs the final verification results as JSON or
@@ -967,26 +890,14 @@ func (v *Vaultik) formatVerifyResult(
return v.outputVerifyJSON(result)
}
// --quiet drops the report but not the errors storage returned, which
// are logged on stderr. A failure is still returned either way, and
// the cli layer prints it on stderr.
if v.UI.Quiet() {
for _, blob := range result.Unchecked {
log.Warn("Could not check blob", "blob", blob.Hash, "error", blob.Error)
}
if result.DatabaseCheckError != "" {
log.Warn("Could not check the encrypted database",
"snapshot", result.SnapshotID, "error", result.DatabaseCheckError)
}
} else {
// Under --quiet a failure is still returned, and the cli layer
// prints it on stderr.
if !v.UI.Quiet() {
v.printVerifySummary(result, failure)
}
// Not errSnapshotVerifyFailed: the cli layer prints this after its own
// "Verification failed:".
if failure != "" {
return fmt.Errorf("%w: %s", errProblemsInStorage, failure)
return fmt.Errorf("%w: %s", errSnapshotVerifyFailed, failure)
}
return nil
@@ -1007,19 +918,10 @@ func (v *Vaultik) printVerifySummary(result *VerifyResult, failure string) {
v.stdoutf(" Wrong size: %d blobs\n", result.Mismatched)
}
if len(result.Unchecked) > 0 {
v.stdoutf(" Could not check: %d blobs\n", len(result.Unchecked))
}
if result.DatabaseMissing {
v.stdoutf(" Encrypted database: missing\n")
}
if result.DatabaseCheckError != "" {
v.stdoutf(" Encrypted database: could not be checked (%s)\n",
result.DatabaseCheckError)
}
v.stdoutf(" Status: ")
if failure != "" {
@@ -1047,19 +949,10 @@ func shallowVerifyFailure(result *VerifyResult) string {
fmt.Sprintf("%d blobs have the wrong size", result.Mismatched))
}
if len(result.Unchecked) > 0 {
parts = append(parts, fmt.Sprintf("%d blobs could not be checked",
len(result.Unchecked)))
}
if result.DatabaseMissing {
parts = append(parts, "the encrypted database is missing")
}
if result.DatabaseCheckError != "" {
parts = append(parts, "the encrypted database could not be checked")
}
return strings.Join(parts, "; ")
}
@@ -1122,7 +1015,7 @@ func (v *Vaultik) CleanupLocalSnapshots(opts *PruneOptions) error {
log.Info("Removing stale local snapshot record", "snapshot_id", id)
if !opts.JSON {
v.UI.Infof("Removing stale local record: %s.", v.UI.Snapshot(id))
v.stdoutf("Removing stale local record: %s\n", id)
}
err = v.deleteSnapshotFromLocalDB(id)
@@ -1145,9 +1038,9 @@ func (v *Vaultik) CleanupLocalSnapshots(opts *PruneOptions) error {
}
if removed == 0 {
v.UI.Infof("No stale local snapshots found.")
v.printlnStdout("No stale local snapshots found.")
} else {
v.UI.Infof("Removed %d stale local snapshot record(s).", removed)
v.stdoutf("Removed %d stale local snapshot record(s).\n", removed)
}
return nil
@@ -1272,11 +1165,9 @@ 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 — 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.
// `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.
func (v *Vaultik) RemoveSnapshot(
snapshotID string, opts *RemoveOptions,
) (*RemoveResult, error) {
@@ -1298,18 +1189,10 @@ func (v *Vaultik) RemoveSnapshot(
return v.removeSnapshotDryRun(result, snapshotID, opts)
}
if !v.confirmRemoveSnapshot(snapshotID, opts) {
if !opts.Force && !opts.JSON && !v.confirmRemoveSnapshot(snapshotID, opts) {
return result, nil
}
// Checked before the local record is deleted: it may be the last
// snapshot in the local index, and the check applies only while the
// local index holds one.
var markerErr error
if !opts.LocalOnly {
markerErr = v.checkDestinationMarker()
}
if inLocalIndex {
log.Info("Removing snapshot from local database", "snapshot_id", snapshotID)
@@ -1319,10 +1202,8 @@ func (v *Vaultik) RemoveSnapshot(
}
}
result.RemoteRemoved, err = v.removeSnapshotRemote(
snapshotID, inLocalIndex, markerErr, opts)
if err != nil {
return result, err
if !opts.LocalOnly {
result.RemoteRemoved = v.removeSnapshotRemote(snapshotID, opts)
}
if v.SnapshotManager != nil {
@@ -1338,15 +1219,14 @@ func (v *Vaultik) RemoveSnapshot(
}
if inLocalIndex {
v.UI.Infof("Removed snapshot '%s' from local database.",
v.UI.Snapshot(snapshotID))
v.stdoutf("Removed snapshot '%s' from local database\n", snapshotID)
}
if result.RemoteRemoved {
v.UI.Infof("Removed snapshot metadata from remote storage.")
v.UI.Noticef("The removed snapshot's blobs remain on the remote. "+
v.printlnStdout("Removed snapshot metadata from remote storage")
v.stdoutf("\nNote: The removed snapshot's blobs remain on the remote. "+
"Run '%s' to delete any blobs no longer referenced by any "+
"remaining remote snapshot.", pruneCommandHint)
"remaining remote snapshot.\n", pruneCommandHint)
}
return result, nil
@@ -1357,9 +1237,7 @@ func (v *Vaultik) RemoveSnapshot(
// remove: no row and, unless LocalOnly is set, no metadata on the
// destination store either. The destination store is consulted only
// when the local index has no row, so a snapshot in the local index can
// still be removed from it while the destination store is unreachable,
// and only after checkDestinationMarker passes, so an unplugged volume's
// empty mount point is not taken for a store without the snapshot.
// still be removed from it while the destination store is unreachable.
func (v *Vaultik) findSnapshotToRemove(
snapshotID string, opts *RemoveOptions,
) (bool, error) {
@@ -1379,11 +1257,6 @@ func (v *Vaultik) findSnapshotToRemove(
errSnapshotNotFound, snapshotID)
}
err := v.checkDestinationMarker()
if err != nil {
return false, err
}
objects, err := v.remoteSnapshotObjects(snapshot.RemoteSnapshotKey(snapshotID))
if err != nil {
return false, fmt.Errorf("looking up snapshot on destination store: %w", err)
@@ -1409,28 +1282,22 @@ func (v *Vaultik) removeSnapshotDryRun(
return result, v.outputRemoveJSON(result)
}
v.UI.Infof("Would remove snapshot: %s.", v.UI.Snapshot(snapshotID))
v.stdoutf("Would remove snapshot: %s\n", snapshotID)
if !opts.LocalOnly {
v.UI.Infof("Would also remove snapshot metadata from " +
"remote storage (blobs untouched).")
v.printlnStdout("Would also remove snapshot metadata from " +
"remote storage (blobs untouched)")
}
v.UI.Noticef("Dry run: no changes made.")
v.printlnStdout("[Dry run - no changes made]")
return result, nil
}
// confirmRemoveSnapshot prompts for confirmation before removing a
// snapshot, unless --force or --json is set. Returns false (treating
// EOF/read errors as "no") unless the user answers "y". The prompt and
// its answer bypass the UI: they are an interactive exchange the
// operator must see, so --quiet does not silence them.
// snapshot. Returns false (treating EOF/read errors as "no") unless the
// user answers "y".
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)
@@ -1458,40 +1325,19 @@ func (v *Vaultik) confirmRemoveSnapshot(snapshotID string, opts *RemoveOptions)
}
// removeSnapshotRemote strips the snapshot's metadata from the
// destination store. It returns true only when the delete finished
// without an error and removed at least one object; under LocalOnly it
// does nothing. markerErr is the result of checkDestinationMarker; when
// it is set, nothing is deleted and it is the failure. When the snapshot
// is only on the destination store, a failure is returned as an error,
// because that removal is all the command does. When the snapshot was in
// the local index, its removal there has already happened, so a failure
// is only a warning telling the user to run `vaultik snapshot remove`
// for the snapshot again once the destination store is reachable
// (`vaultik prune` never removes snapshot metadata).
func (v *Vaultik) removeSnapshotRemote(
snapshotID string, inLocalIndex bool, markerErr error,
opts *RemoveOptions,
) (bool, error) {
if opts.LocalOnly {
return false, nil
}
// 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 {
log.Info("Removing snapshot metadata from remote storage",
"snapshot_id", snapshotID)
var deleted int
err := markerErr
if err == nil {
deleted, err = v.deleteRemoteSnapshotByKey(
snapshot.RemoteSnapshotKey(snapshotID))
}
if err != nil && !inLocalIndex {
return false, fmt.Errorf(
"removing snapshot metadata from destination store: %w", err)
}
remoteKey := snapshot.RemoteSnapshotKey(snapshotID)
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 "+
@@ -1506,10 +1352,10 @@ func (v *Vaultik) removeSnapshotRemote(
err, snapshotRemoveCommandHint, snapshotID)
}
return false, nil
return false
}
return deleted > 0, nil
return deleted > 0
}
// RemoveAllSnapshots removes every snapshot known to the local
@@ -1556,7 +1402,7 @@ func (v *Vaultik) RemoveAllSnapshots(opts *RemoveOptions) (*RemoveResult, error)
if len(localSnaps) == 0 && len(orphanRemoteKeys) == 0 {
if !opts.JSON {
v.UI.Infof("No snapshots found.")
v.printlnStdout("No snapshots found")
}
return &RemoveResult{}, nil
@@ -1595,8 +1441,8 @@ func (v *Vaultik) localSnapshotIDs() ([]string, error) {
// listAllRemoteSnapshotKeys collects the hashed remote keys
// (subdirectories under metadata/) currently present in the
// destination store. Returns (nil, err) when the store cannot be
// listed, or is not present by checkDestinationMarker; callers must
// treat that as "no remote info available," not fatal.
// listed; callers must treat that as "no remote info available," not
// fatal.
func (v *Vaultik) listAllRemoteSnapshotKeys() ([]string, error) {
log.Info("Listing all remote snapshots")
@@ -1645,11 +1491,6 @@ func (v *Vaultik) listAllRemoteSnapshotKeys() ([]string, error) {
}
}
err := v.checkDestinationMarker()
if err != nil {
return nil, err
}
return keys, nil
}
@@ -1666,27 +1507,27 @@ func (v *Vaultik) handleRemoveAllDryRun(
}
if !opts.JSON {
v.UI.Infof("Would remove %d local snapshot(s):", len(localSnaps))
v.stdoutf("Would remove %d local snapshot(s):\n", len(localSnaps))
for _, id := range localSnaps {
v.UI.Detailf("%s", v.UI.Snapshot(id))
v.stdoutf(" %s\n", id)
}
if !opts.LocalOnly {
if len(orphanRemoteKeys) > 0 {
v.UI.Infof("Would also remove %d orphan remote snapshot key(s):",
v.stdoutf("Would also remove %d orphan remote snapshot key(s):\n",
len(orphanRemoteKeys))
for _, key := range orphanRemoteKeys {
v.UI.Detailf("%s", key)
v.stdoutf(" %s\n", key)
}
} else {
v.UI.Infof("Would also remove snapshot metadata from " +
"remote storage (blobs untouched).")
v.printlnStdout("Would also remove snapshot metadata from " +
"remote storage (blobs untouched)")
}
}
v.UI.Noticef("Dry run: no changes made.")
v.printlnStdout("[Dry run - no changes made]")
}
if opts.JSON {
@@ -1698,8 +1539,8 @@ func (v *Vaultik) handleRemoveAllDryRun(
// executeRemoveAll deletes every local snapshot and, unless LocalOnly
// is set, every corresponding remote metadata directory plus any
// orphan remote keys. Blobs are not touched. It returns an error when
// any snapshot could not be removed.
// orphan remote keys. Blobs are not touched; the printed prune-command
// hint is the next step.
func (v *Vaultik) executeRemoveAll(
localSnaps, orphanRemoteKeys []string, opts *RemoveOptions,
) (*RemoveResult, error) {
@@ -1713,11 +1554,18 @@ func (v *Vaultik) executeRemoveAll(
result := &RemoveResult{}
failures := v.removeAllLocalSnapshots(localSnaps, opts, result)
remoteErrors := v.removeAllLocalSnapshots(localSnaps, opts, result)
if !opts.LocalOnly {
failures += v.removeAllOrphanRemotes(orphanRemoteKeys, result)
result.RemoteRemoved = failures == 0
remoteErrors += v.removeAllOrphanRemotes(orphanRemoteKeys, result)
if remoteErrors == 0 {
result.RemoteRemoved = true
} else if v.UI != nil {
v.UI.Warningf("Some remote metadata deletions failed. Run '%s' "+
"once the remote is healthy to clean up unreferenced blobs.",
pruneCommandHint)
}
}
if v.SnapshotManager != nil {
@@ -1727,18 +1575,17 @@ func (v *Vaultik) executeRemoveAll(
}
}
if failures > 0 {
return result, fmt.Errorf("%d %w", failures, errSnapshotRemoveFailed)
}
if opts.JSON {
return result, v.outputRemoveJSON(result)
}
v.UI.Infof("Removed %d snapshot(s).", len(result.SnapshotsRemoved))
v.stdoutf("Removed %d snapshot(s)\n", len(result.SnapshotsRemoved))
if !opts.LocalOnly && result.RemoteRemoved {
v.UI.Infof("Removed snapshot metadata from remote storage.")
v.printlnStdout("Removed snapshot metadata from remote storage")
v.stdoutf("\nNote: Removed snapshots' blobs remain on the remote. "+
"Run '%s' to delete any blobs no longer referenced by any "+
"remaining remote snapshot.\n", pruneCommandHint)
}
return result, nil
@@ -1781,13 +1628,12 @@ func (v *Vaultik) deleteIncompleteSnapshot(snapshotIDStr string, id any) bool {
}
// 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.
// --local-only, its remote metadata), returning the number of remote
// deletion failures.
func (v *Vaultik) removeAllLocalSnapshots(
localSnaps []string, opts *RemoveOptions, result *RemoveResult,
) int {
failures := 0
remoteErrors := 0
for _, snapshotID := range localSnaps {
log.Info("Removing snapshot", "snapshot_id", snapshotID)
@@ -1797,8 +1643,6 @@ func (v *Vaultik) removeAllLocalSnapshots(
log.Error("Failed to remove from local database",
"snapshot_id", snapshotID, "error", err)
failures++
continue
}
@@ -1809,14 +1653,14 @@ func (v *Vaultik) removeAllLocalSnapshots(
log.Warn("Failed to remove snapshot metadata from remote",
"snapshot_id", snapshotID, "error", err)
failures++
remoteErrors++
}
}
result.SnapshotsRemoved = append(result.SnapshotsRemoved, snapshotID)
}
return failures
return remoteErrors
}
// removeAllOrphanRemotes deletes remote snapshot metadata that has no
@@ -1995,17 +1839,13 @@ 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 "+
"(total snapshots left in the local index: %s).",
v.UI.Detailf("Incomplete snapshots: %s removed (%s remain).",
countText(&result.SnapshotsDeleted), countText(snapshotsRemain))
v.UI.Detailf("Orphaned files: %s removed "+
"(total files left in the local index: %s).",
v.UI.Detailf("Orphaned files: %s removed (%s remain).",
countText(result.FilesDeleted), countText(fileCountAfter))
v.UI.Detailf("Orphaned chunks: %s removed "+
"(total chunks left in the local index: %s).",
v.UI.Detailf("Orphaned chunks: %s removed (%s remain).",
countText(result.ChunksDeleted), countText(chunkCountAfter))
v.UI.Detailf("Orphaned blobs: %s removed "+
"(total blobs left in the local index: %s).",
v.UI.Detailf("Orphaned blobs: %s removed (%s remain).",
countText(result.BlobsDeleted), countText(blobCountAfter))
return result, nil
internal/vaultik/snapshot_deleted_count_test.go
-249
View File
@@ -1,249 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"fmt"
"os"
"path/filepath"
"testing"
"time"
"github.com/spf13/afero"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/config"
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/storage"
"sneak.berlin/go/vaultik/internal/ui"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// These tests cover https://git.eeqj.de/sneak/vaultik/issues/304: a
// backup counts a file as deleted only when the previous snapshot of
// the same name had it and it is gone, and never counts an excluded
// file.
// deletedCountEnv is a backup setup over the source directory src whose
// user-facing output is kept in out. Each test configures its snapshots
// with setSnapshot.
type deletedCountEnv struct {
v *vaultik.Vaultik
out *bytes.Buffer
src string
}
// newDeletedCountEnv writes files, keyed by path relative to src.
func newDeletedCountEnv(t *testing.T, files map[string][]byte) *deletedCountEnv {
t.Helper()
ctx := context.Background()
fs := afero.NewOsFs()
tempDir := t.TempDir()
srcDir := filepath.Join(tempDir, "src")
for rel, content := range files {
path := filepath.Join(srcDir, rel)
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
require.NoError(t, afero.WriteFile(fs, path, content, 0o644))
}
cfg := faultTestConfig()
cfg.IndexPath = filepath.Join(tempDir, "index.sqlite")
cfg.Snapshots = map[string]config.SnapshotConfig{}
store, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
db, err := database.New(ctx, cfg.IndexPath)
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
out := &bytes.Buffer{}
v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
v.UI = ui.NewWithColor(out, false)
return &deletedCountEnv{v: v, out: out, src: srcDir}
}
// setSnapshot configures the snapshot name to back up the path rel
// beneath src, with the given excludes.
func (e *deletedCountEnv) setSnapshot(name, rel string, exclude ...string) {
e.v.Config.Snapshots[name] = config.SnapshotConfig{
Paths: []string{filepath.Join(e.src, rel)},
Exclude: exclude,
}
}
// backUp runs a backup of the named snapshot and returns its output.
func (e *deletedCountEnv) backUp(t *testing.T, name string) string {
t.Helper()
e.out.Reset()
require.NoError(t, e.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
Snapshots: []string{name},
}))
return e.out.String()
}
// A file this snapshot excludes is not counted as deleted: neither one
// that another snapshot backs up, nor one that the previous snapshot of
// this name had before the exclude was added.
func TestBackupDoesNotCountExcludedFileAsDeleted(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"top.txt": []byte("top"),
"cache/tmp.bin": []byte("cache"),
"photos/a.jpg": []byte("photo a"),
"photos/b.jpg": []byte("photo b"),
"photos/c.jpg": []byte("photo c"),
})
env.setSnapshot("photos", "photos")
env.setSnapshot("home", "", "/photos")
env.backUp(t, "photos")
assert.Contains(t, env.backUp(t, "home"), filesLine(2, 2, 0))
env.setSnapshot("home", "", "/photos", "/cache")
assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
}
// A file inside a directory that an exclude added after a backup
// matches is not counted as deleted, though the pattern matches only the
// directory and the directory is gone from disk.
func TestBackupDoesNotCountFileInExcludedDirectoryAsDeleted(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"top.txt": []byte("top"),
"user/.local/share/Trash/old.txt": []byte("old"),
})
env.setSnapshot("home", "")
assert.Contains(t, env.backUp(t, "home"), filesLine(2, 2, 0))
require.NoError(t, os.RemoveAll(
filepath.Join(env.src, "user/.local/share/Trash")))
env.setSnapshot("home", "", "*/.local/share/Trash")
assert.Contains(t, env.backUp(t, "home"), filesLine(1, 0, 1))
}
// A file whose directory was replaced by a regular file of the same name
// is counted as deleted.
func TestBackupCountsFileInDirectoryReplacedByFileAsDeleted(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"dir/inside.txt": []byte("inside"),
})
env.setSnapshot("home", "")
assert.Contains(t, env.backUp(t, "home"), filesLine(1, 1, 0))
dir := filepath.Join(env.src, "dir")
require.NoError(t, os.RemoveAll(dir))
require.NoError(t, os.WriteFile(dir, []byte("now a file"), 0o600))
assert.Contains(t, env.backUp(t, "home"),
"Files: 1 examined, 1 backed up, 0 unchanged, 1 deleted.")
}
// Under --skip-errors a file inside a directory that the walk cannot
// open is not counted as deleted: it is still on disk.
func TestBackupDoesNotCountFileInUnopenableDirectoryAsDeleted(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
env := newDeletedCountEnv(t, map[string][]byte{
"open.txt": []byte("open"),
"locked/inside.txt": []byte("inside"),
})
env.setSnapshot("work", "")
assert.Contains(t, env.backUp(t, "work"), filesLine(2, 2, 0))
// A directory's mode does not lock out root, who runs the tests, so
// opening the directory is made to fail instead.
env.v.Fs = &openFailFs{
path: filepath.Join(env.src, "locked"),
err: os.ErrPermission,
}
env.out.Reset()
require.NoError(t, env.v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
SkipErrors: true,
Snapshots: []string{"work"},
}))
assert.Contains(t, env.out.String(), filesLine(1, 0, 1))
}
// 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
+1 -1
View File
@@ -87,7 +87,7 @@ func TestSnapshotSummaryCountsFileNotStoredAsFailed(t *testing.T) {
"src": {Paths: []string{srcDir}},
}
store, err := storage.NewFileStorer(t.TempDir())
store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
db, err := database.New(ctx, cfg.IndexPath)
internal/vaultik/snapshot_list.go
+7 -36
View File
@@ -61,9 +61,7 @@ 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, unless the local index
// is bound to a different destination than the configured one: that is
// reported instead.
// store are reported as drift below the table.
//
// If remote listing fails (unmounted volume, permission denied,
// network), we degrade to local-only with a warning. List never fails
@@ -105,26 +103,7 @@ 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)
}
@@ -146,13 +125,8 @@ 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, boundElsewhere)
v.reportListDrift(snapshots, listing)
}
return nil
@@ -458,9 +432,7 @@ 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. Local records are not reported when
// boundElsewhere is set: ListSnapshots has already said why they are
// missing.
// unreadable or omitted.
//
// This is what remains of the old reportRemoteDrift, and it no longer
// touches the destination store. Its remote-only half collapsed into
@@ -469,7 +441,6 @@ 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
@@ -479,7 +450,7 @@ func (v *Vaultik) reportListDrift(
}
}
if len(localOnly) > 0 && !boundElsewhere {
if len(localOnly) > 0 {
v.UI.Warningf("%d local snapshot record(s) not found in backup "+
"destination store:", len(localOnly))
@@ -582,8 +553,8 @@ func (v *Vaultik) printSnapshotTable(snapshots []SnapshotInfo) error {
if snap.LocallyTracked {
id = snap.ID.String()
uncompressed = ubytes(snap.UncompressedSize)
newChunks = ubytes(snap.NewChunkSize)
uncompressed = formatBytes(snap.UncompressedSize)
newChunks = formatBytes(snap.NewChunkSize)
} else {
id = formatRemoteOnlyID(snap.RemoteKey)
uncompressed = remoteOnlyCell
@@ -593,7 +564,7 @@ func (v *Vaultik) printSnapshotTable(snapshots []SnapshotInfo) error {
_, err = fmt.Fprintf(w, "%s\t%s\t%s\t%s\t%s\n",
id,
snap.Timestamp.Format("2006-01-02 15:04:05"),
ubytes(snap.CompressedSize),
formatBytes(snap.CompressedSize),
uncompressed,
newChunks)
if err != nil {
internal/vaultik/snapshot_list_test.go
+8 -123
View File
@@ -122,9 +122,6 @@ func newListEnv(t *testing.T) *listEnv {
store := newObservingStorer()
stdout := &bytes.Buffer{}
// A backup wrote to this destination, so it carries the marker.
require.NoError(t, store.Put(ctx, markerFile, strings.NewReader("")))
v := &vaultik.Vaultik{
Config: &config.Config{
AgeSecretKey: "",
@@ -215,8 +212,8 @@ const (
listConfiguredName = "home"
listLocalID = "testhost_home_2026-03-01T10:00:00Z"
listRemoteID = "otherhost_media_2026-03-02T11:22:33Z"
// fiveMegabytes is printed as "5.0 MB" by every command.
fiveMegabytes = 5_000_000
// fiveMegabytes formats as "5.0 MB" through formatBytes.
fiveMegabytes = 5 * 1024 * 1024
)
// TestListSnapshots_RemoteWithoutSecretKey is the regression guard for
@@ -309,48 +306,6 @@ func TestListSnapshots_RemoteOnlyRowRendering(t *testing.T) {
"are not in the local index")
}
// TestSnapshotListAndPurgePrintSizesLikeRemoteInfo checks that the
// `snapshot list` table and the purge listing print a byte count the way
// `remote info` does: in powers of 1000, as the MB label says.
func TestSnapshotListAndPurgePrintSizesLikeRemoteInfo(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
const wantSize = "5.0 MB" // fiveMegabytes
env := newListEnv(t)
// A remote-only snapshot: `snapshot list` and `remote info` both take
// its size from the manifest.
remoteKey := env.addRemote(t, listRemoteID,
time.Date(2026, 3, 2, 11, 22, 33, 0, time.UTC))
// A locally tracked snapshot of the same size for the purge to list.
// The purge prints the snapshot's blob size, the last argument here.
start := time.Date(2026, 3, 1, 10, 0, 0, 0, time.UTC)
env.addLocal(t, listLocalID, start)
env.addRemote(t, listLocalID, start)
require.NoError(t, env.v.Repositories.Snapshots.UpdateCounts(
context.Background(), nil, listLocalID, 0, 0, 0, 0, fiveMegabytes))
require.NoError(t, env.v.RemoteInfo(false))
assert.Contains(t, findTableRow(t, env.stdout.String(), remoteKey[:16]),
wantSize, "remote info")
env.stdout.Reset()
require.NoError(t, env.v.ListSnapshots(false))
assert.Contains(t, findTableRow(t, env.stdout.String(),
"<remote only:"+remoteKey[:12]+">"), wantSize, "snapshot list")
// Without --force and with nothing on stdin the purge lists what it
// would delete, reads no confirmation, and deletes nothing.
env.stdout.Reset()
require.NoError(t, env.v.PurgeSnapshotsWithOptions(
&vaultik.SnapshotPurgeOptions{OlderThan: "1d"}))
assert.Contains(t, findTableRow(t, env.stdout.String(), listLocalID),
wantSize, "snapshot purge")
}
// findTableRow returns the single output line containing needle.
func findTableRow(t *testing.T, out, needle string) string {
t.Helper()
@@ -424,74 +379,6 @@ 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.
@@ -554,14 +441,12 @@ func TestListSnapshots_UnreadableManifestDoesNotHideOthers(t *testing.T) {
//
//nolint:tagliatelle // snake_case is the established output format
type listJSONRow struct {
ID string `json:"id"`
RemoteKey string `json:"remote_key"`
Timestamp string `json:"timestamp"`
CompressedSize int64 `json:"compressed_size"`
UncompressedSize int64 `json:"uncompressed_size"`
NewChunkSize int64 `json:"new_chunk_size"`
LocallyTracked bool `json:"locally_tracked"`
RemotePresent *bool `json:"remote_present"`
ID string `json:"id"`
RemoteKey string `json:"remote_key"`
Timestamp string `json:"timestamp"`
CompressedSize int64 `json:"compressed_size"`
LocallyTracked bool `json:"locally_tracked"`
RemotePresent *bool `json:"remote_present"`
}
// decodeListJSON parses the command's stdout, which must contain
internal/vaultik/snapshot_skip_errors_test.go
+1 -1
View File
@@ -45,7 +45,7 @@ func TestSkipErrorsBackupStopsOnIndexErrorRecordingDirectory(t *testing.T) {
"tree": {Paths: []string{srcDir}},
}
store, err := storage.NewFileStorer(t.TempDir())
store, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
db, err := database.New(ctx, cfg.IndexPath)
internal/vaultik/snapshot_summary_test.go
+1 -1
View File
@@ -84,7 +84,7 @@ func newSummaryEnv(t *testing.T) *summaryEnv {
"split": {Paths: []string{dirOne, dirTwo}},
}
inner, err := storage.NewFileStorer(t.TempDir())
inner, err := storage.NewFileStorer(filepath.Join(tempDir, "remote"))
require.NoError(t, err)
store := faultstore.New(inner)
internal/vaultik/storage_bind.go
+10 -23
View File
@@ -45,9 +45,17 @@ func (v *Vaultik) EnsureStorageBinding() error {
return nil
}
stored, configured, err := v.storageBinding()
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 err
return fmt.Errorf("reading local storage binding: %w", err)
}
if stored == "" {
@@ -70,27 +78,6 @@ 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/symlinked_destination_test.go
-147
View File
@@ -1,147 +0,0 @@
package vaultik_test
import (
"context"
"io/fs"
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestPruneDeletesNothingThroughSymlinkedDirectory checks that prune keeps
// every blob and the local snapshot record when the metadata/ or blobs/
// directory of a file:// destination is a symlink to a directory elsewhere
// (https://git.eeqj.de/sneak/vaultik/issues/296). A backup writes through
// such a link, so prune has to list through it too.
func TestPruneDeletesNothingThroughSymlinkedDirectory(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
for _, dir := range []string{"metadata", "blobs"} {
t.Run(dir, func(t *testing.T) {
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
blobFiles := blobFilesIn(t, storeDir)
moveBehindSymlink(t, storeDir, dir)
require.NoError(t, v.Prune(&vaultik.PruneOptions{Force: true}))
// When blobs/ is the link, these paths run through it.
for _, blobFile := range blobFiles {
assert.FileExists(t, blobFile, "prune must delete no blob")
}
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
require.NoError(t, err)
assert.Len(t, snapshots, 1, "prune must delete no local snapshot record")
})
}
}
// TestPruneFailsOnSymlinkedDirectoryWithMissingTarget checks that prune
// fails, deleting no blob and keeping the local snapshot record, when the
// metadata/ or blobs/ directory of a file:// destination is a symlink
// whose target is missing, as a link to a volume that is not mounted is.
func TestPruneFailsOnSymlinkedDirectoryWithMissingTarget(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
for _, dir := range []string{"metadata", "blobs"} {
t.Run(dir, func(t *testing.T) {
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
blobFiles := blobFilesIn(t, storeDir)
targetPath := moveBehindSymlink(t, storeDir, dir)
// Unmount the volume the link points to, and mount it again
// once prune has run.
unmountedPath := targetPath + "-unmounted"
require.NoError(t, os.Rename(targetPath, unmountedPath))
err := v.Prune(&vaultik.PruneOptions{Force: true})
require.ErrorIs(t, err, fs.ErrNotExist)
require.NoError(t, os.Rename(unmountedPath, targetPath))
// When blobs/ is the link, these paths run through it.
for _, blobFile := range blobFiles {
assert.FileExists(t, blobFile, "prune must delete no blob")
}
snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
require.NoError(t, err)
assert.Len(t, snapshots, 1, "prune must delete no local snapshot record")
})
}
}
// TestRemoveSnapshotWarnsOnSymlinkedMetadataWithMissingTarget checks that
// snapshot remove warns that the metadata could not be removed from the
// destination when metadata/ is a symlink whose target is missing, as it
// does when the destination directory is missing, instead of finding no
// metadata to remove.
func TestRemoveSnapshotWarnsOnSymlinkedMetadataWithMissingTarget(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
ctx := context.Background()
storeDir := filepath.Join(t.TempDir(), "store")
v, repos, out := backUpToFileDestination(ctx, t, storeDir)
targetPath := moveBehindSymlink(t, storeDir, "metadata")
require.NoError(t, os.Rename(targetPath, targetPath+"-unmounted"))
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.NotContains(t, out.String(),
"Removed snapshot metadata from remote storage")
}
// blobFilesIn returns the paths of the blob files under storeDir/blobs, and
// fails the test when there are none.
func blobFilesIn(t *testing.T, storeDir string) []string {
t.Helper()
var blobFiles []string
err := filepath.WalkDir(filepath.Join(storeDir, "blobs"),
func(path string, entry fs.DirEntry, err error) error {
if err == nil && !entry.IsDir() {
blobFiles = append(blobFiles, path)
}
return err
})
require.NoError(t, err)
require.NotEmpty(t, blobFiles)
return blobFiles
}
// moveBehindSymlink moves storeDir/dir to a directory elsewhere, puts a
// symlink to it in its place, and returns where it went.
func moveBehindSymlink(t *testing.T, storeDir, dir string) string {
t.Helper()
linkPath := filepath.Join(storeDir, dir)
targetPath := filepath.Join(t.TempDir(), dir)
require.NoError(t, os.Rename(linkPath, targetPath))
require.NoError(t, os.Symlink(targetPath, linkPath))
return targetPath
}
internal/vaultik/two_path_snapshot_test.go
+1 -1
View File
@@ -28,7 +28,7 @@ func TestBackupWithoutCronOfTwoPathSnapshotRestoresBothPaths(t *testing.T) {
tempDir := t.TempDir()
firstDir := filepath.Join(tempDir, "first")
secondDir := filepath.Join(tempDir, "second")
storeDir := t.TempDir()
storeDir := filepath.Join(tempDir, "remote")
restoreDir := filepath.Join(tempDir, "restored")
dbPath := filepath.Join(tempDir, "index.sqlite")
internal/vaultik/uncompressed_size_test.go
-85
View File
@@ -1,85 +0,0 @@
package vaultik_test
import (
"bytes"
"context"
"path/filepath"
"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/storage"
"sneak.berlin/go/vaultik/internal/vaultik"
)
// TestUncompressedSizeOfChangedFileStaysFixed covers
// https://git.eeqj.de/sneak/vaultik/issues/360. A backup that changes a
// file leaves the earlier snapshot's UNCOMPRESSED SIZE as it was when that
// snapshot's backup completed. The file's row in the local index is shared
// by both snapshots and rewritten by the second backup.
func TestUncompressedSizeOfChangedFileStaysFixed(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
fs := afero.NewOsFs()
tempDir := t.TempDir()
dataDir := filepath.Join(tempDir, "src")
dbPath := filepath.Join(tempDir, "index.sqlite")
changedPath := filepath.Join(dataDir, "changed.bin")
ctx := context.Background()
files := writeFaultSourceTree(t, fs, dataDir)
cfg := changedFileConfig(dataDir, dbPath)
appendRandomBytes(t, fs, files, changedPath, appendedFileSize)
store, err := storage.NewFileStorer(t.TempDir())
require.NoError(t, err)
db, err := database.New(ctx, dbPath)
require.NoError(t, err)
t.Cleanup(func() { _ = db.Close() })
repos := database.NewRepositories(db)
v := newBackupVaultik(ctx, cfg, store, repos, db, fs)
require.NoError(t, backUp(v, "first"))
// With nothing to compare against, sizeOfNewChunks totals every
// distinct chunk of the files.
firstID := localSnapshotID(ctx, t, repos, "first")
firstSize := sizeOfNewChunks(t, files, nil)
require.Equal(t, firstSize, listedUncompressedSizes(t, v)[firstID],
"the first snapshot must count the chunks of every file it holds")
appendRandomBytes(t, fs, files, changedPath, faultChunkSize)
require.NoError(t, backUp(v, "second"))
secondID := localSnapshotID(ctx, t, repos, "second")
sizes := listedUncompressedSizes(t, v)
assert.Equal(t, firstSize, sizes[firstID],
"a later backup must not change the first snapshot's figure")
assert.Equal(t, sizeOfNewChunks(t, files, nil), sizes[secondID],
"the second snapshot must count the changed file's chunks")
}
// listedUncompressedSizes runs `snapshot list --json` and returns each
// listed snapshot's uncompressed_size by snapshot ID.
func listedUncompressedSizes(t *testing.T, v *vaultik.Vaultik) map[string]int64 {
t.Helper()
var out bytes.Buffer
v.Stdout = &out
require.NoError(t, v.ListSnapshots(true))
sizes := make(map[string]int64)
for _, row := range decodeListJSON(t, out.String()) {
sizes[row.ID] = row.UncompressedSize
}
return sizes
}
internal/vaultik/verify.go
+20 -58
View File
@@ -17,7 +17,6 @@ import (
"sneak.berlin/go/vaultik/internal/database"
"sneak.berlin/go/vaultik/internal/log"
"sneak.berlin/go/vaultik/internal/snapshot"
"sneak.berlin/go/vaultik/internal/storage"
)
// Sentinel errors for snapshot verification failures.
@@ -33,9 +32,7 @@ var (
errManifestExtraBlob = errors.New("manifest contains blob not in database")
errManifestMissingBlob = errors.New(
"manifest omits blob present in database")
errBlobSizeMismatch = errors.New("blob size mismatch")
errBlobsNotInStorage = errors.New(
"blobs missing from storage or stored with the wrong size")
errBlobSizeMismatch = errors.New("blob size mismatch")
)
// verifyStatusFailed is the JSON status value for a failed verification.
@@ -60,25 +57,11 @@ type VerifyResult struct {
Missing int `json:"missing"`
MissingSize int64 `json:"missing_size,omitempty"`
Mismatched int `json:"mismatched,omitempty"`
// Unchecked lists the blobs shallow verify could not check, because
// storage answered with an error other than not-found, so whether
// they are present is unknown.
Unchecked []UncheckedBlob `json:"unchecked,omitempty"`
// DatabaseMissing is set by shallow verify when the snapshot's
// encrypted database (metadata/<key>/db.zst.age) is absent, which
// makes the snapshot unrestorable regardless of the blobs.
DatabaseMissing bool `json:"database_missing,omitempty"`
// DatabaseCheckError is set by shallow verify to the error storage
// returned when the encrypted database could not be checked.
DatabaseCheckError string `json:"database_check_error,omitempty"`
ErrorMessage string `json:"error,omitempty"`
}
// UncheckedBlob is a blob shallow verify could not check, with the error
// storage returned for it.
type UncheckedBlob struct {
Hash string `json:"hash"`
Error string `json:"error"`
DatabaseMissing bool `json:"database_missing,omitempty"`
ErrorMessage string `json:"error,omitempty"`
}
// deepVerifyFailure records a failure in the result and returns it appropriately
@@ -152,6 +135,7 @@ func (v *Vaultik) RunDeepVerify(snapshotID string, opts *VerifyOptions) error {
}
result.Status = "ok"
result.Verified = len(dbBlobs)
if opts.JSON {
return v.outputVerifyJSON(result)
@@ -262,8 +246,6 @@ func (v *Vaultik) downloadVerifiedSnapshotDB(
fmt.Errorf("failed to download database: %w", err))
}
dbReader = newCloseOnCancelReader(v.ctx, dbReader)
defer func() { _ = dbReader.Close() }()
tdb, err := v.decryptAndLoadDatabase(dbReader, identities)
@@ -308,7 +290,7 @@ func (v *Vaultik) runVerificationSteps(
v.stdoutf("Checking blob existence in remote storage...\n")
}
err = v.verifyBlobExistenceFromDB(dbBlobs, result)
err = v.verifyBlobExistenceFromDB(dbBlobs)
if err != nil {
return v.deepVerifyFailure(result, opts, err.Error(), err)
}
@@ -319,8 +301,7 @@ func (v *Vaultik) runVerificationSteps(
len(dbBlobs), ubytes(totalSize))
}
err = v.performDeepVerificationFromDB(
dbBlobs, tdb.db.Conn(), opts, result, identities)
err = v.performDeepVerificationFromDB(dbBlobs, tdb.db.Conn(), opts, identities)
if err != nil {
return v.deepVerifyFailure(result, opts, err.Error(), err)
}
@@ -672,15 +653,9 @@ func (v *Vaultik) verifyManifestAgainstDatabase(
return nil
}
// verifyBlobExistenceFromDB checks that every blob from the database is
// in storage with the size the database records. It checks them all,
// counting the missing and wrong-size blobs in result, and fails if it
// found any. Any storage error other than not found stops the check and
// fails with that error.
func (v *Vaultik) verifyBlobExistenceFromDB(
blobs []snapshot.BlobInfo, result *VerifyResult,
) error {
log.Info("Verifying blob existence in storage", "blob_count", len(blobs))
// verifyBlobExistenceFromDB checks that all blobs from database exist in S3
func (v *Vaultik) verifyBlobExistenceFromDB(blobs []snapshot.BlobInfo) error {
log.Info("Verifying blob existence in S3", "blob_count", len(blobs))
for i, blob := range blobs {
// The hash is read from the snapshot database, which is not
@@ -692,23 +667,17 @@ func (v *Vaultik) verifyBlobExistenceFromDB(
// Construct blob path
blobPath := fmt.Sprintf("blobs/%s/%s/%s", blob.Hash[:2], blob.Hash[2:4], blob.Hash)
// Check blob exists
stat, err := v.Storage.Stat(v.ctx, blobPath)
switch {
case errors.Is(err, storage.ErrNotFound):
log.Warn("Blob missing from storage", "hash", blob.Hash)
if err != nil {
return fmt.Errorf("blob %s missing from storage: %w", blob.Hash, err)
}
result.Missing++
result.MissingSize += blob.CompressedSize
case err != nil:
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",
"hash", blob.Hash,
"storage_size", stat.Size,
"database_size", blob.CompressedSize)
result.Mismatched++
// Verify size matches
if stat.Size != blob.CompressedSize {
return fmt.Errorf(
"%w: blob %s: S3 has %d bytes, database has %d bytes",
errBlobSizeMismatch, blob.Hash, stat.Size, blob.CompressedSize)
}
// Progress update every 100 blobs
@@ -722,22 +691,16 @@ func (v *Vaultik) verifyBlobExistenceFromDB(
}
}
if result.Missing > 0 || result.Mismatched > 0 {
return fmt.Errorf("%w: %d missing, %d with the wrong size",
errBlobsNotInStorage, result.Missing, result.Mismatched)
}
log.Info("✓ All blobs exist in storage")
return nil
}
// performDeepVerificationFromDB downloads and verifies the content of
// each blob using the database as source, stopping at the first blob that
// fails. Each blob that passes is counted in result.Verified.
// each blob using the database as source.
func (v *Vaultik) performDeepVerificationFromDB(
blobs []snapshot.BlobInfo, db *sql.DB, opts *VerifyOptions,
result *VerifyResult, identities []age.Identity,
identities []age.Identity,
) error {
// Calculate total bytes for ETA
var totalBytesExpected int64
@@ -760,7 +723,6 @@ func (v *Vaultik) performDeepVerificationFromDB(
return fmt.Errorf("blob %s verification failed: %w", blobInfo.Hash, err)
}
result.Verified++
bytesProcessed += blobInfo.CompressedSize
elapsed := time.Since(startTime)
remaining := len(blobs) - (i + 1)

Some files were not shown because too many files have changed in this diff Show More