Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ad7941c215 | ||
|
|
94412d9ef3 | ||
|
|
167c0a0746 |
@@ -349,9 +349,11 @@ the backup destination store. Blobs are NOT touched — deleting blobs
|
||||
requires reading every remaining remote manifest (the destination store
|
||||
may hold snapshots this host doesn't know about), which is what
|
||||
`vaultik prune` does. On success the command prints the exact `vaultik
|
||||
prune` invocation to run as a follow-up. Local row cleanup (files,
|
||||
chunks, blobs the snapshot was the last referrer for) runs
|
||||
automatically. If the destination store is unreachable, the local-DB
|
||||
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 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
|
||||
@@ -399,7 +401,9 @@ orphaned blob figures are reported as unknown; `--json` gives them as
|
||||
`null`, lists the remote key of each unreadable manifest in
|
||||
`unreadable_manifests` and counts the manifests under skipped names in
|
||||
`skipped_manifest_count`. An unreadable manifest also leaves its
|
||||
snapshot's blob count and blob size unknown, `null` in `--json`.
|
||||
snapshot's blob count and blob size unknown, `null` in `--json`. A file
|
||||
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 snapshot's metadata and every blob from the
|
||||
|
||||
@@ -22,14 +22,34 @@ the tag exists and is exercised; what is left is merging `next` to
|
||||
|
||||
# Completed Steps
|
||||
|
||||
- 2026-10-13: Made an exclude pattern starting with `**/` also match
|
||||
directly under the snapshot path
|
||||
([issue #303](https://git.eeqj.de/sneak/vaultik/issues/303)).
|
||||
`**/node_modules` and `**/*.pyc`, the patterns `config.example.yml`
|
||||
uses, excluded `sub/node_modules` and `sub/y.pyc` but backed up
|
||||
`node_modules/` and `x.pyc` at the top of the path, since the pattern
|
||||
required a `/` before the name. As in gitignore, such a pattern now
|
||||
matches at every depth, the top included.
|
||||
- 2026-10-13: Made a `file://` destination list through a symlinked
|
||||
directory ([issue #296](https://git.eeqj.de/sneak/vaultik/issues/296)).
|
||||
A `metadata/` or `blobs/` directory that was a symlink to a directory
|
||||
elsewhere was listed as one file, so the destination store listed as
|
||||
empty while backups and restores still worked through the link.
|
||||
`prune` then removed the local snapshot records and deleted every blob,
|
||||
and `remote info` and `remote nuke` found no blobs. The listings now
|
||||
read through the link as `Get` and `Stat` do. A link whose target is
|
||||
missing, such as one to a volume that is not mounted, or a link
|
||||
pointing back up the tree makes them fail.
|
||||
|
||||
- 2026-10-13: Stopped `remote info` counting a file under `blobs/` that
|
||||
is not a blob as an orphaned blob
|
||||
([issue #295](https://git.eeqj.de/sneak/vaultik/issues/295)). A stray
|
||||
file such as `.DS_Store` was reported as an orphaned blob and the
|
||||
report advised running `prune`, which skips such a file and deleted
|
||||
nothing. `remote info` now takes its blob list from the same listing
|
||||
`prune` uses, in the table and in `--json`.
|
||||
|
||||
- 2026-10-13: Made `snapshot remove` fail for a snapshot that does not
|
||||
exist ([issue #293](https://git.eeqj.de/sneak/vaultik/issues/293)).
|
||||
The command never checked the ID: it reported the snapshot removed
|
||||
from the local database and from the destination store and exited 0,
|
||||
under `--json`, `--dry-run` and `--local-only` too. An ID that names
|
||||
no snapshot in the local index or on the destination store is now an
|
||||
error; with `--local-only`, the snapshot must be in the local index.
|
||||
The command now reports a removal from either side only when one
|
||||
happened, and `remote_removed` is true only when metadata was deleted.
|
||||
|
||||
- 2026-10-12: Bound the local index to the destination an `s3.*` config
|
||||
names ([issue #298](https://git.eeqj.de/sneak/vaultik/issues/298)).
|
||||
|
||||
@@ -255,8 +255,12 @@ manifest (the destination store may hold snapshots this host doesn't
|
||||
know about), which is what 'vaultik prune' does. On success the command
|
||||
prints the exact 'vaultik prune' invocation to run as a follow-up.
|
||||
|
||||
An ID that names no snapshot in the local index or on the destination
|
||||
store is an error.
|
||||
|
||||
Use --local-only to skip the remote half (e.g. when you want to forget a
|
||||
snapshot locally without touching the destination store).
|
||||
snapshot locally without touching the destination store); the snapshot
|
||||
must then be in the local index.
|
||||
|
||||
If the remote is unreachable, the local-database removal still completes
|
||||
and a warning is emitted; run 'vaultik snapshot remove <snapshot-id>' again
|
||||
|
||||
@@ -531,50 +531,3 @@ func TestExcludePatterns_UnanchoredPatternFile(t *testing.T) {
|
||||
require.Equal(t, 1, result.FilesScanned,
|
||||
"Unanchored pattern for file should match anywhere")
|
||||
}
|
||||
|
||||
func TestExcludePatterns_DoubleStarDirectoryAtEveryDepth(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
// As in gitignore, a leading **/ 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,
|
||||
"**/ directory pattern should match at the top level and nested")
|
||||
}
|
||||
|
||||
func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
// As in gitignore, a leading **/ also matches directly under the source dir
|
||||
fs := setupAnchoredTestFS(t)
|
||||
|
||||
scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/*.txt"})
|
||||
defer cleanup()
|
||||
|
||||
ctx := context.Background()
|
||||
createSnapshotRecord(ctx, t, repos, "test-snapshot")
|
||||
|
||||
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
|
||||
require.NoError(t, err)
|
||||
|
||||
// **/*.txt should exclude ALL .txt files:
|
||||
// - /backup/file.txt
|
||||
// - /backup/projectname/file.txt
|
||||
// - /backup/otherproject/projectname/file.txt
|
||||
// Total files: 4, excluded: 3
|
||||
require.Equal(t, 1, result.FilesScanned,
|
||||
"**/ file pattern should match at the top level and nested")
|
||||
}
|
||||
|
||||
@@ -2013,14 +2013,6 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
|
||||
// Remove trailing slash if present (directory indicator)
|
||||
pattern = strings.TrimSuffix(pattern, "/")
|
||||
|
||||
// A leading "**/" demands a "/" before the name and so misses an
|
||||
// entry directly under the source path. An unanchored pattern
|
||||
// already matches at every depth, so drop the prefix: as in
|
||||
// gitignore, "**/x" then also matches a top-level "x".
|
||||
if !anchored {
|
||||
pattern = strings.TrimPrefix(pattern, "**/")
|
||||
}
|
||||
|
||||
// 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
|
||||
|
||||
+45
-10
@@ -120,9 +120,10 @@ func (f *FileStorer) Delete(_ context.Context, key string) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// 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.
|
||||
// List returns all keys with the given prefix, reading through symlinked
|
||||
// directories. It fails when the destination directory is missing or the
|
||||
// prefix is a symlink whose target is missing; a missing prefix under the
|
||||
// destination directory is an empty listing.
|
||||
func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) {
|
||||
var keys []string
|
||||
|
||||
@@ -133,8 +134,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
|
||||
|
||||
basePath := f.fullPath(prefix)
|
||||
|
||||
// Check if the prefix exists
|
||||
exists, err := afero.Exists(f.fs, basePath)
|
||||
exists, err := f.prefixExists(basePath)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("checking path: %w", err)
|
||||
}
|
||||
@@ -143,7 +143,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
|
||||
return keys, nil // Empty list for non-existent prefix
|
||||
}
|
||||
|
||||
err = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
|
||||
err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -176,7 +176,9 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
|
||||
}
|
||||
|
||||
// ListStream returns a channel of ObjectInfo for large result sets. Like
|
||||
// List, it sends an error when the destination directory is missing.
|
||||
// List, it reads through symlinked directories and sends an error when
|
||||
// the destination directory is missing or the prefix is a symlink whose
|
||||
// target is missing.
|
||||
func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan ObjectInfo {
|
||||
ch := make(chan ObjectInfo)
|
||||
|
||||
@@ -192,8 +194,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
|
||||
|
||||
basePath := f.fullPath(prefix)
|
||||
|
||||
// Check if the prefix exists
|
||||
exists, err := afero.Exists(f.fs, basePath)
|
||||
exists, err := f.prefixExists(basePath)
|
||||
if err != nil {
|
||||
ch <- ObjectInfo{Err: fmt.Errorf("checking path: %w", err)}
|
||||
|
||||
@@ -204,7 +205,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
|
||||
return // Empty channel for non-existent prefix
|
||||
}
|
||||
|
||||
_ = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
|
||||
_ = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
|
||||
// Check context cancellation
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
@@ -352,6 +353,40 @@ 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 is afero.Exists, except that it does not follow a symlink
|
||||
// at path. A symlinked prefix whose target is missing, such as a link to
|
||||
// a volume that is not mounted, therefore exists, and walk then fails on
|
||||
// it; with afero.Exists it would list as empty, and prune would delete
|
||||
// every blob.
|
||||
func (f *FileStorer) prefixExists(path string) (bool, error) {
|
||||
lstater, ok := f.fs.(afero.Lstater)
|
||||
if !ok {
|
||||
return afero.Exists(f.fs, path)
|
||||
}
|
||||
|
||||
_, _, err := lstater.LstatIfPossible(path)
|
||||
if err == nil {
|
||||
return true, nil
|
||||
}
|
||||
|
||||
if os.IsNotExist(err) {
|
||||
return false, nil
|
||||
}
|
||||
|
||||
return false, err
|
||||
}
|
||||
|
||||
// fullPath returns the full filesystem path for a key.
|
||||
func (f *FileStorer) fullPath(key string) string {
|
||||
return filepath.Join(f.basePath, key)
|
||||
|
||||
@@ -4,7 +4,10 @@ import (
|
||||
"context"
|
||||
"errors"
|
||||
"io/fs"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"reflect"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"sneak.berlin/go/vaultik/internal/storage"
|
||||
@@ -60,3 +63,151 @@ func TestFileStorerListMissingDestination(t *testing.T) {
|
||||
t.Errorf("ListStream error = %v, want a not-exist error", streamErr)
|
||||
}
|
||||
}
|
||||
|
||||
// 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.
|
||||
func TestFileStorerListsThroughSymlinkedDirectory(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
for _, dir := range []string{"metadata", "blobs"} {
|
||||
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)
|
||||
}
|
||||
|
||||
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)
|
||||
}
|
||||
|
||||
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)
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// 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.
|
||||
func TestFileStorerListFailsOnSymlinkWithMissingTarget(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
ctx := context.Background()
|
||||
|
||||
for _, dir := range []string{"metadata", "blobs"} {
|
||||
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 + "/"} {
|
||||
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")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -167,10 +167,6 @@ const (
|
||||
// metadataKeyParts is the minimum "/"-separated segment count of a
|
||||
// metadata object key (metadata/<snapshot-id>/<filename>).
|
||||
metadataKeyParts = 3
|
||||
|
||||
// blobKeyParts is the minimum "/"-separated segment count of a blob
|
||||
// object key (blobs/<aa>/<bb>/<hash>).
|
||||
blobKeyParts = 4
|
||||
)
|
||||
|
||||
// SnapshotMetadataInfo contains information about a single snapshot's metadata
|
||||
@@ -454,23 +450,16 @@ func (v *Vaultik) scanRemoteBlobStorage(
|
||||
v.stdoutf("Scanning blobs...\n")
|
||||
}
|
||||
|
||||
blobCh := v.Storage.ListStream(v.ctx, "blobs/")
|
||||
allBlobs := make(map[string]int64)
|
||||
|
||||
for obj := range blobCh {
|
||||
if obj.Err != nil {
|
||||
return fmt.Errorf("listing blobs: %w", obj.Err)
|
||||
// Use prune's listing, so a file under blobs/ that prune would never
|
||||
// delete is not counted as a blob, and so not as an orphaned one.
|
||||
allBlobs, err := v.listAllRemoteBlobs()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
parts := strings.Split(obj.Key, "/")
|
||||
if len(parts) < blobKeyParts {
|
||||
continue
|
||||
}
|
||||
|
||||
hash := parts[3]
|
||||
allBlobs[hash] = obj.Size
|
||||
for _, size := range allBlobs {
|
||||
result.TotalBlobCount++
|
||||
result.TotalBlobSize += obj.Size
|
||||
result.TotalBlobSize += size
|
||||
}
|
||||
|
||||
// A blob named only by a manifest that could not be read, or by one
|
||||
|
||||
@@ -23,6 +23,10 @@ var errNukeRequiresForce = errors.New(
|
||||
// metadata.
|
||||
const metadataDirName = "metadata"
|
||||
|
||||
// blobKeyParts is the "/"-separated segment count of a blob object key
|
||||
// (blobs/<aa>/<bb>/<hash>).
|
||||
const blobKeyParts = 4
|
||||
|
||||
// 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
|
||||
|
||||
@@ -185,6 +185,39 @@ func TestRemoteInfo_SkipsNonConformingMetadataName(t *testing.T) {
|
||||
assert.NotContains(t, doc, "unreadable_manifests")
|
||||
}
|
||||
|
||||
// TestRemoteInfo_DoesNotCountNonBlobFileUnderBlobs checks that a file
|
||||
// under blobs/ whose name is not a blob hash is not counted as a blob.
|
||||
// prune never deletes such a file, so counting it as an orphaned blob
|
||||
// would advise a prune that removes nothing.
|
||||
func TestRemoteInfo_DoesNotCountNonBlobFileUnderBlobs(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
t.Parallel()
|
||||
|
||||
env := newListEnv(t)
|
||||
env.addRemote(t, listRemoteID, time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
|
||||
addBlob(t, env.store.testStorer, testBlobHashA)
|
||||
require.NoError(t, env.store.Put(context.Background(),
|
||||
"blobs/"+testBlobHashA[:2]+"/"+testBlobHashA[2:4]+"/.DS_Store",
|
||||
bytes.NewReader([]byte("junk"))))
|
||||
|
||||
require.NoError(t, env.v.RemoteInfo(false))
|
||||
|
||||
text := env.stdout.String()
|
||||
assert.Contains(t, text, "Total blobs on remote: 1 (")
|
||||
assert.Contains(t, text, "Orphaned (unreferenced): 0 (")
|
||||
assert.NotContains(t, text, "vaultik prune")
|
||||
|
||||
env.stdout.Reset()
|
||||
require.NoError(t, env.v.RemoteInfo(true))
|
||||
|
||||
var doc map[string]any
|
||||
|
||||
require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &doc))
|
||||
assert.InDelta(t, 1, doc["total_blob_count"], 0)
|
||||
assert.InDelta(t, 0, doc["orphaned_blob_count"], 0)
|
||||
assert.InDelta(t, 0, doc["orphaned_blob_size"], 0)
|
||||
}
|
||||
|
||||
// TestRemoteInfo_DirectoryWithoutManifestLeavesOrphansKnown checks that
|
||||
// a directory under metadata/ holding no manifest.json.zst, such as one
|
||||
// left by a backup interrupted before its manifest upload, leaves the
|
||||
|
||||
@@ -3,17 +3,21 @@ package vaultik_test
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"database/sql"
|
||||
"io"
|
||||
"strings"
|
||||
"sync"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/klauspost/compress/zstd"
|
||||
"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/storage"
|
||||
"sneak.berlin/go/vaultik/internal/types"
|
||||
"sneak.berlin/go/vaultik/internal/vaultik"
|
||||
)
|
||||
|
||||
@@ -214,6 +218,37 @@ func addBlob(t *testing.T, store *testStorer, hash string) {
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
// newLocalIndex returns an in-memory local index holding a completed
|
||||
// snapshot row for each of ids.
|
||||
func newLocalIndex(t *testing.T, ids ...string) *database.Repositories {
|
||||
t.Helper()
|
||||
|
||||
ctx := context.Background()
|
||||
|
||||
db, err := database.New(ctx, ":memory:")
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() { _ = db.Close() })
|
||||
|
||||
repos := database.NewRepositories(db)
|
||||
|
||||
for _, id := range ids {
|
||||
completedAt := time.Now().UTC()
|
||||
snap := &database.Snapshot{
|
||||
ID: types.SnapshotID(id),
|
||||
Hostname: snapHostname,
|
||||
StartedAt: completedAt,
|
||||
CompletedAt: &completedAt,
|
||||
}
|
||||
|
||||
err = repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
|
||||
return repos.Snapshots.Create(ctx, tx, snap)
|
||||
})
|
||||
require.NoError(t, err)
|
||||
}
|
||||
|
||||
return repos
|
||||
}
|
||||
|
||||
// ============================================================================
|
||||
// Unit Tests for RemoveSnapshot
|
||||
// ============================================================================
|
||||
@@ -233,6 +268,7 @@ func TestRemoveSnapshot_LocalOnly_PreservesRemote(t *testing.T) {
|
||||
addBlob(t, store, blobA)
|
||||
|
||||
tv := vaultik.NewForTesting(store)
|
||||
tv.Repositories = newLocalIndex(t, "snapshot-001")
|
||||
|
||||
opts := &vaultik.RemoveOptions{Force: true, LocalOnly: true}
|
||||
result, err := tv.RemoveSnapshot("snapshot-001", opts)
|
||||
@@ -268,6 +304,7 @@ func TestRemoveSnapshot_DefaultRemovesMetadataNotBlobs(t *testing.T) {
|
||||
addBlob(t, store, blobShared)
|
||||
|
||||
tv := vaultik.NewForTesting(store)
|
||||
tv.Repositories = newLocalIndex(t, "snapshot-001", "snapshot-002")
|
||||
|
||||
opts := &vaultik.RemoveOptions{Force: true}
|
||||
result, err := tv.RemoveSnapshot("snapshot-001", opts)
|
||||
@@ -316,6 +353,84 @@ func TestRemoveSnapshot_DryRun(t *testing.T) {
|
||||
assert.Contains(t, tv.Stdout.String(), "[Dry run - no changes made]")
|
||||
}
|
||||
|
||||
// TestRemoveSnapshot_UnknownIDIsError checks that an ID naming no
|
||||
// snapshot in the local index or on the destination store is an error
|
||||
// under every option, and that nothing is reported as removed.
|
||||
func TestRemoveSnapshot_UnknownIDIsError(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
t.Parallel()
|
||||
|
||||
for name, opts := range map[string]vaultik.RemoveOptions{
|
||||
"force": {Force: true},
|
||||
"json": {JSON: true},
|
||||
"dry-run": {Force: true, DryRun: true},
|
||||
"local-only": {Force: true, LocalOnly: true},
|
||||
} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
store := newTestStorer()
|
||||
addManifest(t, store, "snapshot-001", nil)
|
||||
|
||||
tv := vaultik.NewForTesting(store)
|
||||
tv.Repositories = newLocalIndex(t, "snapshot-001")
|
||||
|
||||
result, err := tv.RemoveSnapshot("snapshot-999", &opts)
|
||||
|
||||
require.ErrorContains(t, err, "snapshot not found")
|
||||
assert.False(t, result.RemoteRemoved)
|
||||
assert.Empty(t, tv.Stdout.String())
|
||||
assert.True(t, store.hasKey(remoteKeyPath("snapshot-001")))
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestRemoveSnapshot_NoMetadataOnDestination checks that removing a
|
||||
// snapshot whose metadata is not on the destination store does not
|
||||
// report metadata removed from it.
|
||||
func TestRemoveSnapshot_NoMetadataOnDestination(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
t.Parallel()
|
||||
|
||||
tv := vaultik.NewForTesting(newTestStorer())
|
||||
tv.Repositories = newLocalIndex(t, "snapshot-001")
|
||||
|
||||
result, err := tv.RemoveSnapshot("snapshot-001",
|
||||
&vaultik.RemoveOptions{Force: true})
|
||||
|
||||
require.NoError(t, err)
|
||||
assert.False(t, result.RemoteRemoved)
|
||||
|
||||
out := tv.Stdout.String()
|
||||
assert.Contains(t, out, "Removed snapshot 'snapshot-001' from local database")
|
||||
assert.NotContains(t, out, "Removed snapshot metadata from remote storage")
|
||||
}
|
||||
|
||||
// TestRemoveSnapshot_NotInLocalIndex checks that removing a snapshot
|
||||
// only the destination store holds removes its metadata there without
|
||||
// reporting a removal from the local database.
|
||||
func TestRemoveSnapshot_NotInLocalIndex(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
t.Parallel()
|
||||
|
||||
store := newTestStorer()
|
||||
addManifest(t, store, "snapshot-001", nil)
|
||||
|
||||
tv := vaultik.NewForTesting(store)
|
||||
tv.Repositories = newLocalIndex(t)
|
||||
|
||||
result, err := tv.RemoveSnapshot("snapshot-001",
|
||||
&vaultik.RemoveOptions{Force: true})
|
||||
|
||||
require.NoError(t, err)
|
||||
assert.True(t, result.RemoteRemoved)
|
||||
assert.False(t, store.hasKey(remoteKeyPath("snapshot-001")))
|
||||
|
||||
out := tv.Stdout.String()
|
||||
assert.NotContains(t, out, "from local database")
|
||||
assert.Contains(t, out, "Removed snapshot metadata from remote storage")
|
||||
}
|
||||
|
||||
func TestRemoveAllSnapshots_RequiresForce(t *testing.T) {
|
||||
log.Initialize(log.Config{})
|
||||
t.Parallel()
|
||||
|
||||
@@ -23,6 +23,7 @@ var (
|
||||
errNoSnapshotsInConfig = errors.New("no snapshots configured")
|
||||
errSnapshotVerifyFailed = errors.New("verification failed")
|
||||
errRemoveAllNeedsForce = errors.New("--all requires --force")
|
||||
errSnapshotNotFound = errors.New("snapshot not found")
|
||||
errInvalidTableName = errors.New("invalid table name")
|
||||
errNoAgeRecipients = errors.New(
|
||||
"creating a snapshot needs at least one public key in " +
|
||||
@@ -643,7 +644,7 @@ func (v *Vaultik) confirmAndExecutePurge(
|
||||
"snapshot_id", snapshotID, "error", err)
|
||||
}
|
||||
|
||||
err = v.deleteRemoteSnapshotByKey(snapshot.RemoteSnapshotKey(snapshotID))
|
||||
_, err = v.deleteRemoteSnapshotByKey(snapshot.RemoteSnapshotKey(snapshotID))
|
||||
if err != nil {
|
||||
return fmt.Errorf("deleting snapshot %s from remote: %w", snapshotID, err)
|
||||
}
|
||||
@@ -1153,6 +1154,11 @@ func (v *Vaultik) RemoveSnapshot(
|
||||
return result, err
|
||||
}
|
||||
|
||||
inLocalIndex, err := v.findSnapshotToRemove(snapshotID, opts)
|
||||
if err != nil {
|
||||
return result, err
|
||||
}
|
||||
|
||||
if opts.DryRun {
|
||||
return v.removeSnapshotDryRun(result, snapshotID, opts)
|
||||
}
|
||||
@@ -1161,12 +1167,14 @@ func (v *Vaultik) RemoveSnapshot(
|
||||
return result, nil
|
||||
}
|
||||
|
||||
if inLocalIndex {
|
||||
log.Info("Removing snapshot from local database", "snapshot_id", snapshotID)
|
||||
|
||||
err = v.deleteSnapshotFromLocalDB(snapshotID)
|
||||
if err != nil {
|
||||
return result, fmt.Errorf("removing from local database: %w", err)
|
||||
}
|
||||
}
|
||||
|
||||
if !opts.LocalOnly {
|
||||
result.RemoteRemoved = v.removeSnapshotRemote(snapshotID, opts)
|
||||
@@ -1184,9 +1192,11 @@ func (v *Vaultik) RemoveSnapshot(
|
||||
return result, v.outputRemoveJSON(result)
|
||||
}
|
||||
|
||||
if inLocalIndex {
|
||||
v.stdoutf("Removed snapshot '%s' from local database\n", snapshotID)
|
||||
}
|
||||
|
||||
if !opts.LocalOnly && result.RemoteRemoved {
|
||||
if result.RemoteRemoved {
|
||||
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 "+
|
||||
@@ -1196,6 +1206,45 @@ func (v *Vaultik) RemoveSnapshot(
|
||||
return result, nil
|
||||
}
|
||||
|
||||
// findSnapshotToRemove reports whether the local index has a row for
|
||||
// snapshotID, and returns errSnapshotNotFound when there is nothing to
|
||||
// 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.
|
||||
func (v *Vaultik) findSnapshotToRemove(
|
||||
snapshotID string, opts *RemoveOptions,
|
||||
) (bool, error) {
|
||||
if v.Repositories != nil {
|
||||
snap, err := v.Repositories.Snapshots.GetByID(v.ctx, snapshotID)
|
||||
if err != nil {
|
||||
return false, fmt.Errorf("looking up snapshot in local index: %w", err)
|
||||
}
|
||||
|
||||
if snap != nil {
|
||||
return true, nil
|
||||
}
|
||||
}
|
||||
|
||||
if opts.LocalOnly {
|
||||
return false, fmt.Errorf("%w in the local index: %s",
|
||||
errSnapshotNotFound, snapshotID)
|
||||
}
|
||||
|
||||
objects, err := v.remoteSnapshotObjects(snapshot.RemoteSnapshotKey(snapshotID))
|
||||
if err != nil {
|
||||
return false, fmt.Errorf("looking up snapshot on destination store: %w", err)
|
||||
}
|
||||
|
||||
if len(objects) == 0 {
|
||||
return false, fmt.Errorf(
|
||||
"%w in the local index or on the destination store: %s",
|
||||
errSnapshotNotFound, snapshotID)
|
||||
}
|
||||
|
||||
return false, nil
|
||||
}
|
||||
|
||||
// removeSnapshotDryRun reports what RemoveSnapshot would do without
|
||||
// making changes.
|
||||
func (v *Vaultik) removeSnapshotDryRun(
|
||||
@@ -1255,14 +1304,14 @@ func (v *Vaultik) confirmRemoveSnapshot(snapshotID string, opts *RemoveOptions)
|
||||
// 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.
|
||||
// succeeded and deleted something.
|
||||
func (v *Vaultik) removeSnapshotRemote(snapshotID string, opts *RemoveOptions) bool {
|
||||
log.Info("Removing snapshot metadata from remote storage",
|
||||
"snapshot_id", snapshotID)
|
||||
|
||||
remoteKey := snapshot.RemoteSnapshotKey(snapshotID)
|
||||
|
||||
err := v.deleteRemoteSnapshotByKey(remoteKey)
|
||||
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 "+
|
||||
@@ -1280,7 +1329,7 @@ func (v *Vaultik) removeSnapshotRemote(snapshotID string, opts *RemoveOptions) b
|
||||
return false
|
||||
}
|
||||
|
||||
return true
|
||||
return deleted > 0
|
||||
}
|
||||
|
||||
// RemoveAllSnapshots removes every snapshot known to the local
|
||||
@@ -1572,7 +1621,7 @@ func (v *Vaultik) removeAllLocalSnapshots(
|
||||
}
|
||||
|
||||
if !opts.LocalOnly {
|
||||
err = v.deleteRemoteSnapshotByKey(
|
||||
_, err = v.deleteRemoteSnapshotByKey(
|
||||
snapshot.RemoteSnapshotKey(snapshotID))
|
||||
if err != nil {
|
||||
log.Warn("Failed to remove snapshot metadata from remote",
|
||||
@@ -1598,7 +1647,7 @@ func (v *Vaultik) removeAllOrphanRemotes(
|
||||
for _, key := range orphanRemoteKeys {
|
||||
log.Info("Removing orphan remote snapshot", "remote_key", key)
|
||||
|
||||
err := v.deleteRemoteSnapshotByKey(key)
|
||||
_, err := v.deleteRemoteSnapshotByKey(key)
|
||||
if err != nil {
|
||||
log.Warn("Failed to remove orphan from remote",
|
||||
"remote_key", key, "error", err)
|
||||
@@ -1645,34 +1694,44 @@ func (v *Vaultik) deleteSnapshotFromLocalDB(snapshotID string) error {
|
||||
}
|
||||
|
||||
// deleteRemoteSnapshotByKey removes everything under
|
||||
// metadata/<remoteKey>/ on the destination store. The argument is a
|
||||
// remote key (double-SHA256 derivation), not a human snapshot ID;
|
||||
// callers that have a human ID must hash via snapshot.RemoteSnapshotKey
|
||||
// first.
|
||||
func (v *Vaultik) deleteRemoteSnapshotByKey(remoteKey string) error {
|
||||
prefix := fmt.Sprintf("metadata/%s/", remoteKey)
|
||||
objectCh := v.Storage.ListStream(v.ctx, prefix)
|
||||
|
||||
var objectsToDelete []string
|
||||
|
||||
for object := range objectCh {
|
||||
if object.Err != nil {
|
||||
return fmt.Errorf("listing objects: %w", object.Err)
|
||||
}
|
||||
|
||||
objectsToDelete = append(objectsToDelete, object.Key)
|
||||
}
|
||||
|
||||
for _, key := range objectsToDelete {
|
||||
err := v.Storage.Delete(v.ctx, key)
|
||||
// metadata/<remoteKey>/ on the destination store and returns how many
|
||||
// objects it deleted. The argument is a remote key (double-SHA256
|
||||
// derivation), not a human snapshot ID; callers that have a human ID
|
||||
// must hash via snapshot.RemoteSnapshotKey first.
|
||||
func (v *Vaultik) deleteRemoteSnapshotByKey(remoteKey string) (int, error) {
|
||||
objectsToDelete, err := v.remoteSnapshotObjects(remoteKey)
|
||||
if err != nil {
|
||||
return fmt.Errorf("removing %s: %w", key, err)
|
||||
return 0, err
|
||||
}
|
||||
|
||||
for i, key := range objectsToDelete {
|
||||
err = v.Storage.Delete(v.ctx, key)
|
||||
if err != nil {
|
||||
return i, fmt.Errorf("removing %s: %w", key, err)
|
||||
}
|
||||
|
||||
log.Debug("Deleted remote object", "key", key)
|
||||
}
|
||||
|
||||
return nil
|
||||
return len(objectsToDelete), nil
|
||||
}
|
||||
|
||||
// remoteSnapshotObjects lists the keys of every object under
|
||||
// metadata/<remoteKey>/ on the destination store.
|
||||
func (v *Vaultik) remoteSnapshotObjects(remoteKey string) ([]string, error) {
|
||||
prefix := fmt.Sprintf("metadata/%s/", remoteKey)
|
||||
|
||||
var keys []string
|
||||
|
||||
for object := range v.Storage.ListStream(v.ctx, prefix) {
|
||||
if object.Err != nil {
|
||||
return nil, fmt.Errorf("listing objects: %w", object.Err)
|
||||
}
|
||||
|
||||
keys = append(keys, object.Key)
|
||||
}
|
||||
|
||||
return keys, nil
|
||||
}
|
||||
|
||||
// outputRemoveJSON outputs the removal result as JSON
|
||||
|
||||
@@ -0,0 +1,121 @@
|
||||
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")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// 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
|
||||
}
|
||||
Reference in New Issue
Block a user