Record the stored size of a blob a backup finds already stored (closes #300)

When a finished blob already existed at the destination, the upload was
skipped but the blob row, and so the manifest, kept the size of the
local copy. That copy differs from the stored object when
compression_level or the recipients changed since it was written, so
shallow and deep verify failed on a good snapshot. Marking a blob
uploaded now records the size of the object in storage: for an existing
blob, the size Stat reports.

Judgement call: the test adds a recipient rather than changing the
compression level, because an extra age recipient always makes the
local copy larger, while two zstd levels need not compress the test
data differently.

Model: opus-5-5

README.md

@@ -401,9 +401,7 @@ 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`. A file
+snapshot's blob count and blob size unknown, `null` in `--json`.
-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

TODO.md

@@ -22,24 +22,15 @@ the tag exists and is exercised; what is left is merging `next` to
 
 # Completed Steps
 
-- 2026-10-13: Made a `file://` destination list through a symlinked
+- 2026-10-13: Recorded the size of the stored object for a blob a backup
-  directory ([issue #296](https://git.eeqj.de/sneak/vaultik/issues/296)).
+  found already stored
-  A `metadata/` or `blobs/` directory that was a symlink to a directory
+  ([issue #300](https://git.eeqj.de/sneak/vaultik/issues/300)). When the
-  elsewhere was listed as one file, so the destination store listed as
+  upload was skipped, the blob row and the manifest kept the size of the
-  empty while backups and restores still worked through the link.
+  local copy, which differs from the stored object's when
-  `prune` then removed the local snapshot records and deleted every blob,
+  `compression_level` or the recipients changed since it was written.
-  and `remote info` and `remote nuke` found no blobs. The listings now
+  `snapshot verify` then failed on a good snapshot, shallow and deep,
-  read through the link as `Get` and `Stat` do. A link whose target is
+  and the listed sizes were wrong. Marking the blob uploaded now records
-  missing, such as one to a volume that is not mounted, or a link
+  the size of the object in storage.
-  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)).

docs/DATAMODEL.md

@@ -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
+- `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 differs from the size of the local copy
 - `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.
@@ -183,7 +183,7 @@ Tracks blob upload metrics.
    - `UPDATE blobs SET blob_hash = ?, finished_ts = ?` - Finalize blob after packing
 
 4. **Upload**
-   - `UPDATE blobs SET uploaded_ts = ?` - Mark blob as uploaded
+   - `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)
    - `INSERT INTO uploads` - Record upload metrics with snapshot_id
    - `INSERT INTO snapshot_blobs` - Associate blob with snapshot
 

internal/database/blobs.go

@@ -159,13 +159,16 @@ func (r *BlobRepository) UpdateFinished(
 	return nil
 }
 
-// UpdateUploaded marks a blob as uploaded
+// 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.
 func (r *BlobRepository) UpdateUploaded(
-	ctx context.Context, tx *sql.Tx, id string,
+	ctx context.Context, tx *sql.Tx, id string, storedSize int64,
 ) error {
 	query := `
-		UPDATE blobs 
+		UPDATE blobs
-		SET uploaded_ts = ?
+		SET uploaded_ts = ?, compressed_size = ?
 		WHERE id = ?
 	`
 
@@ -173,9 +176,9 @@ func (r *BlobRepository) UpdateUploaded(
 
 	var err error
 	if tx != nil {
-		_, err = tx.ExecContext(ctx, query, now, id)
+		_, err = tx.ExecContext(ctx, query, now, storedSize, id)
 	} else {
-		_, err = r.db.ExecWithLog(ctx, query, now, id)
+		_, err = r.db.ExecWithLog(ctx, query, now, storedSize, id)
 	}
 
 	if err != nil {

internal/database/blobs_test.go

@@ -122,8 +122,8 @@ func TestBlobRepositoryUpdates(t *testing.T) {
 		t.Errorf("expected compressed size 500, got %d", updated.CompressedSize)
 	}
 
-	// Test UpdateUploaded
+	// Test UpdateUploaded, with a stored object larger than the local copy
-	err = repo.UpdateUploaded(ctx, nil, blob.ID.String())
+	err = repo.UpdateUploaded(ctx, nil, blob.ID.String(), 600)
 	if err != nil {
 		t.Fatalf("failed to update blob as uploaded: %v", err)
 	}
@@ -141,6 +141,10 @@ 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/snapshot/scanner.go

@@ -1509,7 +1509,8 @@ 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)
+				err := s.repos.Blobs.UpdateUploaded(
+					ctx, tx, b.ID, b.Compressed)
 				if err != nil {
 					return fmt.Errorf("marking blob uploaded: %w", err)
 				}
@@ -1545,7 +1546,7 @@ func (s *Scanner) handleBlobReady(
 	blobPath := fmt.Sprintf("blobs/%s/%s/%s",
 		finishedBlob.Hash[:2], finishedBlob.Hash[2:4], finishedBlob.Hash)
 
-	blobExists, err := s.uploadBlobIfNeeded(
+	storedSize, blobExists, err := s.uploadBlobIfNeeded(
 		ctx, blobPath, blobWithReader, startTime, result)
 	if err != nil {
 		s.cleanupBlobTempFile(blobWithReader)
@@ -1553,7 +1554,8 @@ func (s *Scanner) handleBlobReady(
 		return fmt.Errorf("uploading blob %s: %w", finishedBlob.Hash, err)
 	}
 
-	err = s.recordBlobMetadata(ctx, finishedBlob, blobExists, startTime)
+	err = s.recordBlobMetadata(
+		ctx, finishedBlob, storedSize, blobExists, startTime)
 	if err != nil {
 		s.cleanupBlobTempFile(blobWithReader)
 
@@ -1575,20 +1577,22 @@ func (s *Scanner) handleBlobReady(
 }
 
 // uploadBlobIfNeeded uploads the blob to storage if it doesn't already
-// exist, returns whether it existed
+// 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.
 func (s *Scanner) uploadBlobIfNeeded(
 	ctx context.Context,
 	blobPath string,
 	blobWithReader *blob.WithReader,
 	startTime time.Time,
 	result *ScanResult,
-) (bool, error) {
+) (int64, bool, error) {
 	finishedBlob := blobWithReader.FinishedBlob
 
 	// Check if blob already exists (deduplication after restart)
 	destination := s.storage.Info().Location
 
-	_, err := s.storage.Stat(ctx, blobPath)
+	stored, err := s.storage.Stat(ctx, blobPath)
 	if err == nil {
 		log.Info("Blob already exists in storage, skipping upload",
 			"hash", finishedBlob.Hash,
@@ -1597,7 +1601,7 @@ func (s *Scanner) uploadBlobIfNeeded(
 			s.ui.Hex(finishedBlob.Hash), s.ui.Size(finishedBlob.Compressed),
 			s.ui.Path(destination))
 
-		return true, nil
+		return stored.Size, true, nil
 	}
 
 	s.ui.Beginf("Uploading blob %s (%s) to %s.",
@@ -1611,7 +1615,7 @@ func (s *Scanner) uploadBlobIfNeeded(
 	if err != nil {
 		log.Error("Failed to upload blob", "hash", finishedBlob.Hash, "error", err)
 
-		return false, fmt.Errorf("uploading blob to storage: %w", err)
+		return 0, false, fmt.Errorf("uploading blob to storage: %w", err)
 	}
 
 	uploadDuration := time.Since(startTime)
@@ -1642,7 +1646,7 @@ func (s *Scanner) uploadBlobIfNeeded(
 		stats.BytesUploaded.Add(finishedBlob.Compressed)
 	}
 
-	return false, nil
+	return finishedBlob.Compressed, false, nil
 }
 
 // makeUploadProgressCallback creates a progress callback for blob uploads.
@@ -1712,6 +1716,7 @@ func (s *Scanner) makeUploadProgressCallback(
 func (s *Scanner) recordBlobMetadata(
 	ctx context.Context,
 	finishedBlob *blob.FinishedBlob,
+	storedSize int64,
 	blobExists bool,
 	startTime time.Time,
 ) error {
@@ -1723,7 +1728,8 @@ 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)
+		err := s.repos.Blobs.UpdateUploaded(
+			txCtx, tx, finishedBlob.ID, storedSize)
 		if err != nil {
 			return fmt.Errorf("updating blob upload timestamp: %w", err)
 		}

internal/storage/file.go

@@ -120,10 +120,9 @@ func (f *FileStorer) Delete(_ context.Context, key string) error {
 	return nil
 }
 
-// List returns all keys with the given prefix, reading through symlinked
+// List returns all keys with the given prefix. It fails when the
-// directories. It fails when the destination directory is missing or the
+// destination directory is missing; a missing prefix under it is an
-// prefix is a symlink whose target is missing; a missing prefix under the
+// empty listing.
-// destination directory is an empty listing.
 func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) {
 	var keys []string
 
@@ -134,7 +133,8 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
 
 	basePath := f.fullPath(prefix)
 
-	exists, err := f.prefixExists(basePath)
+	// Check if the prefix exists
+	exists, err := afero.Exists(f.fs, 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 = 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
 		}
@@ -176,9 +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
+// List, it sends an error when the destination directory is missing.
-// 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)
 
@@ -194,7 +192,8 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
 
 		basePath := f.fullPath(prefix)
 
-		exists, err := f.prefixExists(basePath)
+		// Check if the prefix exists
+		exists, err := afero.Exists(f.fs, basePath)
 		if err != nil {
 			ch <- ObjectInfo{Err: fmt.Errorf("checking path: %w", err)}
 
@@ -205,7 +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():
@@ -353,40 +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 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)

internal/storage/file_backend_test.go

@@ -4,10 +4,7 @@ import (
 	"context"
 	"errors"
 	"io/fs"
-	"os"
 	"path/filepath"
-	"reflect"
-	"strings"
 	"testing"
 
 	"sneak.berlin/go/vaultik/internal/storage"
@@ -63,151 +60,3 @@ 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")
-	}
-}

internal/vaultik/info.go

@@ -167,6 +167,10 @@ 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
@@ -450,16 +454,23 @@ func (v *Vaultik) scanRemoteBlobStorage(
 		v.stdoutf("Scanning blobs...\n")
 	}
 
-	// Use prune's listing, so a file under blobs/ that prune would never
+	blobCh := v.Storage.ListStream(v.ctx, "blobs/")
-	// delete is not counted as a blob, and so not as an orphaned one.
+	allBlobs := make(map[string]int64)
-	allBlobs, err := v.listAllRemoteBlobs()
-	if err != nil {
-		return err
-	}
 
-	for _, size := range allBlobs {
+	for obj := range blobCh {
+		if obj.Err != nil {
+			return fmt.Errorf("listing blobs: %w", obj.Err)
+		}
+
+		parts := strings.Split(obj.Key, "/")
+		if len(parts) < blobKeyParts {
+			continue
+		}
+
+		hash := parts[3]
+		allBlobs[hash] = obj.Size
 		result.TotalBlobCount++
-		result.TotalBlobSize += size
+		result.TotalBlobSize += obj.Size
 	}
 
 	// A blob named only by a manifest that could not be read, or by one

internal/vaultik/prune.go

@@ -23,10 +23,6 @@ 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

internal/vaultik/remote_info_test.go

@@ -185,39 +185,6 @@ 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

internal/vaultik/reused_blob_verify_test.go

@@ -0,0 +1,83 @@
+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 := filepath.Join(tempDir, "remote")
+	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/symlinked_destination_test.go

@@ -1,121 +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")
-		})
-	}
-}
-
-// 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
-}