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 can differ from the stored object when
compression_level or the recipients changed since it was written, and
then 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

@@ -294,8 +294,7 @@ needed.
 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.
+were not stored before, recorded when its backup ran).
 
 Listing the destination store does **not** require the age secret key,
 so it works in vaultik's intended configuration, where the backed-up

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 can differ 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.
@@ -122,7 +122,6 @@ Tracks backup snapshots.
 - `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 +184,7 @@ 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 
-		SET uploaded_ts = ?
+		UPDATE blobs
+		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
-	err = repo.UpdateUploaded(ctx, nil, blob.ID.String())
+	// Test UpdateUploaded, with a stored object larger than the local copy
+	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/database/schema/001.sql

@@ -89,7 +89,6 @@ CREATE TABLE IF NOT EXISTS snapshots (
     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

@@ -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,
@@ -149,17 +145,7 @@ func (r *SnapshotRepository) UpdateExtendedStats(
 		    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
-		    )
+		    new_chunk_size = ?
 		WHERE id = ?
 	`
 
@@ -584,22 +570,30 @@ 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

internal/snapshot/scanner.go

@@ -1517,7 +1517,8 @@ 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)
 				}
@@ -1553,7 +1554,7 @@ 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)
@@ -1561,7 +1562,8 @@ 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)
 
@@ -1583,20 +1585,22 @@ 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,
@@ -1605,7 +1609,7 @@ 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.",
@@ -1619,7 +1623,7 @@ 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)
@@ -1650,7 +1654,7 @@ 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.
@@ -1720,6 +1724,7 @@ func (s *Scanner) makeUploadProgressCallback(
 func (s *Scanner) recordBlobMetadata(
 	ctx context.Context,
 	finishedBlob *blob.FinishedBlob,
+	storedSize int64,
 	blobExists bool,
 	startTime time.Time,
 ) error {
@@ -1731,7 +1736,8 @@ 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/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/snapshot_list_test.go

@@ -483,14 +483,13 @@ 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"`
+	NewChunkSize   int64  `json:"new_chunk_size"`
+	LocallyTracked bool   `json:"locally_tracked"`
+	RemotePresent  *bool  `json:"remote_present"`
 }
 
 // decodeListJSON parses the command's stdout, which must contain

internal/vaultik/uncompressed_size_test.go

@@ -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(filepath.Join(tempDir, "remote"))
-	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
-}