Sync cached files and refuse ones left empty or partial (closes #252)

A crash could leave a cached source or transformed image empty or cut
short, and pixa then served it, or fetched it again forever. Source and
transformed image files, and the .meta file beside each transformed
image, are now written under a temporary name, synced, renamed into
place and their directory synced; a failed directory sync removes the
renamed file. The reconciliation pass compares each cached file's size
with the size its row records and removes a file that is empty or of
another size, with its rows and a warning. Requests compare no sizes.

Not verified by a test: the syncs, and the removal after a failed sync.

Model: opus-5-5

internal/imgcache/storage.go

@@ -80,8 +80,8 @@ func (s *ContentStorage) Store(r io.Reader) (ContentHash, int64, error) {
 // from hash, without recomputing it. Callers that already know the
 // hash before writing (e.g. because they must hold a hash-keyed lock
 // across the whole store operation) use this instead of Store. Like
-// Store, it is idempotent: content already on disk at that path is
-// left untouched.
+// Store, it is idempotent: a file of the content's size already at that
+// path is left untouched, and a file of another size is replaced.
 func (s *ContentStorage) StoreHashed(
 	hash ContentHash, data []byte,
 ) (int64, error) {
@@ -152,28 +152,35 @@ func (s *ContentStorage) Exists(hash ContentHash) bool {
 	return err == nil
 }
 
-// writeIfAbsent writes data to the path derived from hash, unless
-// content already exists there, via a temp-file-plus-rename so
-// concurrent readers never observe a partial file.
+// writeIfAbsent writes data with writeFileSynced to the path derived
+// from hash, unless a file of the data's size is already there.
 func (s *ContentStorage) writeIfAbsent(hash ContentHash, data []byte) error {
 	// Build path: <basedir>/<ab>/<cd>/<hash>
 	path := s.hashToPath(hash)
 
-	// Check if already exists
-	_, statErr := os.Stat(path)
-	if statErr == nil {
+	// A file of another size there is damaged, and is replaced
+	info, statErr := os.Stat(path)
+	if statErr == nil && info.Size() == int64(len(data)) {
 		return nil
 	}
 
-	// Create directory structure
-	dir := filepath.Dir(path)
-
-	err := os.MkdirAll(dir, StorageDirPerm)
+	err := os.MkdirAll(filepath.Dir(path), StorageDirPerm)
 	if err != nil {
 		return fmt.Errorf("failed to create directory: %w", err)
 	}
 
-	// Write to temp file first, then rename for atomicity
+	return writeFileSynced(path, data)
+}
+
+// writeFileSynced writes data to path through a temp file in the same
+// directory: the temp file is synced to disk, renamed to path, and the
+// directory synced after, so that neither a concurrent reader nor a
+// crash finds a partial file under path. When the directory sync fails,
+// the file is removed from path, so that a failed write leaves no file
+// there.
+func writeFileSynced(path string, data []byte) error {
+	dir := filepath.Dir(path)
+
 	tmpFile, err := os.CreateTemp(dir, ".tmp-*")
 	if err != nil {
 		return fmt.Errorf("failed to create temp file: %w", err)
@@ -181,18 +188,20 @@ func (s *ContentStorage) writeIfAbsent(hash ContentHash, data []byte) error {
 
 	tmpPath := tmpFile.Name()
 
-	// Each failure path below unlinks the temp file explicitly. This
-	// replaces a deferred cleanup that read a named result, which the
-	// canonical config does not permit; the set of paths that remove
-	// tmpPath, and the order relative to Close, is unchanged. This
-	// mirrors how MetadataStorage.Store and VariantStorage.Store below
-	// already express the same cleanup.
 	_, err = tmpFile.Write(data)
 	if err != nil {
 		_ = tmpFile.Close()
 		_ = os.Remove(tmpPath)
 
-		return fmt.Errorf("failed to write content: %w", err)
+		return fmt.Errorf("failed to write temp file: %w", err)
+	}
+
+	err = tmpFile.Sync()
+	if err != nil {
+		_ = tmpFile.Close()
+		_ = os.Remove(tmpPath)
+
+		return fmt.Errorf("failed to sync temp file: %w", err)
 	}
 
 	err = tmpFile.Close()
@@ -202,7 +211,6 @@ func (s *ContentStorage) writeIfAbsent(hash ContentHash, data []byte) error {
 		return fmt.Errorf("failed to close temp file: %w", err)
 	}
 
-	// Atomic rename
 	err = os.Rename(filepath.Clean(tmpPath), filepath.Clean(path))
 	if err != nil {
 		_ = os.Remove(tmpPath)
@@ -210,6 +218,31 @@ func (s *ContentStorage) writeIfAbsent(hash ContentHash, data []byte) error {
 		return fmt.Errorf("failed to rename temp file: %w", err)
 	}
 
+	err = syncDirectory(dir)
+	if err != nil {
+		_ = os.Remove(path)
+
+		return err
+	}
+
+	return nil
+}
+
+// syncDirectory syncs the directory dir to disk, so that a file just
+// renamed into it is still there after a crash.
+func syncDirectory(dir string) error {
+	d, err := os.Open(filepath.Clean(dir))
+	if err != nil {
+		return fmt.Errorf("failed to open directory: %w", err)
+	}
+
+	err = d.Sync()
+	_ = d.Close()
+
+	if err != nil {
+		return fmt.Errorf("failed to sync directory: %w", err)
+	}
+
 	return nil
 }
 
@@ -427,7 +460,9 @@ func NewVariantStorage(baseDir string, log *slog.Logger) (*VariantStorage, error
 	return &VariantStorage{baseDir: baseDir, log: log}, nil
 }
 
-// Store writes content and metadata to storage at the given key.
+// Store writes content and metadata to storage at the given key, each
+// with writeFileSynced. The .meta file is written first, so that a crash
+// cannot leave the content in place without it.
 func (s *VariantStorage) Store(
 	key VariantKey, r io.Reader, contentType string,
 ) (int64, error) {
@@ -440,46 +475,11 @@ func (s *VariantStorage) Store(
 	path := s.keyToPath(key)
 	metaPath := path + ".meta"
 
-	// Create directory structure
-	dir := filepath.Dir(path)
-
-	err = os.MkdirAll(dir, StorageDirPerm)
+	err = os.MkdirAll(filepath.Dir(path), StorageDirPerm)
 	if err != nil {
 		return 0, fmt.Errorf("failed to create directory: %w", err)
 	}
 
-	// Write content to temp file first, then rename for atomicity
-	tmpFile, err := os.CreateTemp(dir, ".tmp-*")
-	if err != nil {
-		return 0, fmt.Errorf("failed to create temp file: %w", err)
-	}
-
-	tmpPath := tmpFile.Name()
-
-	_, err = tmpFile.Write(data)
-	if err != nil {
-		_ = tmpFile.Close()
-		_ = os.Remove(tmpPath)
-
-		return 0, fmt.Errorf("failed to write content: %w", err)
-	}
-
-	err = tmpFile.Close()
-	if err != nil {
-		_ = os.Remove(tmpPath)
-
-		return 0, fmt.Errorf("failed to close temp file: %w", err)
-	}
-
-	// Atomic rename content
-	err = os.Rename(filepath.Clean(tmpPath), filepath.Clean(path))
-	if err != nil {
-		_ = os.Remove(tmpPath)
-
-		return 0, fmt.Errorf("failed to rename temp file: %w", err)
-	}
-
-	// Write metadata
 	meta := VariantMeta{
 		ContentType: contentType,
 		Size:        size,
@@ -491,13 +491,19 @@ func (s *VariantStorage) Store(
 		return 0, fmt.Errorf("failed to marshal metadata: %w", err)
 	}
 
-	// Metadata write failure is non-fatal; content is already stored.
-	err = os.WriteFile(metaPath, metaData, StorageFilePerm)
+	// Metadata write failure is non-fatal: the content is then served as
+	// application/octet-stream.
+	err = writeFileSynced(metaPath, metaData)
 	if err != nil {
 		s.log.Warn("failed to write variant metadata sidecar",
 			"path", metaPath, "error", err)
 	}
 
+	err = writeFileSynced(path, data)
+	if err != nil {
+		return 0, err
+	}
+
 	return size, nil
 }