Do not prune when a backup misses an earlier mount point (closes #395)

snapshot create --prune purged the older snapshots holding a volume's
files when the volume, mounted below a configured path, was not
mounted: its empty mount point read as deleted files.

The scan now records in the local index each directory at or below a
configured path that the walk found an entry in and that, once listed,
is on a different device from its parent; listing mounts an
automounted volume. Under --prune, when an earlier snapshot of that
name recorded such a directory and this run does not, the run skips
the prune, keeps every older snapshot and exits non-zero, naming the
directory. For a volume retired on purpose, snapshot purge removes the
older snapshots.

Model: opus-5-5

internal/snapshot/scanner.go

@@ -73,6 +73,9 @@ type Scanner struct {
 	skipErrors bool
 	// ui is the user-facing output; never nil (defaults to a discarding writer).
 	ui *ui.Writer
+	// deviceNumber returns the number of the device that holds a file;
+	// never nil (defaults to deviceNumberFromStat).
+	deviceNumber func(info os.FileInfo) (uint64, bool)
 
 	// In-memory cache of known chunk hashes for fast existence checks
 	knownChunks   map[string]struct{}
@@ -136,6 +139,10 @@ type ScannerConfig struct {
 	// PreviousSnapshotID is the most recent completed snapshot of the
 	// same name, "" for none.
 	PreviousSnapshotID string
+	// DeviceNumber returns the number of the device that holds a file,
+	// and false when there is none to read. nil reads it from the file's
+	// stat; tests replace it, since the in-memory test filesystem has none.
+	DeviceNumber func(info os.FileInfo) (uint64, bool)
 }
 
 // ScanResult contains the results of a scan operation. Files and bytes
@@ -214,6 +221,11 @@ func NewScanner(cfg ScannerConfig) *Scanner {
 		uiw = ui.NewWithColor(io.Discard, false)
 	}
 
+	deviceNumber := cfg.DeviceNumber
+	if deviceNumber == nil {
+		deviceNumber = deviceNumberFromStat
+	}
+
 	return &Scanner{
 		fs:                 cfg.FS,
 		chunker:            chunker.NewChunker(cfg.ChunkSize),
@@ -229,6 +241,7 @@ func NewScanner(cfg ScannerConfig) *Scanner {
 		skipErrors:         cfg.SkipErrors,
 		previousSnapshotID: cfg.PreviousSnapshotID,
 		ui:                 uiw,
+		deviceNumber:       deviceNumber,
 		pendingChunkHashes: make(map[string]struct{}),
 	}
 }
@@ -297,7 +310,7 @@ func (s *Scanner) Scan(
 		}
 	}
 
-	err = s.recordDirectories(ctx, scanResult.Directories)
+	err = s.recordDirectories(ctx, scanResult)
 	if err != nil {
 		return nil, err
 	}
@@ -875,6 +888,11 @@ type ScanPhaseResult struct {
 	FilesToProcess   []*FileToProcess
 	UnchangedFileIDs []types.FileID   // IDs of unchanged files to associate with snapshot
 	Directories      []*FileToProcess // Every directory found, to record
+	// MountPoints are the directories, the scanned path included, that
+	// the walk found an entry in and, once it had listed them, on a
+	// different device from their parent directory (see
+	// recordIfMountPoint).
+	MountPoints []string
 }
 
 // scanPhase performs the initial directory scan to identify files to process
@@ -894,7 +912,7 @@ func (s *Scanner) scanPhase(
 	// estimate leaves them out.
 	estimatedTotal := countNonDirectories(knownFiles)
 
-	collector := &scanCollector{}
+	collector := &scanCollector{dirsWithEntries: make(map[string]struct{})}
 
 	// Set up periodic status output
 	startTime := time.Now()
@@ -939,6 +957,8 @@ func (s *Scanner) scanPhase(
 			result.EntriesFound++
 		}
 
+		s.recordIfMountPoint(filePath, path, collector)
+
 		// Handle symlinks and directories
 		handled, err := s.recordSpecialEntry(
 			filePath, info, existingFiles, knownFiles, collector, result)
@@ -973,6 +993,7 @@ func (s *Scanner) scanPhase(
 		FilesToProcess:   collector.filesToProcess,
 		UnchangedFileIDs: collector.unchangedFileIDs,
 		Directories:      collector.directories,
+		MountPoints:      collector.mountPoints,
 	}, nil
 }
 
@@ -1099,6 +1120,29 @@ type scanCollector struct {
 	unchangedFileIDs []types.FileID // Just IDs - no new records needed
 	directories      []*FileToProcess
 	filesScanned     int64
+	// dirsWithEntries holds each directory the walk has found an entry in.
+	dirsWithEntries map[string]struct{}
+	mountPoints     []string
+}
+
+// firstEntryIn notes that the walk found an entry in directory dir and
+// reports whether it is the first one.
+func (c *scanCollector) firstEntryIn(dir string) bool {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	_, seen := c.dirsWithEntries[dir]
+	c.dirsWithEntries[dir] = struct{}{}
+
+	return !seen
+}
+
+// addMountPoint sets a mount point aside to be recorded.
+func (c *scanCollector) addMountPoint(dir string) {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
+	c.mountPoints = append(c.mountPoints, dir)
 }
 
 // addDirectory sets a directory aside to be recorded. It is not counted
@@ -1290,20 +1334,100 @@ func (s *Scanner) buildDirectoryEntry(path string, info os.FileInfo) *database.F
 	}
 }
 
-// recordDirectories records every directory the walk found. A directory
-// has no data to back up, so it is not among the files counted and
-// backed up.
+// recordDirectories records every directory the walk found, and its
+// mount points (see recordMountPoints). A directory has no data to back
+// up, so it is not among the files counted and backed up.
 func (s *Scanner) recordDirectories(
-	ctx context.Context, directories []*FileToProcess,
+	ctx context.Context, scanned *ScanPhaseResult,
 ) error {
-	for _, dir := range directories {
+	for _, dir := range scanned.Directories {
 		err := s.recordNonRegularFile(ctx, dir)
 		if err != nil {
 			return fmt.Errorf("recording directory %s: %w", dir.Path, err)
 		}
 	}
 
-	return nil
+	return s.recordMountPoints(ctx, scanned.MountPoints)
+}
+
+// recordMountPoints records with the snapshot the mount points the walk
+// found (see ScanPhaseResult.MountPoints).
+func (s *Scanner) recordMountPoints(
+	ctx context.Context, mountPoints []string,
+) error {
+	return s.repos.WithTx(ctx, func(txCtx context.Context, tx *sql.Tx) error {
+		for _, dir := range mountPoints {
+			log.Info("Found a mount point", "path", dir)
+
+			err := s.repos.Snapshots.AddMountPoint(txCtx, tx, s.snapshotID, dir)
+			if err != nil {
+				return fmt.Errorf("recording mount point %s: %w", dir, err)
+			}
+		}
+
+		return nil
+	})
+}
+
+// recordIfMountPoint sets the directory that holds entry, a path the
+// walk found, aside to be recorded as a mount point if it is on a
+// different device from its parent directory. The walk calls it for each
+// entry it finds, and it decides on the first entry in a directory, so a
+// directory the walk found no entry in is never recorded. By then the
+// walk has listed the directory, which mounts a volume mounted there on
+// first access, so the directory and its parent are looked up again:
+// before the listing, the directory can be on the automounter's own
+// device (a systemd automount) or on its parent's (an autofs map that
+// shows its mount points before mounting them). The scanned path is in
+// no listing the walk made, so it is skipped as an entry. A directory
+// that cannot be looked up then, or whose parent cannot, is not
+// recorded, so this snapshot does not stop the prune of a later backup
+// that misses its volume.
+func (s *Scanner) recordIfMountPoint(
+	entry, scannedPath string, collector *scanCollector,
+) {
+	dir := filepath.Dir(entry)
+
+	if entry == scannedPath || !collector.firstEntryIn(dir) {
+		return
+	}
+
+	dirDevice, ok := s.deviceNumberAt(dir)
+	if !ok {
+		return
+	}
+
+	parentDevice, ok := s.deviceNumberAt(filepath.Dir(dir))
+	if ok && dirDevice != parentDevice {
+		collector.addMountPoint(dir)
+	}
+}
+
+// deviceNumberAt looks path up now and returns the number of the device
+// that holds it, and false when the lookup fails (logged) or gives no
+// device number.
+func (s *Scanner) deviceNumberAt(path string) (uint64, bool) {
+	info, err := s.fs.Stat(path)
+	if err != nil {
+		log.Warn("Could not look up a directory to check for a mount point",
+			"path", path, "error", err)
+
+		return 0, false
+	}
+
+	return s.deviceNumber(info)
+}
+
+// deviceNumberFromStat returns the number of the device that holds the
+// file info describes, and false when info carries no stat, as from the
+// in-memory test filesystem.
+func deviceNumberFromStat(info os.FileInfo) (uint64, bool) {
+	stat, ok := info.Sys().(*syscall.Stat_t)
+	if !ok {
+		return 0, false
+	}
+
+	return uint64(stat.Dev), true //nolint:unconvert // Dev is an int32 on darwin
 }
 
 // recordNonRegularFile writes a symlink or directory entry to the database