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 is on a different device from its parent
directory. Under --prune, when an earlier snapshot of that name
recorded such a directory and this run does not find it on a different
device, the run skips the prune, keeps every older snapshot, names the
directory and exits non-zero, as for an empty configured path. For a
volume retired, or a directory no longer backed up, on purpose, the
older snapshots are removed with snapshot purge.

Model: opus-5-5

internal/cli/entry_snapshot_create_prune_test.go

@@ -1,6 +1,7 @@
 package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
 
 import (
+	"context"
 	"os"
 	"path/filepath"
 	"strings"
@@ -8,6 +9,7 @@ import (
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/vaultik/internal/database"
 )
 
 // Flags of `snapshot create` used to build argument vectors below.
@@ -117,6 +119,51 @@ func TestEntrySnapshotCreatePruneExitsNonZeroWhenSourceIsEmpty(t *testing.T) {
 	assert.Len(t, snapshots, 2, "the older snapshot is kept")
 }
 
+// TestEntrySnapshotCreatePruneExitsNonZeroWhenMountPointIsMissing backs
+// up, records in the local index that this backup found the source
+// directory as a mount point, and runs `snapshot create --prune`, which
+// does not find it as one. The command exits non-zero, reports the
+// backup as completed, not as a failed snapshot creation, and keeps the
+// older snapshot. See https://git.eeqj.de/sneak/vaultik/issues/395.
+//
+//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
+func TestEntrySnapshotCreatePruneExitsNonZeroWhenMountPointIsMissing(
+	t *testing.T,
+) {
+	configPath, storeDir := writeBackupConfig(t)
+
+	code, _, _ := runEntry(t, flagConfig, configPath, cmdSnapshot, cmdCreate)
+	require.Equal(t, 0, code)
+
+	// writeBackupConfig puts the source directory and the local index
+	// beside the config file.
+	dir := filepath.Dir(configPath)
+	ctx := context.Background()
+
+	db, err := database.New(ctx, filepath.Join(dir, "index.sqlite"))
+	require.NoError(t, err)
+
+	repos := database.NewRepositories(db)
+
+	backedUp, err := repos.Snapshots.GetOnlySnapshot(ctx)
+	require.NoError(t, err)
+	require.NoError(t, repos.Snapshots.AddMountPoint(ctx, nil,
+		backedUp.ID.String(), filepath.Join(dir, "source")))
+	require.NoError(t, db.Close())
+
+	code, _, stderr := runEntry(t,
+		flagConfig, configPath, cmdSnapshot, cmdCreate, flagPrune)
+
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "Backup completed, but 1 mount point(s) "+
+		"an earlier snapshot recorded were not found")
+	assert.NotContains(t, stderr, "Snapshot creation failed")
+
+	snapshots, err := os.ReadDir(filepath.Join(storeDir, "metadata"))
+	require.NoError(t, err)
+	assert.Len(t, snapshots, 2, "the older snapshot is kept")
+}
+
 // writeBackupConfig builds a hermetic config with one small file in its
 // source directory and an empty destination store directory. Returns the
 // config path and the store directory.

internal/cli/snapshot.go

@@ -116,7 +116,8 @@ on Linux), then /etc/vaultik/config.yml.`,
 				}
 
 				if errors.Is(err, vaultik.ErrFilesUnreadable) ||
-					errors.Is(err, vaultik.ErrSourcePathEmpty) {
+					errors.Is(err, vaultik.ErrSourcePathEmpty) ||
+					errors.Is(err, vaultik.ErrVolumeNotMounted) {
 					log.Error("Backup completed with an error", "error", err)
 					ReportErrorf("Backup completed, but %v", err)
 
@@ -137,7 +138,8 @@ on Linux), then /etc/vaultik/config.yml.`,
 			"directory under metadata/ with no manifest once all its "+
 			"objects are older than prune_grace_period and its snapshot is "+
 			"not in the local index (not after a backup that skipped "+
-			"unreadable files or found a configured path empty)")
+			"unreadable files, found a configured path empty, or did not "+
+			"find a mount point an earlier snapshot found)")
 	cmd.Flags().StringVar(&opts.KeepNewerThan, "keep-newer-than", "",
 		"With --prune: keep snapshots newer than this duration "+
 			"(e.g. 30d, 4w, 6mo, 1y; m is minutes, mo is months) "+

internal/database/schema/001.sql

@@ -123,6 +123,16 @@ CREATE TABLE IF NOT EXISTS snapshot_blobs (
 -- Index for efficient blob lookups (used in orphan detection)
 CREATE INDEX IF NOT EXISTS idx_snapshot_blobs_blob_id ON snapshot_blobs(blob_id);
 
+-- Snapshot mount points table: the directories at or below a configured
+-- path that the snapshot's backup found on a different filesystem from
+-- their parent directory, as a mount point is
+CREATE TABLE IF NOT EXISTS snapshot_mount_points (
+    snapshot_id TEXT NOT NULL,
+    path TEXT NOT NULL,
+    PRIMARY KEY (snapshot_id, path),
+    FOREIGN KEY (snapshot_id) REFERENCES snapshots(id) ON DELETE CASCADE
+);
+
 -- Uploads table: tracks blob upload metrics
 CREATE TABLE IF NOT EXISTS uploads (
     blob_hash TEXT PRIMARY KEY,

internal/database/snapshots.go

@@ -24,7 +24,8 @@ var (
 )
 
 // SnapshotRepository provides access to the snapshots table and its
-// snapshot_files / snapshot_blobs association tables.
+// snapshot_files / snapshot_blobs association tables, and to the mount
+// points each snapshot's backup found (snapshot_mount_points).
 type SnapshotRepository struct {
 	db *DB
 }
@@ -494,33 +495,63 @@ func (r *SnapshotRepository) GetBlobHashes(
 	ctx context.Context, snapshotID string,
 ) ([]string, error) {
 	query := `
-		SELECT sb.blob_hash 
+		SELECT sb.blob_hash
 		FROM snapshot_blobs sb
 		WHERE sb.snapshot_id = ?
 		ORDER BY sb.blob_hash
 	`
 
-	rows, err := r.db.conn.QueryContext(ctx, query, snapshotID)
+	blobs, err := r.queryStrings(ctx, query, snapshotID)
 	if err != nil {
 		return nil, fmt.Errorf("querying blob hashes: %w", err)
 	}
 
-	defer func() { _ = rows.Close() }()
+	return blobs, nil
+}
 
-	var blobs []string
+// AddMountPoint records dir as a directory that the backup of a snapshot
+// found on a different filesystem from its parent directory, as a mount
+// point is, using tx when non-nil.
+func (r *SnapshotRepository) AddMountPoint(
+	ctx context.Context, tx *sql.Tx, snapshotID string, dir string,
+) error {
+	query := `
+		INSERT OR IGNORE INTO snapshot_mount_points (snapshot_id, path)
+		VALUES (?, ?)
+	`
 
-	for rows.Next() {
-		var blobHash string
-
-		err := rows.Scan(&blobHash)
-		if err != nil {
-			return nil, fmt.Errorf("scanning blob hash: %w", err)
-		}
-
-		blobs = append(blobs, blobHash)
+	var err error
+	if tx != nil {
+		_, err = tx.ExecContext(ctx, query, snapshotID, dir)
+	} else {
+		_, err = r.db.ExecWithLog(ctx, query, snapshotID, dir)
 	}
 
-	return blobs, rows.Err()
+	if err != nil {
+		return fmt.Errorf("adding mount point to snapshot: %w", err)
+	}
+
+	return nil
+}
+
+// GetMountPoints returns the directories AddMountPoint recorded for a
+// snapshot, sorted.
+func (r *SnapshotRepository) GetMountPoints(
+	ctx context.Context, snapshotID string,
+) ([]string, error) {
+	query := `
+		SELECT path
+		FROM snapshot_mount_points
+		WHERE snapshot_id = ?
+		ORDER BY path
+	`
+
+	dirs, err := r.queryStrings(ctx, query, snapshotID)
+	if err != nil {
+		return nil, fmt.Errorf("querying mount points: %w", err)
+	}
+
+	return dirs, nil
 }
 
 // GetSnapshotTotalCompressedSize returns the total compressed size of all
@@ -709,6 +740,34 @@ func (r *SnapshotRepository) DeleteSnapshotUploads(
 	return nil
 }
 
+// queryStrings runs query, which selects one text column, and returns
+// its values in the order of the rows.
+func (r *SnapshotRepository) queryStrings(
+	ctx context.Context, query string, args ...any,
+) ([]string, error) {
+	rows, err := r.db.conn.QueryContext(ctx, query, args...)
+	if err != nil {
+		return nil, err
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	var values []string
+
+	for rows.Next() {
+		var value string
+
+		err := rows.Scan(&value)
+		if err != nil {
+			return nil, err
+		}
+
+		values = append(values, value)
+	}
+
+	return values, rows.Err()
+}
+
 // extendedCompressionRatio computes the compression ratio for a snapshot
 // from its stored blob_size and the given uncompressed size. Returns 1.0
 // when the uncompressed size is zero.

internal/database/snapshots_test.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"fmt"
 	"math"
+	"slices"
 	"testing"
 	"time"
 
@@ -422,3 +423,52 @@ func TestSnapshotRepositoryDuplicate(t *testing.T) {
 		t.Error("expected error for duplicate snapshot")
 	}
 }
+
+// Deleting a snapshot from the local index deletes the mount points its
+// backup recorded, and no other snapshot's. See
+// https://git.eeqj.de/sneak/vaultik/issues/395.
+func TestSnapshotRepositoryDeleteRemovesMountPoints(t *testing.T) {
+	t.Parallel()
+
+	db, cleanup := setupTestDB(t)
+	defer cleanup()
+
+	ctx := context.Background()
+	repo := database.NewSnapshotRepository(db)
+
+	for _, id := range []types.SnapshotID{"kept", "deleted"} {
+		err := repo.Create(ctx, nil, &database.Snapshot{
+			ID:             id,
+			Hostname:       testHostname,
+			VaultikVersion: testVersion,
+			StartedAt:      time.Now().Truncate(time.Second),
+		})
+		if err != nil {
+			t.Fatalf("failed to create snapshot: %v", err)
+		}
+
+		err = repo.AddMountPoint(ctx, nil, id.String(), "/data/nas")
+		if err != nil {
+			t.Fatalf("failed to add mount point: %v", err)
+		}
+	}
+
+	err := repo.Delete(ctx, "deleted")
+	if err != nil {
+		t.Fatalf("failed to delete snapshot: %v", err)
+	}
+
+	for id, want := range map[string][]string{
+		"kept":    {"/data/nas"},
+		"deleted": nil,
+	} {
+		got, err := repo.GetMountPoints(ctx, id)
+		if err != nil {
+			t.Fatalf("failed to read mount points: %v", err)
+		}
+
+		if !slices.Equal(got, want) {
+			t.Errorf("mount points of %s: got %v, want %v", id, got, want)
+		}
+	}
+}

internal/snapshot/device_number_test.go

@@ -0,0 +1,40 @@
+//nolint:testpackage // exercises the unexported deviceNumberFromStat
+package snapshot
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// The device number a real backup reads is the same for two entries of
+// one directory and differs between two filesystems. Without it no
+// mount point is ever found. See
+// https://git.eeqj.de/sneak/vaultik/issues/395.
+func TestDeviceNumberFromStat(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	file := filepath.Join(dir, "file.txt")
+	require.NoError(t, os.WriteFile(file, nil, 0o600))
+
+	deviceOf := func(path string) uint64 {
+		t.Helper()
+
+		info, err := os.Stat(path)
+		require.NoError(t, err)
+
+		device, ok := deviceNumberFromStat(info)
+		require.True(t, ok, "no device number read for %s", path)
+
+		return device
+	}
+
+	assert.Equal(t, deviceOf(dir), deviceOf(file))
+
+	// /dev is a different filesystem from the temp dir on Linux, macOS and in Docker.
+	assert.NotEqual(t, deviceOf(dir), deviceOf("/dev"))
+}

internal/snapshot/module.go

@@ -1,6 +1,8 @@
 package snapshot
 
 import (
+	"os"
+
 	"github.com/spf13/afero"
 	"go.uber.org/fx"
 	"sneak.berlin/go/vaultik/internal/config"
@@ -19,6 +21,9 @@ type ScannerParams struct {
 	// PreviousSnapshotID is the most recent completed snapshot of the
 	// same name, "" for none.
 	PreviousSnapshotID string
+	// DeviceNumber is ScannerConfig.DeviceNumber; nil reads it from the
+	// file's stat.
+	DeviceNumber func(info os.FileInfo) (uint64, bool)
 }
 
 // Module exports backup functionality as an fx module.
@@ -59,6 +64,7 @@ func provideScannerFactory(
 			Exclude:            excludes,
 			SkipErrors:         params.SkipErrors,
 			PreviousSnapshotID: params.PreviousSnapshotID,
+			DeviceNumber:       params.DeviceNumber,
 		})
 	}
 }

internal/snapshot/mount_point_test.go

@@ -0,0 +1,97 @@
+package snapshot_test
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"slices"
+	"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/snapshot"
+)
+
+// A scan records with the snapshot each directory on a different device
+// from its parent directory, as a mount point is, the scanned path
+// included. A filesystem that gives no device numbers, as the in-memory
+// one, records none. See https://git.eeqj.de/sneak/vaultik/issues/395.
+func TestScanRecordsMountPoints(t *testing.T) {
+	t.Parallel()
+
+	const (
+		scannedPath = "/data/source"
+		snapshotID  = "mount-points"
+	)
+
+	tests := []struct {
+		name string
+		// onVolume names the directories on the volume's device; every
+		// other directory is on another one. nil leaves the device
+		// numbers to the in-memory filesystem, which has none.
+		onVolume []string
+		want     []string
+	}{
+		{
+			name:     "volume below the scanned path",
+			onVolume: []string{"nas"},
+			want:     []string{scannedPath + "/nas"},
+		},
+		{
+			name:     "volume at the scanned path",
+			onVolume: []string{"source", "nas"},
+			want:     []string{scannedPath},
+		},
+		{name: "no device numbers", want: nil},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			ctx := context.Background()
+			fs := afero.NewMemMapFs()
+
+			for _, path := range []string{
+				scannedPath + "/notes.txt", scannedPath + "/nas/a.txt",
+			} {
+				require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0o755))
+				require.NoError(t, afero.WriteFile(fs, path, []byte(path), 0o644))
+			}
+
+			db, err := database.NewTestDB()
+			require.NoError(t, err)
+			t.Cleanup(func() { _ = db.Close() })
+
+			repos := database.NewRepositories(db)
+			createTestSnapshotRecord(ctx, t, repos, snapshotID)
+
+			cfg := snapshot.ScannerConfig{
+				FS:               fs,
+				ChunkSize:        int64(1024 * 16),
+				Repositories:     repos,
+				MaxBlobSize:      int64(1024 * 1024),
+				CompressionLevel: 3,
+				AgeRecipients:    []string{testAgePublicKey},
+			}
+			if tt.onVolume != nil {
+				cfg.DeviceNumber = func(info os.FileInfo) (uint64, bool) {
+					if slices.Contains(tt.onVolume, info.Name()) {
+						return 2, true
+					}
+
+					return 1, true
+				}
+			}
+
+			_, err = snapshot.NewScanner(cfg).Scan(ctx, scannedPath, snapshotID)
+			require.NoError(t, err)
+
+			got, err := repos.Snapshots.GetMountPoints(ctx, snapshotID)
+			require.NoError(t, err)
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}

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{}),
 	}
 }
@@ -1290,9 +1303,9 @@ 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,
 ) error {
@@ -1303,7 +1316,97 @@ func (s *Scanner) recordDirectories(
 		}
 	}
 
-	return nil
+	return s.recordMountPoints(ctx, directories)
+}
+
+// recordMountPoints records with the snapshot each directory the walk
+// found on a different device from its parent directory, as a mount
+// point is, the scanned path included.
+func (s *Scanner) recordMountPoints(
+	ctx context.Context, directories []*FileToProcess,
+) error {
+	mountPoints, err := s.findMountPoints(directories)
+	if err != nil {
+		return err
+	}
+
+	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
+	})
+}
+
+// findMountPoints returns the directories, among those the walk found,
+// that are on a different device from their parent directory. The
+// scanned path is compared with the directory that holds it, which the
+// walk did not reach.
+func (s *Scanner) findMountPoints(
+	directories []*FileToProcess,
+) ([]string, error) {
+	walked := make(map[string]os.FileInfo, len(directories))
+	for _, dir := range directories {
+		walked[dir.Path] = dir.FileInfo
+	}
+
+	var mountPoints []string
+
+	for _, dir := range directories {
+		parentPath := filepath.Dir(dir.Path)
+
+		parent, ok := walked[parentPath]
+		if !ok {
+			var err error
+
+			parent, err = s.fs.Stat(parentPath)
+			if err != nil {
+				return nil, fmt.Errorf(
+					"looking up the parent of %s: %w", dir.Path, err)
+			}
+		}
+
+		if s.onOtherDevice(dir.FileInfo, parent) {
+			mountPoints = append(mountPoints, dir.Path)
+		}
+	}
+
+	return mountPoints, nil
+}
+
+// onOtherDevice reports whether dir is on a different device from
+// parent. A file whose device number cannot be read counts as on the
+// same device as its parent.
+func (s *Scanner) onOtherDevice(dir, parent os.FileInfo) bool {
+	dirDevice, ok := s.deviceNumber(dir)
+	if !ok {
+		return false
+	}
+
+	parentDevice, ok := s.deviceNumber(parent)
+	if !ok {
+		return false
+	}
+
+	return dirDevice != parentDevice
+}
+
+// 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

internal/snapshot/snapshot.go

@@ -518,8 +518,8 @@ type CleanupStats struct {
 //
 // The cleanup is performed in a specific order to maintain referential integrity:
 //  1. Delete other snapshots
-//  2. Delete orphaned snapshot associations (snapshot_files, snapshot_blobs)
-//     for deleted snapshots
+//  2. Delete orphaned snapshot associations (snapshot_files, snapshot_blobs,
+//     snapshot_mount_points) for deleted snapshots
 //  3. Delete orphaned files (not in the current snapshot)
 //  4. Delete orphaned chunk-to-file mappings (references to deleted files)
 //  5. Delete orphaned blobs (not in the current snapshot)
@@ -948,8 +948,8 @@ func (sm *SnapshotManager) deleteOtherSnapshots(
 	return nil
 }
 
-// deleteOrphanedSnapshotAssociations deletes snapshot_files and
-// snapshot_blobs for deleted snapshots
+// deleteOrphanedSnapshotAssociations deletes snapshot_files,
+// snapshot_blobs and snapshot_mount_points for deleted snapshots
 func (sm *SnapshotManager) deleteOrphanedSnapshotAssociations(
 	ctx context.Context, tx *sql.Tx, currentSnapshotID string,
 ) error {
@@ -983,6 +983,19 @@ func (sm *SnapshotManager) deleteOrphanedSnapshotAssociations(
 	log.Debug("[Temp DB Cleanup] Deleted snapshot_blobs associations",
 		"count", rowsAffected)
 
+	// Delete the mount points other snapshots recorded
+	query := "DELETE FROM snapshot_mount_points WHERE snapshot_id != ?"
+	database.LogSQL("Execute", query, currentSnapshotID)
+
+	result, err = tx.ExecContext(ctx, query, currentSnapshotID)
+	if err != nil {
+		return fmt.Errorf("deleting orphaned snapshot_mount_points: %w", err)
+	}
+
+	rowsAffected, _ = result.RowsAffected()
+	log.Debug("[Temp DB Cleanup] Deleted snapshot_mount_points rows",
+		"count", rowsAffected)
+
 	return nil
 }
 

internal/snapshot/snapshot_test.go

@@ -7,12 +7,14 @@ import (
 	"database/sql"
 	"io"
 	"path/filepath"
+	"slices"
 	"testing"
 
 	"github.com/spf13/afero"
 	"sneak.berlin/go/vaultik/internal/config"
 	"sneak.berlin/go/vaultik/internal/database"
 	"sneak.berlin/go/vaultik/internal/log"
+	"sneak.berlin/go/vaultik/internal/types"
 )
 
 const (
@@ -387,6 +389,77 @@ func TestCleanSnapshotDBNonExistentSnapshot(t *testing.T) {
 	}
 }
 
+// The exported metadata database keeps only the mount points that the
+// exported snapshot recorded. See
+// https://git.eeqj.de/sneak/vaultik/issues/395.
+func TestCleanSnapshotDBKeepsOnlyTheSnapshotsMountPoints(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	ctx := context.Background()
+	dbPath := filepath.Join(t.TempDir(), "export.db")
+
+	db, err := database.New(ctx, dbPath)
+	if err != nil {
+		t.Fatalf("failed to create database: %v", err)
+	}
+
+	repos := database.NewRepositories(db)
+
+	for _, id := range []types.SnapshotID{"exported", "other"} {
+		err = repos.Snapshots.Create(ctx, nil, &database.Snapshot{ID: id})
+		if err != nil {
+			t.Fatalf("failed to create snapshot: %v", err)
+		}
+
+		err = repos.Snapshots.AddMountPoint(ctx, nil, id.String(), "/data/"+id.String())
+		if err != nil {
+			t.Fatalf("failed to add mount point: %v", err)
+		}
+	}
+
+	err = db.Close()
+	if err != nil {
+		t.Fatalf("failed to close database: %v", err)
+	}
+
+	sm := &SnapshotManager{
+		config: &config.Config{
+			CompressionLevel: 3,
+			AgeRecipients:    []string{testAgeRecipient},
+		},
+		fs: afero.NewOsFs(),
+	}
+
+	_, err = sm.cleanSnapshotDB(ctx, dbPath, "exported")
+	if err != nil {
+		t.Fatalf("failed to clean snapshot database: %v", err)
+	}
+
+	cleaned, err := database.New(ctx, dbPath)
+	if err != nil {
+		t.Fatalf("failed to open cleaned database: %v", err)
+	}
+
+	defer func() { _ = cleaned.Close() }()
+
+	cleanedRepos := database.NewRepositories(cleaned)
+
+	for id, want := range map[string][]string{
+		"exported": {"/data/exported"},
+		"other":    nil,
+	} {
+		got, err := cleanedRepos.Snapshots.GetMountPoints(ctx, id)
+		if err != nil {
+			t.Fatalf("failed to read mount points: %v", err)
+		}
+
+		if !slices.Equal(got, want) {
+			t.Errorf("mount points of %s: got %v, want %v", id, got, want)
+		}
+	}
+}
+
 // Two creates of one snapshot name back to back start within one second,
 // the resolution of the timestamp in a snapshot ID. See
 // https://git.eeqj.de/sneak/vaultik/issues/270.

internal/vaultik/fault_injection_test.go

@@ -679,6 +679,7 @@ func faultScannerFactory(
 			Exclude:            params.Exclude,
 			SkipErrors:         params.SkipErrors,
 			PreviousSnapshotID: params.PreviousSnapshotID,
+			DeviceNumber:       params.DeviceNumber,
 		})
 	}
 }

internal/vaultik/snapshot.go

@@ -7,6 +7,7 @@ import (
 	"os"
 	"path/filepath"
 	"regexp"
+	"slices"
 	"sort"
 	"strconv"
 	"strings"
@@ -52,6 +53,17 @@ var ErrFilesUnreadable = errors.New("file(s) could not be read")
 // returns ErrFilesUnreadable instead.
 var ErrSourcePathEmpty = errors.New("source path(s) were empty")
 
+// ErrVolumeNotMounted is returned when --prune skipped the post-backup
+// prune because a directory that an earlier snapshot of the same name
+// found as a mount point was not found as one in this run: the volume
+// mounted there is not mounted, or the directory is no longer backed up.
+// The snapshots are complete and kept, so the caller can report it apart
+// from a failed backup. A run that also skipped unreadable files or
+// found a configured path empty returns ErrFilesUnreadable or
+// ErrSourcePathEmpty instead.
+var ErrVolumeNotMounted = errors.New(
+	"mount point(s) an earlier snapshot recorded were not found")
+
 // listRecentLimit caps how many snapshot rows are fetched from the
 // local index for listing and purge operations.
 const listRecentLimit = 10000
@@ -142,7 +154,7 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
 		return err
 	}
 
-	filesUnreadable, emptyPaths, err := v.createNamedSnapshots(
+	filesUnreadable, emptyPaths, unmountedPaths, err := v.createNamedSnapshots(
 		opts, hostname, snapshotNames)
 	if err != nil {
 		return err
@@ -155,8 +167,10 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
 	}
 
 	switch {
-	case opts.Prune && (filesUnreadable > 0 || len(emptyPaths) > 0):
-		return v.skipPostBackupPrune(filesUnreadable, emptyPaths)
+	case opts.Prune && (filesUnreadable > 0 || len(emptyPaths) > 0 ||
+		len(unmountedPaths) > 0):
+		return v.skipPostBackupPrune(
+			filesUnreadable, emptyPaths, unmountedPaths)
 	case opts.Prune:
 		err = v.runPostBackupPrune(snapshotNames, opts.KeepNewerThan)
 		if err != nil {
@@ -169,20 +183,22 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
 
 // createNamedSnapshots creates each named snapshot in turn. It returns
 // the number of entries --skip-errors skipped because it could not read
-// or list them, and each configured path in which the scan found
-// nothing, named with its snapshot.
+// or list them, each configured path in which the scan found nothing,
+// and, under --prune, each directory where an earlier snapshot found a
+// volume mounted and this run did not, the paths named with their
+// snapshot.
 func (v *Vaultik) createNamedSnapshots(
 	opts *SnapshotCreateOptions, hostname string, snapshotNames []string,
-) (int, []string, error) {
+) (int, []string, []string, error) {
 	filesUnreadable := 0
 
-	var emptyPaths []string
+	var emptyPaths, unmountedPaths []string
 
 	for snapIdx, snapName := range snapshotNames {
 		stats, err := v.createNamedSnapshot(
 			opts, hostname, snapName, snapIdx+1, len(snapshotNames))
 		if err != nil {
-			return 0, nil, err
+			return 0, nil, nil, err
 		}
 
 		filesUnreadable += stats.totalFilesUnreadable
@@ -190,21 +206,27 @@ func (v *Vaultik) createNamedSnapshots(
 		for _, dir := range stats.emptyPaths {
 			emptyPaths = append(emptyPaths, dir+" of snapshot "+snapName)
 		}
+
+		for _, dir := range stats.unmountedPaths {
+			unmountedPaths = append(unmountedPaths,
+				dir+" of snapshot "+snapName)
+		}
 	}
 
-	return filesUnreadable, emptyPaths, nil
+	return filesUnreadable, emptyPaths, unmountedPaths, nil
 }
 
 // skipPostBackupPrune says why the post-backup prune does not run, naming
 // every cause, and returns the error the run ends with. An older snapshot
 // may be the only one that still holds a file this run could not read,
-// or what an empty path held. The previous snapshot is no guide: after
-// one run with an empty path it is empty too.
+// or what an empty path or a volume that is not mounted held. The
+// previous snapshot is no guide: after one such run it lacks them too.
 func (v *Vaultik) skipPostBackupPrune(
-	filesUnreadable int, emptyPaths []string,
+	filesUnreadable int, emptyPaths, unmountedPaths []string,
 ) error {
 	log.Warn("Skipping post-backup prune",
-		"files_unreadable", filesUnreadable, "empty_paths", emptyPaths)
+		"files_unreadable", filesUnreadable, "empty_paths", emptyPaths,
+		"unmounted_paths", unmountedPaths)
 
 	if len(emptyPaths) > 0 {
 		v.UI.Warningf("Skipped the post-backup prune because nothing was "+
@@ -212,6 +234,17 @@ func (v *Vaultik) skipPostBackupPrune(
 			strings.Join(emptyPaths, ", "))
 	}
 
+	if len(unmountedPaths) > 0 {
+		v.UI.Warningf("Skipped the post-backup prune because this backup "+
+			"did not find a mount point at %s, where an earlier snapshot "+
+			"found one: either the volume is not mounted or the directory "+
+			"is no longer backed up. Older snapshots are kept. Mount the "+
+			"volume again, or, if the volume was retired or the directory "+
+			"is no longer backed up on purpose, remove the older snapshots "+
+			"by hand with 'vaultik snapshot purge'.",
+			strings.Join(unmountedPaths, ", "))
+	}
+
 	if filesUnreadable > 0 {
 		v.UI.Warningf("Skipped the post-backup prune because %d file(s) "+
 			"could not be read; older snapshots are kept.", filesUnreadable)
@@ -219,7 +252,11 @@ func (v *Vaultik) skipPostBackupPrune(
 		return fmt.Errorf("%d %w", filesUnreadable, ErrFilesUnreadable)
 	}
 
-	return fmt.Errorf("%d %w", len(emptyPaths), ErrSourcePathEmpty)
+	if len(emptyPaths) > 0 {
+		return fmt.Errorf("%d %w", len(emptyPaths), ErrSourcePathEmpty)
+	}
+
+	return fmt.Errorf("%d %w", len(unmountedPaths), ErrVolumeNotMounted)
 }
 
 // finishCreateSnapshot ends a run whose snapshots are all complete and
@@ -329,6 +366,10 @@ type snapshotStats struct {
 	// The configured paths in which the scan found nothing.
 	emptyPaths []string
 
+	// Under --prune, the directories where an earlier snapshot of the
+	// same name found a volume mounted and this one did not.
+	unmountedPaths []string
+
 	// The sizes of all blobs the snapshot references, set by
 	// finalizeSnapshotMetadata once snapshot_blobs is populated.
 	blobSize             int64
@@ -394,9 +435,57 @@ func (v *Vaultik) createNamedSnapshot(
 
 	v.printSnapshotSummary(snapshotID, snapshotStartTime, stats)
 
+	if opts.Prune {
+		stats.unmountedPaths, err = v.findUnmountedPaths(snapName, snapshotID)
+		if err != nil {
+			return nil, err
+		}
+	}
+
 	return stats, nil
 }
 
+// findUnmountedPaths returns each directory that an earlier snapshot
+// named snapName in the local index recorded as a mount point and
+// snapshot snapshotID did not, as when the volume mounted there is not
+// mounted.
+func (v *Vaultik) findUnmountedPaths(
+	snapName, snapshotID string,
+) ([]string, error) {
+	found, err := v.Repositories.Snapshots.GetMountPoints(v.ctx, snapshotID)
+	if err != nil {
+		return nil, err
+	}
+
+	snapshots, err := v.Repositories.Snapshots.ListRecent(v.ctx, listRecentLimit)
+	if err != nil {
+		return nil, fmt.Errorf("listing snapshots: %w", err)
+	}
+
+	var unmounted []string
+
+	for _, s := range snapshots {
+		if s.ID.String() == snapshotID ||
+			parseSnapshotName(s.ID.String(), s.Hostname.String()) != snapName {
+			continue
+		}
+
+		recorded, err := v.Repositories.Snapshots.GetMountPoints(
+			v.ctx, s.ID.String())
+		if err != nil {
+			return nil, err
+		}
+
+		for _, dir := range recorded {
+			if !slices.Contains(found, dir) && !slices.Contains(unmounted, dir) {
+				unmounted = append(unmounted, dir)
+			}
+		}
+	}
+
+	return unmounted, nil
+}
+
 // previousSnapshotID returns the ID of the most recent completed snapshot
 // named snapName in the local index, or "" when there is none.
 func (v *Vaultik) previousSnapshotID(snapName string) (string, error) {

internal/vaultik/snapshot_prune_test.go

@@ -10,6 +10,7 @@ import (
 	"github.com/stretchr/testify/require"
 	"sneak.berlin/go/vaultik/internal/config"
 	"sneak.berlin/go/vaultik/internal/log"
+	"sneak.berlin/go/vaultik/internal/snapshot"
 	"sneak.berlin/go/vaultik/internal/vaultik"
 )
 
@@ -259,3 +260,98 @@ func TestBackupWithNoEmptySourcePathPrunes(t *testing.T) {
 		})
 	}
 }
+
+// A backup under --prune in which a volume that an earlier snapshot found
+// mounted below the configured path is not mounted does not prune: run
+// after run, the snapshot that holds the volume's files is kept with
+// everything it stored, and the run fails. Once the volume is mounted
+// again, the prune runs. See https://git.eeqj.de/sneak/vaultik/issues/395.
+func TestBackupWithVolumeNotMountedDoesNotPrune(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	// volume is the directory, below the configured path, where the
+	// volume is mounted.
+	const (
+		snapshotName = "data"
+		volume       = "nas"
+	)
+
+	ctx := context.Background()
+	env := newDeletedCountEnv(t, map[string][]byte{
+		volume + "/a.txt": []byte("file a"),
+		"notes.txt":       []byte("notes"),
+	})
+	env.v.Config.Snapshots[snapshotName] = config.SnapshotConfig{
+		Paths: []string{env.src},
+	}
+	prune := &vaultik.SnapshotCreateOptions{
+		Prune: true, Snapshots: []string{snapshotName},
+	}
+
+	// While the volume is mounted, its directory is on a device of its
+	// own.
+	mounted := true
+	newScanner := env.v.ScannerFactory
+	env.v.ScannerFactory = func(params snapshot.ScannerParams) *snapshot.Scanner {
+		params.DeviceNumber = func(info os.FileInfo) (uint64, bool) {
+			if mounted && info.Name() == volume {
+				return 2, true
+			}
+
+			return 1, true
+		}
+
+		return newScanner(params)
+	}
+
+	env.backUp(t, snapshotName)
+
+	firstID := localSnapshotID(ctx, t, env.v.Repositories, snapshotName)
+	stored, err := env.v.Storage.List(ctx, "")
+	require.NoError(t, err)
+
+	// A volume that is not mounted leaves its mount point behind as an
+	// empty directory on its parent's device.
+	volumeDir := filepath.Join(env.src, volume)
+	require.NoError(t, os.RemoveAll(volumeDir))
+	require.NoError(t, os.Mkdir(volumeDir, 0o750))
+
+	mounted = false
+
+	for range 2 {
+		env.out.Reset()
+
+		err := env.v.CreateSnapshot(prune)
+		require.ErrorIs(t, err, vaultik.ErrVolumeNotMounted)
+		assert.Contains(t, env.out.String(),
+			"did not find a mount point at "+volumeDir+" of snapshot "+snapshotName)
+		assert.Contains(t, env.out.String(), "'vaultik snapshot purge'")
+		assert.NotContains(t, env.out.String(), "Running post-backup prune.")
+	}
+
+	snapshots, err := env.v.Repositories.Snapshots.ListRecent(
+		ctx, listRecentTestLimit)
+	require.NoError(t, err)
+	require.Len(t, snapshots, 3)
+	assert.Equal(t, firstID, snapshots[2].ID.String(),
+		"the snapshot that holds the volume's files is kept")
+
+	for _, key := range stored {
+		_, err := env.v.Storage.Stat(ctx, key)
+		require.NoError(t, err, "%s is kept", key)
+	}
+
+	// The volume is mounted again.
+	require.NoError(t, os.WriteFile(
+		filepath.Join(volumeDir, "a.txt"), []byte("file a"), 0o600))
+
+	mounted = true
+
+	require.NoError(t, env.v.CreateSnapshot(prune))
+
+	snapshots, err = env.v.Repositories.Snapshots.ListRecent(
+		ctx, listRecentTestLimit)
+	require.NoError(t, err)
+	require.Len(t, snapshots, 1, "the older snapshots are pruned")
+}