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/vaultik/snapshot_prune_test.go

@@ -4,12 +4,15 @@ import (
 	"context"
 	"os"
 	"path/filepath"
+	"syscall"
 	"testing"
 
+	"github.com/spf13/afero"
 	"github.com/stretchr/testify/assert"
 	"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 +262,152 @@ func TestBackupWithNoEmptySourcePathPrunes(t *testing.T) {
 		})
 	}
 }
+
+// automountFs is the real filesystem with a volume at volumeDir that is
+// mounted on first access, as by an autofs map that shows its mount
+// points before mounting them: listing volumeDir mounts the volume or,
+// while cannotMount, fails with "no such file or directory".
+type automountFs struct {
+	afero.OsFs
+
+	volumeDir   string
+	cannotMount bool
+	mounted     bool
+}
+
+//nolint:ireturn // afero.Fs.Open is defined to return the interface.
+func (f *automountFs) Open(name string) (afero.File, error) {
+	if name == f.volumeDir && f.cannotMount {
+		return nil, &os.PathError{Op: "open", Path: name, Err: syscall.ENOENT}
+	}
+
+	if name == f.volumeDir {
+		f.mounted = true
+	}
+
+	return f.OsFs.Open(name)
+}
+
+// A backup under --prune in which a volume that an earlier snapshot found
+// mounted below the configured path is missing 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 back, the prune runs.
+// The volume is mounted on first access and every backup starts with it
+// not mounted, so its directory is on its parent's device until the walk
+// lists it. While the volume is missing, its directory is left empty, or
+// listing it fails with "no such file or directory", as when an autofs
+// volume cannot be mounted, which the walk counts as a directory removed
+// during the backup. See https://git.eeqj.de/sneak/vaultik/issues/395.
+func TestBackupWithVolumeNotMountedDoesNotPrune(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	tests := []struct {
+		name         string
+		listingFails bool
+	}{
+		{name: "directory left empty", listingFails: false},
+		{name: "listing fails", listingFails: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			backUpWithVolumeNotMounted(t, tt.listingFails)
+		})
+	}
+}
+
+// backUpWithVolumeNotMounted runs the backups of
+// TestBackupWithVolumeNotMountedDoesNotPrune. While the volume is
+// missing, listing its directory fails if listingFails; otherwise the
+// directory is empty.
+func backUpWithVolumeNotMounted(t *testing.T, listingFails bool) {
+	t.Helper()
+
+	// 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.setSnapshot(snapshotName, "")
+	prune := &vaultik.SnapshotCreateOptions{
+		Prune: true, Snapshots: []string{snapshotName},
+	}
+
+	// The volume's directory is on the volume's device, 2, while the
+	// volume is mounted. Everything else is on device 1.
+	volumeDir := filepath.Join(env.src, volume)
+	fs := &automountFs{volumeDir: volumeDir}
+	newScanner := env.v.ScannerFactory
+	env.v.ScannerFactory = func(params snapshot.ScannerParams) *snapshot.Scanner {
+		fs.mounted = false
+		params.Fs = fs
+		params.DeviceNumber = func(info os.FileInfo) (uint64, bool) {
+			if info.Name() == volume && fs.mounted {
+				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)
+
+	// The volume goes missing.
+	fs.cannotMount = listingFails
+
+	if !listingFails {
+		require.NoError(t, os.RemoveAll(volumeDir))
+		require.NoError(t, os.Mkdir(volumeDir, 0o750))
+	}
+
+	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 back.
+	fs.cannotMount = false
+
+	require.NoError(t, os.WriteFile(
+		filepath.Join(volumeDir, "a.txt"), []byte("file a"), 0o600))
+	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")
+}