vaultik/internal/snapshot/mount_point_test.go

package snapshot_test

import (
	"context"
	"os"
	"path/filepath"
	"slices"
	"strings"
	"syscall"
	"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 that the walk found an entry in, 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)
		})
	}
}

// automountFs is an in-memory filesystem with a volume at mountPoint
// that is mounted on first access: opening mountPoint to list it mounts
// the volume or, if it cannot be mounted, fails with "no such file or
// directory", as with the autofs daemon. Stat records the device an
// entry is on at that moment, as a real stat does: unmountedDevice for
// mountPoint until the volume is mounted; the volume's, 2, for
// mountPoint once it is and for everything in it; 1 for everything else.
type automountFs struct {
	afero.Fs

	mountPoint      string
	unmountedDevice uint64
	canMount        bool
	mounted         bool
}

//nolint:ireturn // afero.Fs.Open is defined to return the interface.
func (fs *automountFs) Open(name string) (afero.File, error) {
	if name == fs.mountPoint && !fs.canMount {
		return nil, &os.PathError{Op: "open", Path: name, Err: syscall.ENOENT}
	}

	if name == fs.mountPoint {
		fs.mounted = true
	}

	return fs.Fs.Open(name)
}

func (fs *automountFs) Stat(name string) (os.FileInfo, error) {
	info, err := fs.Fs.Stat(name)
	if err != nil {
		return nil, err
	}

	device := uint64(1)

	switch {
	case name == fs.mountPoint && !fs.mounted:
		device = fs.unmountedDevice
	case name == fs.mountPoint || strings.HasPrefix(name, fs.mountPoint+"/"):
		device = 2
	}

	return statWithDevice{FileInfo: info, device: device}, nil
}

// statWithDevice is an entry automountFs.Stat looked up, with the device
// it was on then.
type statWithDevice struct {
	os.FileInfo

	device uint64
}

// deviceAtLookup returns the device automountFs.Stat recorded for info.
func deviceAtLookup(info os.FileInfo) (uint64, bool) {
	stat, ok := info.(statWithDevice)

	return stat.device, ok
}

// A volume mounted on first access is mounted when the walk lists its
// mount point. Until then the mount point is 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). Either way only the
// mount point is recorded, by the backup that mounts the volume and by a
// later one that finds it mounted. Listing an automount point whose
// volume cannot be mounted fails; it is not recorded, because the walk
// finds no entry in it. See https://git.eeqj.de/sneak/vaultik/issues/395.
func TestScanRecordsOnlyTheMountPointOfAnAutomountedVolume(t *testing.T) {
	t.Parallel()

	const scannedPath = "/data/source"

	mountPoint := scannedPath + "/nas"

	tests := []struct {
		name            string
		unmountedDevice uint64
		canMount        bool
		want            []string
	}{
		{
			name:            "on the automounter's device until listed",
			unmountedDevice: 3, canMount: true, want: []string{mountPoint},
		},
		{
			name:            "on its parent's device until listed",
			unmountedDevice: 1, canMount: true, want: []string{mountPoint},
		},
		{
			name:            "volume that cannot be mounted",
			unmountedDevice: 1, canMount: false, want: nil,
		},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			t.Parallel()

			ctx := context.Background()
			fs := &automountFs{
				Fs: afero.NewMemMapFs(), mountPoint: mountPoint,
				unmountedDevice: tt.unmountedDevice, canMount: tt.canMount,
			}

			require.NoError(t, fs.MkdirAll(mountPoint+"/photos", 0o755))

			for _, path := range []string{
				scannedPath + "/notes.txt", mountPoint + "/photos/a.jpg",
			} {
				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)

			for _, snapshotID := range []string{"first", "later"} {
				createTestSnapshotRecord(ctx, t, repos, snapshotID)

				scanner := snapshot.NewScanner(snapshot.ScannerConfig{
					FS:               fs,
					ChunkSize:        int64(1024 * 16),
					Repositories:     repos,
					MaxBlobSize:      int64(1024 * 1024),
					CompressionLevel: 3,
					AgeRecipients:    []string{testAgePublicKey},
					DeviceNumber:     deviceAtLookup,
				})

				_, err = scanner.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, "mount points of the %s backup", snapshotID)
			}
		})
	}
}