vaultik/internal/vaultik/changed_file_restore_test.go

package vaultik_test

import (
	"context"
	"crypto/rand"
	"path/filepath"
	"slices"
	"strings"
	"testing"

	"github.com/spf13/afero"
	"github.com/stretchr/testify/require"
	"sneak.berlin/go/vaultik/internal/chunker"
	"sneak.berlin/go/vaultik/internal/config"
	"sneak.berlin/go/vaultik/internal/database"
	"sneak.berlin/go/vaultik/internal/log"
	"sneak.berlin/go/vaultik/internal/storage"
	"sneak.berlin/go/vaultik/internal/storage/faultstore"
	"sneak.berlin/go/vaultik/internal/vaultik"
)

// These tests cover https://git.eeqj.de/sneak/vaultik/issues/214: once
// the only snapshot referencing a changed file's current blob is
// dropped, an older snapshot still keeps the file's row, and the next
// backup must re-chunk the file instead of treating it as unchanged.
//
// Each backup run uses its own snapshot name over the same source
// directory, so the snapshot IDs differ without waiting for their
// one-second timestamps to tick over. File rows are keyed by path, so
// the runs share them exactly as runs of one snapshot name would.

// changedFileConfig returns a full-backup config with the snapshot names
// "first", "second" and "third", all backing up dataDir.
func changedFileConfig(dataDir, dbPath string) *config.Config {
	source := config.SnapshotConfig{Paths: []string{dataDir}}

	cfg := faultTestConfig()
	cfg.IndexPath = dbPath
	cfg.ChunkSize = config.Size(faultChunkSize)
	cfg.Snapshots = map[string]config.SnapshotConfig{
		"first":  source,
		"second": source,
		"third":  source,
	}

	return cfg
}

// backUp runs a full backup of the named snapshot.
func backUp(v *vaultik.Vaultik, name string) error {
	return v.CreateSnapshot(&vaultik.SnapshotCreateOptions{
		Cron:      true,
		Snapshots: []string{name},
	})
}

// appendedFileSize is the size of the file before the tests append to it.
// It is twice the largest chunk the chunker cuts, so the file's first
// chunk ends before the appended bytes and stays in a blob the first
// snapshot still references, while its new chunks are only in the blob
// that gets dropped.
const appendedFileSize = 2 * chunker.ChunkSizeSpread * faultChunkSize

// appendRandomBytes appends n random bytes to the file at path, creating
// the file if it does not exist, and records the new content in files.
// Random content gives the chunker real cut points.
func appendRandomBytes(
	t *testing.T, fs afero.Fs, files map[string][]byte, path string, n int64,
) {
	t.Helper()

	added := make([]byte, n)
	_, err := rand.Read(added)
	require.NoError(t, err)

	content := slices.Concat(files[path], added)
	require.NoError(t, afero.WriteFile(fs, path, content, 0o644))

	files[path] = content
}

// localSnapshotID returns the ID of the one snapshot in the local index
// that was backed up under name.
func localSnapshotID(
	ctx context.Context, t *testing.T,
	repos *database.Repositories, name string,
) string {
	t.Helper()

	snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
	require.NoError(t, err)

	var ids []string

	for _, s := range snapshots {
		if strings.Contains(s.ID.String(), "_"+name+"_") {
			ids = append(ids, s.ID.String())
		}
	}

	require.Lenf(t, ids, 1, "expected one local snapshot named %q", name)

	return ids[0]
}

// assertThirdSnapshotRestores closes the local index, then restores the
// snapshot named "third" from store alone and byte-compares every file
// against files.
func assertThirdSnapshotRestores(
	ctx context.Context, t *testing.T, cfg *config.Config,
	store storage.Storer, repos *database.Repositories, db *database.DB,
	fs afero.Fs, restoreDir string, files map[string][]byte,
) {
	t.Helper()

	id := localSnapshotID(ctx, t, repos, "third")
	require.NoError(t, db.Close())

	reader := newReaderVaultik(ctx, cfg, store, nil, fs)
	require.NoError(t, reader.Restore(&vaultik.RestoreOptions{
		SnapshotID: id,
		TargetDir:  restoreDir,
		Verify:     true,
	}), "the backup after the drop must restore the changed file")

	assertRestoredTree(t, fs, restoreDir, files)
}

// Trigger 1: bytes are appended to the file, a second snapshot backs it
// up, and that snapshot is removed. The first snapshot keeps the file row,
// which now lists the appended content's chunks, while removal drops the
// blob that held them.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestBackupAfterRemovingNewestSnapshotRestoresChangedFile(t *testing.T) {
	log.Initialize(log.Config{})

	fs := afero.NewOsFs()
	tempDir := t.TempDir()
	dataDir := filepath.Join(tempDir, "src")
	storeDir := filepath.Join(tempDir, "remote")
	restoreDir := filepath.Join(tempDir, "restored")
	dbPath := filepath.Join(tempDir, "index.sqlite")
	changedPath := filepath.Join(dataDir, "appended.bin")

	ctx := context.Background()
	files := writeFaultSourceTree(t, fs, dataDir)
	cfg := changedFileConfig(dataDir, dbPath)

	appendRandomBytes(t, fs, files, changedPath, appendedFileSize)

	store, err := storage.NewFileStorer(storeDir)
	require.NoError(t, err)

	db, err := database.New(ctx, dbPath)
	require.NoError(t, err)

	repos := database.NewRepositories(db)
	v := newBackupVaultik(ctx, cfg, store, repos, db, fs)

	require.NoError(t, backUp(v, "first"))

	appendRandomBytes(t, fs, files, changedPath, faultChunkSize)
	require.NoError(t, backUp(v, "second"))

	_, err = v.RemoveSnapshot(localSnapshotID(ctx, t, repos, "second"),
		&vaultik.RemoveOptions{Force: true})
	require.NoError(t, err)

	require.NoError(t, backUp(v, "third"))

	assertThirdSnapshotRestores(
		ctx, t, cfg, store, repos, db, fs, restoreDir, files)
}

// Trigger 2: bytes are appended to the file and the run that backs it up
// is interrupted at the manifest upload, after its blobs were uploaded.
// The next run's prune drops that incomplete snapshot and its blob, while
// the first snapshot keeps the file row, which now lists the appended
// content's chunks.
//
//nolint:paralleltest // installs the global logger via log.Initialize
func TestBackupAfterInterruptedRunRestoresChangedFile(t *testing.T) {
	log.Initialize(log.Config{})

	fs := afero.NewOsFs()
	tempDir := t.TempDir()
	dataDir := filepath.Join(tempDir, "src")
	storeDir := filepath.Join(tempDir, "remote")
	restoreDir := filepath.Join(tempDir, "restored")
	dbPath := filepath.Join(tempDir, "index.sqlite")
	changedPath := filepath.Join(dataDir, "appended.bin")

	ctx := context.Background()
	files := writeFaultSourceTree(t, fs, dataDir)
	cfg := changedFileConfig(dataDir, dbPath)

	appendRandomBytes(t, fs, files, changedPath, appendedFileSize)

	inner, err := storage.NewFileStorer(storeDir)
	require.NoError(t, err)

	failManifest := false
	store := faultstore.New(inner)
	store.OnPut = func(key string) faultstore.PutAction {
		if failManifest && strings.HasSuffix(key, "manifest.json.zst") {
			return faultstore.PutFail
		}

		return faultstore.PutNormal
	}

	db, err := database.New(ctx, dbPath)
	require.NoError(t, err)

	repos := database.NewRepositories(db)
	v := newBackupVaultik(ctx, cfg, store, repos, db, fs)

	require.NoError(t, backUp(v, "first"))

	appendRandomBytes(t, fs, files, changedPath, faultChunkSize)

	failManifest = true

	require.Error(t, backUp(v, "second"),
		"the run must fail when its manifest upload fails")

	failManifest = false

	require.NoError(t, backUp(v, "third"))

	assertThirdSnapshotRestores(
		ctx, t, cfg, inner, repos, db, fs, restoreDir, files)
}