Skip vaultik's own index and PID file in a backup (closes #421)

A backup of a directory that holds the local index stored a torn copy
of it, its -wal and -shm side files and vaultik.pid, all being written
while they were read. The scan now treats these files as excluded,
whatever the config says. Their paths come from index_path and the lock
directory, with symlinks in their directories resolved the way source
paths are. If index_path is itself a symlink, SQLite writes the file it
points to, so that file and its side files are skipped too. pidlock now
owns the lock directory and the PID file name, so the CLI and the
scanner use the same path. database delete now removes the side files
database.IndexFiles lists, the -journal file included.

Model: opus-5-5

internal/cli/app.go

@@ -7,11 +7,9 @@ import (
 	"context"
 	"errors"
 	"fmt"
-	"path/filepath"
 	"sync"
 	"time"
 
-	"github.com/adrg/xdg"
 	"github.com/spf13/cobra"
 	"go.uber.org/dig"
 	"go.uber.org/fx"
@@ -351,8 +349,7 @@ func runVaultikApp(
 // only one runs at a time; a read-only command runs without it and is not
 // blocked while a mutator holds the lock (opts.Mode).
 func RunWithApp(ctx context.Context, opts AppOptions) error {
-	release, err := acquireLockIfMutating(opts.Mode,
-		filepath.Join(xdg.DataHome, "vaultik"))
+	release, err := acquireLockIfMutating(opts.Mode, pidlock.Dir())
 	if err != nil {
 		return err
 	}

internal/cli/database.go

@@ -6,7 +6,9 @@ import (
 
 	"github.com/spf13/cobra"
 	"sneak.berlin/go/vaultik/internal/config"
+	"sneak.berlin/go/vaultik/internal/database"
 	"sneak.berlin/go/vaultik/internal/log"
+	"sneak.berlin/go/vaultik/internal/vaultik"
 )
 
 // NewDatabaseCommand creates the database command group
@@ -90,27 +92,25 @@ Use --force to skip the confirmation prompt.`,
 
 				var confirm string
 
-				_, err = fmt.Scanln(&confirm)
+				// A failure to read the answer means no confirmation.
+				_, err = fmt.Fscanln(cmd.InOrStdin(), &confirm)
 				if err != nil || confirm != "yes" {
 					_, _ = fmt.Fprintln(w, "Aborted.")
 
-					//nolint:nilerr // a failed/aborted confirmation is a clean abort
-					return nil
+					return vaultik.ErrNotConfirmed
 				}
 			}
 
-			// Delete the database file
-			err = os.Remove(dbPath)
-			if err != nil {
-				return fmt.Errorf("failed to delete database: %w", err)
+			// Delete the database file and its side files. A side file
+			// may not exist, so only failing to delete the database file
+			// is an error.
+			for _, indexFile := range database.IndexFiles(dbPath) {
+				err = os.Remove(indexFile)
+				if err != nil && indexFile == dbPath {
+					return fmt.Errorf("failed to delete database: %w", err)
+				}
 			}
 
-			// Also delete WAL and SHM files if they exist
-			walPath := dbPath + "-wal"
-			shmPath := dbPath + "-shm"
-			_ = os.Remove(walPath) // Ignore errors - files may not exist
-			_ = os.Remove(shmPath)
-
 			out.Infof("Local state database deleted: %s.", dbPath)
 			log.Info("Local state database deleted", "path", dbPath)
 

internal/cli/database_test.go

@@ -0,0 +1,75 @@
+package cli //nolint:testpackage // sets the unexported rootFlags directly
+
+import (
+	"bytes"
+	"errors"
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"sneak.berlin/go/vaultik/internal/database"
+	"sneak.berlin/go/vaultik/internal/vaultik"
+)
+
+// TestDatabaseDeleteDeclinedIsError checks that answering anything but
+// "yes" keeps the database and returns ErrNotConfirmed, so the command
+// exits non-zero.
+//
+//nolint:paralleltest // mutates the process-global rootFlags
+func TestDatabaseDeleteDeclinedIsError(t *testing.T) {
+	dir := t.TempDir()
+	dbPath, cfgPath := seedDatabaseDeleteConfig(t, dir)
+
+	setRootFlags(t, RootFlags{ConfigPath: cfgPath})
+
+	var out bytes.Buffer
+
+	cmd := newDatabaseDeleteCommand()
+	cmd.SetOut(&out)
+	cmd.SetErr(io.Discard)
+	cmd.SetIn(strings.NewReader("no\n"))
+	cmd.SetArgs(nil)
+
+	err := cmd.Execute()
+	if !errors.Is(err, vaultik.ErrNotConfirmed) {
+		t.Errorf("declined database delete returned %v, want %v",
+			err, vaultik.ErrNotConfirmed)
+	}
+
+	_, err = os.Stat(dbPath)
+	if err != nil {
+		t.Errorf("declined database delete removed the file: %v", err)
+	}
+
+	if !strings.Contains(out.String(), "Aborted.") {
+		t.Errorf("declined database delete printed %q, want Aborted.",
+			out.String())
+	}
+}
+
+// TestDatabaseDeleteRemovesSideFiles checks that the side files SQLite
+// keeps beside the database file are deleted with it.
+//
+//nolint:paralleltest // mutates the process-global rootFlags
+func TestDatabaseDeleteRemovesSideFiles(t *testing.T) {
+	dir := t.TempDir()
+	dbPath, cfgPath := seedDatabaseDeleteConfig(t, dir)
+
+	indexFiles := database.IndexFiles(dbPath)
+	for _, indexFile := range indexFiles {
+		seedFile(t, dir, filepath.Base(indexFile), "data")
+	}
+
+	setRootFlags(t, RootFlags{ConfigPath: cfgPath})
+
+	mustExecute(t, newDatabaseDeleteCommand(), "--force")
+
+	for _, indexFile := range indexFiles {
+		_, err := os.Stat(indexFile)
+		if !os.IsNotExist(err) {
+			t.Errorf("database delete left %s: stat err = %v", indexFile, err)
+		}
+	}
+}

internal/cli/entry_snapshot_create_index_and_lock_files_test.go

@@ -0,0 +1,69 @@
+package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/adrg/xdg"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestEntrySnapshotCreateSkipsIndexAndLockFiles backs up a directory
+// that holds vaultik's index and PID file beside one other file, with no
+// exclude pattern set. The summary counts only the other file. See
+// https://git.eeqj.de/sneak/vaultik/issues/421.
+//
+// Not parallel: it replaces os.Args, os.Stdout, os.Stderr and the xdg
+// globals.
+func TestEntrySnapshotCreateSkipsIndexAndLockFiles(t *testing.T) {
+	for _, testCase := range []struct {
+		name string
+		// linked sets index_path to a symlink outside the backed-up
+		// directory that points to the index inside it.
+		linked bool
+	}{
+		{name: "index in the backed-up directory"},
+		{name: "index_path links into the backed-up directory", linked: true},
+	} {
+		t.Run(testCase.name, func(t *testing.T) {
+			dir := t.TempDir()
+			configPath := filepath.Join(dir, "config.yml")
+			sourceDir := filepath.Join(dir, "source")
+			storeDir := filepath.Join(dir, "store")
+
+			indexPath := filepath.Join(sourceDir, "index.sqlite")
+
+			if testCase.linked {
+				link := filepath.Join(dir, "index.sqlite")
+				require.NoError(t, os.Symlink(indexPath, link))
+
+				indexPath = link
+			}
+
+			contents := fmt.Sprintf(hermeticConfig,
+				sourceDir, storeDir, indexPath)
+			require.NoError(t,
+				os.WriteFile(configPath, []byte(contents), configFileMode))
+			require.NoError(t, os.Mkdir(storeDir, 0o750))
+			require.NoError(t, os.Mkdir(sourceDir, 0o750))
+			require.NoError(t, os.WriteFile(
+				filepath.Join(sourceDir, "file.txt"), []byte("hello"), 0o600))
+
+			// The PID file goes in a directory under XDG_DATA_HOME, which
+			// xdg reads at package init.
+			t.Setenv("XDG_DATA_HOME", filepath.Join(sourceDir, "data"))
+			xdg.Reload()
+			t.Cleanup(xdg.Reload)
+
+			code, stdout, _ := runEntry(t,
+				flagConfig, configPath, cmdSnapshot, cmdCreate)
+
+			require.Equal(t, 0, code)
+			assert.Contains(t, stdout,
+				"Files: 1 examined, 1 backed up, 0 unchanged.")
+		})
+	}
+}

internal/database/module.go

@@ -20,6 +20,17 @@ const indexDirPerm = 0o700
 // backed-up path and chunk hash and must stay private.
 const indexFilePerm = 0o600
 
+// IndexFiles returns the path of the index at indexPath and the paths of
+// the side files SQLite keeps beside it while it writes.
+func IndexFiles(indexPath string) []string {
+	return []string{
+		indexPath,
+		indexPath + "-wal",
+		indexPath + "-shm",
+		indexPath + "-journal",
+	}
+}
+
 // ensureIndexFileMode makes the index file owner-only before the SQLite
 // driver opens it: it creates the file 0600 if absent, or chmods an existing
 // one to 0600. Doing this first matters because SQLite creates its -wal and

internal/pidlock/pidlock.go

@@ -11,6 +11,7 @@ import (
 	"strconv"
 	"strings"
 
+	"github.com/adrg/xdg"
 	"golang.org/x/sys/unix"
 )
 
@@ -29,8 +30,20 @@ const (
 	lockDirPerm = 0o700
 	// pidFilePerm is the mode for the PID file (owner-only).
 	pidFilePerm = 0o600
+	// pidFileName is the name of the PID file in the lock directory.
+	pidFileName = "vaultik.pid"
 )
 
+// Dir returns the directory that holds vaultik's PID file.
+func Dir() string {
+	return filepath.Join(xdg.DataHome, "vaultik")
+}
+
+// Path returns the path of the PID file that Acquire uses in lockDir.
+func Path(lockDir string) string {
+	return filepath.Join(lockDir, pidFileName)
+}
+
 // Acquire attempts to acquire a PID lock in the specified directory.
 // If another process holds the lock, it returns ErrAlreadyRunning with
 // that process's PID. On success, it writes the current PID to the lock
@@ -42,7 +55,7 @@ func Acquire(lockDir string) (*Lock, error) {
 		return nil, fmt.Errorf("creating lock directory: %w", err)
 	}
 
-	lockPath := filepath.Join(lockDir, "vaultik.pid")
+	lockPath := Path(lockDir)
 
 	// No O_TRUNC: the file may hold the PID of the process that has the
 	// lock, which the error below reports.

internal/snapshot/index_and_lock_files_test.go

@@ -0,0 +1,65 @@
+package snapshot_test
+
+import (
+	"context"
+	"testing"
+
+	"github.com/spf13/afero"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/vaultik/internal/database"
+	"sneak.berlin/go/vaultik/internal/snapshot"
+)
+
+// A backup of the directory that holds vaultik's index and PID file
+// stores neither, with no exclude pattern set, and still stores the
+// files beside them. See https://git.eeqj.de/sneak/vaultik/issues/421.
+func TestScanSkipsIndexAndLockFiles(t *testing.T) {
+	t.Parallel()
+
+	const dataDir = "/home/user/.local/share/vaultik"
+
+	indexAndLockFiles := append(database.IndexFiles(dataDir+"/index.sqlite"),
+		dataDir+"/vaultik.pid")
+
+	fs := afero.NewMemMapFs()
+	for _, p := range append(indexAndLockFiles, dataDir+"/notes.txt") {
+		require.NoError(t, afero.WriteFile(fs, p, []byte("data"), 0o600))
+	}
+
+	db, err := database.NewTestDB()
+	require.NoError(t, err)
+
+	defer func() { _ = db.Close() }()
+
+	repos := database.NewRepositories(db)
+
+	scanner := snapshot.NewScanner(snapshot.ScannerConfig{
+		FS:               fs,
+		ChunkSize:        64 * 1024,
+		Repositories:     repos,
+		MaxBlobSize:      1024 * 1024,
+		CompressionLevel: 3,
+		AgeRecipients: []string{
+			"age1ql3z7hjy54pw3hyww5ayyfg7zqgvc7w3j2elw8zmrj2kg5sfn9aqmcac8p"},
+		IndexAndLockFiles: indexAndLockFiles,
+	})
+	require.NotNil(t, scanner)
+
+	ctx := context.Background()
+	createSnapshotRecord(ctx, t, repos, "test-snapshot")
+
+	result, err := scanner.Scan(ctx, "/home/user", "test-snapshot")
+	require.NoError(t, err)
+
+	require.Equal(t, 1, result.FilesScanned)
+
+	stored, err := repos.Files.GetByPath(ctx, dataDir+"/notes.txt")
+	require.NoError(t, err)
+	require.NotNil(t, stored, "a file beside the index is stored")
+
+	for _, p := range indexAndLockFiles {
+		f, err := repos.Files.GetByPath(ctx, p)
+		require.NoError(t, err)
+		require.Nil(t, f, "%s is not stored", p)
+	}
+}

internal/snapshot/module.go

@@ -2,11 +2,13 @@ package snapshot
 
 import (
 	"os"
+	"path/filepath"
 
 	"github.com/spf13/afero"
 	"go.uber.org/fx"
 	"sneak.berlin/go/vaultik/internal/config"
 	"sneak.berlin/go/vaultik/internal/database"
+	"sneak.berlin/go/vaultik/internal/pidlock"
 	"sneak.berlin/go/vaultik/internal/storage"
 	"sneak.berlin/go/vaultik/internal/ui"
 )
@@ -62,9 +64,52 @@ func provideScannerFactory(
 			EnableProgress:     params.EnableProgress,
 			UI:                 params.UI,
 			Exclude:            excludes,
+			IndexAndLockFiles:  indexAndLockFiles(cfg.IndexPath, pidlock.Dir()),
 			SkipErrors:         params.SkipErrors,
 			PreviousSnapshotID: params.PreviousSnapshotID,
 			DeviceNumber:       params.DeviceNumber,
 		})
 	}
 }
+
+// indexAndLockFiles returns the paths of the index at indexPath, its side
+// files and the PID file in lockDir. Symlinks in their directories are
+// resolved, as they are in the snapshot's source paths, so the scan finds
+// them under the same names. If indexPath is a symlink, the file it points
+// to and that file's side files are returned too.
+func indexAndLockFiles(indexPath, lockDir string) []string {
+	paths := append(database.IndexFiles(indexPath), pidlock.Path(lockDir))
+	for i, p := range paths {
+		paths[i] = resolveParentDir(p)
+	}
+
+	// SQLite writes the file a symlinked index points to and keeps the
+	// side files beside that file. The database package creates the index
+	// before the scanner is built, so the link resolves.
+	index := resolveParentDir(indexPath)
+
+	target, err := filepath.EvalSymlinks(index)
+	if err == nil && target != index {
+		paths = append(paths, database.IndexFiles(target)...)
+	}
+
+	return paths
+}
+
+// resolveParentDir returns the absolute form of path with the symlinks in
+// its parent directory resolved. If the parent directory cannot be
+// resolved, it returns the absolute form unresolved. If path has no
+// absolute form, it returns path.
+func resolveParentDir(path string) string {
+	abs, err := filepath.Abs(path)
+	if err != nil {
+		return path
+	}
+
+	dir, err := filepath.EvalSymlinks(filepath.Dir(abs))
+	if err != nil {
+		return abs
+	}
+
+	return filepath.Join(dir, filepath.Base(abs))
+}

internal/snapshot/module_test.go

@@ -0,0 +1,32 @@
+//nolint:testpackage // exercises the unexported indexAndLockFiles helper
+package snapshot
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+// The scan walks source paths with symlinks resolved, so vaultik's own
+// files are named the same way, or a symlinked home would back them up.
+func TestIndexAndLockFilesResolvesSymlinkedDirectory(t *testing.T) {
+	t.Parallel()
+
+	realDir, err := filepath.EvalSymlinks(t.TempDir())
+	require.NoError(t, err)
+
+	link := filepath.Join(t.TempDir(), "link")
+	require.NoError(t, os.Symlink(realDir, link))
+
+	paths := indexAndLockFiles(filepath.Join(link, "index.sqlite"), link)
+
+	require.Equal(t, []string{
+		filepath.Join(realDir, "index.sqlite"),
+		filepath.Join(realDir, "index.sqlite-wal"),
+		filepath.Join(realDir, "index.sqlite-shm"),
+		filepath.Join(realDir, "index.sqlite-journal"),
+		filepath.Join(realDir, "vaultik.pid"),
+	}, paths)
+}

internal/snapshot/scanner.go

@@ -67,6 +67,9 @@ type Scanner struct {
 	currentSourcePath string
 	exclude           []string          // Glob patterns for files/directories to exclude
 	compiledExclude   []compiledPattern // Compiled glob patterns
+	// indexAndLockFiles holds the paths of vaultik's own working files,
+	// which the scan treats as excluded (ScannerConfig.IndexAndLockFiles).
+	indexAndLockFiles map[string]struct{}
 	progress          *ProgressReporter
 	// skipErrors skips files that cannot be opened or read (logged loudly);
 	// packer, database, encryption, and upload errors still abort the run.
@@ -133,6 +136,11 @@ type ScannerConfig struct {
 	EnableProgress   bool       // Enable the live progress reporter (ETAs, throughput)
 	UI               *ui.Writer // Where user-facing scanner messages go; nil = discard
 	Exclude          []string   // Glob patterns for files/directories to exclude
+	// IndexAndLockFiles are the absolute paths of vaultik's own working
+	// files: the index, its side files and the PID file. The scan treats
+	// them as excluded, whatever Exclude says, since a copy taken while
+	// they are being written is torn.
+	IndexAndLockFiles []string
 	// SkipErrors skips files that cannot be opened or read (log loudly but
 	// continue); packer, database, encryption, and upload errors still abort.
 	SkipErrors bool
@@ -226,6 +234,11 @@ func NewScanner(cfg ScannerConfig) *Scanner {
 		deviceNumber = deviceNumberFromStat
 	}
 
+	indexAndLockFiles := make(map[string]struct{}, len(cfg.IndexAndLockFiles))
+	for _, p := range cfg.IndexAndLockFiles {
+		indexAndLockFiles[filepath.Clean(p)] = struct{}{}
+	}
+
 	return &Scanner{
 		fs:                 cfg.FS,
 		chunker:            chunker.NewChunker(cfg.ChunkSize),
@@ -237,6 +250,7 @@ func NewScanner(cfg ScannerConfig) *Scanner {
 		ageRecipient:       strings.Join(cfg.AgeRecipients, ","),
 		exclude:            cfg.Exclude,
 		compiledExclude:    compiledExclude,
+		indexAndLockFiles:  indexAndLockFiles,
 		progress:           progress,
 		skipErrors:         cfg.SkipErrors,
 		previousSnapshotID: cfg.PreviousSnapshotID,
@@ -2248,8 +2262,9 @@ func (s *Scanner) detectDeletedFiles(
 
 // excludedOrInExcludedDir reports whether filePath, which is at or
 // beneath rootPath, or any directory between rootPath and it, matches an
-// exclude pattern. A pattern such as */.local/share/Trash matches the
-// directory but not the files inside it, which the walk skips too.
+// exclude pattern or is one of vaultik's own files. A pattern such as
+// */.local/share/Trash matches the directory but not the files inside it,
+// which the walk skips too.
 func (s *Scanner) excludedOrInExcludedDir(filePath, rootPath string) bool {
 	for p := filePath; len(p) > len(rootPath); p = filepath.Dir(p) {
 		if s.shouldExclude(p, rootPath) {
@@ -2373,9 +2388,14 @@ func doubleStarVariants(pattern string) []string {
 }
 
 // shouldExclude checks if a path should be excluded based on exclude patterns
+// or because it is one of vaultik's own working files.
 // filePath is the full path to the file
 // rootPath is the root of the backup source directory
 func (s *Scanner) shouldExclude(filePath, rootPath string) bool {
+	if _, ok := s.indexAndLockFiles[filePath]; ok {
+		return true
+	}
+
 	if len(s.compiledExclude) == 0 {
 		return false
 	}

internal/vaultik/missing_destination_test.go

@@ -7,6 +7,7 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
+	"sync"
 	"testing"
 
 	"github.com/spf13/afero"
@@ -24,19 +25,28 @@ import (
 // that is not plugged in, cannot be listed. It is not an empty store, so
 // no command may conclude from it that the local snapshots are gone.
 
-// newFileDestinationVaultik returns a Vaultik that backs up the
-// snapshot named "first" to a file:// destination at storeDir.
+// newFileDestinationVaultik writes the fault source tree and returns a
+// Vaultik that backs it up to a file:// destination at storeDir.
 func newFileDestinationVaultik(
 	ctx context.Context, t *testing.T, storeDir string,
 ) (*vaultik.Vaultik, *database.Repositories) {
 	t.Helper()
 
-	osFs := afero.NewOsFs()
 	tempDir := t.TempDir()
 	dataDir := filepath.Join(tempDir, "src")
-	dbPath := filepath.Join(tempDir, "index.sqlite")
+	writeFaultSourceTree(t, afero.NewOsFs(), dataDir)
 
-	writeFaultSourceTree(t, osFs, dataDir)
+	return openFileDestinationVaultik(ctx, t, storeDir, dataDir,
+		filepath.Join(tempDir, "index.sqlite"))
+}
+
+// openFileDestinationVaultik returns a Vaultik that backs up dataDir to a
+// file:// destination at storeDir, with its local index at dbPath. The
+// index is closed when the test ends.
+func openFileDestinationVaultik(
+	ctx context.Context, t *testing.T, storeDir, dataDir, dbPath string,
+) (*vaultik.Vaultik, *database.Repositories) {
+	t.Helper()
 
 	store, err := storage.NewFileStorer(storeDir)
 	require.NoError(t, err)
@@ -48,22 +58,84 @@ func newFileDestinationVaultik(
 	repos := database.NewRepositories(db)
 	cfg := changedFileConfig(dataDir, dbPath)
 
-	return newBackupVaultik(ctx, cfg, store, repos, db, osFs), repos
+	return newBackupVaultik(ctx, cfg, store, repos, db, afero.NewOsFs()), repos
+}
+
+// firstBackup is one backup of the snapshot named "first" to a file://
+// destination. dir holds its source tree in src, its store in store and
+// its closed local index in index/index.sqlite. The first test that
+// needs it makes it, and TestMain removes it. Every test that copies it
+// backs up the same source tree, so no test may change that tree.
+//
+//nolint:gochecknoglobals // made once and shared by the tests that copy it
+var firstBackup struct {
+	once  sync.Once
+	dir   string
+	ready bool
+}
+
+// TestMain removes firstBackup once every test has run.
+func TestMain(m *testing.M) {
+	code := m.Run()
+
+	_ = os.RemoveAll(firstBackup.dir)
+
+	os.Exit(code)
+}
+
+// makeFirstBackup writes the fault source tree and backs it up as the
+// snapshot named "first", all in a new directory that it records in
+// firstBackup.
+func makeFirstBackup(ctx context.Context, t *testing.T) {
+	t.Helper()
+
+	dir, err := os.MkdirTemp("", "vaultik-first-backup-")
+	require.NoError(t, err)
+
+	firstBackup.dir = dir
+	storeDir := filepath.Join(dir, "store")
+	dataDir := filepath.Join(dir, "src")
+	indexDir := filepath.Join(dir, "index")
+
+	require.NoError(t, os.Mkdir(storeDir, 0o750))
+	require.NoError(t, os.Mkdir(indexDir, 0o750))
+	writeFaultSourceTree(t, afero.NewOsFs(), dataDir)
+
+	v, _ := openFileDestinationVaultik(ctx, t, storeDir, dataDir,
+		filepath.Join(indexDir, "index.sqlite"))
+	require.NoError(t, backUp(v, "first"))
+	require.NoError(t, v.DB.Close())
+
+	firstBackup.ready = true
 }
 
 // backUpToFileDestination creates the directory storeDir, as a user must
-// before the first backup, and backs up the snapshot named "first" to a
-// file:// destination there. Everything the returned Vaultik prints
-// after the backup goes to the returned buffer.
+// before the first backup, and returns a Vaultik whose file://
+// destination there holds a backup of the snapshot named "first". The
+// store and the local index are copies of firstBackup's, which is faster
+// than backing up in every test. The returned Vaultik backs up a source
+// tree shared with every other caller, so no test may change that tree.
+// Everything the returned Vaultik prints after the backup goes to the
+// returned buffer.
 func backUpToFileDestination(
 	ctx context.Context, t *testing.T, storeDir string,
 ) (*vaultik.Vaultik, *database.Repositories, *bytes.Buffer) {
 	t.Helper()
 
-	require.NoError(t, os.MkdirAll(storeDir, 0o750))
+	firstBackup.once.Do(func() { makeFirstBackup(ctx, t) })
+	require.True(t, firstBackup.ready, "another test failed to make firstBackup")
 
-	v, repos := newFileDestinationVaultik(ctx, t, storeDir)
-	require.NoError(t, backUp(v, "first"))
+	require.NoError(t, os.MkdirAll(storeDir, 0o750))
+	require.NoError(t, os.CopyFS(storeDir,
+		os.DirFS(filepath.Join(firstBackup.dir, "store"))))
+
+	indexDir := t.TempDir()
+	require.NoError(t, os.CopyFS(indexDir,
+		os.DirFS(filepath.Join(firstBackup.dir, "index"))))
+
+	v, repos := openFileDestinationVaultik(ctx, t, storeDir,
+		filepath.Join(firstBackup.dir, "src"),
+		filepath.Join(indexDir, "index.sqlite"))
 
 	out := &bytes.Buffer{}
 	v.Stdout = out

internal/vaultik/prune.go

@@ -267,7 +267,7 @@ func (v *Vaultik) PruneBlobs(opts *PruneOptions) error {
 
 	if !v.confirmPrune(opts, len(unreferencedBlobs), totalSize,
 		dirsWithoutManifest) {
-		return nil
+		return ErrNotConfirmed
 	}
 
 	v.deleteUnreferencedBlobs(unreferencedBlobs, allBlobs, result)

internal/vaultik/prune_metadata_dir_test.go

@@ -176,7 +176,8 @@ func TestPruneDeclinedKeepsMetadataDirWithoutManifest(t *testing.T) {
 
 	env.v.Stdin = strings.NewReader("n\n")
 
-	require.NoError(t, env.v.PruneBlobs(&vaultik.PruneOptions{}))
+	require.ErrorIs(t, env.v.PruneBlobs(&vaultik.PruneOptions{}),
+		vaultik.ErrNotConfirmed)
 
 	assert.True(t, env.store.hasKey(leftDB),
 		"a declined prune must keep the directory")

internal/vaultik/remove_quiet_test.go

@@ -54,9 +54,10 @@ func TestPurgeSnapshots_QuietPromptListsSnapshots(t *testing.T) {
 	v.UI.SetQuiet(true)
 
 	// Stdin is empty, so the prompt reads no answer and cancels.
-	require.NoError(t, v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
+	err := v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
 		KeepLatest: true,
-	}))
+	})
+	require.ErrorIs(t, err, vaultik.ErrNotConfirmed)
 
 	assert.Contains(t, out.String(), snapHomeT0)
 	assert.Contains(t, out.String(), "Delete 1 snapshot(s)? [y/N]")
@@ -77,7 +78,8 @@ func TestPruneBlobs_QuietPromptShowsBlobTotal(t *testing.T) {
 	addBlob(t, env.store.testStorer, testBlobHashA)
 
 	// Stdin is empty, so the prompt reads no answer and cancels.
-	require.NoError(t, env.v.PruneBlobs(&vaultik.PruneOptions{}))
+	require.ErrorIs(t, env.v.PruneBlobs(&vaultik.PruneOptions{}),
+		vaultik.ErrNotConfirmed)
 
 	assert.Contains(t, env.stdout.String(),
 		"Found 1 unreferenced blob(s) totaling")

internal/vaultik/remove_snapshot_test.go

@@ -337,6 +337,27 @@ func TestRemoveSnapshot_DefaultRemovesMetadataNotBlobs(t *testing.T) {
 	assert.Contains(t, out, "vaultik prune")
 }
 
+// TestRemoveSnapshot_DeclinedIsError checks that answering no to the
+// prompt keeps the snapshot and returns ErrNotConfirmed, so the command
+// exits non-zero.
+func TestRemoveSnapshot_DeclinedIsError(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	store := newTestStorer()
+	addManifest(t, store, "snapshot-001", nil)
+
+	tv := vaultik.NewForTesting(store)
+	tv.Repositories = newLocalIndex(t, "snapshot-001")
+	tv.Stdin.WriteString("n\n")
+
+	_, err := tv.RemoveSnapshot("snapshot-001", &vaultik.RemoveOptions{})
+
+	require.ErrorIs(t, err, vaultik.ErrNotConfirmed)
+	assert.True(t, store.hasKey(remoteKeyPath("snapshot-001")))
+	assert.Contains(t, tv.Stdout.String(), "Cancelled")
+}
+
 func TestRemoveSnapshot_DryRun(t *testing.T) {
 	log.Initialize(log.Config{})
 	t.Parallel()

internal/vaultik/restore_locality_test.go

@@ -46,11 +46,11 @@ import (
 //     slice out a few KB — currently the dominant cost in restore.
 //
 // The test deliberately constructs an adversarial scenario: three
-// blobs A/B/C of ~6 MB each, nine files distributed across them, and
-// path-ordered names that interleave the blobs (a1, b1, c1, a2, b2,
-// c2, …) so naive path-order processing would touch every blob before
-// finishing any of them.
-// localitySource is one 1 MiB fixture file used by the locality test.
+// blobs A/B/C of five 64 KiB chunks each, nine files distributed across
+// them, and path-ordered names that interleave the blobs (a1, b1, c1,
+// a2, b2, c2, …) so naive path-order processing would touch every blob
+// before finishing any of them.
+// localitySource is one 64 KiB fixture file used by the locality test.
 type localitySource struct {
 	path string
 	data []byte
@@ -65,10 +65,10 @@ type localityCopy struct {
 
 // localitySourceBytes is the size of each source file of the locality
 // fixture.
-const localitySourceBytes = 1024 * 1024
+const localitySourceBytes = 64 * 1024
 
 // buildLocalityFixture writes the adversarial source layout described
-// in TestRestoreLocalityAndReadAt: 15 sources of 1 MiB each (which the
+// in TestRestoreLocalityAndReadAt: 15 sources of 64 KiB each (which the
 // backup packs into 3 blobs of 5 chunks) plus 9 interleaved-name copies
 // (3 per blob group).
 func buildLocalityFixture(

internal/vaultik/restore_sweeper_integration_test.go

@@ -27,10 +27,10 @@ import (
 // TestRestoreSweeperEvictsBlobs exercises the reference-counted blob
 // disk cache eviction during restore.
 //
-// The scenario: 30 unique 1 MB random files plus 10 duplicates of those
-// (40 files total, 30 MB of unique content) get backed up with a 10 MB
-// blob_size_limit. After backup the snapshot's encrypted blobs are
-// restored through Vaultik.Restore, and per-key Get counts on the
+// The scenario: 30 unique 128 KiB random files plus 10 duplicates of
+// those (40 files total, 3.75 MiB of unique content) get backed up with
+// a 1 MiB blob_size_limit. After backup the snapshot's encrypted blobs
+// are restored through Vaultik.Restore, and per-key Get counts on the
 // storage layer are recorded. Each blob in the snapshot MUST be
 // downloaded exactly once — re-downloads would mean the sweeper either
 // evicted a blob that was still needed (LRU regression) or that the
@@ -41,7 +41,7 @@ import (
 // original AND every duplicate referencing its chunks have been
 // restored.
 // buildSweeperFixture writes the source layout for the sweeper test: 30
-// unique 1 MB random files plus 10 duplicates of a random subset. The
+// unique 128 KiB random files plus 10 duplicates of a random subset. The
 // PRNG seed is fixed so failures are reproducible; the entropy is what
 // matters here — the FastCDC chunker needs realistic-looking data to
 // pick chunk boundaries naturally. Returns the expected content by
@@ -51,7 +51,7 @@ func buildSweeperFixture(
 ) map[string][]byte {
 	t.Helper()
 
-	const fileSize = 1 * 1024 * 1024
+	const fileSize = 128 * 1024
 
 	rng := rand.New(rand.NewSource(42)) //nolint:gosec // G404: fixture data only
 
@@ -159,7 +159,7 @@ func runSweeperBackup(
 	require.NoError(t, err)
 	require.Equal(t, uniqueFiles+duplicateFiles, scanResult.FilesScanned)
 	require.Greater(t, scanResult.BlobsCreated, 1,
-		"30 MB of unique data at 10 MB blob size should yield multiple blobs")
+		"3.75 MiB of unique data at 1 MiB blob size should yield multiple blobs")
 
 	require.NoError(t, sm.CompleteSnapshot(ctx, snapshotID))
 	require.NoError(t, sm.ExportSnapshotMetadata(ctx, dbPath, snapshotID))
@@ -199,8 +199,8 @@ func TestRestoreSweeperEvictsBlobs(t *testing.T) {
 
 	expected := buildSweeperFixture(t, fs, dataDir, uniqueFiles, duplicateFiles)
 
-	chunkSize := int64(64 * 1024)
-	maxBlobSize := int64(10 * 1024 * 1024)
+	chunkSize := int64(16 * 1024)
+	maxBlobSize := int64(1024 * 1024)
 
 	storer, err := storage.NewFileStorer(storeDir)
 	require.NoError(t, err)

internal/vaultik/snapshot.go

@@ -881,17 +881,12 @@ func (v *Vaultik) confirmAndExecutePurge(
 
 		var confirm string
 
+		// A failure to read the answer means no confirmation.
 		_, err := v.scanStdin(&confirm)
-		if err != nil {
+		if err != nil || strings.ToLower(confirm) != "y" {
 			v.printlnStdout("Cancelled")
 
-			return nil //nolint:nilerr // treat EOF or read error as "no"
-		}
-
-		if strings.ToLower(confirm) != "y" {
-			v.printlnStdout("Cancelled")
-
-			return nil
+			return ErrNotConfirmed
 		}
 	} else if !quiet {
 		v.UI.Infof("The following snapshots will be deleted:")
@@ -1490,7 +1485,7 @@ func (v *Vaultik) RemoveSnapshot(
 	}
 
 	if !v.confirmRemoveSnapshot(snapshotID, opts) {
-		return result, nil
+		return result, ErrNotConfirmed
 	}
 
 	// Checked before the local record is deleted: it may be the last

internal/vaultik/snapshot_list_test.go

@@ -187,6 +187,17 @@ func (e *listEnv) addRemoteRawTimestamp(
 	t.Helper()
 
 	remoteKey := snapshot.RemoteSnapshotKey(snapshotID)
+	e.putRemoteManifest(t, remoteKey,
+		encodeRemoteManifest(t, remoteKey, timestamp))
+
+	return remoteKey
+}
+
+// encodeRemoteManifest returns the encoded manifest of a one-blob
+// snapshot whose remote key is remoteKey.
+func encodeRemoteManifest(t *testing.T, remoteKey, timestamp string) []byte {
+	t.Helper()
+
 	manifest := &snapshot.Manifest{
 		// Note: the hashed key, never the human ID. That is precisely
 		// why a remote-only snapshot cannot be named.
@@ -202,11 +213,17 @@ func (e *listEnv) addRemoteRawTimestamp(
 	data, err := snapshot.EncodeManifest(manifest, 3)
 	require.NoError(t, err)
 
-	err = e.store.Put(context.Background(),
+	return data
+}
+
+// putRemoteManifest stores an encoded manifest on the destination store
+// under remoteKey.
+func (e *listEnv) putRemoteManifest(t *testing.T, remoteKey string, data []byte) {
+	t.Helper()
+
+	err := e.store.Put(context.Background(),
 		"metadata/"+remoteKey+"/manifest.json.zst", bytes.NewReader(data))
 	require.NoError(t, err)
-
-	return remoteKey
 }
 
 // Fixtures shared across the listing tests.
@@ -345,8 +362,9 @@ func TestSnapshotListAndPurgePrintSizesLikeRemoteInfo(t *testing.T) {
 	// Without --force and with nothing on stdin the purge lists what it
 	// would delete, reads no confirmation, and deletes nothing.
 	env.stdout.Reset()
-	require.NoError(t, env.v.PurgeSnapshotsWithOptions(
-		&vaultik.SnapshotPurgeOptions{OlderThan: "1d"}))
+	require.ErrorIs(t, env.v.PurgeSnapshotsWithOptions(
+		&vaultik.SnapshotPurgeOptions{OlderThan: "1d"}),
+		vaultik.ErrNotConfirmed)
 	assert.Contains(t, findTableRow(t, env.stdout.String(), listLocalID),
 		wantSize, "snapshot purge")
 }
@@ -791,9 +809,17 @@ func TestListSnapshots_JSONReportsTruncation(t *testing.T) {
 
 	timestamp := time.Date(2026, 3, 2, 11, 22, 33, 0, time.UTC)
 
-	// One past the cap, so exactly one snapshot is omitted.
+	// One past the cap, so exactly one snapshot is omitted. The listing
+	// names a snapshot by the key its manifest is stored under, never by
+	// the manifest's own ID. So all of them share one encoded manifest:
+	// encoding 1001 took seconds.
+	data := encodeRemoteManifest(t,
+		snapshot.RemoteSnapshotKey("otherhost_bulk"),
+		timestamp.Format(time.RFC3339))
+
 	for i := range maxRemoteOnlyRowsForTest + 1 {
-		env.addRemote(t, fmt.Sprintf("otherhost_bulk_%04d", i), timestamp)
+		env.putRemoteManifest(t, snapshot.RemoteSnapshotKey(
+			fmt.Sprintf("otherhost_bulk_%04d", i)), data)
 	}
 
 	stderr := captureProcessStderr(t, func() {

internal/vaultik/vaultik.go

@@ -5,6 +5,7 @@ package vaultik
 import (
 	"bytes"
 	"context"
+	"errors"
 	"fmt"
 	"io"
 	"os"
@@ -184,6 +185,12 @@ func (v *Vaultik) printlnStdout(args ...any) {
 	_, _ = fmt.Fprintln(v.Stdout, args...)
 }
 
+// ErrNotConfirmed is returned when a confirmation prompt gets any answer
+// but the one it asks for (`y` or `Y`, or `yes` for `database delete`), or
+// stdin ends first. Nothing the prompt asked about is deleted, and the
+// command exits non-zero.
+var ErrNotConfirmed = errors.New("deletion not confirmed")
+
 // scanStdin reads a line of input from stdin.
 func (v *Vaultik) scanStdin(a ...any) (int, error) {
 	return fmt.Fscanln(v.Stdin, a...)