Remove the blob temp file when a backup stops part-way (closes #302)

When `snapshot create` stopped on a file error, a full temporary
directory or Ctrl-C, the blob being packed was never finalized, and its
`vaultik-blob-*.tmp` file (up to `blob_size_limit` of encrypted data)
stayed in `$TMPDIR`. Phase 2 now calls the new
`Packer.DiscardCurrentBlob` on the way out, which closes and removes
that file. After a successful flush no blob is in progress, so the call
then does nothing.

The blob's row in the local index is left, as before, for the next
run's repair of interrupted blobs to remove.

Model: opus-5-5

README.md

@@ -286,9 +286,7 @@ needed.
   remove orphaned blobs from remote storage. By default keeps only the latest
   snapshot per name; use `--keep-newer-than` for a rolling window.
 * `--keep-newer-than <duration>`: With `--prune`, keep snapshots newer than
-  this duration instead of only the latest (e.g. `4w`, `30d`, `6mo`, `1y`).
-  Without `--prune`, or with a value that is not a valid duration, the
-  command fails before the backup starts.
+  this duration instead of only the latest (e.g. `4w`, `30d`, `6mo`, `1y`)
 
 **`snapshot list`**: Show every snapshot known to this host — the union
 of the local index and the backup destination store — with timestamps

internal/blob/packer.go

@@ -245,6 +245,17 @@ func (p *Packer) Flush(ctx context.Context) error {
 	return nil
 }
 
+// DiscardCurrentBlob closes and removes the temp file of the blob being
+// packed, if any, and drops that blob. A caller that stops before Flush
+// must call it, or the temp file is left behind. Thread-safe.
+func (p *Packer) DiscardCurrentBlob() {
+	p.mu.Lock()
+	defer p.mu.Unlock()
+
+	p.cleanupTempFile()
+	p.currentBlob = nil
+}
+
 // FinalizeBlob finalizes the current blob being assembled.
 // This compresses the accumulated chunks, encrypts the result, and computes
 // the content-addressed hash. The finalized blob is either passed to the

internal/cli/entry_snapshot_create_prune_test.go

@@ -1,108 +0,0 @@
-package cli //nolint:testpackage // shares runEntry and the hermetic config helpers
-
-import (
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-// Flags of `snapshot create` used to build argument vectors below.
-const (
-	flagPrune         = "--prune"
-	flagKeepNewerThan = "--keep-newer-than"
-)
-
-// TestEntrySnapshotCreateRejectsKeepNewerThanBeforeBackup checks that a
-// --keep-newer-than the post-backup prune could not use stops `snapshot
-// create` before the backup: the command fails and the destination
-// store stays empty. It used to be read only by the prune, after the
-// snapshot was uploaded, and without --prune it was ignored.
-//
-//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
-func TestEntrySnapshotCreateRejectsKeepNewerThanBeforeBackup(t *testing.T) {
-	for _, testCase := range []struct {
-		name string
-		args []string
-	}{
-		{
-			name: "decimal in a day count",
-			args: []string{flagPrune, flagKeepNewerThan, "1.5d"},
-		},
-		{
-			name: "unknown unit",
-			args: []string{flagPrune, flagKeepNewerThan, "4x"},
-		},
-		{
-			name: "without --prune",
-			args: []string{flagKeepNewerThan, "4w"},
-		},
-	} {
-		t.Run(testCase.name, func(t *testing.T) {
-			configPath, storeDir := writeBackupConfig(t)
-
-			code, _, _ := runEntry(t, append(
-				[]string{flagConfig, configPath, cmdSnapshot, cmdCreate},
-				testCase.args...)...)
-
-			assert.Equal(t, 1, code)
-
-			stored, err := os.ReadDir(storeDir)
-			require.NoError(t, err)
-			assert.Empty(t, stored, "nothing may be uploaded")
-		})
-	}
-}
-
-// TestEntrySnapshotCreateReportsPostBackupPruneFailure makes the
-// post-backup prune fail after a good backup, by planting a manifest
-// that cannot be decoded, and checks that the failure is reported as the
-// prune's and not as a failed snapshot creation.
-//
-//nolint:paralleltest // replaces os.Args, os.Stdout, os.Stderr and the xdg globals
-func TestEntrySnapshotCreateReportsPostBackupPruneFailure(t *testing.T) {
-	configPath, storeDir := writeBackupConfig(t)
-
-	// A remote key is 64 lowercase hex characters. The prune reads every
-	// manifest on the store and fails on one it cannot decode.
-	plantedDir := filepath.Join(storeDir, "metadata", strings.Repeat("a", 64))
-	require.NoError(t, os.MkdirAll(plantedDir, 0o750))
-	require.NoError(t, os.WriteFile(
-		filepath.Join(plantedDir, "manifest.json.zst"),
-		[]byte("not a valid manifest"), 0o600))
-
-	code, _, stderr := runEntry(t,
-		flagConfig, configPath, cmdSnapshot, cmdCreate, flagPrune)
-
-	assert.Equal(t, 1, code)
-	assert.Contains(t, stderr, "Backup completed, but post-backup prune failed")
-	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 new snapshot is on the store beside the planted one")
-}
-
-// 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.
-func writeBackupConfig(t *testing.T) (string, string) {
-	t.Helper()
-
-	configPath := writeHermeticPruneConfig(t, false)
-
-	// writeHermeticPruneConfig puts the source and store directories
-	// beside the config file.
-	dir := filepath.Dir(configPath)
-	sourceDir := filepath.Join(dir, "source")
-
-	require.NoError(t, os.Mkdir(sourceDir, 0o750))
-	require.NoError(t, os.WriteFile(
-		filepath.Join(sourceDir, "file.txt"), []byte("hello"), 0o600))
-
-	return configPath, filepath.Join(dir, "store")
-}

internal/cli/snapshot.go

@@ -71,11 +71,6 @@ otherwise from the platform config directory (~/.config/vaultik/config.yml
 on Linux), then /etc/vaultik/config.yml.`,
 		Args: cobra.ArbitraryArgs,
 		RunE: func(cmd *cobra.Command, args []string) error {
-			err := opts.Validate()
-			if err != nil {
-				return err
-			}
-
 			// Pass snapshot names from args
 			opts.Snapshots = args
 			// --skip-errors is a global flag on the root command.
@@ -102,13 +97,6 @@ on Linux), then /etc/vaultik/config.yml.`,
 			}, func(v *vaultik.Vaultik) error {
 				return v.CreateSnapshot(opts)
 			}, func(err error) {
-				if errors.Is(err, vaultik.ErrPostBackupPruneFailed) {
-					log.Error("Post-backup prune failed", "error", err)
-					ReportErrorf("Backup completed, but %v", err)
-
-					return
-				}
-
 				log.Error("Snapshot creation failed", "error", err)
 				ReportErrorf("Snapshot creation failed: %v", err)
 			})

internal/database/repositories.go

@@ -3,7 +3,6 @@ package database
 import (
 	"context"
 	"database/sql"
-	"errors"
 	"fmt"
 )
 
@@ -61,24 +60,22 @@ func (r *Repositories) WithTx(ctx context.Context, fn TxFunc) error {
 
 	defer func() {
 		if p := recover(); p != nil {
-			// The panic is the failure to report, so a rollback error
-			// is dropped.
-			_ = tx.Rollback()
+			rollbackErr := tx.Rollback()
+			if rollbackErr != nil {
+				Fatalf("failed to rollback transaction: %v", rollbackErr)
+			}
 
 			panic(p)
+		} else if err != nil {
+			rollbackErr := tx.Rollback()
+			if rollbackErr != nil {
+				Fatalf("failed to rollback transaction: %v", rollbackErr)
+			}
 		}
 	}()
 
 	err = fn(ctx, tx)
 	if err != nil {
-		// Once ctx is cancelled, database/sql rolls the transaction
-		// back itself and Rollback returns sql.ErrTxDone.
-		rollbackErr := tx.Rollback()
-		if rollbackErr != nil && !errors.Is(rollbackErr, sql.ErrTxDone) {
-			return fmt.Errorf("%w; rolling back transaction: %w",
-				err, rollbackErr)
-		}
-
 		return err
 	}
 

internal/database/repositories_test.go

@@ -4,7 +4,6 @@ import (
 	"context"
 	"database/sql"
 	"errors"
-	"strings"
 	"testing"
 	"time"
 
@@ -236,121 +235,6 @@ func TestRepositoriesTransactionRollback(t *testing.T) {
 	}
 }
 
-// When the context is cancelled during the body, database/sql rolls the
-// transaction back itself, so WithTx's own rollback finds it already
-// done. WithTx must still return the body's error.
-func TestRepositoriesTransactionContextCancelled(t *testing.T) {
-	t.Parallel()
-
-	db, cleanup := setupTestDB(t)
-	defer cleanup()
-
-	ctx, cancel := context.WithCancel(context.Background())
-	defer cancel()
-
-	repos := database.NewRepositories(db)
-
-	err := repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
-		file := &database.File{
-			Path:  "/test/cancelled_file.txt",
-			MTime: time.Now().Truncate(time.Second),
-			Size:  1024,
-			Mode:  0644,
-			UID:   1000,
-			GID:   1000,
-		}
-
-		err := repos.Files.Create(ctx, tx, file)
-		if err != nil {
-			return err
-		}
-
-		cancel()
-
-		// database/sql rolls back from a goroutine of its own; wait
-		// until it has, so the test does not depend on that race.
-		for {
-			_, err = tx.ExecContext(context.WithoutCancel(ctx), "SELECT 1")
-			if errors.Is(err, sql.ErrTxDone) {
-				return ctx.Err()
-			}
-
-			time.Sleep(time.Millisecond)
-		}
-	})
-	if !errors.Is(err, context.Canceled) {
-		t.Fatalf("expected context.Canceled, got: %v", err)
-	}
-
-	file, err := repos.Files.GetByPath(
-		context.Background(), "/test/cancelled_file.txt",
-	)
-	if err != nil {
-		t.Fatalf("error checking for file: %v", err)
-	}
-
-	if file != nil {
-		t.Error("file should not exist after the cancelled transaction")
-	}
-}
-
-// A body that ends the transaction itself with ROLLBACK makes WithTx's
-// own rollback fail. WithTx must return that failure together with the
-// body's error.
-func TestRepositoriesTransactionRollbackFails(t *testing.T) {
-	t.Parallel()
-
-	db, cleanup := setupTestDB(t)
-	defer cleanup()
-
-	ctx := context.Background()
-	repos := database.NewRepositories(db)
-
-	err := repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
-		_, err := tx.ExecContext(ctx, "ROLLBACK")
-		if err != nil {
-			return err
-		}
-
-		return errIntentionalRollback
-	})
-	if !errors.Is(err, errIntentionalRollback) {
-		t.Fatalf("expected the body's error, got: %v", err)
-	}
-
-	if !strings.Contains(err.Error(), "rolling back transaction") {
-		t.Errorf("expected the failed rollback in the error, got: %v", err)
-	}
-}
-
-// When the body ends the transaction itself with ROLLBACK and then
-// panics, WithTx's own rollback fails; the panic must still reach the
-// caller.
-func TestRepositoriesTransactionPanicRollbackFails(t *testing.T) {
-	t.Parallel()
-
-	db, cleanup := setupTestDB(t)
-	defer cleanup()
-
-	ctx := context.Background()
-	repos := database.NewRepositories(db)
-
-	defer func() {
-		if recover() == nil {
-			t.Error("expected the body's panic to reach the caller")
-		}
-	}()
-
-	_ = repos.WithTx(ctx, func(ctx context.Context, tx *sql.Tx) error {
-		_, err := tx.ExecContext(ctx, "ROLLBACK")
-		if err != nil {
-			return err
-		}
-
-		panic(errIntentionalRollback)
-	})
-}
-
 func TestRepositoriesReadTransaction(t *testing.T) {
 	t.Parallel()
 

internal/snapshot/scanner.go

@@ -1295,6 +1295,11 @@ func (s *Scanner) batchAddFilesToSnapshot(
 func (s *Scanner) processPhase(
 	ctx context.Context, filesToProcess []*FileToProcess, result *ScanResult,
 ) error {
+	// On an error or cancellation the blob being packed is never
+	// finalized, so its temp file must be removed here. After a
+	// successful flush there is no such blob and this does nothing.
+	defer s.packer.DiscardCurrentBlob()
+
 	// Calculate total bytes to process
 	var totalBytes int64
 	for _, f := range filesToProcess {

internal/snapshot/skip_errors_test.go

@@ -381,3 +381,60 @@ func TestScannerCancelStopsSkipErrorsRun(t *testing.T) {
 		})
 	}
 }
+
+// TestScannerRemovesBlobTempFileWhenRunStops checks that a run stopped
+// part-way, by a file it cannot read or by a cancellation, removes the
+// temp file of the blob it was packing.
+func TestScannerRemovesBlobTempFileWhenRunStops(t *testing.T) {
+	t.Parallel()
+
+	// a.txt is backed up first and starts a blob; the run stops at b.txt.
+	const target = "/source/b.txt"
+
+	tests := []struct {
+		name  string
+		newFs func(cancel context.CancelFunc) afero.Fs
+	}{
+		{
+			name: "file cannot be read",
+			newFs: func(context.CancelFunc) afero.Fs {
+				return &readFailFs{Fs: afero.NewMemMapFs(), target: target}
+			},
+		},
+		{
+			name: "cancelled",
+			newFs: func(cancel context.CancelFunc) afero.Fs {
+				return &cancelOnOpenFs{
+					Fs: afero.NewMemMapFs(), target: target, cancel: cancel,
+				}
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			ctx, cancel := context.WithCancel(context.Background())
+			defer cancel()
+
+			fs := tt.newFs(cancel)
+			writeSkipErrorTestFile(t, fs, "/source/a.txt", "first file content")
+			writeSkipErrorTestFile(t, fs, target, "second file content")
+
+			_, err := runSkipErrorScan(ctx, t, fs, "/source", false, nil)
+			if err == nil {
+				t.Fatal("expected the scan to stop with an error, got nil")
+			}
+
+			left, err := afero.Glob(fs, filepath.Join(os.TempDir(), "vaultik-blob-*"))
+			if err != nil {
+				t.Fatalf("listing blob temp files: %v", err)
+			}
+
+			if len(left) != 0 {
+				t.Fatalf("expected no blob temp file left, got %v", left)
+			}
+		})
+	}
+}

internal/vaultik/snapshot.go

@@ -28,14 +28,8 @@ var (
 	errNoAgeRecipients      = errors.New(
 		"creating a snapshot needs at least one public key in " +
 			"age_recipients (generate a keypair with: age-keygen)")
-	errKeepNewerThanNeedsPrune = errors.New("--keep-newer-than requires --prune")
 )
 
-// ErrPostBackupPruneFailed wraps a failure of the post-backup prune,
-// which runs only after every snapshot was created and uploaded, so the
-// caller can report it apart from a failed backup.
-var ErrPostBackupPruneFailed = errors.New("post-backup prune failed")
-
 // listRecentLimit caps how many snapshot rows are fetched from the
 // local index for listing and purge operations.
 const listRecentLimit = 10000
@@ -51,26 +45,6 @@ type SnapshotCreateOptions struct {
 	Snapshots     []string // Optional list of snapshot names to process (empty = all)
 }
 
-// Validate fails when KeepNewerThan is set without Prune or is not a
-// valid duration. Only the post-backup prune reads KeepNewerThan, after
-// the backup, so the caller checks it before starting one.
-func (opts *SnapshotCreateOptions) Validate() error {
-	if opts.KeepNewerThan == "" {
-		return nil
-	}
-
-	if !opts.Prune {
-		return errKeepNewerThanNeedsPrune
-	}
-
-	_, err := parseDuration(opts.KeepNewerThan)
-	if err != nil {
-		return fmt.Errorf("--keep-newer-than: %w", err)
-	}
-
-	return nil
-}
-
 // CreateSnapshot executes the snapshot creation operation
 func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
 	// config.Load accepts an empty list, since listing, verifying and
@@ -149,7 +123,7 @@ func (v *Vaultik) CreateSnapshot(opts *SnapshotCreateOptions) error {
 	if opts.Prune {
 		err = v.runPostBackupPrune(snapshotNames, opts.KeepNewerThan)
 		if err != nil {
-			return fmt.Errorf("%w: %w", ErrPostBackupPruneFailed, err)
+			return fmt.Errorf("post-backup prune: %w", err)
 		}
 	}