Stop a stalled blob read when restore or deep verify is interrupted (closes #325)

Restore and deep verify looked for a cancel only between blobs, and the
file backend's reader ignores the context. A blob read stalled on a
slow USB stick or network share outlasted the 30-second shutdown
timeout, so the process exited before removing the decrypted snapshot
database and blob cache from the temp directory.

FetchBlob, through which both read every blob, now closes the storage
reader as soon as the context is cancelled, ending a blocked read on
any backend; Read then returns the context's error, not the closed
reader's.

Limitation: a read stuck in the kernel that closing cannot interrupt,
such as one on an unresponsive hard NFS mount, still cannot be stopped.

Model: opus-5-5

internal/cli/config.go

@@ -251,12 +251,6 @@ func NewConfigCommand() *cobra.Command {
 		Use:   "config",
 		Short: "Manage the configuration file",
 		Long:  "Commands for creating, editing, and querying the vaultik config file.",
-		// cobra checks Args only on a command that has a Run: without
-		// one, a mistyped subcommand printed help and exited 0.
-		Args: cobra.NoArgs,
-		Run: func(cmd *cobra.Command, _ []string) {
-			_ = cmd.Help()
-		},
 	}
 
 	cmd.AddCommand(newConfigInitCommand())

internal/cli/database.go

@@ -15,12 +15,6 @@ func NewDatabaseCommand() *cobra.Command {
 		Use:   "database",
 		Short: "Manage the local state database",
 		Long:  `Commands for managing the local SQLite state database.`,
-		// cobra checks Args only on a command that has a Run: without
-		// one, a mistyped subcommand printed help and exited 0.
-		Args: cobra.NoArgs,
-		Run: func(cmd *cobra.Command, _ []string) {
-			_ = cmd.Help()
-		},
 	}
 
 	cmd.AddCommand(

internal/cli/entry_unknown_subcommand_test.go

@@ -1,43 +0,0 @@
-package cli //nolint:testpackage // shares runEntry and the command-word constants
-
-import (
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-)
-
-// TestEntryGroupRejectsUnknownSubcommand runs each group command with a
-// mistyped subcommand, as a crontab line might carry one. It must fail
-// with exit 1 and name the word, as `vaultik bogus` does at the top
-// level, instead of printing the group's help and exiting 0 having done
-// nothing. The group name alone still prints its help.
-//
-//nolint:paralleltest // replaces os.Args, os.Stdout and os.Stderr
-func TestEntryGroupRejectsUnknownSubcommand(t *testing.T) {
-	for _, testCase := range []struct {
-		group    string
-		mistyped string
-	}{
-		{group: cmdSnapshot, mistyped: "craete"},
-		{group: "config", mistyped: "inti"},
-		{group: cmdRemote, mistyped: "ifno"},
-		{group: "database", mistyped: "delte"},
-		{group: "completion", mistyped: "nosuchshell"},
-	} {
-		t.Run(testCase.group, func(t *testing.T) {
-			code, stdout, stderr := runEntry(t,
-				testCase.group, testCase.mistyped)
-
-			assert.Equal(t, 1, code)
-			assert.Empty(t, stdout)
-			assert.Contains(t, stderr,
-				`unknown command "`+testCase.mistyped+`"`)
-
-			code, stdout, _ = runEntry(t, testCase.group)
-
-			assert.Equal(t, 0, code)
-			assert.Contains(t, stdout,
-				programName+" "+testCase.group+" [command]")
-		})
-	}
-}

internal/cli/remote.go

@@ -18,12 +18,6 @@ func NewRemoteCommand() *cobra.Command {
 		Use:   "remote",
 		Short: "Remote storage management commands",
 		Long:  "Commands for inspecting and managing remote storage",
-		// cobra checks Args only on a command that has a Run: without
-		// one, a mistyped subcommand printed help and exited 0.
-		Args: cobra.NoArgs,
-		Run: func(cmd *cobra.Command, _ []string) {
-			_ = cmd.Help()
-		},
 	}
 
 	// Add subcommands

internal/cli/root.go

@@ -74,21 +74,6 @@ on the source system.`,
 		NewDatabaseCommand(),
 	)
 
-	// cobra adds the completion command only when Execute runs, and with
-	// no Run, so it skipped its own cobra.NoArgs and a mistyped shell name
-	// printed help and exited 0. Adding it here lets it have a Run. Its
-	// scripts go to os.Stdout as it is now: a later SetOut does not
-	// redirect them.
-	cmd.InitDefaultCompletionCmd()
-
-	for _, sub := range cmd.Commands() {
-		if sub.Name() == "completion" {
-			sub.Run = func(completion *cobra.Command, _ []string) {
-				_ = completion.Help()
-			}
-		}
-	}
-
 	return cmd
 }
 

internal/cli/snapshot.go

@@ -41,12 +41,6 @@ func NewSnapshotCommand() *cobra.Command {
 		Use:   "snapshot",
 		Short: "Snapshot management commands",
 		Long:  "Commands for creating, listing, and managing snapshots",
-		// cobra checks Args only on a command that has a Run: without
-		// one, a mistyped subcommand printed help and exited 0.
-		Args: cobra.NoArgs,
-		Run: func(cmd *cobra.Command, _ []string) {
-			_ = cmd.Help()
-		},
 	}
 
 	// Add subcommands

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"
 
@@ -236,125 +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 return the body's error alone, without that rollback.
-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)
-	}
-
-	if errors.Is(err, sql.ErrTxDone) {
-		t.Fatalf("the already-done rollback was reported: %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/exclude_test.go

@@ -531,50 +531,3 @@ func TestExcludePatterns_UnanchoredPatternFile(t *testing.T) {
 	require.Equal(t, 1, result.FilesScanned,
 		"Unanchored pattern for file should match anywhere")
 }
-
-func TestExcludePatterns_DoubleStarDirectoryAtEveryDepth(t *testing.T) {
-	t.Parallel()
-
-	// As in gitignore, a leading **/ also matches directly under the source dir
-	fs := setupAnchoredTestFS(t)
-
-	scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/projectname"})
-	defer cleanup()
-
-	ctx := context.Background()
-	createSnapshotRecord(ctx, t, repos, "test-snapshot")
-
-	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
-	require.NoError(t, err)
-
-	// **/projectname should exclude BOTH:
-	// - /backup/projectname/file.txt
-	// - /backup/otherproject/projectname/file.txt
-	// Total files: 4, excluded: 2
-	require.Equal(t, 2, result.FilesScanned,
-		"**/ directory pattern should match at the top level and nested")
-}
-
-func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
-	t.Parallel()
-
-	// As in gitignore, a leading **/ also matches directly under the source dir
-	fs := setupAnchoredTestFS(t)
-
-	scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/*.txt"})
-	defer cleanup()
-
-	ctx := context.Background()
-	createSnapshotRecord(ctx, t, repos, "test-snapshot")
-
-	result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
-	require.NoError(t, err)
-
-	// **/*.txt should exclude ALL .txt files:
-	// - /backup/file.txt
-	// - /backup/projectname/file.txt
-	// - /backup/otherproject/projectname/file.txt
-	// Total files: 4, excluded: 3
-	require.Equal(t, 1, result.FilesScanned,
-		"**/ file pattern should match at the top level and nested")
-}

internal/snapshot/scanner.go

@@ -2018,14 +2018,6 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
 		// Remove trailing slash if present (directory indicator)
 		pattern = strings.TrimSuffix(pattern, "/")
 
-		// A leading "**/" demands a "/" before the name and so misses an
-		// entry directly under the source path. An unanchored pattern
-		// already matches at every depth, so drop the prefix: as in
-		// gitignore, "**/x" then also matches a top-level "x".
-		if !anchored {
-			pattern = strings.TrimPrefix(pattern, "**/")
-		}
-
 		// Compile the glob pattern
 		// For patterns without path separators, we need to match them as components
 		// e.g., ".git" should match ".git" anywhere in the path

internal/vaultik/blob_fetch.go

@@ -103,6 +103,8 @@ func (v *Vaultik) FetchAndDecryptBlob(
 }
 
 // FetchBlob downloads a blob and returns a reader for the encrypted data.
+// The reader is closed as soon as ctx is cancelled, which ends a read
+// blocked inside it.
 func (v *Vaultik) FetchBlob(
 	ctx context.Context, blobHash string,
 ) (io.ReadCloser, error) {
@@ -120,5 +122,47 @@ func (v *Vaultik) FetchBlob(
 		return nil, fmt.Errorf("downloading blob %s: %w", shortHash(blobHash), err)
 	}
 
-	return rc, nil
+	return newCloseOnCancelReader(ctx, rc), nil
+}
+
+// closeOnCancelReader closes the reader it wraps when ctx is cancelled.
+// Not every backend's reader stops on cancel by itself (the file
+// backend's does not), and a read stalled on a slow or hung source would
+// otherwise outlast the shutdown timeout, so the process would exit
+// before restore or deep verify removed its decrypted temporary files.
+type closeOnCancelReader struct {
+	io.ReadCloser
+
+	ctx  context.Context //nolint:containedctx // Read reports its error
+	stop func() bool
+}
+
+func newCloseOnCancelReader(
+	ctx context.Context, rc io.ReadCloser,
+) *closeOnCancelReader {
+	return &closeOnCancelReader{
+		ReadCloser: rc,
+		ctx:        ctx,
+		stop:       context.AfterFunc(ctx, func() { _ = rc.Close() }),
+	}
+}
+
+// Read returns the context's error, not the closed reader's, once ctx
+// has been cancelled.
+func (r *closeOnCancelReader) Read(p []byte) (int, error) {
+	n, err := r.ReadCloser.Read(p)
+	if err != nil && r.ctx.Err() != nil {
+		return n, r.ctx.Err()
+	}
+
+	return n, err
+}
+
+// Close closes the wrapped reader, unless the cancel already closed it.
+func (r *closeOnCancelReader) Close() error {
+	if !r.stop() {
+		return nil
+	}
+
+	return r.ReadCloser.Close()
 }

internal/vaultik/restore_interrupt_test.go

@@ -142,14 +142,14 @@ func TestRestoreCleansTempDirOnInterrupt(t *testing.T) {
 }
 
 // scratchEntries returns the vaultik blob-cache and snapshot-database
-// scratch entries currently present in dir.
+// scratch entries (restore's and deep verify's) currently present in dir.
 func scratchEntries(t *testing.T, dir string) []string {
 	t.Helper()
 
 	var matches []string
 
 	for _, pattern := range []string{
-		"vaultik-blobcache-*", "vaultik-restore-*",
+		"vaultik-blobcache-*", "vaultik-restore-*", "vaultik-verify-*",
 	} {
 		found, err := filepath.Glob(filepath.Join(dir, pattern))
 		require.NoError(t, err)
@@ -206,3 +206,119 @@ func TestRestoreSkipErrorsCancelDuringBlobDownload(t *testing.T) {
 	assert.NotContains(t, out.String(), srcPath,
 		"the cancel was reported as a failed file")
 }
+
+// stallingBlobStorer wraps a Storer so that every blob download hands
+// over the first half of the blob and then stalls, ignoring the context,
+// as a file:// blob on a hung USB stick or network share does. Only
+// closing the returned reader ends the stall.
+type stallingBlobStorer struct {
+	storage.Storer
+
+	once    sync.Once
+	stalled chan struct{}
+}
+
+func newStallingBlobStorer(inner storage.Storer) *stallingBlobStorer {
+	return &stallingBlobStorer{Storer: inner, stalled: make(chan struct{})}
+}
+
+func (s *stallingBlobStorer) Get(
+	ctx context.Context, key string,
+) (io.ReadCloser, error) {
+	rc, err := s.Storer.Get(ctx, key)
+	if err != nil || !strings.HasPrefix(key, "blobs/") {
+		return rc, err
+	}
+
+	blob, err := io.ReadAll(rc)
+	_ = rc.Close()
+
+	if err != nil {
+		return nil, err
+	}
+
+	// The writer is never closed, so once the first half has been read
+	// the next Read blocks until the reader is closed.
+	pr, pw := io.Pipe()
+
+	go func() {
+		_, _ = pw.Write(blob[:len(blob)/2])
+
+		s.once.Do(func() { close(s.stalled) })
+	}()
+
+	return pr, nil
+}
+
+// TestInterruptDuringStalledBlobReadCleansTempDir stops a restore and a
+// deep verify while a blob read is stalled on a source that ignores the
+// context. Stopping must end that read, so the operation unwinds and
+// removes its decrypted scratch files well within the shutdown timeout
+// (issue #325).
+//
+// Not parallel: it points TMPDIR at a private directory (via t.Setenv)
+// so it can assert on exactly the scratch files the operation created.
+func TestInterruptDuringStalledBlobReadCleansTempDir(t *testing.T) {
+	log.Initialize(log.Config{})
+
+	operations := map[string]func(v *Vaultik, snapshotID, targetDir string) error{
+		"restore": func(v *Vaultik, snapshotID, targetDir string) error {
+			return v.Restore(&RestoreOptions{
+				SnapshotID: snapshotID,
+				TargetDir:  targetDir,
+			})
+		},
+		"deep verify": func(v *Vaultik, snapshotID, _ string) error {
+			return v.RunDeepVerify(snapshotID, &VerifyOptions{Deep: true})
+		},
+	}
+
+	for name, op := range operations {
+		t.Run(name, func(t *testing.T) {
+			fs := afero.NewOsFs()
+			root := t.TempDir()
+
+			// Random content, so the blob stays large enough to stall
+			// part-way through its compressed, encrypted body.
+			cfg, storer, snapshotID, _ := backupOneFile(context.Background(),
+				t, fs, root, "a.bin", randomBytes(t, 256*1024), 0o644)
+
+			scratch := filepath.Join(root, "scratch")
+			require.NoError(t, fs.MkdirAll(scratch, 0o755))
+			t.Setenv("TMPDIR", scratch)
+
+			stalling := newStallingBlobStorer(storer)
+
+			ctx, cancel := context.WithCancel(context.Background())
+			defer cancel()
+
+			v := newRestoreVaultik(ctx, cfg, stalling, fs)
+			v.cancel = cancel
+
+			var opErr error
+
+			stop := v.StartOperation(func() {
+				opErr = op(v, snapshotID, filepath.Join(root, "restored"))
+			})
+
+			select {
+			case <-stalling.stalled:
+			case <-time.After(30 * time.Second):
+				t.Fatal("the operation never reached a blob read")
+			}
+
+			require.NotEmpty(t, scratchEntries(t, scratch),
+				"expected decrypted scratch files to exist mid-read")
+
+			stopCtx, stopCancel := context.WithTimeout(
+				context.Background(), 10*time.Second)
+			defer stopCancel()
+
+			require.True(t, stop(stopCtx),
+				"stop timed out; the stalled blob read was not interrupted")
+			require.ErrorIs(t, opErr, context.Canceled)
+			require.Empty(t, scratchEntries(t, scratch),
+				"decrypted scratch files remained after the interrupt")
+		})
+	}
+}