Parallelize the walk and commit per operand

Replace the single-goroutine WalkDir traversal with a per-directory
worker pool: workers read directories concurrently and lstat entries
while each directory is fresh in cache, recording size and mtime
during the walk. This folds the separate stat pass away (halving
metadata I/O per run) and overlaps metadata latency, which dominated
on busy pools — a sequential walk of a ~22M-file tree was observed
taking over 4 hours.

Each PATH operand now loads its scope, walks, hashes, and commits in
its own transaction, so an interrupted scan keeps every operand
completed so far; a later overlapping operand sees the records
committed by earlier ones and reuses them unchanged.

TODO.md

@@ -14,16 +14,19 @@
 
 # Next Step
 
-- parallel walk (branch `parallel-walk`): the walk pass is a single
+- convert Makefile targets to scripts-to-rule-them-all `script/`
-  goroutine and takes hours at ~20M files on a busy pool (observed:
+  entrypoints like the other managed repos
-  22M files in 4h on a ZFS server); make it a per-directory
-  worker-pool traversal that records size/mtime during the walk
-  (folding away the separate stat pass, halving metadata I/O), and
-  commit each `PATH` operand in its own transaction so an interrupted
-  scan keeps completed operands
 
 # Completed Steps
 
+- parallel walk (2026-07-24, branch `parallel-walk`): the walk pass
+  was a single goroutine and took hours at ~20M files on a busy pool
+  (observed: 22M files in 4h on a ZFS server); it is now a
+  per-directory worker-pool traversal that records size/mtime during
+  the walk (folding away the separate stat pass, halving metadata
+  I/O), and each `PATH` operand commits in its own transaction so an
+  interrupted scan keeps completed operands
+
 - persistent scan database (2026-07-24, branch `persistent-database`):
   `scan` now maintains a SQLite database (`modernc.org/sqlite`, pure
   Go, cgo stays disabled) keyed by absolute path that survives between
@@ -49,8 +52,6 @@
 
 # Future Steps
 
-- convert Makefile targets to scripts-to-rule-them-all `script/`
-  entrypoints like the other managed repos
 - possible later features (explicitly out of scope per README):
   full-content verification of candidates, removal-script helpers
 

scan.go

@@ -11,6 +11,7 @@ import (
 	"path/filepath"
 	"slices"
 	"strings"
+	"sync"
 	"syscall"
 )
 
@@ -21,8 +22,8 @@ const chunk = 1024
 // and hash worker pools.
 const workQueueDepth = 1024
 
-// errNotRegular reports a path that stopped being a regular file
+// errNotRegular reports a path whose type changed between the
-// between the walk and stat passes.
+// directory read and its lstat.
 var errNotRegular = errors.New("no longer a regular file")
 
 // fileRec carries one file between the stat and hash passes.
@@ -98,27 +99,42 @@ type scanStats struct {
 	skipped   int
 }
 
-// syncScan synchronizes the database with the filesystem under roots:
+// syncScan synchronizes the database with the filesystem under roots.
-// walk and stat everything, hash only new or changed files, and apply
+// Operands are processed in order, each one walked, hashed, and
-// the resulting record insertions, updates, and deletions in a single
+// committed independently, so an interrupted scan keeps every operand
-// transaction. Records outside the roots are never touched.
+// completed so far. Records outside the roots are never touched.
 func syncScan(db *sql.DB, roots []string, workers int,
 	oneFS bool,
 ) (scanStats, error) {
 	var st scanStats
 
-	existing, err := loadScopedRows(db, roots)
+	for _, root := range roots {
-	if err != nil {
+		err := syncRoot(db, root, workers, oneFS, &st)
-		return st, err
+		if err != nil {
+			return st, err
+		}
 	}
 
-	paths, walkErrs := walkPass(roots, oneFS)
+	return st, nil
-	recs, statErrs := statPass(uniquePaths(paths), workers)
+}
-	toHash, unchanged := partitionChanged(recs, existing)
+
+// syncRoot walks one PATH operand, hashes its new and changed files,
+// and commits the operand's record insertions, updates, and deletions
+// in a single transaction.
+func syncRoot(db *sql.DB, root string, workers int, oneFS bool,
+	st *scanStats,
+) error {
+	existing, err := loadScopedRows(db, root)
+	if err != nil {
+		return err
+	}
+
+	walked, walkErrs := walkPass(root, oneFS, workers)
+	toHash, unchanged := partitionChanged(walked, existing)
 	hashed, hashErrs := hashPass(toHash, workers)
 
-	st.unchanged = len(unchanged)
+	st.unchanged += len(unchanged)
-	st.skipped = walkErrs + statErrs + hashErrs
+	st.skipped += walkErrs + hashErrs
 
 	for _, r := range hashed {
 		if _, ok := existing[r.path]; ok {
@@ -129,15 +145,15 @@ func syncScan(db *sql.DB, roots []string, workers int,
 	}
 
 	deletes := collectDeletes(existing, unchanged, hashed)
-	st.removed = len(deletes)
+	st.removed += len(deletes)
 
-	return st, applyPass(db, hashed, deletes)
+	return applyPass(db, hashed, deletes)
 }
 
-// loadScopedRows loads the database records whose paths lie under any
+// loadScopedRows loads the database records whose paths lie under
-// of the scan roots, keyed by path. Records outside the roots belong
+// root, keyed by path. Records outside the scanned operands belong to
-// to other trees and are left untouched by this scan.
+// other trees and are left untouched.
-func loadScopedRows(db *sql.DB, roots []string) (map[string]scanRec, error) {
+func loadScopedRows(db *sql.DB, root string) (map[string]scanRec, error) {
 	all, err := loadFileRows(db)
 	if err != nil {
 		return nil, err
@@ -146,7 +162,7 @@ func loadScopedRows(db *sql.DB, roots []string) (map[string]scanRec, error) {
 	scoped := make(map[string]scanRec)
 
 	for _, r := range all {
-		if underAnyRoot(r.path, roots) {
+		if underRoot(r.path, root) {
 			scoped[r.path] = r
 		}
 	}
@@ -154,18 +170,6 @@ func loadScopedRows(db *sql.DB, roots []string) (map[string]scanRec, error) {
 	return scoped, nil
 }
 
-// underAnyRoot reports whether path is any of the roots or lies under
-// one of them.
-func underAnyRoot(path string, roots []string) bool {
-	for _, root := range roots {
-		if underRoot(path, root) {
-			return true
-		}
-	}
-
-	return false
-}
-
 // underRoot reports whether path is root itself or lies under it. Both
 // must be absolute and lexically clean.
 func underRoot(path, root string) bool {
@@ -181,26 +185,6 @@ func underRoot(path, root string) bool {
 	return strings.HasPrefix(path, prefix)
 }
 
-// uniquePaths deduplicates the walked paths, preserving order.
-// Overlapping operands can reach the same file more than once, but the
-// database keys records by path, so each file is processed once.
-func uniquePaths(paths []string) []string {
-	seen := make(map[string]bool, len(paths))
-	out := make([]string, 0, len(paths))
-
-	for _, p := range paths {
-		if seen[p] {
-			continue
-		}
-
-		seen[p] = true
-
-		out = append(out, p)
-	}
-
-	return out
-}
-
 // partitionChanged splits the stat results into files that must be
 // hashed (new, or changed) and files whose existing records are reused
 // without reading them: a file is unchanged when its statted size
@@ -270,105 +254,247 @@ func applyPass(db *sql.DB, upserts []scanRec, deletes []string) error {
 	return err
 }
 
-// treeWalker carries the walk-pass state shared by all PATH operands.
+// dirJob is one directory awaiting traversal by the walk workers. It
-type treeWalker struct {
+// carries its operand's filesystem device so -x can stop at
-	prog  *progress
+// filesystem boundaries.
-	oneFS bool
+type dirJob struct {
-	paths []string
+	path      string
-	errs  int
+	rootDev   uint64
+	rootDevOK bool
 }
 
-// walkPass enumerates every regular file under each root operand in
+// walkEvent is one walk result delivered to the main goroutine: a
-// order. It never follows symlinks, never descends into directories
+// regular file's stat record, or a warning when fail is set.
-// named .zfs, and warns and continues on any per-path error. With
+type walkEvent struct {
-// oneFS set it never descends into a directory on a different
+	rec  fileRec
-// filesystem than its root operand.
+	warn string
-func walkPass(roots []string, oneFS bool) ([]string, int) {
+	fail bool
-	w := &treeWalker{prog: newProgress("walk", -1), oneFS: oneFS}
-
-	for _, root := range roots {
-		w.walkRoot(root)
-	}
-
-	w.prog.finish()
-
-	return w.paths, w.errs
 }
 
-// walkRoot walks a single PATH operand, appending regular-file paths.
+// walkPass enumerates every regular file under root with a
-func (w *treeWalker) walkRoot(root string) {
+// per-directory worker pool, recording size and mtime from lstat
-	rootDev, rootDevOK := deviceOf(root)
+// while each directory is fresh in cache. It never follows symlinks,
+// never descends into directories named .zfs, and warns and continues
+// on any per-path error. With oneFS set it never descends into a
+// directory on a different filesystem than root.
+func walkPass(root string, oneFS bool, workers int) ([]fileRec, int) {
+	prog := newProgress("walk", -1)
 
-	walkErr := filepath.WalkDir(root, func(p string, d fs.DirEntry, err error) error {
+	recs, initial, errs := seedRoot(root, prog)
-		if err != nil {
+	jobs, subdirs, events := startWalkWorkers(workers, oneFS)
-			w.errs++
 
-			w.prog.warnf("walk %s: %v", p, err)
+	dispatchDirs(initial, jobs, subdirs)
 
-			if d != nil && d.IsDir() {
+	for ev := range events {
-				return filepath.SkipDir
+		if ev.fail {
-			}
+			errs++
 
-			return nil
+			prog.warnf("%s", ev.warn)
+
+			continue
 		}
 
-		if d.IsDir() {
+		recs = append(recs, ev.rec)
-			return w.dirAction(p, d, rootDev, rootDevOK)
+
+		prog.increment()
+	}
+
+	prog.finish()
+
+	return recs, errs
+}
+
+// seedRoot turns the PATH operand into the walk's starting state: a
+// regular-file operand becomes a record directly, a directory operand
+// becomes the initial job, and a symlink or other non-regular operand
+// yields nothing (symlinks are never followed, including as
+// operands).
+func seedRoot(root string, prog *progress) ([]fileRec, []dirJob, int) {
+	fi, err := os.Lstat(root)
+	if err != nil {
+		prog.warnf("walk %s: %v", root, err)
+
+		return nil, nil, 1
+	}
+
+	switch {
+	case fi.IsDir():
+		if filepath.Base(root) == ".zfs" {
+			return nil, nil, 0
+		}
+
+		dev, ok := deviceOfInfo(fi)
+
+		return nil, []dirJob{{path: root, rootDev: dev, rootDevOK: ok}}, 0
+	case fi.Mode().IsRegular():
+		rec := fileRec{path: root, size: fi.Size(), mtime: fi.ModTime().Unix()}
+
+		prog.increment()
+
+		return []fileRec{rec}, nil, 0
+	default:
+		return nil, nil, 0
+	}
+}
+
+// startWalkWorkers starts the walk worker pool. Each worker processes
+// one directory at a time, emitting an event per regular file and
+// handing discovered subdirectories back to the dispatcher; events is
+// closed once every worker has finished.
+func startWalkWorkers(workers int,
+	oneFS bool,
+) (chan dirJob, chan []dirJob, chan walkEvent) {
+	jobs := make(chan dirJob, workQueueDepth)
+	subdirs := make(chan []dirJob, workers)
+	events := make(chan walkEvent, workQueueDepth)
+
+	var wg sync.WaitGroup
+
+	for range workers {
+		wg.Go(func() {
+			for job := range jobs {
+				subdirs <- walkOneDir(job, oneFS, events)
+			}
+		})
+	}
+
+	go func() {
+		wg.Wait()
+		close(events)
+	}()
+
+	return jobs, subdirs, events
+}
+
+// dispatchDirs feeds directory jobs to the walk workers, queueing
+// newly discovered subdirectories (newest first, which keeps the
+// frontier small) until every directory has been processed, then
+// closes jobs.
+func dispatchDirs(initial []dirJob, jobs chan<- dirJob,
+	subdirs <-chan []dirJob,
+) {
+	go func() {
+		queue := slices.Clone(initial)
+		pending := len(queue)
+
+		for pending > 0 {
+			var (
+				out  chan<- dirJob
+				next dirJob
+			)
+
+			if len(queue) > 0 {
+				out = jobs
+				next = queue[len(queue)-1]
+			}
+
+			select {
+			case out <- next:
+				queue = queue[:len(queue)-1]
+			case subs := <-subdirs:
+				pending += len(subs) - 1
+				queue = append(queue, subs...)
+			}
+		}
+
+		close(jobs)
+	}()
+}
+
+// walkOneDir reads one directory, emitting an event per regular-file
+// entry and a warning event per unreadable one, and returns the
+// subdirectories to descend into.
+func walkOneDir(job dirJob, oneFS bool, events chan<- walkEvent) []dirJob {
+	entries, err := os.ReadDir(job.path)
+	if err != nil {
+		events <- walkEvent{
+			warn: fmt.Sprintf("walk %s: %v", job.path, err),
+			fail: true,
+		}
+
+		return nil
+	}
+
+	var subs []dirJob
+
+	for _, e := range entries {
+		p := filepath.Join(job.path, e.Name())
+
+		if e.IsDir() {
+			if sub, ok := subdirJob(p, e, job, oneFS, events); ok {
+				subs = append(subs, sub)
+			}
+
+			continue
 		}
 		// Regular files only: skip symlinks, sockets, FIFOs, and
 		// device nodes.
-		if !d.Type().IsRegular() {
+		if !e.Type().IsRegular() {
-			return nil
+			continue
 		}
 
-		w.paths = append(w.paths, p)
+		events <- fileEvent(p, e)
+	}
 
-		w.prog.increment()
+	return subs
+}
 
-		return nil
+// fileEvent lstats one regular-file directory entry into its walk
-	})
+// event.
-	if walkErr != nil {
+func fileEvent(p string, e fs.DirEntry) walkEvent {
-		fatalf("walk %s: %v", root, walkErr)
+	fi, err := e.Info()
+
+	switch {
+	case err != nil:
+		return walkEvent{
+			warn: fmt.Sprintf("walk %s: %v", p, err),
+			fail: true,
+		}
+	case !fi.Mode().IsRegular():
+		return walkEvent{
+			warn: fmt.Sprintf("walk %s: %v", p, errNotRegular),
+			fail: true,
+		}
+	default:
+		return walkEvent{rec: fileRec{
+			path:  p,
+			size:  fi.Size(),
+			mtime: fi.ModTime().Unix(),
+		}}
 	}
 }
 
-// dirAction decides whether the walk descends into directory p.
+// subdirJob applies the descent rules to directory p: never enter
-func (w *treeWalker) dirAction(p string, d fs.DirEntry, rootDev uint64, rootDevOK bool) error {
+// .zfs (ZFS snapshot pseudo-dirs would list every file once per
-	// ZFS snapshot pseudo-dirs would list every file once per
+// snapshot), and with -x never enter a directory on a different
-	// snapshot; never descend.
+// filesystem than its operand.
-	if d.Name() == ".zfs" {
+func subdirJob(p string, e fs.DirEntry, parent dirJob, oneFS bool,
-		return filepath.SkipDir
+	events chan<- walkEvent,
+) (dirJob, bool) {
+	if e.Name() == ".zfs" {
+		return dirJob{}, false
 	}
 
-	if !w.oneFS || !rootDevOK {
+	job := dirJob{path: p, rootDev: parent.rootDev, rootDevOK: parent.rootDevOK}
-		return nil
+	if !oneFS || !parent.rootDevOK {
+		return job, true
 	}
 
-	info, err := d.Info()
+	info, err := e.Info()
 	if err != nil {
-		w.errs++
+		events <- walkEvent{
+			warn: fmt.Sprintf("walk %s: %v", p, err),
+			fail: true,
+		}
 
-		w.prog.warnf("walk %s: %v", p, err)
+		return dirJob{}, false
-
-		return filepath.SkipDir
 	}
 
-	if dev, ok := deviceOfInfo(info); ok && dev != rootDev {
+	if dev, ok := deviceOfInfo(info); ok && dev != parent.rootDev {
-		return filepath.SkipDir
+		return dirJob{}, false
 	}
 
-	return nil
+	return job, true
-}
-
-// deviceOf returns the filesystem device ID of path without following
-// symlinks.
-func deviceOf(path string) (uint64, bool) {
-	fi, err := os.Lstat(path)
-	if err != nil {
-		return 0, false
-	}
-
-	return deviceOfInfo(fi)
 }
 
 // deviceOfInfo extracts the filesystem device ID from a FileInfo, when
@@ -382,72 +508,6 @@ func deviceOfInfo(fi fs.FileInfo) (uint64, bool) {
 	return statDev(st), true
 }
 
-// statPass lstats every collected path in a worker pool, recording size
-// and mtime. Paths that fail to stat (or are no longer regular files)
-// are warned about and dropped.
-func statPass(paths []string, workers int) ([]fileRec, int) {
-	type result struct {
-		rec fileRec
-		err error
-	}
-
-	jobs := make(chan string, workQueueDepth)
-	results := make(chan result, workQueueDepth)
-
-	for range workers {
-		go func() {
-			for p := range jobs {
-				fi, err := os.Lstat(p)
-				switch {
-				case err != nil:
-					results <- result{rec: fileRec{path: p}, err: err}
-				case !fi.Mode().IsRegular():
-					results <- result{
-						rec: fileRec{path: p},
-						err: errNotRegular,
-					}
-				default:
-					results <- result{rec: fileRec{
-						path:  p,
-						size:  fi.Size(),
-						mtime: fi.ModTime().Unix(),
-					}}
-				}
-			}
-		}()
-	}
-
-	go func() {
-		for _, p := range paths {
-			jobs <- p
-		}
-
-		close(jobs)
-	}()
-
-	prog := newProgress("stat", int64(len(paths)))
-
-	var errs int
-
-	recs := make([]fileRec, 0, len(paths))
-	for range paths {
-		r := <-results
-		if r.err != nil {
-			errs++
-
-			prog.warnf("stat %s: %v", r.rec.path, r.err)
-		} else {
-			recs = append(recs, r.rec)
-		}
-
-		prog.increment()
-	}
-
-	prog.finish()
-
-	return recs, errs
-}
-
 // hashResult carries one file's head/tail hashes (or the error that
 // prevented hashing it) from the hash workers to the main goroutine.
 type hashResult struct {

scan_test.go

@@ -5,6 +5,7 @@ import (
 	"crypto/sha256"
 	"database/sql"
 	"encoding/hex"
+	"fmt"
 	"os"
 	"path/filepath"
 	"slices"
@@ -109,6 +110,33 @@ func TestHashHeadTailErrors(t *testing.T) {
 	}
 }
 
+// walkedPaths returns the sorted paths of walked records.
+func walkedPaths(recs []fileRec) []string {
+	paths := make([]string, 0, len(recs))
+	for _, r := range recs {
+		paths = append(paths, r.path)
+	}
+
+	slices.Sort(paths)
+
+	return paths
+}
+
+// walkedByPath finds the walked record with the given path.
+func walkedByPath(t *testing.T, recs []fileRec, path string) fileRec {
+	t.Helper()
+
+	for _, r := range recs {
+		if r.path == path {
+			return r
+		}
+	}
+
+	t.Fatalf("no walked record for %q", path)
+
+	return fileRec{}
+}
+
 func TestWalkPass(t *testing.T) {
 	t.Parallel()
 
@@ -130,37 +158,46 @@ func TestWalkPass(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	paths, errs := walkPass([]string{dir}, false)
+	recs, errs := walkPass(dir, false, 4)
 	if errs != 0 {
 		t.Fatalf("errs = %d, want 0", errs)
 	}
 
-	slices.Sort(paths)
+	if got := walkedPaths(recs); !slices.Equal(got, want) {
+		t.Fatalf("paths = %q, want %q", got, want)
+	}
 
-	if !slices.Equal(paths, want) {
+	// The walk records lstat sizes and mtimes.
-		t.Fatalf("paths = %q, want %q", paths, want)
+	if r := walkedByPath(t, recs, want[0]); r.size != 1 || r.mtime <= 0 {
+		t.Fatalf("rec = %+v, want size 1 and a positive mtime", r)
 	}
 }
 
-func TestWalkPassMultipleRoots(t *testing.T) {
+func TestWalkPassDeepAndWide(t *testing.T) {
 	t.Parallel()
 
-	rootA := t.TempDir()
+	// Exercise the dispatcher with more directories than workers and
-	rootB := t.TempDir()
+	// with nesting deeper than the worker count.
-	want := []string{
+	dir := t.TempDir()
-		writeFile(t, rootA, "a1", []byte("1")),
+	deep := "deep" + strings.Repeat("/d", 30)
-		writeFile(t, rootA, "sub/a2", []byte("2")),
+
-		writeFile(t, rootB, "b1", []byte("3")),
+	want := make([]string, 0, 41)
+	want = append(want, writeFile(t, dir, deep+"/f", []byte("x")))
+
+	for i := range 40 {
+		want = append(want, writeFile(t, dir,
+			fmt.Sprintf("wide/%02d/f", i), []byte("y")))
 	}
 
-	paths, errs := walkPass([]string{rootA, rootB}, false)
+	slices.Sort(want)
+
+	recs, errs := walkPass(dir, false, 8)
 	if errs != 0 {
 		t.Fatalf("errs = %d, want 0", errs)
 	}
 
-	// Operands are walked in the order given.
+	if got := walkedPaths(recs); !slices.Equal(got, want) {
-	if !slices.Equal(paths, want) {
+		t.Fatalf("walked %d paths, want %d", len(got), len(want))
-		t.Fatalf("paths = %q, want %q", paths, want)
 	}
 }
 
@@ -178,15 +215,15 @@ func TestWalkPassFileAndSymlinkOperands(t *testing.T) {
 	}
 
 	// A regular-file operand is emitted as itself.
-	paths, errs := walkPass([]string{f}, false)
+	recs, errs := walkPass(f, false, 2)
-	if errs != 0 || !slices.Equal(paths, []string{f}) {
+	if errs != 0 || len(recs) != 1 || recs[0].path != f || recs[0].size != 4 {
-		t.Fatalf("file operand: paths = %q, errs = %d", paths, errs)
+		t.Fatalf("file operand: recs = %+v, errs = %d", recs, errs)
 	}
 
 	// A symlink operand is not followed and yields nothing.
-	paths, errs = walkPass([]string{link}, false)
+	recs, errs = walkPass(link, false, 2)
-	if errs != 0 || len(paths) != 0 {
+	if errs != 0 || len(recs) != 0 {
-		t.Fatalf("symlink operand: paths = %q, errs = %d", paths, errs)
+		t.Fatalf("symlink operand: recs = %+v, errs = %d", recs, errs)
 	}
 }
 
@@ -200,58 +237,37 @@ func TestWalkPassOneFilesystemSameFS(t *testing.T) {
 		writeFile(t, dir, "sub/deep/b", []byte("b")),
 	}
 
-	paths, errs := walkPass([]string{dir}, true)
+	recs, errs := walkPass(dir, true, 4)
 	if errs != 0 {
 		t.Fatalf("errs = %d, want 0", errs)
 	}
 
-	slices.Sort(paths)
+	if got := walkedPaths(recs); !slices.Equal(got, want) {
-
+		t.Fatalf("paths = %q, want %q", got, want)
-	if !slices.Equal(paths, want) {
-		t.Fatalf("paths = %q, want %q", paths, want)
 	}
 }
 
-func TestDeviceOf(t *testing.T) {
+func TestDeviceOfInfo(t *testing.T) {
 	t.Parallel()
 
 	dir := t.TempDir()
 
-	dev1, ok1 := deviceOf(dir)
+	fi1, err := os.Lstat(dir)
+	if err != nil {
+		t.Fatal(err)
+	}
 
-	dev2, ok2 := deviceOf(dir)
+	fi2, err := os.Lstat(dir)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	dev1, ok1 := deviceOfInfo(fi1)
+
+	dev2, ok2 := deviceOfInfo(fi2)
 	if !ok1 || !ok2 || dev1 != dev2 {
-		t.Fatalf("deviceOf unstable: %d/%v vs %d/%v", dev1, ok1, dev2, ok2)
+		t.Fatalf("deviceOfInfo unstable: %d/%v vs %d/%v",
-	}
+			dev1, ok1, dev2, ok2)
-
-	if _, ok := deviceOf(filepath.Join(dir, "missing")); ok {
-		t.Fatal("deviceOf reported ok for a missing path")
-	}
-}
-
-func TestStatPass(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	a := writeFile(t, dir, "a", pattern(1, 10))
-	b := writeFile(t, dir, "b", pattern(2, 20))
-	missing := filepath.Join(dir, "vanished")
-
-	recs, errs := statPass([]string{a, b, missing}, 2)
-	if errs != 1 {
-		t.Fatalf("errs = %d, want 1 for the vanished file", errs)
-	}
-
-	slices.SortFunc(recs, func(x, y fileRec) int {
-		return strings.Compare(x.path, y.path)
-	})
-
-	if len(recs) != 2 || recs[0].size != 10 || recs[1].size != 20 {
-		t.Fatalf("recs = %+v, want sizes 10 and 20", recs)
-	}
-
-	if recs[0].mtime <= 0 || recs[1].mtime <= 0 {
-		t.Fatalf("recs = %+v, want positive mtimes", recs)
 	}
 }
 
@@ -607,10 +623,17 @@ func TestSyncScanOverlappingRoots(t *testing.T) {
 
 	writeFile(t, dir, "sub/f", pattern(1, 10))
 
-	// A file reachable via two overlapping operands yields one record.
+	// A file reachable via two overlapping operands yields one
+	// record: the second operand sees the rows the first operand
+	// committed and reuses them unchanged, which also proves each
+	// operand commits before the next starts.
 	st := syncTree(t, db, dir, filepath.Join(dir, "sub"))
-	if st.added != 1 {
+	if st != (scanStats{added: 1, unchanged: 1}) {
-		t.Fatalf("stats = %+v, want 1 added", st)
+		t.Fatalf("stats = %+v, want 1 added 1 unchanged", st)
+	}
+
+	if got := recordPaths(dbRecords(t, db)); len(got) != 1 {
+		t.Fatalf("records = %q, want exactly one", got)
 	}
 }
 
@@ -659,14 +682,3 @@ func TestUnderRoot(t *testing.T) {
 		}
 	}
 }
-
-func TestUniquePaths(t *testing.T) {
-	t.Parallel()
-
-	got := uniquePaths([]string{"/a", "/b", "/a", "/c", "/b"})
-
-	want := []string{"/a", "/b", "/c"}
-	if !slices.Equal(got, want) {
-		t.Fatalf("uniquePaths = %q, want %q", got, want)
-	}
-}