Skip removed paths silently and fix the progress line (closes #133)

A path removed while the scan runs gets no warning and no skipped
count, in the walk or the hash phase. If the first of several hard
links is gone, the next is read. Any other error is still warned about.

On a terminal every display is the library's spinner, then the line. A
phase with an exact total ends the padded line with its percent and a
bar at a fixed column. sfdupes draws that bar: the library shows no
spinner beside its own.

The time remaining is labelled remain, not eta.

Judgement call: an operand removed after the scan starts is passed over
silently too.
Deviation: README's 80-column promise for stalled lines is narrowed to
its example.

Model: opus-5-5

db.go

@@ -47,15 +47,14 @@ const dbFilePerm = 0o644
 const lockFilePerm = 0o600
 
 // createTableSQL is the schema applied to a fresh database. Paths are
-// BLOBs because Unix paths are raw bytes, not guaranteed UTF-8.
+// BLOBs because Unix paths are raw bytes, not guaranteed UTF-8. mtime
-// disk_size holds the bytes the file takes on disk. mtime holds whole
+// holds whole Unix seconds and mtime_nsec the nanoseconds within that
-// Unix seconds and mtime_nsec the nanoseconds within that second. head,
+// second. head, tail and content each hold the raw 32 bytes of a
-// tail and content each hold the raw 32 bytes of a SHA-256.
+// SHA-256.
 const createTableSQL = `
 CREATE TABLE files (
     path       BLOB PRIMARY KEY,
     size       INTEGER NOT NULL,
-    disk_size  INTEGER NOT NULL,
     mtime      INTEGER NOT NULL,
     mtime_nsec INTEGER NOT NULL,
     head       BLOB NOT NULL,
@@ -70,59 +69,14 @@ const createIndexSQL = `
 CREATE INDEX files_signature ON files (size, head, tail, content)
 `
 
-// createTotalsSQL creates the totals table, which holds one row: the
-// number of records and the sizes of all records added up. Counting
-// them over files would read every record. The three triggers below
-// keep the row current, in the transaction of each change to files.
-const createTotalsSQL = `
-CREATE TABLE totals (
-    records INTEGER NOT NULL,
-    size    INTEGER NOT NULL
-)
-`
-
-// insertTotalsSQL adds the one row of totals, for an empty files table.
-const insertTotalsSQL = `
-INSERT INTO totals (records, size) VALUES (0, 0)
-`
-
-// totalsAfterInsertSQL counts each inserted record into totals.
-const totalsAfterInsertSQL = `
-CREATE TRIGGER totals_after_insert AFTER INSERT ON files BEGIN
-    UPDATE totals SET records = records + 1, size = size + NEW.size;
-END
-`
-
-// totalsAfterDeleteSQL takes each deleted record out of totals.
-const totalsAfterDeleteSQL = `
-CREATE TRIGGER totals_after_delete AFTER DELETE ON files BEGIN
-    UPDATE totals SET records = records - 1, size = size - OLD.size;
-END
-`
-
-// totalsAfterUpdateSQL replaces a record's old size in totals with its
-// new one. scan's upsert of an existing record is such an update.
-const totalsAfterUpdateSQL = `
-CREATE TRIGGER totals_after_update AFTER UPDATE OF size ON files BEGIN
-    UPDATE totals SET size = size + NEW.size - OLD.size;
-END
-`
-
-// recordCountSQL reads the number of records from totals.
-const recordCountSQL = `
-SELECT records FROM totals
-`
-
 // upsertSQL inserts one file record, replacing any existing record for
 // the same path.
 const upsertSQL = `
-INSERT INTO files (
+INSERT INTO files (path, size, mtime, mtime_nsec, head, tail, content)
-    path, size, disk_size, mtime, mtime_nsec, head, tail, content
+VALUES (?, ?, ?, ?, ?, ?, ?)
-)
-VALUES (?, ?, ?, ?, ?, ?, ?, ?)
 ON CONFLICT (path) DO UPDATE SET
-    size = excluded.size, disk_size = excluded.disk_size,
+    size = excluded.size, mtime = excluded.mtime,
-    mtime = excluded.mtime, mtime_nsec = excluded.mtime_nsec,
+    mtime_nsec = excluded.mtime_nsec,
     head = excluded.head, tail = excluded.tail,
     content = excluded.content
 `
@@ -196,14 +150,9 @@ func createDatabaseDirectory(path string) error {
 // scanParams are the connection parameters for scan: read-write, with
 // WAL journaling and a busy timeout, so a report can run while a cron
 // scan is in progress. closeScanDatabase leaves WAL mode again.
-//
-// Each write to files fires a trigger, so SQLite keeps a statement
-// journal for it. temp_store(MEMORY) keeps that journal in memory,
-// which costs far less than a temporary file.
 const scanParams = "_pragma=busy_timeout(10000)" +
 	"&_pragma=journal_mode(WAL)" +
-	"&_pragma=synchronous(NORMAL)" +
+	"&_pragma=synchronous(NORMAL)"
-	"&_pragma=temp_store(MEMORY)"
 
 // reportParams are the connection parameters for report, trees and
 // info: read-only, with the same busy timeout. They set no journal
@@ -477,14 +426,14 @@ func createSchema(ctx context.Context, db *sql.DB) error {
 
 	defer func() { _ = tx.Rollback() }()
 
-	for _, stmt := range []string{
+	_, err = tx.ExecContext(ctx, createTableSQL)
-		createTableSQL, createIndexSQL, createTotalsSQL, insertTotalsSQL,
+	if err != nil {
-		totalsAfterInsertSQL, totalsAfterDeleteSQL, totalsAfterUpdateSQL,
+		return fmt.Errorf("create schema: %w", err)
-	} {
+	}
-		_, err = tx.ExecContext(ctx, stmt)
+
-		if err != nil {
+	_, err = tx.ExecContext(ctx, createIndexSQL)
-			return fmt.Errorf("create schema: %w", err)
+	if err != nil {
-		}
+		return fmt.Errorf("create schema: %w", err)
 	}
 
 	_, err = tx.ExecContext(ctx,
@@ -531,7 +480,7 @@ func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
 
 	var n int64
 
-	err = tx.QueryRowContext(ctx, recordCountSQL).Scan(&n)
+	err = tx.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
 	if err != nil {
 		return fmt.Errorf("count records: %w", err)
 	}
@@ -539,8 +488,8 @@ func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
 	total(n)
 
 	rows, err := tx.QueryContext(ctx,
-		"SELECT path, size, disk_size, mtime, mtime_nsec, head, tail, "+
+		"SELECT path, size, mtime, mtime_nsec, head, tail, content "+
-			"content FROM files ORDER BY path")
+			"FROM files ORDER BY path")
 	if err != nil {
 		return fmt.Errorf("read records: %w", err)
 	}
@@ -554,8 +503,7 @@ func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
 			r                         scanRec
 		)
 
-		err = rows.Scan(&path, &r.size, &r.diskSize, &sec, &nsec,
+		err = rows.Scan(&path, &r.size, &sec, &nsec, &head, &tail, &content)
-			&head, &tail, &content)
 		if err != nil {
 			return fmt.Errorf("read record: %w", err)
 		}
@@ -590,11 +538,10 @@ ORDER BY size DESC, head DESC, tail DESC, content DESC
 `
 
 // loadSignatureRows gives total the number of records, then streams
-// every record's signature and path to fn, without its mtime or its
+// every record's signature and path to fn, without its mtime, in the
-// disk_size, in the order of signatureRowsSQL. The count and the
+// order of signatureRowsSQL. The count and the records are read in one
-// records are read in one transaction, so they agree while a scan is
+// transaction, so they agree while a scan is committing. An error from
-// committing. An error from fn stops the reading and is returned as it
+// fn stops the reading and is returned as it is.
-// is.
 func loadSignatureRows(ctx context.Context, db *sql.DB,
 	total func(n int64), fn func(r scanRec) error,
 ) error {
@@ -609,7 +556,7 @@ func loadSignatureRows(ctx context.Context, db *sql.DB,
 
 	var n int64
 
-	err = tx.QueryRowContext(ctx, recordCountSQL).Scan(&n)
+	err = tx.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
 	if err != nil {
 		return fmt.Errorf("count records: %w", err)
 	}
@@ -675,7 +622,7 @@ func (r *scanRec) setHashes(head, tail, content []byte) error {
 func countRecords(ctx context.Context, db *sql.DB) (int64, error) {
 	var n int64
 
-	err := db.QueryRowContext(ctx, recordCountSQL).Scan(&n)
+	err := db.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
 	if err != nil {
 		return 0, fmt.Errorf("count records: %w", err)
 	}
@@ -683,10 +630,12 @@ func countRecords(ctx context.Context, db *sql.DB) (int64, error) {
 	return n, nil
 }
 
-// databaseCountsSQL reads the number of records and the sizes of all
+// databaseCountsSQL counts the records and adds up their sizes, in one
-// records added up from totals.
+// pass over the table. A SUM over no rows is NULL, so on an empty table
+// the SUM falls back to 0.
 const databaseCountsSQL = `
-SELECT records, size FROM totals
+SELECT COUNT(*), COALESCE(SUM(size), 0)
+FROM files
 `
 
 // databaseCounts is what info reads from the database: its schema
@@ -729,15 +678,15 @@ func readDatabaseCounts(ctx context.Context,
 	return c, nil
 }
 
-// loadFileMeta streams every record's path, size, disk_size and mtime
+// loadFileMeta streams every record's path, size and mtime to fn. Scan
-// to fn. Scan change detection needs no hash values, and skipping the
+// change detection needs no hash values, and skipping the hash columns
-// hash columns keeps the scan's in-memory index small on
+// keeps the scan's in-memory index small on multi-million-file
-// multi-million-file databases.
+// databases.
 func loadFileMeta(ctx context.Context, db *sql.DB,
-	fn func(path string, m fileMeta),
+	fn func(path string, size int64, mtime time.Time),
 ) error {
 	rows, err := db.QueryContext(ctx,
-		"SELECT path, size, disk_size, mtime, mtime_nsec FROM files")
+		"SELECT path, size, mtime, mtime_nsec FROM files")
 	if err != nil {
 		return fmt.Errorf("read records: %w", err)
 	}
@@ -746,19 +695,16 @@ func loadFileMeta(ctx context.Context, db *sql.DB,
 
 	for rows.Next() {
 		var (
-			path      []byte
+			path            []byte
-			m         fileMeta
+			size, sec, nsec int64
-			sec, nsec int64
 		)
 
-		err = rows.Scan(&path, &m.size, &m.diskSize, &sec, &nsec)
+		err = rows.Scan(&path, &size, &sec, &nsec)
 		if err != nil {
 			return fmt.Errorf("read record: %w", err)
 		}
 
-		m.mtime = time.Unix(sec, nsec)
+		fn(string(path), size, time.Unix(sec, nsec))
-
-		fn(string(path), m)
 	}
 
 	err = rows.Err()
@@ -776,21 +722,21 @@ func loadFileMeta(ctx context.Context, db *sql.DB,
 // WAL small and let concurrent reports observe progress.
 const updateBatchSize = 10000
 
-// applyChanges writes upserts for new and changed files and deletes for
+// applyChanges writes one scan's database changes — upserts for new and
-// vanished ones, in batched transactions. Progress is rendered on prog
+// changed files, deletes for vanished ones — in batched transactions.
-// (one increment per change).
+// Progress is rendered on prog (one increment per change).
 func applyChanges(ctx context.Context, db *sql.DB, upserts []scanRec,
 	deletes []string, prog *progress,
 ) error {
 	for batch := range slices.Chunk(upserts, updateBatchSize) {
-		err := applyBatch(ctx, db, batch, nil, nil, prog)
+		err := applyBatch(ctx, db, batch, nil, prog)
 		if err != nil {
 			return err
 		}
 	}
 
 	for batch := range slices.Chunk(deletes, updateBatchSize) {
-		err := applyBatch(ctx, db, nil, nil, batch, prog)
+		err := applyBatch(ctx, db, nil, batch, prog)
 		if err != nil {
 			return err
 		}
@@ -799,26 +745,10 @@ func applyChanges(ctx context.Context, db *sql.DB, upserts []scanRec,
 	return nil
 }
 
-// applyDiskSizes writes the disk_size of each of recs into its record,
+// applyBatch commits one batch of upserts and deletes in a single
-// in batched transactions, and leaves the rest of the record alone.
+// transaction.
-// Progress is rendered on prog (one increment per record).
-func applyDiskSizes(ctx context.Context, db *sql.DB, recs []fileRec,
-	prog *progress,
-) error {
-	for batch := range slices.Chunk(recs, updateBatchSize) {
-		err := applyBatch(ctx, db, nil, batch, nil, prog)
-		if err != nil {
-			return err
-		}
-	}
-
-	return nil
-}
-
-// applyBatch commits one batch of upserts, disk_size updates and
-// deletes in a single transaction.
 func applyBatch(ctx context.Context, db *sql.DB, upserts []scanRec,
-	diskSizes []fileRec, deletes []string, prog *progress,
+	deletes []string, prog *progress,
 ) error {
 	tx, err := db.BeginTx(ctx, nil)
 	if err != nil {
@@ -832,11 +762,6 @@ func applyBatch(ctx context.Context, db *sql.DB, upserts []scanRec,
 		return err
 	}
 
-	err = execDiskSizes(ctx, tx, diskSizes, prog)
-	if err != nil {
-		return err
-	}
-
 	err = execDeletes(ctx, tx, deletes, prog)
 	if err != nil {
 		return err
@@ -862,7 +787,7 @@ func execUpserts(ctx context.Context, tx *sql.Tx, upserts []scanRec,
 	defer func() { _ = st.Close() }()
 
 	for _, r := range upserts {
-		_, err = st.ExecContext(ctx, []byte(r.path), r.size, r.diskSize,
+		_, err = st.ExecContext(ctx, []byte(r.path), r.size,
 			r.mtime.Unix(), r.mtime.Nanosecond(),
 			r.head[:], r.tail[:], r.content[:])
 		if err != nil {
@@ -875,31 +800,6 @@ func execUpserts(ctx context.Context, tx *sql.Tx, upserts []scanRec,
 	return nil
 }
 
-// execDiskSizes sets the disk_size of the record of each of recs. It
-// does not touch size, so the totals triggers do not fire.
-func execDiskSizes(ctx context.Context, tx *sql.Tx, recs []fileRec,
-	prog *progress,
-) error {
-	st, err := tx.PrepareContext(ctx,
-		"UPDATE files SET disk_size = ? WHERE path = ?")
-	if err != nil {
-		return fmt.Errorf("prepare disk_size update: %w", err)
-	}
-
-	defer func() { _ = st.Close() }()
-
-	for _, r := range recs {
-		_, err = st.ExecContext(ctx, r.diskSize, []byte(r.path))
-		if err != nil {
-			return fmt.Errorf("update disk_size of %s: %w", r.path, err)
-		}
-
-		prog.increment()
-	}
-
-	return nil
-}
-
 // execDeletes removes the records for paths no longer present.
 func execDeletes(ctx context.Context, tx *sql.Tx, deletes []string,
 	prog *progress,

db_test.go

@@ -535,12 +535,17 @@ func TestLoadRowsRefuseWrongSizeHash(t *testing.T) {
 	}
 }
 
-// queryPlan returns the detail of each line of SQLite's EXPLAIN QUERY
+// TestSignatureRowsNeedNoSort checks that SQLite reads signatureRowsSQL
-// PLAN for query.
+// from the files_signature index alone, with nothing to sort: the
-func queryPlan(t *testing.T, db *sql.DB, query string) []string {
+// first record comes at once, so report's read phase counts each
-	t.Helper()
+// record as it comes rather than waiting on SQLite for all of them.
+func TestSignatureRowsNeedNoSort(t *testing.T) {
+	t.Parallel()
 
-	rows, err := db.QueryContext(t.Context(), "EXPLAIN QUERY PLAN "+query)
+	db := openTestDB(t)
+
+	rows, err := db.QueryContext(t.Context(),
+		"EXPLAIN QUERY PLAN "+signatureRowsSQL)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -568,164 +573,12 @@ func queryPlan(t *testing.T, db *sql.DB, query string) []string {
 		t.Fatal(err)
 	}
 
-	return plan
-}
-
-// TestSignatureRowsNeedNoSort checks that SQLite reads signatureRowsSQL
-// from the files_signature index alone, with nothing to sort: the
-// first record comes at once, so report's read phase counts each
-// record as it comes rather than waiting on SQLite for all of them.
-func TestSignatureRowsNeedNoSort(t *testing.T) {
-	t.Parallel()
-
-	db := openTestDB(t)
-
-	plan := queryPlan(t, db, signatureRowsSQL)
-
 	want := []string{"SCAN files USING COVERING INDEX files_signature"}
 	if !slices.Equal(plan, want) {
 		t.Errorf("query plan = %q, want %q", plan, want)
 	}
 }
 
-// TestCountsReadOnlyTotals checks that SQLite answers the queries for
-// the number of records and their total size from the one row of
-// totals. A plan that reads files or its index reads every record.
-func TestCountsReadOnlyTotals(t *testing.T) {
-	t.Parallel()
-
-	db := openTestDB(t)
-
-	for _, query := range []string{recordCountSQL, databaseCountsSQL} {
-		plan := queryPlan(t, db, query)
-
-		want := []string{"SCAN totals"}
-		if !slices.Equal(plan, want) {
-			t.Errorf("query plan of %q = %q, want %q", query, plan, want)
-		}
-	}
-}
-
-// TestCountsComeFromTotals sets the row of totals to numbers that files
-// does not hold, then checks that scan's load phase, the read phases of
-// trees and report, and info each report the numbers from totals.
-func TestCountsComeFromTotals(t *testing.T) {
-	t.Parallel()
-
-	// files is empty, so a count over files gives 0 records of 0 bytes.
-	const records, size = 7, 9000
-
-	db := openTestDB(t)
-
-	_, err := db.ExecContext(t.Context(),
-		"UPDATE totals SET records = ?, size = ?", records, size)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	scanTotal, err := countRecords(t.Context(), db)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	var treesTotal, reportTotal int64
-
-	err = loadFileRows(t.Context(), db,
-		func(n int64) { treesTotal = n }, func(scanRec) {})
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	err = loadSignatureRows(t.Context(), db,
-		func(n int64) { reportTotal = n },
-		func(scanRec) error { return nil })
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	info, err := readDatabaseCounts(t.Context(), db)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	for name, got := range map[string]int64{
-		"scan's load":   scanTotal,
-		"trees' read":   treesTotal,
-		"report's read": reportTotal,
-		"info":          info.records,
-	} {
-		if got != records {
-			t.Errorf("%s: %d records, want %d from totals",
-				name, got, records)
-		}
-	}
-
-	if info.size != size {
-		t.Errorf("info: size %d, want %d from totals", info.size, size)
-	}
-}
-
-// assertTotalsMatchFiles fails unless the row of totals holds the
-// number of records and the sizes of all records added up, as counted
-// over files.
-func assertTotalsMatchFiles(t *testing.T, db *sql.DB) {
-	t.Helper()
-
-	got, err := readDatabaseCounts(t.Context(), db)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	var records, size int64
-
-	err = db.QueryRowContext(t.Context(),
-		"SELECT COUNT(*), COALESCE(SUM(size), 0) FROM files").
-		Scan(&records, &size)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	if got.records != records || got.size != size {
-		t.Errorf("totals = %d records of %d bytes, files holds %d of %d",
-			got.records, got.size, records, size)
-	}
-}
-
-// TestTotalsMatchFiles scans the smoke tree, rescans it after two files
-// change size, and rescans it after two files are removed. After each
-// scan the row of totals must agree with files.
-func TestTotalsMatchFiles(t *testing.T) {
-	t.Parallel()
-
-	dir := buildSmokeTree(t)
-	db := openTestDB(t)
-
-	syncTree(t, db, dir)
-	assertTotalsMatchFiles(t, db)
-
-	writeFile(t, dir, "a/one.bin", pattern(10, 2500))
-	writeFile(t, dir, "t1/f1", pattern(30, 1000))
-
-	if st := syncTree(t, db, dir); st.updated != 2 {
-		t.Fatalf("rescan stats = %+v, want 2 updated", st)
-	}
-
-	assertTotalsMatchFiles(t, db)
-
-	for _, name := range []string{"a/unique.bin", "t2/sub/f2"} {
-		err := os.Remove(filepath.Join(dir, name))
-		if err != nil {
-			t.Fatal(err)
-		}
-	}
-
-	if st := syncTree(t, db, dir); st.removed != 2 {
-		t.Fatalf("rescan stats = %+v, want 2 removed", st)
-	}
-
-	assertTotalsMatchFiles(t, db)
-}
-
 func TestApplyChangesRoundTrip(t *testing.T) {
 	t.Parallel()
 

exclude_test.go

@@ -17,9 +17,7 @@ import (
 func TestDefaultExcludes(t *testing.T) {
 	t.Parallel()
 
-	// README "Rules for the walk": the Linux and macOS lists, and none
+	// README "Rules for the walk": each system's list.
-	// on any other system. The Windows list exists in the code only: the
-	// binary does not build for Windows, so the README leaves it out.
 	cases := map[string][]string{
 		goosLinux: {"/proc", "/sys", "/dev", "/run", "/tmp", "/var/tmp"},
 		goosDarwin: {

info.go

@@ -26,11 +26,11 @@ func infoPhase(name string) string {
 // it. Any database problem, including a missing database, is fatal.
 //
 // The work runs in two phases, each under a progress display of its
-// own on stderr: open (open the database) and count (read the number of
+// own on stderr: open (open the database) and count (count the records,
-// records and their total size from the totals table). Each display
+// with one query). Each display ends before the next phase starts, and
-// ends before the next phase starts, and before an error is returned
+// before an error is returned to be printed. The details are written
-// to be printed. The details are written once the last display has
+// once the last display has ended, so no display is drawn while they
-// ended, so no display is drawn while they are written.
+// are written.
 func runInfo(ctx context.Context, stdout io.Writer) error {
 	dbPath, source, err := databasePath()
 	if err != nil {
@@ -56,7 +56,7 @@ func runInfo(ctx context.Context, stdout io.Writer) error {
 
 	defer func() { _ = db.Close() }()
 
-	// One row holds both counts, so the phase never has a total.
+	// One query counts everything, so the phase never has a total.
 	prog = newProgress(progressParams{
 		label: infoPhase("count"), total: -1,
 		waitingFor: countingRecords,

main_test.go

@@ -180,9 +180,9 @@ func capture(t *testing.T, std **os.File) func() string {
 }
 
 // brokenDatabase writes a database that opens cleanly and passes the
-// schema-version check but has no tables, so the first query fails
+// schema-version check but has no files table, so the first query
-// with the database already open: a fatal error on a path that owns an
+// fails with the database already open: a fatal error on a path that
-// open database. It closes the database the way scan does.
+// owns an open database. It closes the database the way scan does.
 func brokenDatabase(t *testing.T) string {
 	t.Helper()
 
@@ -265,9 +265,8 @@ func TestRunFatalAfterOpenClosesDatabase(t *testing.T) {
 			assertFatalOutput(t, stderr.String(), stdout())
 
 			// Proof that the failure happened after the open: only a
-			// query against the opened database can report this. Each
+			// query against the opened database can report this.
-			// subcommand's first query reads totals.
+			if !strings.Contains(stderr.String(), "no such table: files") {
-			if !strings.Contains(stderr.String(), "no such table: totals") {
 				t.Errorf("stderr = %q, want the failure to come from a "+
 					"query on the open database", stderr.String())
 			}
@@ -394,7 +393,7 @@ func TestRunNamesRelativeDatabase(t *testing.T) {
 }
 
 func TestRunUsesDatabaseThroughSymlinkedDirectory(t *testing.T) {
-	// README §Settings: the path names the file exactly. With link a
+	// README §Database: the path names the file exactly. With link a
 	// symlink to the directory real/sub, link/../db.sqlite names
 	// real/db.sqlite, not db.sqlite beside link. Every subcommand must
 	// use that file, relative or absolute, and its first line must name
@@ -649,7 +648,7 @@ func TestRunUsageErrors(t *testing.T) {
 }
 
 func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
-	// README §Settings: --workers below 1 is a usage error reported in
+	// README §scan mode: --workers below 1 is a usage error reported in
 	// one line on stderr, before the scan opens the database.
 	for _, workers := range []string{"0", "-1"} {
 		t.Run(workers, func(t *testing.T) {
@@ -687,8 +686,8 @@ func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
 func TestRunHelp(t *testing.T) {
 	t.Parallel()
 
-	// README §Settings: help goes to stderr, exits 0, and leaves stdout
+	// README §Subcommands: help goes to stderr, exits 0, and leaves
-	// empty.
+	// stdout empty.
 	cases := [][]string{{"--help"}, {"-h"}, {cmdScan, "--help"}}
 
 	for _, args := range cases {
@@ -714,8 +713,8 @@ func TestRunHelp(t *testing.T) {
 func TestRunVersion(t *testing.T) {
 	t.Parallel()
 
-	// README §Settings: the version is one line on stdout, with nothing
+	// README §Subcommands: the version is one line on stdout, with
-	// on stderr, and exits 0.
+	// nothing on stderr, and exits 0.
 	info, _ := debug.ReadBuildInfo()
 
 	for _, arg := range []string{"--version", "-v"} {
@@ -774,8 +773,8 @@ func TestBuildVersion(t *testing.T) {
 func TestRunVersionWriteFailureIsFatal(t *testing.T) {
 	t.Parallel()
 
-	// README §Error handling: a failed write to stdout is a fatal error,
+	// README §Error handling: a stdout write failure exits 1, reported
-	// exit 1, reported on stderr starting with "sfdupes:".
+	// in one line on stderr.
 	var stderr bytes.Buffer
 
 	code := run([]string{"--version"}, failingWriter{}, &stderr)
@@ -818,23 +817,6 @@ func scanFixture(t *testing.T) []string {
 	return dupes
 }
 
-// storedDiskSize returns the disk_size of the record for path in the
-// database at dbPath. A test of a trees run compares with this rather
-// than with a new lstat, which on ZFS can differ from the scan's (see
-// diskSizeOf).
-func storedDiskSize(t *testing.T, dbPath, path string) int64 {
-	t.Helper()
-
-	db, err := openReportDatabase(t.Context(), dbPath)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	defer func() { _ = db.Close() }()
-
-	return recordByPath(t, dbRecords(t, db), path).diskSize
-}
-
 // scanOK runs scan over operands, fails the test unless it exits 0 with
 // nothing on stdout, and returns everything it printed to stderr.
 func scanOK(t *testing.T, operands ...string) string {
@@ -946,21 +928,24 @@ func TestRunScanWalksOperandUnderSymlinkOperand(t *testing.T) {
 }
 
 func TestRunScanSkipsZFSOperand(t *testing.T) {
-	zfs := filepath.Join(t.TempDir(), ".zfs")
+	path := testDBPath(t)
-	f := writeFile(t, zfs, "snapshot/hourly/f", pattern(1, 10))
-
-	// No scan records a file inside a .zfs directory, so the record
-	// beneath the operand is written straight into the database.
-	path := seedDatabase(t, []scanRec{{size: 10, path: f}})
 	t.Setenv(databaseEnv, path)
 
+	zfs := filepath.Join(t.TempDir(), ".zfs")
+	snapshot := filepath.Join(zfs, "snapshot", "hourly")
+	f := writeFile(t, snapshot, "f", pattern(1, 10))
+
+	// An operand beneath a .zfs directory is walked, because it is not
+	// itself named .zfs.
+	scanOK(t, snapshot)
+
 	assertOperandSkipped(t, path, zfs, ".zfs directory", f)
 }
 
 // assertOperandSkipped scans operand alone and checks that it is skipped
 // as kind: a warning naming it, one skip in the summary, exit 0, and the
-// record for kept, stored beneath operand before this scan, still in the
+// record for kept, which an earlier scan stored beneath operand, still
-// database at dbPath.
+// in the database at dbPath.
 func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
 	kept string,
 ) {
@@ -989,121 +974,6 @@ func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
 	recordByPath(t, dbRecords(t, db), kept)
 }
 
-// TestRunScanSkipsOperandInsideZFS scans a directory inside a .zfs
-// directory, first alone and then under another operand. Each time it
-// is warned about and counted as skipped, and nothing in it is walked.
-// The other operand is scanned as usual.
-func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := t.TempDir()
-	hourly := filepath.Join(dir, ".zfs", "snapshot", "hourly")
-	writeFile(t, hourly, "f", pattern(1, 10))
-	f := writeFile(t, dir, "f", pattern(2, 10))
-
-	warning := "walk " + hourly + ": skipping operand inside a .zfs directory\n"
-
-	for _, tc := range []struct {
-		operands []string
-		summary  string
-	}{
-		{
-			[]string{hourly},
-			"scan: 0 files seen (0 added, 0 updated, 0 removed, " +
-				"0 unchanged), 1 skipped\n",
-		},
-		{
-			[]string{dir, hourly},
-			"scan: 1 files seen (1 added, 0 updated, 0 removed, " +
-				"0 unchanged), 1 skipped\n",
-		},
-	} {
-		stderr := scanOK(t, tc.operands...)
-		if !strings.Contains(stderr, warning) ||
-			!strings.Contains(stderr, tc.summary) {
-			t.Errorf("scan %q: stderr = %q, want %q and %q", tc.operands,
-				stderr, warning, tc.summary)
-		}
-	}
-
-	db, err := openDB(path, reportParams)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	t.Cleanup(func() { _ = db.Close() })
-
-	if got := recordPaths(dbRecords(t, db)); !slices.Equal(got, []string{f}) {
-		t.Errorf("records = %q, want %q", got, []string{f})
-	}
-}
-
-// TestRunScanSkipsOperandThroughSymlinkIntoZFS scans snaps/daily, where
-// snaps is a symlink to pool/.zfs/snapshot. The operand is warned about
-// by the path given, counted as skipped, and not walked.
-func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
-	t.Setenv(databaseEnv, testDBPath(t))
-
-	dir := t.TempDir()
-	writeFile(t, dir, "pool/.zfs/snapshot/daily/f", pattern(1, 10))
-
-	snaps := filepath.Join(dir, "snaps")
-
-	err := os.Symlink(filepath.Join(dir, "pool", ".zfs", "snapshot"), snaps)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	daily := filepath.Join(snaps, "daily")
-	stderr := scanOK(t, daily)
-
-	warning := "walk " + daily + ": skipping operand inside a .zfs directory\n"
-	summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
-		"0 unchanged), 1 skipped\n"
-
-	if !strings.Contains(stderr, warning) ||
-		!strings.Contains(stderr, summary) {
-		t.Errorf("stderr = %q, want %q and %q", stderr, warning, summary)
-	}
-}
-
-// TestRunScanWalksOperandThroughSymlink scans data/daily, where data is
-// a symlink to a directory outside any .zfs directory. The operand is
-// scanned as usual, and its file is recorded by the path given.
-func TestRunScanWalksOperandThroughSymlink(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := t.TempDir()
-	writeFile(t, dir, "pool/data/daily/f", pattern(1, 10))
-
-	data := filepath.Join(dir, "data")
-
-	err := os.Symlink(filepath.Join(dir, "pool", "data"), data)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	daily := filepath.Join(data, "daily")
-	stderr := scanOK(t, daily)
-
-	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
-		"0 unchanged), 0 skipped\n"
-	if !strings.Contains(stderr, summary) {
-		t.Errorf("stderr = %q, want %q", stderr, summary)
-	}
-
-	db, err := openDB(path, reportParams)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	t.Cleanup(func() { _ = db.Close() })
-
-	recordByPath(t, dbRecords(t, db), filepath.Join(daily, "f"))
-}
-
 func TestRunReportSucceeds(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
@@ -1158,9 +1028,8 @@ func TestRunTreesSucceeds(t *testing.T) {
 
 	// The two directories holding the duplicate pair are duplicate
 	// trees of each other.
-	want := "first\tdupe\tfiles\tsize\tdisk_size\n" +
+	want := "first\tdupe\tfiles\tsize\n" +
-		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\t" +
+		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
-		strconv.FormatInt(storedDiskSize(t, path, dupes[1]), 10) + "\n"
 	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
@@ -1194,10 +1063,9 @@ func TestRunReportsNeedOnlyReadAccess(t *testing.T) {
 	cases := map[string]string{
 		cmdReport: "first\tdupe\tsize\n" +
 			dupes[0] + "\t" + dupes[1] + "\t300\n",
-		cmdTrees: "first\tdupe\tfiles\tsize\tdisk_size\n" +
+		cmdTrees: "first\tdupe\tfiles\tsize\n" +
 			filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) +
-			"\t1\t300\t" +
+			"\t1\t300\n",
-			strconv.FormatInt(storedDiskSize(t, path, dupes[1]), 10) + "\n",
 	}
 
 	for name, want := range cases {
@@ -1232,11 +1100,8 @@ func assertRunsUseDatabase(t *testing.T, dir, name string) {
 		t.Errorf("report stdout = %q, want %q", got, want)
 	}
 
-	diskSize := storedDiskSize(t, filepath.Join(dir, name), dupes[1])
+	want = "first\tdupe\tfiles\tsize\n" +
-
+		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
-	want = "first\tdupe\tfiles\tsize\tdisk_size\n" +
-		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\t" +
-		strconv.FormatInt(diskSize, 10) + "\n"
 	if got := runStdout(t, cmdTrees); got != want {
 		t.Errorf("trees stdout = %q, want %q", got, want)
 	}
@@ -1257,7 +1122,7 @@ func assertRunsUseDatabase(t *testing.T, dir, name string) {
 }
 
 func TestRunDatabasePathUsedAsGiven(t *testing.T) {
-	// README §Settings: the path names the database file exactly. In
+	// README §Database: the path names the database file exactly. In
 	// SQLite's connection string an unescaped ? or # would end the file
 	// name and % would start an escape, and a path starting with //
 	// could be read as a host name. %25 is a valid escape, so unescaped
@@ -1302,8 +1167,9 @@ func holdScanLock(t *testing.T, path string) {
 }
 
 func TestRunSecondScanFails(t *testing.T) {
-	// README §Database: a second scan that finds the lock held fails
+	// README §Database: while one scan holds the lock, a second scan
-	// at once, naming the lock file, without opening the database.
+	// fails at once, naming the lock file, without opening the
+	// database.
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
@@ -1362,7 +1228,7 @@ func assertSecondScanFails(t *testing.T, path string) {
 }
 
 func TestRunSecondScanThroughSymlinkFails(t *testing.T) {
-	// README §Database: a path through a symlink names the same lock
+	// README §Database: every path to one database names the same lock
 	// file, so while a scan holds it through one path, a scan through
 	// another fails, naming the lock file beside the database's real
 	// path.
@@ -1467,8 +1333,8 @@ func TestRunReportsDuringScan(t *testing.T) {
 }
 
 func TestRunStdoutClosedIsFatal(t *testing.T) {
-	// README §Error handling: a failed write to stdout is a fatal error,
+	// README §Error handling: a stdout write failure exits 1, reported
-	// exit 1, reported on stderr starting with "sfdupes:".
+	// in one line on stderr.
 	for _, name := range []string{cmdReport, cmdTrees, cmdInfo} {
 		t.Run(name, func(t *testing.T) {
 			t.Setenv(databaseEnv, testDBPath(t))

progress.go

@@ -60,7 +60,7 @@ const fallbackWidth = 80
 const spinnerMargin = 5
 
 // countingRecords is what the display of a phase that reads the records
-// says until it has the number of records, its total.
+// says while it counts them, before it has its total.
 const countingRecords = "counting the records"
 
 // openPhase is the name of the phase in which report, trees and info
@@ -217,13 +217,27 @@ func (p *progress) draw() {
 	}
 
 	if p.width == nil {
-		fmt.Fprintln(os.Stderr, p.line(now, math.MaxInt, false))
+		fmt.Fprintln(os.Stderr, p.line(now, math.MaxInt, true))
 
 		return
 	}
 
 	width := p.width()
-	text := p.line(now, width-spinnerMargin, true)
+	room := width - spinnerMargin
+	text := p.line(now, room, true)
+
+	// A phase with an exact total ends its text with its percent and bar
+	// when its whole line, without the percent the bar shows, fits beside
+	// them: the bar gives way before any part of the line. The line is
+	// padded to the room the bar leaves it, so the bar stays at the
+	// terminal's right edge however long the line is. A total of 0 leaves
+	// the bar nothing to fill.
+	if p.total > 0 && !p.estimate {
+		line := p.line(now, math.MaxInt, false)
+		if len(line) <= room-barColumns {
+			text = fmt.Sprintf("%-*s%s", room-barColumns, line, p.percentBar())
+		}
+	}
 
 	// Before each draw the library erases its line with as many spaces as
 	// the widest line it has drawn. A display gets a new one when the
@@ -428,24 +442,20 @@ func (p *progress) finish() {
 //
 //	[3/4] hash: [1234/5000] 25%, 300 files/s, elapsed 4s, remain 13s
 //
-// where "files" is the phase's unit. A phase with no total shows the
+// where "files" is the phase's unit, without the percent when percent
-// items done instead, or what it waits for. The rate is that since the
+// is false, as before the bar, which shows its own. A phase with no
-// first draw in drawn, and the time remaining comes from the rate since
+// total shows the items done instead, or what it waits for. The rate is
-// the count started. Once no item has been completed for stallTime, the
+// that since the first draw in drawn, and the time remaining comes from
-// rate, which would read 0, gives way to the word "stalled" and where
+// the rate since the count started. Once no item has been completed for
-// the phase waits, as "stalled disk/db".
+// stallTime, the rate, which would read 0, gives way to the word
-//
+// "stalled" and where the phase waits, as "stalled disk/db".
-// When bar is true, as on a terminal, a phase with an exact total ends
-// the line with its percent and bar, in place of the percent after its
-// count. A total of 0 leaves the bar nothing to fill.
 //
 // The phase and its place, the progress, the elapsed time and the time
-// remaining are kept whole. A line wider than room first leaves out the
+// remaining are kept whole. A line wider than room leaves out the rate,
-// rate, the words of a stalled phase, or what the phase waits for. Next
+// the words of a stalled phase, or what the phase waits for; only if it
-// it leaves out the bar. Only if it is still wider is it cut at room.
+// is still wider is it cut at room. Every part is ASCII, so its length
-// Every part but the bar is ASCII, so its length is its width in
+// is its width in columns. p.mu must be held.
-// columns. p.mu must be held.
+func (p *progress) line(now time.Time, room int, percent bool) string {
-func (p *progress) line(now time.Time, room int, bar bool) string {
 	elapsed := now.Sub(p.start).Round(time.Second)
 
 	// head and tail hold the parts kept whole; extra, between them, is
@@ -460,7 +470,7 @@ func (p *progress) line(now time.Time, room int, bar bool) string {
 		rate := perSecond(p.count-since.count, now.Sub(since.at))
 		average := perSecond(p.count, now.Sub(p.rateStart))
 
-		head = p.label + ": " + p.itemsDone(true) + ", "
+		head = p.label + ": " + p.itemsDone(percent) + ", "
 		extra = fmt.Sprintf("%.0f %s/s, ", rate, p.unit)
 		tail = fmt.Sprintf("elapsed %s, remain %s", elapsed, p.remain(average))
 
@@ -469,26 +479,6 @@ func (p *progress) line(now time.Time, room int, bar bool) string {
 		}
 	}
 
-	if bar && p.total > 0 && !p.estimate {
-		// Beside the bar, which shows the percent, the count shows none.
-		// The line is padded to the room the bar leaves it, so the bar
-		// stays at room's right edge however long the line is.
-		beside := room - barColumns
-		barHead := p.label + ": " + p.itemsDone(false) + ", "
-
-		switch {
-		case len(barHead+extra+tail) <= beside:
-			return fmt.Sprintf("%-*s%s", beside, barHead+extra+tail,
-				p.percentBar())
-		case len(barHead+tail) <= beside:
-			return fmt.Sprintf("%-*s%s", beside, barHead+tail, p.percentBar())
-		}
-
-		// The bar gives way. The rate, or the words of a stalled phase,
-		// gave way before it and stay out.
-		extra = ""
-	}
-
 	full, kept := head+extra+tail, head+tail
 
 	switch {

progress_test.go

@@ -163,7 +163,7 @@ func TestProgressLine(t *testing.T) {
 		tc.p.start, tc.p.rateStart, tc.p.lastItem = ago, ago, now
 		tc.p.drawn = []drawnCount{{at: ago}}
 
-		if got := tc.p.line(now, math.MaxInt, false); got != tc.want {
+		if got := tc.p.line(now, math.MaxInt, true); got != tc.want {
 			t.Errorf("line = %q, want %q", got, tc.want)
 		}
 	}
@@ -198,40 +198,39 @@ func TestLineFitsRoom(t *testing.T) {
 	}
 
 	cases := []struct {
-		p    *progress
+		p       *progress
-		room int
+		room    int
-		bar  bool
+		percent bool
-		want string
+		want    string
 	}{{
-		p: hash, room: 60,
+		p: hash, room: 60, percent: true,
 		want: "[3/4] hash: [20/100] 20%, 2 files/s, elapsed 10s, remain 40s",
 	}, {
-		p: hash, room: 59,
+		p: hash, room: 59, percent: true,
 		want: "[3/4] hash: [20/100] 20%, elapsed 10s, remain 40s",
 	}, {
-		p: hash, room: 48,
+		p: hash, room: 48, percent: true,
 		want: "[3/4] hash: [20/100] 20%, elapsed 10s, remain 40",
 	}, {
-		// The bar shows the percent.
+		// Before the bar, which shows the percent.
-		p: hash, room: 74, bar: true,
+		p: hash, room: 60, percent: false,
-		want: "[3/4] hash: [20/100], 2 files/s, elapsed 10s, remain 40s" +
+		want: "[3/4] hash: [20/100], 2 files/s, elapsed 10s, remain 40s",
-			"  20% |██        |",
 	}, {
-		p: load, room: 43,
+		p: load, room: 43, percent: true,
 		want: "[1/4] load: elapsed 10s, remain unknown",
 	}, {
-		p: stalled, room: 68,
+		p: stalled, room: 68, percent: true,
 		want: "[3/4] hash: [20/100] 20%, stalled disk/db, elapsed 50s, " +
 			"remain 3m20s",
 	}, {
-		p: stalled, room: 67,
+		p: stalled, room: 67, percent: true,
 		want: "[3/4] hash: [20/100] 20%, elapsed 50s, remain 3m20s",
 	}}
 
 	for _, tc := range cases {
-		if got := tc.p.line(now, tc.room, tc.bar); got != tc.want {
+		if got := tc.p.line(now, tc.room, tc.percent); got != tc.want {
-			t.Errorf("line(%d, %t) = %q, want %q", tc.room, tc.bar, got,
+			t.Errorf("line(%d, %t) = %q, want %q",
-				tc.want)
+				tc.room, tc.percent, got, tc.want)
 		}
 	}
 }
@@ -257,14 +256,14 @@ func TestSetTotalStartsRate(t *testing.T) {
 	clock.Add(5 * time.Second)
 
 	want := "[1/4] load: [0/100] 0%, 0 files/s, elapsed 25s, remain unknown"
-	if got := p.line(clock.Now(), math.MaxInt, false); got != want {
+	if got := p.line(clock.Now(), math.MaxInt, true); got != want {
 		t.Errorf("line = %q, want %q", got, want)
 	}
 
 	clock.Add(5 * time.Second)
 
 	want = "[1/4] load: [0/100] 0%, stalled db, elapsed 30s, remain unknown"
-	if got := p.line(clock.Now(), math.MaxInt, false); got != want {
+	if got := p.line(clock.Now(), math.MaxInt, true); got != want {
 		t.Errorf("line = %q, want %q", got, want)
 	}
 
@@ -274,7 +273,7 @@ func TestSetTotalStartsRate(t *testing.T) {
 	}
 
 	want = "[1/4] load: [20/100] 20%, 2 files/s, elapsed 30s, remain 40s"
-	if got := p.line(clock.Now(), math.MaxInt, false); got != want {
+	if got := p.line(clock.Now(), math.MaxInt, true); got != want {
 		t.Errorf("line = %q, want %q", got, want)
 	}
 }
@@ -596,32 +595,31 @@ func TestTerminalLinesKeepTimeRemaining(t *testing.T) {
 	}
 }
 
-// TestTerminalStalledLines draws every phase's line once the phase has
+// TestTerminalStalledLines draws every phase's line on an 80-column
-// stalled, its last item done 42 seconds before. At an ordinary scan's
+// terminal once the phase has stalled, its last item done 42 seconds
-// counts and times, 12345 of 45678 items done four and a half minutes
+// before. At an ordinary scan's counts and times, 12345 of 45678 items
-// in, on a terminal 100 columns wide, the line shows where the phase
+// done four and a half minutes in, the line shows where the phase waits
-// waits whole, beside the phase, progress, elapsed time and time
+// whole, beside the phase, progress, elapsed time and time remaining.
-// remaining. At a large scan's, 1234567 of 9876543 two and a half hours
+// At a large scan's, 1234567 of 9876543 two and a half hours in, those
-// in, on an 80-column terminal, those four still show whole, as the
+// four still show whole, as the words give way first where they do not
-// words give way first where they do not fit.
+// fit.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestTerminalStalledLines(t *testing.T) {
 	stderr := captureStderr(t)
 
-	// drawStalled draws the display params describes on a terminal width
+	// drawStalled draws the display params describes as it starts and
-	// columns wide as it starts and once more as it ends, with count of
+	// once more as it ends, with count of total items done elapsed into
-	// total items done elapsed into the phase, and returns what the
+	// the phase, and returns what the terminal shows.
-	// terminal shows.
+	drawStalled := func(params progressParams, total, count int64,
-	drawStalled := func(params progressParams, width int, total,
+		elapsed time.Duration,
-		count int64, elapsed time.Duration,
 	) string {
 		before := len(stderr())
 		clock := &testClock{now: time.Now()}
 		params.total = total
 
 		// No timed draws come between the two.
-		p := startProgress(params, func() int { return width }, time.Hour,
+		p := startProgress(params, func() int { return 80 }, time.Hour,
 			clock.Now)
 
 		clock.Add(elapsed - 42*time.Second)
@@ -653,19 +651,16 @@ func TestTerminalStalledLines(t *testing.T) {
 			approx = "~"
 		}
 
-		// The percent is in the line, or beside the bar.
+		shown := drawStalled(params, 45678, 12345,
-		shown := drawStalled(params, 100, 45678, 12345,
 			4*time.Minute+30*time.Second)
-		for _, want := range []string{
+		want := params.label + ": [12345/" + approx + "45678] 27%, stalled " +
-			params.label + ": [12345/" + approx + "45678]",
+			params.stalledOn + ", elapsed 4m30s, remain 12m9s"
-			", stalled " + params.stalledOn + ", elapsed 4m30s, remain 12m9s",
+
-		} {
+		if !strings.Contains(shown, want) {
-			if !strings.Contains(shown, want) {
+			t.Errorf("terminal shows %q, want %q", shown, want)
-				t.Errorf("terminal shows %q, want %q", shown, want)
-			}
 		}
 
-		shown = drawStalled(params, 80, 9876543, 1234567, 150*time.Minute)
+		shown = drawStalled(params, 9876543, 1234567, 150*time.Minute)
 		for _, want := range []string{
 			params.label + ": [1234567/" + approx + "9876543] 12%, ",
 			", elapsed 2h30m0s, remain 17h30m0s",
@@ -743,12 +738,9 @@ func TestTerminalLinesStartWithSpinner(t *testing.T) {
 
 // TestTerminalBarStaysAtRightEdge draws the hash phase's display two
 // and a half hours in, at two counts whose lines differ in length, on
-// terminals 110 and 120 columns wide. The bar is partly filled at the
+// terminals 110 and 120 columns wide. Its bar must start the same number
-// first count and full at the second. It must start the same number of
+// of columns from the terminal's right edge each time: a line that grows
-// columns from the terminal's right edge each time, and end the same
+// or shrinks, as its time remaining does, never moves the bar.
-// number of columns from it: a line that grows or shrinks, as its time
-// remaining does, never moves the bar, and nor do the bar's filled
-// cells.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestTerminalBarStaysAtRightEdge(t *testing.T) {
@@ -759,8 +751,7 @@ func TestTerminalBarStaysAtRightEdge(t *testing.T) {
 
 	widths := []int{110, 120}
 	counts := []int64{1234567, 9876543}
-	startFromEdge := make([]int, 0, len(widths)*len(counts))
+	fromEdge := make([]int, 0, len(widths)*len(counts))
-	endFromEdge := make([]int, 0, len(widths)*len(counts))
 
 	for _, width := range widths {
 		for _, count := range counts {
@@ -771,96 +762,14 @@ func TestTerminalBarStaysAtRightEdge(t *testing.T) {
 				t.Fatalf("terminal %d wide shows %q, want a bar", width, shown)
 			}
 
-			// The bar ends with the last "|".
+			fromEdge = append(fromEdge,
-			throughBar := shown[:strings.LastIndex(shown, "|")+1]
-
-			startFromEdge = append(startFromEdge,
 				width-utf8.RuneCountInString(beforeBar))
-			endFromEdge = append(endFromEdge,
-				width-utf8.RuneCountInString(throughBar))
 		}
 	}
 
-	if slices.Min(startFromEdge) != slices.Max(startFromEdge) {
+	if slices.Min(fromEdge) != slices.Max(fromEdge) {
 		t.Errorf("bar starts %v columns from the right edge, want the same "+
-			"every time", startFromEdge)
+			"every time", fromEdge)
-	}
-
-	if slices.Min(endFromEdge) != slices.Max(endFromEdge) {
-		t.Errorf("bar ends %v columns from the right edge, want the same "+
-			"every time", endFromEdge)
-	}
-}
-
-// TestTerminalRateGivesWayBeforeBar draws the hash phase's display two
-// and a half hours in. On a terminal 90 columns wide the line fits
-// beside the bar without its rate, but not with it: the bar is drawn
-// and the rate is not. On a terminal 85 columns wide the line does not
-// fit beside the bar even without its rate: neither is drawn, though
-// the rate would fit where the bar was.
-//
-//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
-func TestTerminalRateGivesWayBeforeBar(t *testing.T) {
-	stderr := captureStderr(t)
-	params := progressParams{
-		label: scanPhase("hash"), unit: scanUnit, total: 9876543,
-	}
-
-	shown := lastFrame(drawLate(stderr, params, 90, 1234567))
-	if !strings.Contains(shown, "% |") || strings.Contains(shown, "files/s") {
-		t.Errorf("terminal 90 wide shows %q, want the bar and no rate", shown)
-	}
-
-	shown = lastFrame(drawLate(stderr, params, 85, 1234567))
-	if strings.Contains(shown, "% |") || strings.Contains(shown, "files/s") {
-		t.Errorf("terminal 85 wide shows %q, want neither bar nor rate", shown)
-	}
-}
-
-// TestTerminalSpinnerTurnsBesideBar draws the hash phase's display, its
-// bar partly filled, several times on a terminal 120 columns wide. The
-// spinner must turn at every draw. A filled cell of the bar takes one
-// column but three bytes. A line measured in bytes would seem too wide
-// for the terminal, and every draw would start the display over, its
-// spinner included.
-//
-//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
-func TestTerminalSpinnerTurnsBesideBar(t *testing.T) {
-	stderr := captureStderr(t)
-	params := progressParams{
-		label: scanPhase("hash"), unit: scanUnit, total: 9876543,
-	}
-
-	// No timed draws: the test draws.
-	p := startProgress(params, func() int { return 120 }, time.Hour,
-		time.Now)
-
-	p.mu.Lock()
-	p.count = 1234567
-	p.mu.Unlock()
-
-	const draws = 4
-
-	spinners := make([]string, 0, draws)
-
-	for range draws {
-		before := len(stderr())
-
-		p.draw()
-
-		spinner, _, _ := strings.Cut(lastFrame(stderr()[before:]), " ")
-		spinners = append(spinners, spinner)
-	}
-
-	p.finish()
-
-	for i := 1; i < len(spinners); i++ {
-		if spinners[i] == spinners[i-1] {
-			t.Errorf("spinners at successive draws are %q, want each to "+
-				"differ from the one before", spinners)
-
-			break
-		}
 	}
 }
 
@@ -888,7 +797,7 @@ func TestTerminalNarrowedRedrawsInPlace(t *testing.T) {
 			progressParams{
 				label: scanPhase("hash"), unit: scanUnit, total: 9876543,
 			},
-			80,
+			90,
 		},
 	}
 

report.go

@@ -21,16 +21,14 @@ const minGroupSize = 2
 
 // scanRec is one file record from the database. The signature (size,
 // head, tail, content) is the duplicate key; mtime is informational
-// only and used by scan for change detection. diskSize is the bytes the
+// only and used by scan for change detection.
-// file takes on disk, which trees adds up.
 type scanRec struct {
-	size     int64
+	size    int64
-	diskSize int64
+	mtime   time.Time
-	mtime    time.Time
+	head    [sha256.Size]byte
-	head     [sha256.Size]byte
+	tail    [sha256.Size]byte
-	tail     [sha256.Size]byte
+	content [sha256.Size]byte
-	content  [sha256.Size]byte
+	path    string
-	path     string
 }
 
 // reportPhase names one phase of report with its place among all of
@@ -47,11 +45,11 @@ func reportPhase(name string) string {
 // problem, including a missing database, is fatal.
 //
 // The work runs in two phases, each under a progress display of its
-// own on stderr: open (open the database) and read (read the number of
+// own on stderr: open (open the database) and read (count the records,
-// records from the totals table, then read the records in signature
+// then read them in signature order, writing each size's duplicate
-// order, writing each size's duplicate groups to stdout once that size
+// groups to stdout once that size is read; see readReport). Each
-// is read; see readReport). Each display ends before the next phase
+// display ends before the next phase starts, and before an error is
-// starts, and before an error is returned to be printed.
+// returned to be printed.
 func runReport(ctx context.Context, stdout io.Writer) error {
 	dbPath, source, err := databasePath()
 	if err != nil {

report_test.go

@@ -38,8 +38,8 @@ func awkwardPairRecs() []scanRec {
 	h, tl, c := testHash("h"), testHash("t"), testHash("c")
 
 	return []scanRec{
-		{size: 5, diskSize: 4096, head: h, tail: tl, content: c, path: "/d/A/f"},
+		{size: 5, head: h, tail: tl, content: c, path: "/d/A/f"},
-		{size: 5, diskSize: 4096, head: h, tail: tl, content: c, path: awkwardDir + "/f"},
+		{size: 5, head: h, tail: tl, content: c, path: awkwardDir + "/f"},
 	}
 }
 

scan.go

@@ -52,26 +52,23 @@ const workQueueDepth = 1024
 // has already printed its line, so run prints nothing more.
 var errInterrupted = errors.New("scan interrupted")
 
-// fileRec carries one statted file between the scan phases. diskSize is
+// fileRec carries one statted file between the scan phases. dev and
-// the bytes the file takes on disk. dev and ino identify the underlying
+// ino identify the underlying inode so hard-linked paths can share
-// inode so hard-linked paths can share one read; both are zero when the
+// one read; both are zero when the platform exposes no inode.
-// platform exposes no inode.
 type fileRec struct {
-	path     string
+	path  string
-	size     int64
+	size  int64
-	diskSize int64
+	mtime time.Time
-	mtime    time.Time
+	dev   uint64
-	dev      uint64
+	ino   uint64
-	ino      uint64
 }
 
 // fileMeta is the in-memory index entry for one existing database
-// record: what the walk compares the file with. Hashes stay on disk; at
+// record: just enough for change detection. Hashes stay on disk; at
 // tens of millions of records they would dominate the scan's memory.
 type fileMeta struct {
-	size     int64
+	size  int64
-	diskSize int64
+	mtime time.Time
-	mtime    time.Time
 }
 
 // scanUnit is what every scan phase counts, as its progress display
@@ -342,12 +339,11 @@ type scanStats struct {
 // whatever remains after the walk and hash phases is deleted by the
 // update phase.
 type scanState struct {
-	db        *sql.DB
+	db       *sql.DB
-	existing  map[string]fileMeta
+	existing map[string]fileMeta
-	toHash    []fileRec // new and changed files: must be read
+	toHash   []fileRec // new and changed files: must be read
-	diskSizes []fileRec // unchanged files whose disk_size changed
+	batch    []scanRec
-	batch     []scanRec
+	st       scanStats
-	st        scanStats
 }
 
 // syncScan synchronizes the database with the filesystem under roots;
@@ -387,8 +383,7 @@ func (s *scanState) runPhases(ctx context.Context, roots []string,
 ) error {
 	// Types and filesystems are checked before pruning so that an
 	// operand under a dropped one is still scanned, not dropped as lying
-	// under it, and so that an operand inside a .zfs directory gets its
+	// under it.
-	// warning even when it lies under another operand.
 	roots = pruneRoots(s.walkableRoots(roots, rules), oneFS, rules,
 		deviceOfPath)
 
@@ -416,15 +411,15 @@ func (s *scanState) runPhases(ctx context.Context, roots []string,
 }
 
 // walkableRoots returns the operands the walk can start from: regular
-// files, and directories not named .zfs, none of them inside a
+// files, and directories not named .zfs. Every other operand is warned
-// directory named .zfs. Every other operand is warned about, counted as
+// about, counted as skipped, and dropped. A dropped operand is no
-// skipped, and dropped. A dropped operand is no longer a root, so the
+// longer a root, so the records stored beneath it are treated as if it
-// records stored beneath it are treated as if it had not been given:
+// had not been given: those under no other root count as outside the
-// those under no other root count as outside the roots and are not
+// roots and are not deleted as unverified. An operand on a filesystem
-// deleted as unverified. An operand on a filesystem in rules that is not
+// in rules that is not persistent is dropped the same way, with a line
-// persistent is dropped the same way, with a line saying so that is not
+// saying so that is not a warning, and is not counted as skipped. An
-// a warning, and is not counted as skipped. An operand that fails lstat
+// operand that fails lstat here is kept, and the walk warns about it
-// here is kept, and the walk warns about it unless it no longer exists.
+// unless it no longer exists.
 func (s *scanState) walkableRoots(roots []string, rules walkRules) []string {
 	kept := make([]string, 0, len(roots))
 
@@ -459,8 +454,8 @@ func (s *scanState) walkableRoots(roots []string, rules walkRules) []string {
 // included, so its display counts against the number of records.
 func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
 	// Indexing tens of millions of records takes real time; without a
-	// display the scan looks hung before the walk begins. The number of
+	// display the scan looks hung before the walk begins. Counting them
-	// records, read first, gives the display its total.
+	// first gives the display its total.
 	prog := newProgress(progressParams{
 		label: scanPhase("load"), unit: scanUnit, total: -1,
 		waitingFor: countingRecords, stalledOn: "db",
@@ -476,24 +471,24 @@ func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
 
 	s.existing = make(map[string]fileMeta)
 
-	return loadFileMeta(ctx, s.db, func(path string, m fileMeta) {
+	return loadFileMeta(ctx, s.db,
-		prog.increment()
+		func(path string, size int64, mtime time.Time) {
+			prog.increment()
 
-		if underAnyRoot(path, roots) {
+			if underAnyRoot(path, roots) {
-			s.existing[path] = m
+				s.existing[path] = fileMeta{size: size, mtime: mtime}
-		}
+			}
-	})
+		})
 }
 
 // walkPhase drains the walk and queues every new or changed file for
-// the hash phase. An unchanged file is not read, and its record counts
+// the hash phase. An unchanged file needs nothing more, and its record
-// as verified. When its disk_size differs from the record's, it is
+// counts as verified. A record at or below a path the walk left out,
-// queued for the update phase, which writes the new disk_size. A record
+// because -x stopped at it, it is a default exclude, or it is not on a
-// at or below a path the walk left out, because -x stopped at it, it is
+// persistent filesystem, counts as outside the roots: it is not
-// a default exclude, or it is not on a persistent filesystem, counts as
+// deleted. That does not hold below a root at or inside that path,
-// outside the roots: it is not deleted. That does not hold below a root
+// since that root's own walk verifies the records below it; nor is a
-// at or inside that path, since that root's own walk verifies the
+// line printed for such a root.
-// records below it; nor is a line printed for such a root.
 func (s *scanState) walkPhase(events <-chan walkEvent, roots []string) {
 	// The records the last scan left under the roots estimate how many
 	// files the walk will find. A first scan has none, and no estimate.
@@ -551,13 +546,6 @@ func (s *scanState) walkPhase(events <-chan walkEvent, roots []string) {
 		delete(s.existing, ev.rec.path)
 
 		s.st.unchanged++
-
-		// The space a file takes on disk can change while its size and
-		// mtime stay the same. ZFS, for one, counts a new file's blocks
-		// up to seconds after the write.
-		if old.diskSize != ev.rec.diskSize {
-			s.diskSizes = append(s.diskSizes, ev.rec)
-		}
 	}
 
 	prog.finish()
@@ -706,13 +694,12 @@ func (s *scanState) recordRun(ctx context.Context, r hashResult) error {
 		s.resolve(rec.path)
 
 		s.batch = append(s.batch, scanRec{
-			size:     rec.size,
+			size:    rec.size,
-			diskSize: rec.diskSize,
+			mtime:   rec.mtime,
-			mtime:    rec.mtime,
+			head:    r.head,
-			head:     r.head,
+			tail:    r.tail,
-			tail:     r.tail,
+			content: r.content,
-			content:  r.content,
+			path:    rec.path,
-			path:     rec.path,
 		})
 	}
 
@@ -728,7 +715,7 @@ func (s *scanState) commitFullBatch(ctx context.Context) error {
 		return nil
 	}
 
-	err := applyBatch(ctx, s.db, s.batch, nil, nil, nil)
+	err := applyBatch(ctx, s.db, s.batch, nil, nil)
 	if err != nil {
 		return err
 	}
@@ -739,10 +726,9 @@ func (s *scanState) commitFullBatch(ctx context.Context) error {
 }
 
 // updatePhase writes the scan's tail under one progress display: the
-// final partial batch of hashed records, the new disk_size of every
+// final partial batch of hashed records, and deletions for every record
-// unchanged file whose disk_size changed, and deletions for every
+// the scan did not verify (vanished files, plus paths that failed to
-// record the scan did not verify (vanished files, plus paths that
+// stat or hash).
-// failed to stat or hash).
 func (s *scanState) updatePhase(ctx context.Context) error {
 	deletes := make([]string, 0, len(s.existing))
 	for path := range s.existing {
@@ -754,7 +740,7 @@ func (s *scanState) updatePhase(ctx context.Context) error {
 
 	s.st.removed = len(deletes)
 
-	total := len(s.batch) + len(s.diskSizes) + len(deletes)
+	total := len(s.batch) + len(deletes)
 	prog := newProgress(progressParams{
 		label: scanPhase("update"), unit: scanUnit, total: int64(total),
 		stalledOn: "db",
@@ -769,11 +755,6 @@ func (s *scanState) updatePhase(ctx context.Context) error {
 
 	s.batch = nil
 
-	err = applyDiskSizes(ctx, s.db, s.diskSizes, prog)
-	if err != nil {
-		return err
-	}
-
 	return applyChanges(ctx, s.db, nil, deletes, prog)
 }
 
@@ -893,24 +874,9 @@ func sendEvent(ctx context.Context, events chan<- walkEvent,
 
 // operandWarning returns the one-line warning for an operand the walk
 // does not start from, naming the path and what it is, or "" for one it
-// does: a regular file, or a directory not named .zfs, that is not
+// does: a regular file, or a directory not named .zfs. Symlinks are
-// inside a directory named .zfs, neither as given nor with its symlinks
+// never followed, including as operands.
-// resolved. Symlinks are never followed, including as operands.
 func operandWarning(root string, fi fs.FileInfo) string {
-	// The walk never enters a .zfs directory, so it starts from nothing
-	// inside one either, not even through a symlink. An operand whose
-	// symlinks cannot be resolved is checked as given.
-	resolved, err := filepath.EvalSymlinks(root)
-	if err != nil {
-		resolved = root
-	}
-
-	if slices.Contains(strings.Split(filepath.Dir(root), "/"), ".zfs") ||
-		slices.Contains(strings.Split(filepath.Dir(resolved), "/"), ".zfs") {
-		return fmt.Sprintf("walk %s: skipping operand inside a .zfs directory",
-			root)
-	}
-
 	var kind string
 
 	switch mode := fi.Mode(); {
@@ -979,12 +945,11 @@ func seedRoot(ctx context.Context, root string, rules walkRules,
 
 	dev, ino := inodeOfInfo(fi)
 	rec := fileRec{
-		path:     root,
+		path:  root,
-		size:     fi.Size(),
+		size:  fi.Size(),
-		diskSize: diskSizeOfInfo(fi),
+		mtime: fi.ModTime(),
-		mtime:    fi.ModTime(),
+		dev:   dev,
-		dev:      dev,
+		ino:   ino,
-		ino:      ino,
 	}
 
 	if !isDatabaseFile(rec, rules) {
@@ -1164,12 +1129,11 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
 
 	dev, ino := inodeOfInfo(info)
 	rec := fileRec{
-		path:     p,
+		path:  p,
-		size:     info.Size(),
+		size:  info.Size(),
-		diskSize: diskSizeOfInfo(info),
+		mtime: info.ModTime(),
-		mtime:    info.ModTime(),
+		dev:   dev,
-		dev:      dev,
+		ino:   ino,
-		ino:      ino,
 	}
 
 	if !isDatabaseFile(rec, rules) {
@@ -1261,23 +1225,6 @@ func inodeOfInfo(fi fs.FileInfo) (uint64, uint64) {
 	return statDev(st), st.Ino
 }
 
-// statBlockSize is the unit of st_blocks in an lstat result on Linux and
-// macOS, whatever the filesystem's own block size.
-const statBlockSize = 512
-
-// diskSizeOfInfo returns the bytes a file takes on disk: its allocated
-// blocks, st_blocks × 512. On a compressed or sparse file it is less
-// than the file's size. It is 0 when the platform exposes no block
-// count.
-func diskSizeOfInfo(fi fs.FileInfo) int64 {
-	st, ok := fi.Sys().(*syscall.Stat_t)
-	if !ok {
-		return 0
-	}
-
-	return st.Blocks * statBlockSize
-}
-
 // hashResult carries the hashes computed for one inode run (or the
 // error that prevented computing them) from the pool's workers to the
 // hash phase. Its run leaves out the paths found removed.

scan_test.go

@@ -42,30 +42,6 @@ func writeFile(t *testing.T, dir, name string, data []byte) string {
 	return p
 }
 
-// diskSizeOf returns the bytes the file at path takes on disk, from its
-// own lstat: st_blocks counts 512-byte units. ZFS counts a write's
-// blocks only when it commits the write, up to seconds later, and one
-// commit can take the file through several growing sizes. So this value
-// can change at any moment. Neither fsync nor unix.Sync hastens that,
-// but a unix.Sync call often takes long enough that the blocks are
-// counted when it returns. A test that needs the value to change waits
-// for the change. A test that compares it with a scan's disk_size reads
-// it before and after the scan. The rewrite test rescans until the two
-// reads match, then compares exactly. The other two tests fail only on
-// a disk_size outside the two reads.
-func diskSizeOf(t *testing.T, path string) int64 {
-	t.Helper()
-
-	var st syscall.Stat_t
-
-	err := syscall.Lstat(path, &st)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	return st.Blocks * 512
-}
-
 // pattern returns n bytes of deterministic content seeded by tag.
 func pattern(tag byte, n int) []byte {
 	data := make([]byte, n)
@@ -1088,9 +1064,8 @@ func TestScanOneFilesystemWalksNestedFileOperand(t *testing.T) {
 	}
 }
 
-// buildSmokeTree recreates the tree of the test under README
+// buildSmokeTree recreates the README smoke-test filesystem layout
-// "Definition of done" with deterministic content and returns the tree
+// with deterministic content and returns the tree root.
-// root.
 func buildSmokeTree(t *testing.T) string {
 	t.Helper()
 
@@ -1253,9 +1228,9 @@ func TestScanPipeline(t *testing.T) {
 // TestScanProgressNamesEachPhase checks the plain progress lines of a
 // first scan, and of a rescan of one operand holding two of the
 // database's records. Each phase's first line names it with its place
-// among the four: load gets the number of records before reading them,
+// among the four: load counts the records before reading them, and the
-// and the walk estimates its total from the records under its operand,
+// walk estimates its total from the records under its operand, or says
-// or says its time remaining is unknown when there are none.
+// its time remaining is unknown when there are none.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestScanProgressNamesEachPhase(t *testing.T) {
@@ -1441,159 +1416,6 @@ func TestScanStoresRawHashes(t *testing.T) {
 	}
 }
 
-// TestScanStoresDiskSize scans a sparse file, which takes less space on
-// disk than its length, once through its directory and once as the
-// operand itself. Each scan stores the disk_size of the file's lstat.
-func TestScanStoresDiskSize(t *testing.T) {
-	t.Parallel()
-
-	const length = 1024 * 1024
-
-	p := sparseFile(t, t.TempDir(), "sparse", length)
-	pokeAt(t, p, 0, []byte("x"))
-
-	unix.Sync() // see diskSizeOf
-
-	size := diskSizeOf(t, p)
-	if size == 0 || size >= length {
-		t.Fatalf("the file takes %d bytes on disk, want more than none "+
-			"and fewer than its length %d", size, length)
-	}
-
-	for _, operand := range []string{filepath.Dir(p), p} {
-		db := openTestDB(t)
-
-		// ZFS may count the blocks during the scan; see diskSizeOf.
-		before := diskSizeOf(t, p)
-
-		syncTree(t, db, operand)
-
-		after := diskSizeOf(t, p)
-
-		got := recordByPath(t, dbRecords(t, db), p).diskSize
-		if got < before || got > after {
-			t.Errorf("scan of %s: disk_size = %d, want %d to %d",
-				operand, got, before, after)
-		}
-	}
-}
-
-// TestSyncScanRewriteUpdatesDiskSize writes into the hole of a scanned
-// sparse file and moves its mtime on. The rescan hashes the file again
-// and rewrites its record with the new disk_size.
-func TestSyncScanRewriteUpdatesDiskSize(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	db := openTestDB(t)
-	p := sparseFile(t, dir, "sparse", 1024*1024)
-	pokeAt(t, p, 0, []byte("x"))
-
-	syncTree(t, db, dir)
-
-	recorded := recordByPath(t, dbRecords(t, db), p).diskSize
-
-	pokeAt(t, p, 512*1024, pattern(7, 64*1024))
-
-	// The write may leave the mtime the scan recorded; a later one makes
-	// the rescan read the file again.
-	later := time.Now().Add(time.Hour)
-
-	err := os.Chtimes(p, later, later)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	// Wait for ZFS to count the write; see diskSizeOf.
-	deadline := time.Now().Add(30 * time.Second)
-	for diskSizeOf(t, p) == recorded {
-		if time.Now().After(deadline) {
-			t.Fatalf("the file still takes %d bytes on disk 30 seconds "+
-				"after the write into its hole", recorded)
-		}
-
-		unix.Sync()
-	}
-
-	// ZFS may still be counting, so the size may change during a rescan.
-	// Only a rescan with the same size on both sides of it can be compared
-	// exactly. A rescan that keeps the old size still fails, because the
-	// wait made before differ from it.
-	for {
-		before := diskSizeOf(t, p)
-
-		st := syncTree(t, db, dir)
-
-		after := diskSizeOf(t, p)
-
-		if st != (scanStats{walked: 1, updated: 1}) {
-			t.Fatalf("rescan stats = %+v, want 1 updated", st)
-		}
-
-		if before == after {
-			got := recordByPath(t, dbRecords(t, db), p).diskSize
-			if got != after {
-				t.Errorf("disk_size = %d, want %d", got, after)
-			}
-
-			return
-		}
-
-		if time.Now().After(deadline) {
-			t.Fatalf("the size on disk was still changing 30 seconds after "+
-				"the write into its hole: %d, then %d", before, after)
-		}
-
-		// A later mtime makes the next rescan read the file again.
-		later = later.Add(time.Second)
-
-		err = os.Chtimes(p, later, later)
-		if err != nil {
-			t.Fatal(err)
-		}
-	}
-}
-
-// TestSyncScanUnchangedUpdatesDiskSize gives a file's record a
-// disk_size the file does not have, as when ZFS had not yet counted the
-// file's blocks at the last scan. The rescan writes the file's own
-// disk_size into the record without reading the file again.
-func TestSyncScanUnchangedUpdatesDiskSize(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	db := openTestDB(t)
-	p := writeFile(t, dir, "a.bin", pattern(1, 500))
-
-	syncTree(t, db, dir)
-
-	// lstat counts 512-byte units, so no file takes 1 byte on disk.
-	_, err := db.ExecContext(t.Context(),
-		"UPDATE files SET disk_size = 1 WHERE path = ?", []byte(p))
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	unix.Sync() // see diskSizeOf
-
-	// ZFS may count the blocks during the rescan; see diskSizeOf.
-	before := diskSizeOf(t, p)
-
-	// A file read again would count as updated.
-	st := syncTree(t, db, dir)
-
-	after := diskSizeOf(t, p)
-
-	if st != (scanStats{walked: 1, unchanged: 1}) {
-		t.Fatalf("rescan stats = %+v, want 1 unchanged", st)
-	}
-
-	got := recordByPath(t, dbRecords(t, db), p).diskSize
-	if got < before || got > after {
-		t.Errorf("disk_size = %d, want %d to %d", got, before, after)
-	}
-}
-
 // TestSyncScanSameSecondRewrite rewrites a file in place at the same
 // size with an mtime later in the same second as the recorded one: the
 // next scan must notice the change and re-hash the file. The operand is

trees.go

@@ -22,10 +22,6 @@ type treeNode struct {
 	digest    [sha256.Size]byte
 	fileCount int64
 	totalSize int64
-	// diskSize is the bytes the directory's files take on disk. Two
-	// copies of one tree have the same totalSize, but their diskSize
-	// can differ.
-	diskSize int64
 }
 
 // treesPhase names one phase of trees with its place among all of them,
@@ -44,11 +40,11 @@ func treesPhase(name string) string {
 // database problem, including a missing database, is fatal.
 //
 // The work runs in four phases, each under a progress display of its
-// own on stderr: open (open the database), read (read the number of
+// own on stderr: open (open the database), read (count the records,
-// records from the totals table, then read the records into the
+// then read them into the hierarchy), group (group the directories by
-// hierarchy), group (group the directories by digest) and write (write
+// digest) and write (write the groups to stdout). Each display ends
-// the groups to stdout). Each display ends before the next phase
+// before the next phase starts, and before an error is returned to be
-// starts, and before an error is returned to be printed.
+// printed.
 func runTrees(ctx context.Context, stdout io.Writer) error {
 	dbPath, source, err := databasePath()
 	if err != nil {
@@ -143,16 +139,15 @@ func readTree(ctx context.Context, db *sql.DB,
 
 // writeTreeGroups writes dupes to stdout as TSV, a header line and then
 // a row for every member of each group but its first, counting each
-// group on prog once its rows are written. The disk_size column is the
+// group on prog once its rows are written. stdout may be the terminal
-// dupe's own. stdout may be the terminal prog is drawn on, so the lines
+// prog is drawn on, so the lines go through prog's writer. It returns
-// go through prog's writer. It returns the number of rows (dupe trees)
+// the number of rows (dupe trees) and the bytes they could reclaim.
-// and the bytes they could reclaim.
 func writeTreeGroups(stdout io.Writer, dupes [][]*treeNode,
 	prog *progress,
 ) (int, int64, error) {
 	out := prog.writer(stdout)
 
-	_, err := fmt.Fprintln(out, "first\tdupe\tfiles\tsize\tdisk_size")
+	_, err := fmt.Fprintln(out, "first\tdupe\tfiles\tsize")
 	if err != nil {
 		return 0, 0, fmt.Errorf("write stdout: %w", err)
 	}
@@ -164,9 +159,9 @@ func writeTreeGroups(stdout io.Writer, dupes [][]*treeNode,
 	for _, g := range dupes {
 		first := g[0]
 		for _, n := range g[1:] {
-			_, err = fmt.Fprintf(out, "%s\t%s\t%d\t%d\t%d\n",
+			_, err = fmt.Fprintf(out, "%s\t%s\t%d\t%d\n",
 				escapePath(first.path), escapePath(n.path),
-				first.fileCount, first.totalSize, n.diskSize)
+				first.fileCount, first.totalSize)
 			if err != nil {
 				return 0, 0, fmt.Errorf("write stdout: %w", err)
 			}
@@ -237,7 +232,6 @@ func (b *treeBuilder) add(r scanRec) {
 	dir.entries = append(dir.entries, fileEntry(name, r))
 	dir.fileCount++
 	dir.totalSize += r.size
-	dir.diskSize += r.diskSize
 }
 
 // openDir starts the directory called name inside the innermost open
@@ -276,7 +270,6 @@ func (b *treeBuilder) closeTo(n int) {
 			"d\x00"+name+"\x00"+string(dir.digest[:]))
 		dir.parent.fileCount += dir.fileCount
 		dir.parent.totalSize += dir.totalSize
-		dir.parent.diskSize += dir.diskSize
 		b.dirs = append(b.dirs, dir)
 	}
 }

trees_test.go

@@ -15,26 +15,20 @@ import (
 const treesOpenLine = "[1/4] open: opening the database, elapsed 0s, " +
 	"remain unknown"
 
-// smokeTreeRecs mirrors the tree of the test under README "Definition
+// smokeTreeRecs mirrors the README smoke-test tree layout: /d/t1 and
-// of done": /d/t1 and /d/t2 are identical, /d/t3 differs from them only
+// /d/t2 are identical, /d/t3 differs from them only by one filename.
-// by one filename. Each file takes one 4 KiB block on disk.
 func smokeTreeRecs() []scanRec {
 	f1Head, f1Tail, f1Content := testHash("f1h"), testHash("f1t"), testHash("f1c")
 	f2Head, f2Tail, f2Content := testHash("f2h"), testHash("f2t"), testHash("f2c")
 
 	return []scanRec{
-		{size: 3000, diskSize: 4096, head: f1Head, tail: f1Tail,
+		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t1/f1"},
-			content: f1Content, path: "/d/t1/f1"},
+		{size: 100, head: f2Head, tail: f2Tail, content: f2Content, path: "/d/t1/sub/f2"},
-		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
+		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t2/f1"},
-			content: f2Content, path: "/d/t1/sub/f2"},
+		{size: 100, head: f2Head, tail: f2Tail, content: f2Content, path: "/d/t2/sub/f2"},
-		{size: 3000, diskSize: 4096, head: f1Head, tail: f1Tail,
+		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t3/f1"},
-			content: f1Content, path: "/d/t2/f1"},
+		{size: 100, head: f2Head, tail: f2Tail, content: f2Content,
-		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
+			path: "/d/t3/sub/f2renamed"},
-			content: f2Content, path: "/d/t2/sub/f2"},
-		{size: 3000, diskSize: 4096, head: f1Head, tail: f1Tail,
-			content: f1Content, path: "/d/t3/f1"},
-		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
-			content: f2Content, path: "/d/t3/sub/f2renamed"},
 	}
 }
 
@@ -204,33 +198,13 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 			code, exitOK, stderr.String())
 	}
 
-	want := "first\tdupe\tfiles\tsize\tdisk_size\n" +
+	want := "first\tdupe\tfiles\tsize\n" +
-		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\t4096\n"
+		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\n"
 	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 }
 
-// TestRunTreesDiskSize runs trees on two copies of a tree whose files
-// take different space on disk. The row's disk_size is the sum over the
-// dupe copy's files, those in its subdirectory included.
-func TestRunTreesDiskSize(t *testing.T) {
-	f, g := testHash("f"), testHash("g")
-	recs := []scanRec{
-		{size: 10, diskSize: 4096, head: f, tail: f, content: f, path: "/a/f"},
-		{size: 20, diskSize: 4096, head: g, tail: g, content: g, path: "/a/sub/g"},
-		{size: 10, diskSize: 512, head: f, tail: f, content: f, path: "/b/f"},
-		{size: 20, diskSize: 1024, head: g, tail: g, content: g, path: "/b/sub/g"},
-	}
-
-	t.Setenv(databaseEnv, seedDatabase(t, recs))
-
-	want := "first\tdupe\tfiles\tsize\tdisk_size\n/a\t/b\t2\t30\t1536\n"
-	if got := runStdout(t, cmdTrees); got != want {
-		t.Errorf("stdout = %q, want %q", got, want)
-	}
-}
-
 // TestRunTreesProgressNamesEachPhase runs trees on the smoke-test
 // records with stderr not a terminal, and checks every line it prints
 // there. After the line naming the database, each phase prints a line
@@ -252,8 +226,7 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
 			code, exitOK, stderr())
 	}
 
-	report := "first\tdupe\tfiles\tsize\tdisk_size\n" +
+	report := "first\tdupe\tfiles\tsize\n/d/t1\t/d/t2\t2\t3100\n"
-		"/d/t1\t/d/t2\t2\t3100\t8192\n"
 	if got := stdout.String(); got != report {
 		t.Errorf("stdout = %q, want %q", got, report)
 	}
@@ -318,9 +291,7 @@ func TestWriteTreeGroupsOnTerminal(t *testing.T) {
 		shown = append(shown, line[strings.LastIndex(line, "\r")+1:])
 	}
 
-	want := []string{
+	want := []string{"first\tdupe\tfiles\tsize", "/d/t1\t/d/t2\t2\t3100"}
-		"first\tdupe\tfiles\tsize\tdisk_size", "/d/t1\t/d/t2\t2\t3100\t8192",
-	}
 	if len(shown) < len(want) || !slices.Equal(shown[:len(want)], want) {
 		t.Errorf("terminal shows lines %q, want %q first", shown, want)
 	}