Keep the record count and total size in a totals table (closes #146)

info counted the records and added up their sizes with a query that
reads every record, which takes minutes on a large database. The
schema now has a totals table of one row, kept current by three
triggers on files, in the transaction of each insert, delete and size
update. info, scan's load phase and the read phases of report and
trees read that row instead of counting over files. scan writes files
with the same statements as before. Each of those writes now fires a
trigger and is slower, so scan keeps SQLite's temporary data in
memory, which wins back part of that time.

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,
@@ -116,13 +115,11 @@ 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
 `
@@ -539,8 +536,8 @@ 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 +551,7 @@ 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 +586,10 @@ 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 {
@@ -729,15 +724,15 @@ 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 +741,16 @@ 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 +768,21 @@ 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 +791,10 @@ 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 +808,6 @@ 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 +833,7 @@ 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 +846,6 @@ 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,

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: {

main_test.go

@@ -394,7 +394,7 @@ 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 +649,7 @@ 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 +687,8 @@ 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 +714,8 @@ 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 +774,8 @@ 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 +818,6 @@ 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 {
@@ -1158,9 +1141,8 @@ 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 +1176,9 @@ 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 +1213,8 @@ 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 +1235,7 @@ 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 +1280,9 @@ 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 +1341,7 @@ 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 +1446,8 @@ 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))

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

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;
@@ -476,24 +472,24 @@ 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 +547,6 @@ 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
-		// only seconds after the write.
-		if old.diskSize != ev.rec.diskSize {
-			s.diskSizes = append(s.diskSizes, ev.rec)
-		}
 	}
 
 	prog.finish()
@@ -706,13 +695,12 @@ 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 +716,7 @@ 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 +727,9 @@ 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 +741,7 @@ 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 +756,6 @@ 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)
 }
 
@@ -979,12 +961,11 @@ 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 +1145,11 @@ 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 +1241,6 @@ 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

@@ -42,24 +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 new file's
-// blocks only seconds after the write, and fsync does not hasten that.
-// A test therefore calls unix.Sync, which waits for it, before the scan
-// whose disk_size it compares with this.
-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)
@@ -1082,9 +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()
 
@@ -1435,116 +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
-
-	want := diskSizeOf(t, p)
-	if want == 0 || want >= length {
-		t.Fatalf("the file takes %d bytes on disk, want more than none "+
-			"and fewer than its length %d", want, length)
-	}
-
-	for _, operand := range []string{filepath.Dir(p), p} {
-		db := openTestDB(t)
-		syncTree(t, db, operand)
-
-		got := recordByPath(t, dbRecords(t, db), p).diskSize
-		if got != want {
-			t.Errorf("scan of %s: disk_size = %d, want %d",
-				operand, got, want)
-		}
-	}
-}
-
-// 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)
-
-	before := 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)
-	}
-
-	unix.Sync() // see diskSizeOf
-
-	want := diskSizeOf(t, p)
-	if want == before {
-		t.Fatalf("the file still takes %d bytes on disk after the write "+
-			"into its hole", want)
-	}
-
-	st := syncTree(t, db, dir)
-	if st != (scanStats{walked: 1, updated: 1}) {
-		t.Fatalf("rescan stats = %+v, want 1 updated", st)
-	}
-
-	got := recordByPath(t, dbRecords(t, db), p).diskSize
-	if got != want {
-		t.Errorf("disk_size = %d, want %d", got, want)
-	}
-}
-
-// 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
-
-	// A file read again would count as updated.
-	st := syncTree(t, db, dir)
-	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 want := diskSizeOf(t, p); got != want {
-		t.Errorf("disk_size = %d, want %d", got, want)
-	}
-}
-
 // 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,
@@ -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)
 	}