Walk an operand below .zfs or a symlink on its own (closes #142)

An operand under another was dropped as covered by it even when a
directory between them was named .zfs or was a symlink. The walk of
the outer operand enters neither, so the files under the inner operand
went unscanned and their records were deleted. walkReaches now reports
such an operand as not reached, so pruneRoots keeps it and walks it on
its own. README lists both cases with the others.

Judgement call: the new constant zfsDirName replaces the .zfs literal
in operandWarning and subdirJob too, because goconst rejects a third
copy.

Model: opus-5-5

README.md

@@ -33,14 +33,14 @@ export SFDUPES_DATABASE="$HOME/.local/share/sfdupes/db.sqlite"
 ```
 
 `scan` walks one or more filesystem trees and maintains one database record per
-regular file (path, size, size on disk, mtime, head hash, tail hash, content
-hash). The database persists between runs. A rescan hashes only the files that
-are new or changed, and removes the records of files that no longer exist.
-`report` reads the database and prints the file-level duplicates report. `trees`
-reads the same database and prints the duplicate-tree report. `info` prints the
-database's details: its path, the sizes of its files and the number of its
-records. A missing/invalid subcommand — or a `scan` invocation with no `PATH`
-operand — prints a usage message and exits 2.
+regular file (path, size, mtime, head hash, tail hash, content hash). The
+database persists between runs. A rescan hashes only the files that are new or
+changed, and removes the records of files that no longer exist. `report` reads
+the database and prints the file-level duplicates report. `trees` reads the same
+database and prints the duplicate-tree report. `info` prints the database's
+details: its path, the sizes of its files and the number of its records. A
+missing/invalid subcommand — or a `scan` invocation with no `PATH` operand —
+prints a usage message and exits 2.
 
 The database defaults to `/var/lib/sfdupes/db.sqlite` and can be placed anywhere
 by setting `SFDUPES_DATABASE`. The intended deployment is a daily `sfdupes scan`
@@ -386,7 +386,6 @@ All four subcommands operate on a single SQLite database file:
     CREATE TABLE files (
         path       BLOB PRIMARY KEY,  -- absolute path, raw bytes
         size       INTEGER NOT NULL,  -- bytes, from lstat
-        disk_size  INTEGER NOT NULL,  -- bytes allocated on disk (st_blocks × 512), from lstat
         mtime      INTEGER NOT NULL,  -- whole Unix seconds of the mtime, from lstat
         mtime_nsec INTEGER NOT NULL,  -- nanoseconds within that second, 0 to 999999999
         head       BLOB NOT NULL,     -- raw 32-byte SHA-256 of the first 64 KiB
@@ -394,20 +393,6 @@ All four subcommands operate on a single SQLite database file:
         content    BLOB NOT NULL      -- raw 32-byte SHA-256; whole file under 100 MiB, else samples
     ) WITHOUT ROWID;
     CREATE INDEX files_signature ON files (size, head, tail, content);
-    CREATE TABLE totals (
-        records INTEGER NOT NULL,  -- number of records in files
-        size    INTEGER NOT NULL   -- sizes of all records in files added up
-    );
-    INSERT INTO totals (records, size) VALUES (0, 0);
-    CREATE TRIGGER totals_after_insert AFTER INSERT ON files BEGIN
-        UPDATE totals SET records = records + 1, size = size + NEW.size;
-    END;
-    CREATE TRIGGER totals_after_delete AFTER DELETE ON files BEGIN
-        UPDATE totals SET records = records - 1, size = size - OLD.size;
-    END;
-    CREATE TRIGGER totals_after_update AFTER UPDATE OF size ON files BEGIN
-        UPDATE totals SET size = size + NEW.size - OLD.size;
-    END;
     ```
 
     Paths are stored as BLOBs because Unix paths are raw bytes, not guaranteed
@@ -421,17 +406,6 @@ All four subcommands operate on a single SQLite database file:
     `files_signature` index lets `report` read the records in signature order
     without sorting the table.
 
-    `totals` holds one row: the number of records in `files` and the sum of
-    their sizes. Three triggers on `files` keep that row current. Each runs in
-    the transaction of the change to `files` that fires it, so the row and the
-    records always agree. `info` reads both numbers from this row. `scan`,
-    `report` and `trees` read the number of records from it as the total of
-    their progress displays. Counting the records in `files` would read every
-    record, which takes minutes on a database of tens of millions. The triggers
-    make each write to `files` slower, so a first scan of many small files takes
-    about two fifths longer. On large files, where reading them takes most of
-    the time, the difference is small.
-
 ### Duplicate detection
 
 Two files are duplicates when they have the same size and the same three hashes.
@@ -481,32 +455,29 @@ scan and are enumerated concurrently: every operand seeds the shared walk worker
 pool. Overlapping operands are harmless — an operand that duplicates another or
 lies under another is dropped before walking, so every file is reached exactly
 once and produces one database record. An operand under another one is kept,
-though, and walked on its own when any directory from it (from its directory,
-for a regular file) up to but not including the operand covering it is a default
-exclude, is not on a persistent filesystem (see "Rules for the walk"), or, with
-`-x`, is on a different filesystem than that operand, because that operand's
-walk does not enter such a directory and so does not reach it.
+though, when the walk of the outer operand does not reach it. It is then walked
+on its own. The walk of the outer operand does not reach the inner one when it,
+or any directory between the two, is:
 
-An operand is not scanned when it is:
+- named `.zfs`;
+- a symlink;
+- a default exclude;
+- not on a persistent filesystem (see "Rules for the walk");
+- with `-x`, on a different filesystem than the outer operand.
 
-- a symlink, which `scan` never follows, not even as an operand;
-- a socket, FIFO or device node;
-- at or inside a directory named `.zfs`.
+For a regular-file operand, only the directories between the two count.
 
-An operand reached through a symlink into a `.zfs` directory is not scanned
-either.
-
-This holds even when the operand lies under another operand. `scan` prints a
-one-line warning naming the path and what it is, counts it as skipped, and drops
-it from the scanned operands before reading the database. An operand beneath a
-symlink operand is still scanned. The records stored beneath the dropped operand
-are not deleted: they are treated like any other record outside the scanned
-operands. If it lies under another operand, they are under that operand instead,
-and are treated like any other record there. This is not an error: a scan whose
-every operand is dropped walks nothing and exits 0. An operand that is not on a
-persistent filesystem (see "Rules for the walk") is dropped the same way. The
-line `scan` prints for it is not a warning, though, and it is not counted as
-skipped.
+An operand that is a symlink (never followed, not even as an operand), socket,
+FIFO, or device node, or a directory named `.zfs`, is not scanned. `scan` prints
+a one-line warning naming the path and what it is, counts it as skipped, and
+drops it from the scanned operands before reading the database. Another operand
+beneath it is still scanned. The records stored beneath it are not deleted: they
+are treated like any other record outside the scanned operands. If it lies under
+another operand, they are under that operand instead, and are treated like any
+other record there. This is not an error: a scan whose every operand is dropped
+walks nothing and exits 0. An operand that is not on a persistent filesystem
+(see "Rules for the walk") is dropped the same way. The line `scan` prints for
+it is not a warning, though, and it is not counted as skipped.
 
 `scan` synchronizes the database with the filesystem state under the scanned
 operands:
@@ -553,7 +524,7 @@ hash phase:
     files; per-directory parallelism is what makes the walk tractable on large
     or busy pools. The walk compares each file with its record as it goes, and
     an unchanged file needs nothing more. Every new or changed file is carried
-    to the hash phase as a (path, size, size on disk, mtime) record.
+    to the hash phase as a (path, size, mtime) record.
 3.  **hash** — the worker pool hashes every carried file as described in
     "Duplicate detection" above, which gives the file its `head`, `tail` and
     `content`. Zero-length files have constant hashes and are never opened.
@@ -714,18 +685,14 @@ Processing:
   database state.
 
 `report` runs in two phases, each with its own progress display on stderr (see
-"Progress"):
-
-- `open` opens the database.
-- `read` gets the number of records from `totals`, then reads the records in
-  signature order, largest size first.
-
-Signature order, largest size first, is the `files_signature` index read
-backwards, so SQLite sorts nothing and returns the first record at once. The
-records sharing a signature come together, and so do the records of one size, so
-`report` holds only the duplicate groups of the size it is reading, and writes
-them, ordered by `first` path, once it reaches a smaller size. Its memory holds
-at most the duplicate paths of one size at a time, never every record.
+"Progress"): `open` opens the database; `read` counts the records, then reads
+them in signature order, largest size first. That is the order of the
+`files_signature` index read backwards, so SQLite sorts nothing and returns the
+first record at once. The records sharing a signature come together, and so do
+the records of one size, so `report` holds only the duplicate groups of the size
+it is reading, and writes them, ordered by `first` path, once it reaches a
+smaller size. Its memory holds at most the duplicate paths of one size at a
+time, never every record.
 
 #### Report output format
 
@@ -799,37 +766,22 @@ Processing:
   ascending. Output must be fully deterministic for a given input.
 
 `trees` runs in four phases, each with its own progress display on stderr (see
-"Progress"):
-
-- `open` opens the database.
-- `read` gets the number of records from `totals`, then reads the records in
-  path order, building the hierarchy and computing the digests as it goes.
-- `group` groups the directories by digest and picks the maximal groups.
-- `write` writes the groups to stdout.
+"Progress"): `open` opens the database; `read` counts the records, then reads
+them in path order, building the hierarchy and computing the digests as it goes;
+`group` groups the directories by digest and picks the maximal groups; `write`
+writes the groups to stdout.
 
 #### Trees output format
 
 TSV on stdout: a header line, then one row per duplicate tree (N-1 rows for a
-group of N). After the `first` and `dupe` paths come three numbers:
-
-- `files`, the number of regular files in one copy of the tree, counted
-  recursively;
-- `size`, the bytes of one copy, its files' sizes added up;
-- `disk_size`, the bytes the `dupe` copy takes on disk, its files' `disk_size`
-  added up.
+group of N). `files` is the recursive regular-file count of one copy of the
+tree; `size` is the recursive total byte size of one copy:
 
 ```
-first	dupe	files	size	disk_size
-/srv/a/project	/srv/backup/project	3417	104857600	61865984
+first	dupe	files	size
+/srv/a/project	/srv/backup/project	3417	104857600
 ```
 
-A file's `disk_size` is the space its blocks take on disk. It is less than the
-file's size on a compressed or sparse file, and a little more on most other
-files. Two copies of one tree can therefore differ in `disk_size`. When a file
-in one copy is a hard link to one in the other, both copies count its blocks in
-full. Removing it from one copy then frees nothing, as the known limitation
-under "`trees` mode" says.
-
 The `first` and `dupe` paths are escaped as described under "Report output
 format". The root directory's path is `/`.
 
@@ -864,19 +816,15 @@ size of recorded files	150000000000000 (136.4 TiB)
   database is in WAL mode, the newest changes may be in the `-wal` file alone.
 - `schema version` is the database's `PRAGMA user_version`. A database with
   another version than this build's is refused, as by `report`.
-- `records` is the number of records. `size of recorded files` is the sum of the
-  sizes of all records, in bytes, then in human units.
+- `records` is the number of records. `size of recorded files` adds up the sizes
+  of all records, in bytes, then in human units.
 
 `info` runs in two phases, each with its own progress display on stderr (see
-"Progress"):
-
-- `open` opens the database.
-- `count` reads the schema version and the row of `totals` (see "Database").
-  Both reads run in one read-only transaction, so the numbers agree with each
-  other while a scan is committing.
-
-`info` writes its lines once the `count` display has ended, so on a terminal
-they come after the displays.
+"Progress"): `open` opens the database; `count` reads the schema version and
+counts the records with one query, a single pass over the table, both in one
+read-only transaction, so the numbers agree with each other while a scan is
+committing. `info` writes its lines once the `count` display has ended, so on a
+terminal they come after the displays.
 
 ### Progress
 
@@ -892,9 +840,8 @@ progress, its elapsed time and its time remaining.
 A scan has four phases (`[1/4] load`, `[2/4] walk`, `[3/4] hash`,
 `[4/4] update`):
 
-- `load` gets the number of records from `totals` first, then reads the records
-  against that number. Until it has the number, the display says it is counting
-  the records.
+- `load` counts the records first, then reads them against that count. While the
+  count runs, the display says it is counting the records.
 - `walk` has no exact total. Its estimate is the number of records the last scan
   left under the operands, known once `load` is done and shown with a `~`. The
   time remaining is unknown once the walk passes the estimate, and when there
@@ -907,9 +854,8 @@ A scan has four phases (`[1/4] load`, `[2/4] walk`, `[3/4] hash`,
 
 - `open` has no total. While it opens the database, waiting on a busy one
   included, the display says it is opening the database.
-- `read` gets the number of records from `totals` first, then reads the records
-  against that number. Until it has the number, the display says it is counting
-  the records.
+- `read` counts the records first, then reads them against that count. While the
+  count runs, the display says it is counting the records.
 - `group` has the directories `read` found as its total, and `write` the
   duplicate-tree groups.
 
@@ -917,16 +863,17 @@ A scan has four phases (`[1/4] load`, `[2/4] walk`, `[3/4] hash`,
 
 - `open` has no total. While it opens the database, waiting on a busy one
   included, the display says it is opening the database.
-- `read` gets the number of records from `totals` first, then reads the records
-  against that number, writing the rows to stdout as it goes. Until it has the
-  number, the display says it is counting the records.
+- `read` counts the records first, then reads them against that count, writing
+  the rows to stdout as it goes. While the count runs, the display says it is
+  counting the records.
 
 `info` has two phases (`[1/2] open`, `[2/2] count`, see "`info` mode"):
 
 - `open` has no total. While it opens the database, waiting on a busy one
   included, the display says it is opening the database.
-- `count` has no total either, because it reads one row: the display says it is
-  counting the records until it has the row, and its time remaining is unknown.
+- `count` has no total either, because one query counts everything: the display
+  says it is counting the records until the query returns, and its time
+  remaining is unknown.
 
 Each display is one line holding:
 
@@ -1213,9 +1160,9 @@ All of the following, run in this directory, must pass:
     ordered by size descending.
 
     Expected from `trees`: exactly one row — `first` `$d/t1`, `dupe` `$d/t2`, 2
-    files, 3100 bytes, and a `disk_size` that depends on the filesystem.
-    `$d/t1/sub` vs `$d/t2/sub` is suppressed as non-maximal (implied by the
-    `t1`/`t2` group), and `t3` appears nowhere (its file set differs by name).
+    files, 3100 bytes. `$d/t1/sub` vs `$d/t2/sub` is suppressed as non-maximal
+    (implied by the `t1`/`t2` group), and `t3` appears nowhere (its file set
+    differs by name).
 
     Expected from the second `report` (after the modify/delete rescan):
     `one.bin` has left its group (its content changed), so

TODO.md

@@ -29,23 +29,10 @@
 
 # Completed Steps
 
-- each record holds `disk_size`, the bytes the file takes on disk: its allocated
-  blocks, `st_blocks` × 512, from the lstat the walk already does. `trees`
-  prints a `disk_size` column after `size`, the sum over the `dupe` copy's
-  files; on a compressed or sparse file it differs from `size` (2026-10-27,
-  https://git.eeqj.de/sneak/sfdupes/issues/147)
-
-- the database keeps the number of records and the sum of their sizes in the one
-  row of a `totals` table, which three triggers on `files` keep current. `info`
-  reads that row, and so do `scan`'s `load` phase and the `read` phases of
-  `report` and `trees` for their totals; no count reads every record any more.
-  The triggers make each write to `files` slower. `scan` keeps SQLite's
-  temporary data in memory, which wins back part of that time (2026-10-27,
-  https://git.eeqj.de/sneak/sfdupes/issues/146)
-
-- an operand at or inside a directory named `.zfs` is never scanned, whether
-  given alone or under another operand. `scan` warns about it, counts it as
-  skipped and does not walk it (2026-10-26,
+- an operand under another is walked on its own when a directory between them,
+  the inner operand included, is named `.zfs` or is a symlink. The walk of the
+  outer operand does not reach it then. `scan` now records the files below it
+  and no longer deletes their records (2026-10-26,
   https://git.eeqj.de/sneak/sfdupes/issues/142)
 
 - a file or directory removed while the scan runs is not an error, in the walk

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.
-// disk_size holds the bytes the file takes on disk. mtime holds whole
-// Unix seconds and mtime_nsec the nanoseconds within that second. head,
-// tail and content each hold the raw 32 bytes of a SHA-256.
+// BLOBs because Unix paths are raw bytes, not guaranteed UTF-8. mtime
+// holds whole Unix seconds and mtime_nsec the nanoseconds within that
+// second. head, tail and content each hold the raw 32 bytes of a
+// 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 (
-    path, size, disk_size, mtime, mtime_nsec, head, tail, content
-)
-VALUES (?, ?, ?, ?, ?, ?, ?, ?)
+INSERT INTO files (path, size, mtime, mtime_nsec, head, tail, content)
+VALUES (?, ?, ?, ?, ?, ?, ?)
 ON CONFLICT (path) DO UPDATE SET
-    size = excluded.size, disk_size = excluded.disk_size,
-    mtime = excluded.mtime, mtime_nsec = excluded.mtime_nsec,
+    size = excluded.size, mtime = excluded.mtime,
+    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=temp_store(MEMORY)"
+	"&_pragma=synchronous(NORMAL)"
 
 // 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{
-		createTableSQL, createIndexSQL, createTotalsSQL, insertTotalsSQL,
-		totalsAfterInsertSQL, totalsAfterDeleteSQL, totalsAfterUpdateSQL,
-	} {
-		_, err = tx.ExecContext(ctx, stmt)
-		if err != nil {
-			return fmt.Errorf("create schema: %w", err)
-		}
+	_, err = tx.ExecContext(ctx, createTableSQL)
+	if err != nil {
+		return fmt.Errorf("create schema: %w", err)
+	}
+
+	_, err = tx.ExecContext(ctx, createIndexSQL)
+	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, "+
-			"content FROM files ORDER BY path")
+		"SELECT path, size, mtime, mtime_nsec, head, tail, content "+
+			"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,
-			&head, &tail, &content)
+		err = rows.Scan(&path, &r.size, &sec, &nsec, &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
-// disk_size, in the order of signatureRowsSQL. The count and the
-// records are read in one transaction, so they agree while a scan is
-// committing. An error from fn stops the reading and is returned as it
-// is.
+// every record's signature and path to fn, without its mtime, in the
+// order of signatureRowsSQL. The count and the records are read in one
+// transaction, so they agree while a scan is committing. An error from
+// fn stops the reading and is returned as it 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
-// records added up from totals.
+// databaseCountsSQL counts the records and adds up their sizes, in one
+// 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
@@ -838,7 +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 {

db_test.go

@@ -535,12 +535,17 @@ func TestLoadRowsRefuseWrongSizeHash(t *testing.T) {
 	}
 }
 
-// queryPlan returns the detail of each line of SQLite's EXPLAIN QUERY
-// PLAN for query.
-func queryPlan(t *testing.T, db *sql.DB, query string) []string {
-	t.Helper()
+// 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()
 
-	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()
 

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
-// records and their total size from the totals table). Each display
-// ends before the next phase starts, and before an error is returned
-// to be printed. The details are written once the last display has
-// ended, so no display is drawn while they are written.
+// own on stderr: open (open the database) and count (count the records,
+// with one query). Each display ends before the next phase starts, and
+// before an error is returned to be printed. The details are written
+// once the last display has ended, so no display is drawn while they
+// 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
-// with the database already open: a fatal error on a path that owns an
-// open database. It closes the database the way scan does.
+// schema-version check but has no files table, so the first query
+// fails with the database already open: a fatal error on a path that
+// 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
-			// subcommand's first query reads totals.
-			if !strings.Contains(stderr.String(), "no such table: totals") {
+			// query against the opened database can report this.
+			if !strings.Contains(stderr.String(), "no such table: files") {
 				t.Errorf("stderr = %q, want the failure to come from a "+
 					"query on the open database", stderr.String())
 			}
@@ -929,21 +928,24 @@ func TestRunScanWalksOperandUnderSymlinkOperand(t *testing.T) {
 }
 
 func TestRunScanSkipsZFSOperand(t *testing.T) {
-	zfs := filepath.Join(t.TempDir(), ".zfs")
-	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}})
+	path := testDBPath(t)
 	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
-// database at dbPath.
+// record for kept, which an earlier scan stored beneath operand, still
+// in the database at dbPath.
 func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
 	kept string,
 ) {
@@ -972,121 +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)
@@ -1141,9 +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" +
-		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\t" +
-		strconv.FormatInt(diskSizeOf(t, dupes[1]), 10) + "\n"
+	want := "first\tdupe\tfiles\tsize\n" +
+		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
 	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
@@ -1177,10 +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" + strconv.FormatInt(diskSizeOf(t, dupes[1]), 10) +
-			"\n",
+			"\t1\t300\n",
 	}
 
 	for name, want := range cases {
@@ -1215,9 +1100,8 @@ func assertRunsUseDatabase(t *testing.T, dir, name string) {
 		t.Errorf("report stdout = %q, want %q", got, want)
 	}
 
-	want = "first\tdupe\tfiles\tsize\tdisk_size\n" +
-		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\t" +
-		strconv.FormatInt(diskSizeOf(t, dupes[1]), 10) + "\n"
+	want = "first\tdupe\tfiles\tsize\n" +
+		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
 	if got := runStdout(t, cmdTrees); got != want {
 		t.Errorf("trees stdout = %q, want %q", got, want)
 	}

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

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
-// file takes on disk, which trees adds up.
+// only and used by scan for change detection.
 type scanRec struct {
-	size     int64
-	diskSize int64
-	mtime    time.Time
-	head     [sha256.Size]byte
-	tail     [sha256.Size]byte
-	content  [sha256.Size]byte
-	path     string
+	size    int64
+	mtime   time.Time
+	head    [sha256.Size]byte
+	tail    [sha256.Size]byte
+	content [sha256.Size]byte
+	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
-// records from the totals table, then read the records in signature
-// order, writing each size's duplicate groups to stdout once that size
-// is read; see readReport). Each display ends before the next phase
-// starts, and before an error is returned to be printed.
+// own on stderr: open (open the database) and read (count the records,
+// then read them in signature order, writing each size's duplicate
+// groups to stdout once that size is read; see readReport). Each
+// display ends before the next phase starts, and before an error is
+// 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, diskSize: 4096, head: h, tail: tl, content: c, path: awkwardDir + "/f"},
+		{size: 5, head: h, tail: tl, content: c, path: "/d/A/f"},
+		{size: 5, head: h, tail: tl, content: c, path: awkwardDir + "/f"},
 	}
 }
 

scan.go

@@ -48,21 +48,24 @@ const sampleWindow = 1024 * 1024
 // and hash worker pools.
 const workQueueDepth = 1024
 
+// zfsDirName is the name of the directory in which ZFS shows a
+// filesystem's snapshots. The walk never enters one, since it would
+// list every file once per snapshot.
+const zfsDirName = ".zfs"
+
 // errInterrupted reports a scan stopped by SIGINT or SIGTERM. runScan
 // 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
-// the bytes the file takes on disk. dev and ino identify the underlying
-// inode so hard-linked paths can share one read; both are zero when the
-// platform exposes no inode.
+// fileRec carries one statted file between the scan phases. dev and
+// ino identify the underlying inode so hard-linked paths can share
+// one read; both are zero when the platform exposes no inode.
 type fileRec struct {
-	path     string
-	size     int64
-	diskSize int64
-	mtime    time.Time
-	dev      uint64
-	ino      uint64
+	path  string
+	size  int64
+	mtime time.Time
+	dev   uint64
+	ino   uint64
 }
 
 // fileMeta is the in-memory index entry for one existing database
@@ -274,9 +277,10 @@ func pruneRoots(roots []string, oneFS bool, rules walkRules,
 }
 
 // walkReaches reports whether the walk of operand above reaches r, an
-// operand under it. That walk does not enter a default exclude in
-// rules, nor a directory that device puts on a filesystem in rules that
-// is not persistent, nor, with -x, one that device puts on a different
+// operand under it. That walk never follows a symlink. It does not
+// enter a directory named .zfs, nor a default exclude in rules, nor a
+// directory that device puts on a filesystem in rules that is not
+// persistent, nor, with -x, one that device puts on a different
 // filesystem than above, when device knows above's. It reaches every
 // regular file in a directory it enters, so for a regular-file operand
 // the directories checked start at its directory; they end below above.
@@ -297,6 +301,15 @@ func walkReaches(above, r string, oneFS bool, rules walkRules,
 			return false
 		}
 
+		if filepath.Base(dir) == zfsDirName {
+			return false
+		}
+
+		fi, err = os.Lstat(dir)
+		if err == nil && fi.Mode()&fs.ModeSymlink != 0 {
+			return false
+		}
+
 		dev, ok := device(dir)
 		if !ok {
 			continue
@@ -385,8 +398,7 @@ 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
-	// warning even when it lies under another operand.
+	// under it.
 	roots = pruneRoots(s.walkableRoots(roots, rules), oneFS, rules,
 		deviceOfPath)
 
@@ -414,15 +426,15 @@ 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
-// directory named .zfs. Every other operand is warned about, counted as
-// skipped, and dropped. A dropped operand is no longer a root, so the
-// records stored beneath it are treated as if it had not been given:
-// those under no other root count as outside the roots and are not
-// deleted as unverified. An operand on a filesystem in rules that is not
-// persistent is dropped the same way, with a line saying so that is not
-// a warning, and is not counted as skipped. An operand that fails lstat
-// here is kept, and the walk warns about it unless it no longer exists.
+// files, and directories not named .zfs. Every other operand is warned
+// about, counted as skipped, and dropped. A dropped operand is no
+// longer a root, so the records stored beneath it are treated as if it
+// had not been given: those under no other root count as outside the
+// roots and are not deleted as unverified. An operand on a filesystem
+// in rules that is not persistent is dropped the same way, with a line
+// saying so that is not a warning, and is not counted as skipped. An
+// operand that fails lstat here is kept, and the walk warns about it
+// unless it no longer exists.
 func (s *scanState) walkableRoots(roots []string, rules walkRules) []string {
 	kept := make([]string, 0, len(roots))
 
@@ -457,8 +469,8 @@ 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
-	// records, read first, gives the display its total.
+	// display the scan looks hung before the walk begins. Counting them
+	// first gives the display its total.
 	prog := newProgress(progressParams{
 		label: scanPhase("load"), unit: scanUnit, total: -1,
 		waitingFor: countingRecords, stalledOn: "db",
@@ -697,13 +709,12 @@ func (s *scanState) recordRun(ctx context.Context, r hashResult) error {
 		s.resolve(rec.path)
 
 		s.batch = append(s.batch, scanRec{
-			size:     rec.size,
-			diskSize: rec.diskSize,
-			mtime:    rec.mtime,
-			head:     r.head,
-			tail:     r.tail,
-			content:  r.content,
-			path:     rec.path,
+			size:    rec.size,
+			mtime:   rec.mtime,
+			head:    r.head,
+			tail:    r.tail,
+			content: r.content,
+			path:    rec.path,
 		})
 	}
 
@@ -878,31 +889,16 @@ 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
-// inside a directory named .zfs, neither as given nor with its symlinks
-// resolved. Symlinks are never followed, including as operands.
+// does: a regular file, or a directory not named .zfs. 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(); {
 	case mode.IsRegular():
 		return ""
 	case mode.IsDir():
-		if filepath.Base(root) != ".zfs" {
+		if filepath.Base(root) != zfsDirName {
 			return ""
 		}
 
@@ -964,12 +960,11 @@ func seedRoot(ctx context.Context, root string, rules walkRules,
 
 	dev, ino := inodeOfInfo(fi)
 	rec := fileRec{
-		path:     root,
-		size:     fi.Size(),
-		diskSize: diskSizeOfInfo(fi),
-		mtime:    fi.ModTime(),
-		dev:      dev,
-		ino:      ino,
+		path:  root,
+		size:  fi.Size(),
+		mtime: fi.ModTime(),
+		dev:   dev,
+		ino:   ino,
 	}
 
 	if !isDatabaseFile(rec, rules) {
@@ -1149,12 +1144,11 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
 
 	dev, ino := inodeOfInfo(info)
 	rec := fileRec{
-		path:     p,
-		size:     info.Size(),
-		diskSize: diskSizeOfInfo(info),
-		mtime:    info.ModTime(),
-		dev:      dev,
-		ino:      ino,
+		path:  p,
+		size:  info.Size(),
+		mtime: info.ModTime(),
+		dev:   dev,
+		ino:   ino,
 	}
 
 	if !isDatabaseFile(rec, rules) {
@@ -1174,7 +1168,7 @@ func subdirJob(ctx context.Context, p string, e fs.DirEntry,
 	parent dirJob, oneFS bool, rules walkRules,
 	events chan<- walkEvent,
 ) (dirJob, bool) {
-	if e.Name() == ".zfs" {
+	if e.Name() == zfsDirName {
 		return dirJob{}, false
 	}
 
@@ -1246,23 +1240,6 @@ 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

@@ -42,21 +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.
-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)
@@ -1243,9 +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,
-// and the walk estimates its total from the records under its operand,
-// or says its time remaining is unknown when there are none.
+// among the four: load counts the records before reading them, and the
+// walk estimates its total from the records under its operand, or says
+// its time remaining is unknown when there are none.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestScanProgressNamesEachPhase(t *testing.T) {
@@ -1431,46 +1416,6 @@ func TestScanStoresRawHashes(t *testing.T) {
 	}
 }
 
-// TestScanStoresDiskSize scans a sparse file, which takes less space on
-// disk than its length, and checks the disk_size stored for it against
-// the file's own lstat.
-func TestScanStoresDiskSize(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	db := openTestDB(t)
-	p := writeFile(t, dir, "sparse", []byte("x"))
-
-	// Truncate makes the file longer without giving it blocks for the
-	// new bytes.
-	const length = 1024 * 1024
-
-	err := os.Truncate(p, length)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	syncTree(t, db, dir)
-
-	want := diskSizeOf(t, p)
-	if want >= length {
-		t.Fatalf("the file takes %d bytes on disk, want fewer than its "+
-			"length %d", want, length)
-	}
-
-	var got int64
-
-	err = db.QueryRowContext(t.Context(),
-		"SELECT disk_size FROM files WHERE path = ?", []byte(p)).Scan(&got)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	if 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
@@ -1727,6 +1672,81 @@ func TestSyncScanOverlappingRoots(t *testing.T) {
 	}
 }
 
+// TestScanWalksOperandInZFSDirectory checks that an operand inside a
+// directory named .zfs below another operand is walked on its own,
+// since the walk of the other operand does not enter .zfs. The file
+// under it is recorded, and a second scan keeps the record.
+func TestScanWalksOperandInZFSDirectory(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	db := openTestDB(t)
+	f := writeFile(t, dir, "pool/.zfs/snapshot/daily/f", pattern(1, 10))
+	daily := filepath.Dir(f)
+
+	syncTree(t, db, dir, daily)
+	recordByPath(t, dbRecords(t, db), f)
+
+	syncTree(t, db, dir, daily)
+	recordByPath(t, dbRecords(t, db), f)
+}
+
+// TestScanWalksOperandBehindSymlink checks that an operand reached
+// through a symlinked directory below another operand is walked on its
+// own, since the walk of the other operand does not follow the symlink.
+// The file under it is recorded, and a second scan keeps the record.
+func TestScanWalksOperandBehindSymlink(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	target := t.TempDir()
+	db := openTestDB(t)
+	writeFile(t, target, "sub/f", pattern(1, 10))
+
+	link := filepath.Join(dir, "link")
+
+	err := os.Symlink(target, link)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	sub := filepath.Join(link, "sub")
+	f := filepath.Join(sub, "f")
+
+	syncTree(t, db, dir, sub)
+	recordByPath(t, dbRecords(t, db), f)
+
+	syncTree(t, db, dir, sub)
+	recordByPath(t, dbRecords(t, db), f)
+}
+
+// TestScanDropsOperandReachedBehindSymlink checks that an operand under
+// another one is still dropped when both lie behind the same symlinked
+// directory: the walk of the other operand starts past the symlink and
+// reaches it, so the file under it is walked once.
+func TestScanDropsOperandReachedBehindSymlink(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	target := t.TempDir()
+	db := openTestDB(t)
+	writeFile(t, target, "sub/deeper/f", pattern(1, 10))
+
+	link := filepath.Join(dir, "link")
+
+	err := os.Symlink(target, link)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	sub := filepath.Join(link, "sub")
+
+	st := syncTree(t, db, sub, filepath.Join(sub, "deeper"))
+	if st != (scanStats{walked: 1, added: 1}) {
+		t.Fatalf("stats = %+v, want 1 walked and added", st)
+	}
+}
+
 // TestScanHashesUniqueSize checks that a file whose size no other file
 // shares is hashed like every other file.
 func TestScanHashesUniqueSize(t *testing.T) {
@@ -2140,6 +2160,16 @@ func TestPruneRoots(t *testing.T) {
 		t.Fatalf("pruneRoots with %s not persistent = %q, want %q",
 			pqRoot, got, want)
 	}
+
+	// Nor does it enter a directory named .zfs, so /p/.zfs/s is kept. The
+	// walk of /p/.zfs/s reaches /p/.zfs/s/t, which is dropped.
+	got = pruneRoots([]string{"/p", "/p/.zfs/s", "/p/.zfs/s/t"}, false,
+		walkRules{}, device)
+
+	want = []string{"/p", "/p/.zfs/s"}
+	if !slices.Equal(got, want) {
+		t.Fatalf("pruneRoots with .zfs = %q, want %q", got, want)
+	}
 }
 
 func TestReportsNeverTouchFilesystem(t *testing.T) {

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
-// records from the totals table, then read the records into the
-// hierarchy), group (group the directories by digest) and write (write
-// the groups to stdout). Each display ends before the next phase
-// starts, and before an error is returned to be printed.
+// own on stderr: open (open the database), read (count the records,
+// then read them into the hierarchy), group (group the directories by
+// digest) and write (write the groups to stdout). Each display ends
+// before the next phase starts, and before an error is returned to be
+// 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
-// dupe's own. stdout may be the terminal prog is drawn on, so the lines
-// go through prog's writer. It returns the number of rows (dupe trees)
-// and the bytes they could reclaim.
+// group on prog once its rows are written. stdout may be the terminal
+// prog is drawn on, so the lines go through prog's writer. It returns
+// the number of rows (dupe trees) 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

@@ -17,24 +17,18 @@ const treesOpenLine = "[1/4] open: opening the database, elapsed 0s, " +
 
 // smokeTreeRecs mirrors the README smoke-test tree layout: /d/t1 and
 // /d/t2 are identical, /d/t3 differs from them only 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,
-			content: f1Content, path: "/d/t1/f1"},
-		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
-			content: f2Content, path: "/d/t1/sub/f2"},
-		{size: 3000, diskSize: 4096, head: f1Head, tail: f1Tail,
-			content: f1Content, path: "/d/t2/f1"},
-		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
-			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"},
+		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t1/f1"},
+		{size: 100, head: f2Head, tail: f2Tail, content: f2Content, path: "/d/t1/sub/f2"},
+		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t2/f1"},
+		{size: 100, head: f2Head, tail: f2Tail, content: f2Content, path: "/d/t2/sub/f2"},
+		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t3/f1"},
+		{size: 100, 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" +
-		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\t4096\n"
+	want := "first\tdupe\tfiles\tsize\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" +
-		"/d/t1\t/d/t2\t2\t3100\t8192\n"
+	report := "first\tdupe\tfiles\tsize\n/d/t1\t/d/t2\t2\t3100\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{
-		"first\tdupe\tfiles\tsize\tdisk_size", "/d/t1\t/d/t2\t2\t3100\t8192",
-	}
+	want := []string{"first\tdupe\tfiles\tsize", "/d/t1\t/d/t2\t2\t3100"}
 	if len(shown) < len(want) || !slices.Equal(shown[:len(want)], want) {
 		t.Errorf("terminal shows lines %q, want %q first", shown, want)
 	}