Hold a lock so a second scan fails at once (closes #53)
check / check (push) Successful in 1m43s

scan takes an exclusive flock(2) on a lock file beside the database
(its path with .lock appended) before it walks anything or opens the
database, and holds it until it returns. A second scan against the
same database fails at once with a one-line error naming the lock
file and exits 1. report and trees never take the lock. The lock ends
with the process, so a fatal error or an interrupt releases it; the
file is never deleted. golang.org/x/sys becomes a direct dependency.

The README smoke test now keeps the database outside the scanned
tree, where its empty lock file would have joined the empty-file
group.

Model: opus-5-5
This commit was merged in pull request #75.
This commit is contained in:
2026-10-04 02:30:21 +02:00
parent 01ff3bb5f0
commit 705c8729ca
6 changed files with 180 additions and 15 deletions
+47
View File
@@ -11,6 +11,7 @@ import (
"slices"
"strconv"
"golang.org/x/sys/unix"
// The pure-Go SQLite driver, registered as "sqlite"; keeps cgo
// disabled.
_ "modernc.org/sqlite"
@@ -32,6 +33,11 @@ const schemaVersion = 1
// scan.
const dbDirPerm = 0o755
// lockFilePerm is the mode for the scan lock file. Anyone who can open
// the file can hold the lock and keep every scan from running, so it
// is open to its owner only.
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.
const createTableSQL = `
@@ -64,6 +70,10 @@ var errNoDatabase = errors.New(
// does not understand.
var errSchemaVersion = errors.New("unsupported database schema version")
// errScanRunning reports that another scan holds the lock on the
// database.
var errScanRunning = errors.New("another scan is running")
// databasePath resolves the database location: SFDUPES_DATABASE when
// set and non-empty, the compiled-in default otherwise.
func databasePath() string {
@@ -104,6 +114,43 @@ func openDB(path, params string) (*sql.DB, error) {
return db, nil
}
// lockScanDatabase takes the lock that keeps a second scan off the
// database at path: an exclusive flock(2) on the file beside it named
// path with ".lock" appended, created along with the database's parent
// directory if missing. A lock held by another scan fails at once
// instead of waiting. The lock lasts until the returned file is closed
// or the process ends. The file is never deleted: a scan that deleted
// it would let the next scan lock a new file while another still holds
// the old one.
func lockScanDatabase(path string) (*os.File, error) {
err := os.MkdirAll(filepath.Dir(path), dbDirPerm)
if err != nil {
return nil, fmt.Errorf("create database directory: %w", err)
}
lockPath := path + ".lock"
//nolint:gosec // the operator chooses the database path
f, err := os.OpenFile(lockPath, os.O_RDWR|os.O_CREATE, lockFilePerm)
if err != nil {
return nil, err
}
err = unix.Flock(int(f.Fd()), unix.LOCK_EX|unix.LOCK_NB)
if err != nil {
_ = f.Close()
if errors.Is(err, unix.EWOULDBLOCK) {
return nil, fmt.Errorf("%w (lock held on %s)",
errScanRunning, lockPath)
}
return nil, fmt.Errorf("lock %s: %w", lockPath, err)
}
return f, nil
}
// openScanDatabase opens the database for the scan subcommand, creating
// the file, its parent directory, and the schema as needed.
func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {