Evict archive writers on deletion and sweep idle archives (closes #89) (#95)

Per-webhook archive writers are now evicted when the webhook or its last
database target is deleted, and a background sweeper prunes expired rows from
idle archives that no longer receive writes. Archive files themselves are never
deleted.

internal/delivery/target_database_archive.go

@@ -24,6 +24,20 @@ const archiveExpiryNever = "never"
 // offline archiving, but never more than once per this window.
 const archiveReopenDebounce = time.Second
 
+const (
+	// archiveModeCreate is the SQLite URI mode used by the write
+	// path: open the archive file, creating it if missing, so a
+	// first write (or a write after the operator moved the file
+	// away) recreates it.
+	archiveModeCreate = "rwc"
+
+	// archiveModeExisting is the SQLite URI mode used by the idle
+	// sweep: open read-write but never create. A sweep must never
+	// conjure an empty archive file for a webhook that has a
+	// database target but has never received an event.
+	archiveModeExisting = "rw"
+)
+
 var (
 	// errArchiveMissingWebhookID is returned when an event to
 	// archive has no webhook id to key its archive file on.
@@ -44,6 +58,15 @@ var (
 	errArchiveExpiryNotPositive = errors.New(
 		"expiry must be a positive duration or \"never\"",
 	)
+
+	// errArchiveWriterEvicted is returned when a writer that has
+	// been evicted (its webhook was deleted, or its last database
+	// target was removed) is used again. An evicted writer is no
+	// longer in the registry, so reopening its file would leak a
+	// handle nothing owns.
+	errArchiveWriterEvicted = errors.New(
+		"archive writer has been evicted",
+	)
 )
 
 // databaseTargetConfig is the optional per-target JSON config
@@ -161,6 +184,25 @@ type archiveWriter struct {
 	db         *gorm.DB
 	lastReopen time.Time
 	reopens    int
+
+	// evicted marks a writer that has been removed from the
+	// per-webhook registry. Its handle is closed and it must
+	// never open the file again: nothing holds it any more, so a
+	// reopen would leak the handle for the process lifetime.
+	evicted bool
+
+	// sweepOwned marks a registry entry that the idle sweep
+	// created because no writer was cached for the webhook. The
+	// sweep removes such an entry again when it is done, so a
+	// sweep can never leave — or resurrect — a registry entry
+	// for a webhook that has been deleted. A delivery that adopts
+	// the writer clears the flag, handing the entry to the
+	// registry proper.
+	//
+	// Unlike every other field here it is guarded by
+	// databaseTarget.mu, not by this writer's mu: it describes the
+	// registry entry rather than the file.
+	sweepOwned bool
 }
 
 // newArchiveWriter builds an archiveWriter for a file path with
@@ -185,6 +227,12 @@ func (w *archiveWriter) write(
 	w.mu.Lock()
 	defer w.mu.Unlock()
 
+	if w.evicted {
+		return fmt.Errorf(
+			"%w: %s", errArchiveWriterEvicted, w.path,
+		)
+	}
+
 	if w.db == nil || !fileExists(w.path) {
 		err := w.reopen(expiry)
 		if err != nil {
@@ -212,7 +260,19 @@ func (w *archiveWriter) write(
 // its schema, records the reopen time, and prunes expired rows
 // when expiry is positive.
 func (w *archiveWriter) open(expiry time.Duration) error {
-	dbURL := fmt.Sprintf("file:%s?mode=rwc", w.path)
+	return w.openMode(archiveModeCreate, expiry)
+}
+
+// openMode opens the archive file with the given SQLite URI
+// mode, migrates its schema, records the reopen time, and
+// prunes expired rows when expiry is positive. The write path
+// passes archiveModeCreate so a missing file is recreated; the
+// idle sweep passes archiveModeExisting so a missing file is an
+// error rather than a newly conjured empty archive.
+func (w *archiveWriter) openMode(
+	mode string, expiry time.Duration,
+) error {
+	dbURL := fmt.Sprintf("file:%s?mode=%s", w.path, mode)
 
 	sqlDB, err := sql.Open("sqlite", dbURL)
 	if err != nil {
@@ -275,11 +335,70 @@ func (w *archiveWriter) close() {
 	w.db = nil
 }
 
+// sweepExpired prunes an archive that may have gone idle, with
+// no write to trigger the usual on-reopen prune. It takes the
+// writer's own mutex for the whole operation, so a sweep is
+// ordered against concurrent writes rather than reaching around
+// them to the file.
+//
+// It never creates the archive file: a missing file is skipped,
+// and the reopen uses archiveModeExisting so SQLite itself
+// refuses to create one if the file disappears between the
+// check and the open.
+//
+// The archive is left CLOSED afterwards. An idle archive holding
+// no handle is what keeps the operator's move-the-file-away
+// workflow working; the next write reopens (and recreates) the
+// file as it always has.
+func (w *archiveWriter) sweepExpired(expiry time.Duration) error {
+	w.mu.Lock()
+	defer w.mu.Unlock()
+
+	if w.evicted {
+		return fmt.Errorf(
+			"%w: %s", errArchiveWriterEvicted, w.path,
+		)
+	}
+
+	if !fileExists(w.path) {
+		return nil
+	}
+
+	// Drop any live handle first so the prune runs against a
+	// freshly opened file, matching the write path's semantics.
+	w.close()
+
+	err := w.openMode(archiveModeExisting, expiry)
+	if err != nil {
+		return err
+	}
+
+	w.close()
+
+	return nil
+}
+
+// evict closes the writer's handle and marks it unusable. It is
+// called when the writer leaves the registry, either because the
+// webhook was deleted or because its last database target was
+// removed. The archive FILE is deliberately left on disk: it is
+// long-term storage an operator may still want.
+func (w *archiveWriter) evict() {
+	w.mu.Lock()
+	defer w.mu.Unlock()
+
+	w.evicted = true
+
+	w.close()
+}
+
 // prune deletes archived rows older than expiry, measured from
-// each row's archived time. It runs on every (re)open, and
-// because the file is reopened after writes this keeps the
-// archive swept without a separate background sweeper. Failures
-// are logged, not fatal: a prune error must not stop archiving.
+// each row's archived time. It runs on every (re)open, so a
+// steadily written archive is swept by its own write traffic. An
+// archive that goes idle receives no further reopens, which is
+// why ArchiveSweeper exists to drive sweepExpired on a timer.
+// Failures are logged, not fatal: a prune error must not stop
+// archiving.
 func (w *archiveWriter) prune(expiry time.Duration) {
 	cutoff := time.Now().Add(-expiry)