TODO.md

@@ -19,6 +19,8 @@ trial run of the finished image: https://git.eeqj.de/sneak/dnswatcher/issues/149
 
 # Completed Steps
 
+- 2026-10-13: a save syncs the state file to disk before renaming it into place,
+  so a crash cannot leave it empty and stop the next start (closes #264).
 - 2026-10-13: a `PORT` that cannot be bound stops startup with an error naming
   the address, instead of running without the HTTP server (closes #266).
 - 2026-10-13: a bad `PORT`, `DNSWATCHER_TLS_EXPIRY_WARNING` or true/false

internal/state/state.go

@@ -4,6 +4,7 @@ package state
 import (
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"log/slog"
 	"maps"
@@ -253,10 +254,20 @@ func (s *State) Save() error {
 		return fmt.Errorf("creating data directory: %w", err)
 	}
 
-	// Atomic write: write to temp file, then rename
+	// Atomic write: write to temp file, then rename. The temp file is
+	// synced before the rename and the directory after it, or a crash
+	// can leave the renamed state file empty.
 	tmpPath := path + ".tmp"
 
-	err = os.WriteFile(tmpPath, data, filePermissions)
+	//nolint:gosec // path is from trusted config
+	tmpFile, err := os.OpenFile(
+		tmpPath, os.O_WRONLY|os.O_CREATE|os.O_TRUNC, filePermissions,
+	)
+	if err == nil {
+		_, err = tmpFile.Write(data)
+		err = errors.Join(err, tmpFile.Sync(), tmpFile.Close())
+	}
+
 	if err != nil {
 		return fmt.Errorf("writing temp state file: %w", err)
 	}
@@ -266,6 +277,15 @@ func (s *State) Save() error {
 		return fmt.Errorf("renaming state file: %w", err)
 	}
 
+	dir, err := os.Open(filepath.Dir(path))
+	if err == nil {
+		err = errors.Join(dir.Sync(), dir.Close())
+	}
+
+	if err != nil {
+		return fmt.Errorf("syncing data directory: %w", err)
+	}
+
 	s.log.Debug("state saved to disk", "path", path)
 
 	return nil

internal/state/state_test.go

@@ -618,6 +618,53 @@ func TestSaveAtomicWrite(t *testing.T) {
 	}
 }
 
+// TestSaveOverLeftoverTempFile verifies that a temp file left by a
+// crash, longer than the state Save writes, leaves nothing of itself in
+// the state file, and that no temp file remains after Save.
+func TestSaveOverLeftoverTempFile(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	statePath := filepath.Join(dir, "state.json")
+	tmpPath := statePath + ".tmp"
+
+	err := os.WriteFile(tmpPath, []byte(strings.Repeat("x", 64*1024)), 0o600)
+	if err != nil {
+		t.Fatalf("writing leftover temp file: %v", err)
+	}
+
+	s := state.NewForTestWithDataDir(dir)
+
+	populateState(t, s)
+
+	err = s.Save()
+	if err != nil {
+		t.Fatalf("Save() error: %v", err)
+	}
+
+	//nolint:gosec // test file with known path
+	data, err := os.ReadFile(statePath)
+	if err != nil {
+		t.Fatalf("reading state file: %v", err)
+	}
+
+	var snap state.Snapshot
+
+	err = json.Unmarshal(data, &snap)
+	if err != nil {
+		t.Fatalf("state file is not complete JSON: %v", err)
+	}
+
+	if len(snap.Domains) != 2 {
+		t.Errorf("state file has %d domains, want 2", len(snap.Domains))
+	}
+
+	_, err = os.Stat(tmpPath)
+	if !os.IsNotExist(err) {
+		t.Error("temp file should not exist after save")
+	}
+}
+
 // TestLoadMissingFile verifies that loading a nonexistent file is not an error.
 func TestLoadMissingFile(t *testing.T) {
 	t.Parallel()