lifecycle/lifecycle.go

@@ -238,7 +238,7 @@ func (a *App) Run(parent context.Context) error {
 			if !ok {
 				signals = nil
 			} else if err := receiveSignal(sig); err != nil {
-				return a.result(err)
+				return a.result(parent, err)
 			}
 			continue
 		default:
@@ -246,7 +246,6 @@ func (a *App) Run(parent context.Context) error {
 
 		a.mu.Lock()
 		if !a.stopping && parent.Err() != nil {
-			a.errs = append(a.errs, parent.Err())
 			a.stopLocked()
 			parentDone = nil
 		}
@@ -288,7 +287,7 @@ func (a *App) Run(parent context.Context) error {
 
 		if stopping {
 			if err := shutdown.Err(); err != nil {
-				return a.result(err)
+				return a.result(parent, err)
 			}
 			if setupDone == nil && teardownDone == nil {
 				if teardownIndex >= 0 {
@@ -297,7 +296,7 @@ func (a *App) Run(parent context.Context) error {
 					teardownDone = result
 					go func() { result <- m.Teardown(shutdown) }()
 				} else if active == 0 {
-					return a.result(nil)
+					return a.result(parent, nil)
 				}
 			}
 		}
@@ -325,7 +324,6 @@ func (a *App) Run(parent context.Context) error {
 		case <-a.wake:
 		case <-parentDone:
 			a.mu.Lock()
-			a.errs = append(a.errs, parent.Err())
 			a.stopLocked()
 			a.mu.Unlock()
 			parentDone = nil
@@ -335,16 +333,17 @@ func (a *App) Run(parent context.Context) error {
 				continue
 			}
 			if err := receiveSignal(sig); err != nil {
-				return a.result(err)
+				return a.result(parent, err)
 			}
 		case <-deadline:
-			return a.result(context.DeadlineExceeded)
+			return a.result(parent, context.DeadlineExceeded)
 		}
 	}
 }
 
-func (a *App) result(extra error) error {
+func (a *App) result(parent context.Context, extra error) error {
 	a.mu.Lock()
 	defer a.mu.Unlock()
-	return errors.Join(append(a.errs, extra)...)
+	// invariant: every completion and abandonment retains parent cancellation exactly once.
+	return errors.Join(append(a.errs, parent.Err(), extra)...)
 }

lifecycle/lifecycle_test.go

@@ -380,28 +380,89 @@ func TestAdmissionRace(t *testing.T) {
 }
 
 func TestIndependentDescendantCancellation(t *testing.T) {
-	signals := make(chan os.Signal, 2)
-	a := newApp(t, signals, time.Second)
-	canceled := make(chan struct{})
-	allowReturn := make(chan struct{})
-	add(t, a, Module{Name: "owner", Setup: func(ctx context.Context) error {
-		child, cancel := context.WithCancel(ctx)
-		err := a.Go(child, "independent", func(ctx context.Context) error {
-			cancel()
-			close(canceled)
-			<-allowReturn
-			return fmt.Errorf("worker result: %w", errors.Join(ctx.Err(), errors.New("other")))
+	for _, mixed := range []bool{false, true} {
+		t.Run(map[bool]string{false: "cancellation-only", true: "mixed"}[mixed], func(t *testing.T) {
+			signals := make(chan os.Signal, 2)
+			a := newApp(t, signals, time.Second)
+			canceled := make(chan struct{})
+			allowReturn := make(chan struct{})
+			other := errors.New("other")
+			add(t, a, Module{Name: "owner", Setup: func(ctx context.Context) error {
+				child, cancel := context.WithCancel(ctx)
+				err := a.Go(child, "independent", func(ctx context.Context) error {
+					cancel()
+					close(canceled)
+					<-allowReturn
+					err := ctx.Err()
+					if mixed {
+						err = errors.Join(err, other)
+					}
+					return fmt.Errorf("worker result: %w", err)
+				})
+				if err != nil {
+					cancel()
+				}
+				return err
+			}, Teardown: func(context.Context) error { close(allowReturn); return nil }})
+			done := run(a, context.Background())
+			wait(t, canceled)
+			signals <- syscall.SIGTERM
+			if err := receive(t, done); !errors.Is(err, context.Canceled) || errors.Is(err, other) != mixed {
+				t.Fatalf("independent cancellation lost: %v", err)
+			}
+		})
+	}
+}
+
+func TestParentCancellationDuringShutdown(t *testing.T) {
+	for _, boundary := range []string{"completion", "deadline", "second-signal"} {
+		t.Run(boundary, func(t *testing.T) {
+			iterations := 1
+			if boundary == "completion" {
+				iterations = 1000
+			}
+			for range iterations {
+				parent, cancel := context.WithCancel(context.Background())
+				signals := make(chan os.Signal, 2)
+				timeout := time.Second
+				if boundary == "deadline" {
+					timeout = 20 * time.Millisecond
+				}
+				a := newApp(t, signals, timeout)
+				exited := make(chan struct{})
+				add(t, a, Module{Name: "last", Teardown: func(ctx context.Context) error {
+					defer close(exited)
+					cancel()
+					switch boundary {
+					case "deadline":
+						<-ctx.Done()
+					case "second-signal":
+						signals <- syscall.SIGINT
+						signals <- syscall.SIGTERM
+						<-ctx.Done()
+					}
+					return nil
+				}})
+				err := a.Run(parent)
+				cancel()
+				wait(t, exited)
+				if !errors.Is(err, context.Canceled) {
+					t.Fatalf("parent cancellation lost: %v", err)
+				}
+				if errors.Is(err, context.DeadlineExceeded) != (boundary == "deadline") {
+					t.Fatalf("unexpected shutdown result: %v", err)
+				}
+				parentErrors := 0
+				for _, child := range err.(interface{ Unwrap() []error }).Unwrap() {
+					if child == context.Canceled {
+						parentErrors++
+					}
+				}
+				if parentErrors != 1 {
+					t.Fatalf("parent error recorded %d times: %v", parentErrors, err)
+				}
+			}
 		})
-		if err != nil {
-			cancel()
-		}
-		return err
-	}, Teardown: func(context.Context) error { close(allowReturn); return nil }})
-	done := run(a, context.Background())
-	wait(t, canceled)
-	signals <- syscall.SIGTERM
-	if err := receive(t, done); !errors.Is(err, context.Canceled) || !strings.Contains(err.Error(), "other") {
-		t.Fatalf("independent cancellation lost: %v", err)
 	}
 }