Bound shutdown hooks by their stop context (closes #102)
All checks were successful
check / check (push) Successful in 3m45s

fx hands OnStop a context carrying the application's stop timeout,
and the delivery engine, the retention reaper, and the archive
sweeper all discarded it and called wg.Wait() bare. A worker wedged
inside a delivery target that never returns, or a sweep blocked on a
locked SQLite database, hung the process forever instead of letting
it exit when the timeout expired.

All three now wait through internal/lifecycle.WaitForShutdown, which
selects the drained WaitGroup against the stop context and, on
timeout, logs at error naming the component and returns an error
rather than reporting a clean stop.

Engine.stop also gains the cancel != nil guard its two mirrored
components already had.
This commit is contained in:
2026-08-12 09:39:59 +00:00
parent d19e33671c
commit e83eb2977e
11 changed files with 392 additions and 51 deletions

View File

@@ -14,7 +14,6 @@ import (
"github.com/google/uuid"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"go.uber.org/fx"
"gorm.io/driver/sqlite"
"gorm.io/gorm"
"gorm.io/gorm/clause"
@@ -226,17 +225,6 @@ func countArchivedRows(path string) (int64, error) {
return count, nil
}
// captureLifecycle is a minimal fx.Lifecycle that records the
// hooks a component registers, so a test can invoke the real
// OnStart/OnStop functions with a context of its choosing.
type captureLifecycle struct {
hooks []fx.Hook
}
func (l *captureLifecycle) Append(h fx.Hook) {
l.hooks = append(l.hooks, h)
}
// TestArchiveSweeper_LoopOutlivesStartHookContext is the
// regression test for a sweeper that never swept. fx calls
// OnStart with a context carrying the application's start
@@ -270,7 +258,7 @@ func TestArchiveSweeper_LoopOutlivesStartHookContext(
// Drive the genuine fx hooks the application registers,
// rather than a test-only entry point.
lc := &captureLifecycle{}
lc := &recordingLifecycle{}
env.sweeper.ExportRegisterHooks(lc)
require.Len(t, lc.hooks, 1)
@@ -924,7 +912,36 @@ func TestArchiveSweeper_StopsCleanly(t *testing.T) {
env.sweeper.ExportSetInterval(time.Millisecond)
env.sweeper.ExportStart()
// stop blocks on the loop's WaitGroup, so returning at all
// proves the loop observed the cancellation and exited.
env.sweeper.ExportStop()
// stop blocks on the loop's WaitGroup, so returning without
// error proves the loop observed the cancellation and exited
// well inside the stop context.
require.NoError(
t, env.sweeper.ExportStop(context.Background()),
)
}
// TestArchiveSweeper_StopHookHonoursStopTimeout is the sweeper's
// half of the same shutdown defect the engine and the retention
// reaper carried: an OnStop that discards its context and waits
// on the WaitGroup bare hangs the process forever on a prune
// wedged inside a locked archive.
func TestArchiveSweeper_StopHookHonoursStopTimeout(
t *testing.T,
) {
t.Parallel()
env := setupSweeperTest(t)
lc := &recordingLifecycle{}
env.sweeper.ExportRegisterHooks(lc)
require.Len(t, lc.hooks, 1)
require.NoError(t, lc.hooks[0].OnStart(context.Background()))
release := make(chan struct{})
t.Cleanup(func() { close(release) })
env.sweeper.ExportWedgeLoop(release)
requireStopHookExpires(t, lc.hooks[0], "archive sweeper")
}