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

@@ -10,6 +10,7 @@ import (
"go.uber.org/fx"
"gorm.io/gorm"
"sneak.berlin/go/webhooker/internal/config"
"sneak.berlin/go/webhooker/internal/lifecycle"
"sneak.berlin/go/webhooker/internal/logger"
)
@@ -62,8 +63,9 @@ func NewRetentionReaper(
}
// registerHooks wires the reaper's start and stop into the fx
// lifecycle. The start hook's context is deliberately ignored: see
// start for why the sweep loop must not inherit it.
// lifecycle. The start hook's context is deliberately ignored (see
// start for why the sweep loop must not inherit it); the stop hook's
// context is honoured (see stop).
func (r *RetentionReaper) registerHooks(lc fx.Lifecycle) {
lc.Append(fx.Hook{
//nolint:contextcheck // Not inheriting the hook context is
@@ -73,10 +75,8 @@ func (r *RetentionReaper) registerHooks(lc fx.Lifecycle) {
return nil
},
OnStop: func(_ context.Context) error {
r.stop()
return nil
OnStop: func(ctx context.Context) error {
return r.stop(ctx)
},
})
}
@@ -105,15 +105,27 @@ func (r *RetentionReaper) start() {
)
}
func (r *RetentionReaper) stop() {
// stop cancels the sweep loop's context and waits for it to
// exit, bounded by the stop hook's context: a sweep wedged on a
// locked database must not hang the process past fx's stop
// timeout.
func (r *RetentionReaper) stop(ctx context.Context) error {
r.log.Info("retention reaper stopping")
if r.cancel != nil {
r.cancel()
}
r.wg.Wait()
err := lifecycle.WaitForShutdown(
ctx, r.log, "retention reaper", &r.wg,
)
if err != nil {
return err
}
r.log.Info("retention reaper stopped")
return nil
}
func (r *RetentionReaper) run(ctx context.Context) {