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

@@ -13,6 +13,7 @@ import (
"go.uber.org/fx"
"gorm.io/gorm"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/lifecycle"
"sneak.berlin/go/webhooker/internal/logger"
)
@@ -234,8 +235,9 @@ func (e *Engine) ScheduleRetry(
}
// registerHooks wires the engine's start and stop into the fx
// lifecycle. The start hook's context is deliberately ignored:
// see start for why the worker pool must not inherit it.
// lifecycle. The start hook's context is deliberately ignored
// (see start for why the worker pool must not inherit it); the
// stop hook's context is honoured (see stop).
func (e *Engine) registerHooks(lc fx.Lifecycle) {
lc.Append(fx.Hook{
//nolint:contextcheck // Not inheriting the hook context
@@ -245,10 +247,8 @@ func (e *Engine) registerHooks(lc fx.Lifecycle) {
return nil
},
OnStop: func(_ context.Context) error {
e.stop()
return nil
OnStop: func(ctx context.Context) error {
return e.stop(ctx)
},
})
}
@@ -289,11 +289,26 @@ func (e *Engine) start() {
)
}
func (e *Engine) stop() {
// stop cancels the worker pool's context and waits for the pool
// to drain, bounded by the stop hook's context: a wedged worker
// must not hang the process past fx's stop timeout.
func (e *Engine) stop(ctx context.Context) error {
e.log.Info("delivery engine stopping")
e.cancel()
e.wg.Wait()
if e.cancel != nil {
e.cancel()
}
err := lifecycle.WaitForShutdown(
ctx, e.log, "delivery engine", &e.wg,
)
if err != nil {
return err
}
e.log.Info("delivery engine stopped")
return nil
}
func (e *Engine) worker(ctx context.Context) {