internal/uploads/worker.go

@@ -176,9 +176,10 @@ func (w *Worker) Submit(j Job) error {
 }
 
 // Run processes queued jobs until ctx ends, then deletes the audio of anything
-// still queued and refuses new jobs. The rows of those jobs stay queued or
-// transcribing and are failed as interrupted by the start-up sweep
-// (store.FailInterruptedUploads): the audio is not retained, so they cannot resume.
+// still queued and refuses new jobs. The job running at shutdown is recorded interrupted
+// by Process; the rows of jobs still queued stay queued and are failed as interrupted by
+// the start-up sweep (store.FailInterruptedUploads): the audio is not retained, so they
+// cannot resume.
 func (w *Worker) Run(ctx context.Context) {
 	defer w.stop()
 	for {
@@ -227,7 +228,7 @@ func (w *Worker) stop() {
 // Process runs one job: row -> transcribing, convert, transcribe, store. The
 // uploaded file and the converted WAV are deleted on every path — the audio is
 // never retained (ADR-033). A failure is recorded with a TYPED kind; a shutdown
-// mid-job is not a failure and leaves the row for the start-up sweep.
+// mid-job is recorded as interrupted at once (see fail).
 //
 // Every phase is reported through one progress.Tracker, which saves it to the row for
 // the page and logs it, and a heartbeat stamps the row on its own while the job runs
@@ -269,7 +270,7 @@ func (w *Worker) Process(ctx context.Context, job Job) {
 	defer func() { stopBeat(); <-hbDone }() // no heartbeat outlives its job
 
 	// abort records where the job stopped. A shutdown (the parent context ended) is not
-	// a failure: the row is left for the start-up sweep, so the step stays as it was.
+	// a failure of the step: it stays as it was, and fail records the row as interrupted.
 	abort := func(kind domain.UploadErrorKind) {
 		if ctx.Err() == nil {
 			tr.FailRunning()
@@ -332,11 +333,19 @@ func (w *Worker) Process(ctx context.Context, job Job) {
 		"segments", len(t.Segments), "elapsed", time.Since(start).Round(time.Second))
 }
 
-// fail records a transcription failure — unless the PARENT context ended, which
-// is a shutdown, not a failure: the row is left for the start-up sweep.
+// interruptedWriteTimeout bounds the one write a dying process makes to record its job.
+const interruptedWriteTimeout = 3 * time.Second
+
+// fail records a transcription failure. When the PARENT context ended the process is
+// shutting down: the job is recorded interrupted at once, on a short context of its own,
+// because the process may exit before any other pod's start-up sweep would do it (#50).
+// The sweep remains the backstop for a process that is killed outright.
 func (w *Worker) fail(ctx context.Context, job Job, log *slog.Logger, kind domain.UploadErrorKind) {
 	if ctx.Err() != nil {
-		return
+		kind = domain.UploadErrInterrupted
+		var cancel context.CancelFunc
+		ctx, cancel = context.WithTimeout(context.WithoutCancel(ctx), interruptedWriteTimeout)
+		defer cancel()
 	}
 	if err := w.store.FailUpload(ctx, job.UserID, job.UploadID, kind); err != nil {
 		log.Error("upload: record failure", "kind", errkind.Of(err))