cmd/tapir/shutdown_test.go

@@ -0,0 +1,30 @@
+package main
+
+import (
+	"context"
+	"os"
+	"syscall"
+	"testing"
+	"time"
+)
+
+// Kubernetes stops a pod with SIGTERM; only SIGINT was handled, so a deploy killed the
+// process without running any shutdown code (#50).
+func TestShutdownContext_IsCancelledBySIGTERMAndSIGINT(t *testing.T) {
+	for _, sig := range []syscall.Signal{syscall.SIGTERM, syscall.SIGINT} {
+		t.Run(sig.String(), func(t *testing.T) {
+			ctx, stop := shutdownContext(context.Background())
+			defer stop()
+
+			if err := syscall.Kill(os.Getpid(), sig); err != nil {
+				t.Fatalf("send %v: %v", sig, err)
+			}
+
+			select {
+			case <-ctx.Done():
+			case <-time.After(2 * time.Second):
+				t.Fatalf("context not cancelled by %v", sig)
+			}
+		})
+	}
+}

internal/uploads/worker_test.go

@@ -53,7 +53,10 @@ func (s *wStore) CompleteUpload(_ context.Context, _, id string, t domain.Transc
 	return nil
 }
 
-func (s *wStore) FailUpload(_ context.Context, _, id string, k domain.UploadErrorKind) error {
+func (s *wStore) FailUpload(ctx context.Context, _, id string, k domain.UploadErrorKind) error {
+	if err := ctx.Err(); err != nil { // like the real store: a cancelled context cannot write
+		return err
+	}
 	s.mu.Lock()
 	defer s.mu.Unlock()
 	s.failed[id] = k
@@ -242,7 +245,9 @@ func TestWorkerProcess_FailuresAreTypedAndStillDeleteTheAudio(t *testing.T) {
 	})
 }
 
-func TestWorkerProcess_ShutdownMidJobLeavesTheRowForTheStartupSweep(t *testing.T) {
+func TestWorkerProcess_ShutdownMidJobRecordsTheRowInterruptedAtOnce(t *testing.T) {
+	// SIGTERM on a deploy used to leave the row "transcribing" until the NEXT pod's
+	// start-up sweep; the process may exit before any sweep runs (#50).
 	r := newWRig(t, time.Minute)
 	r.tr.block = make(chan struct{})
 	ctx, cancel := context.WithCancel(context.Background())
@@ -255,8 +260,8 @@ func TestWorkerProcess_ShutdownMidJobLeavesTheRowForTheStartupSweep(t *testing.T
 	<-done
 
 	_, f := r.st.snapshot()
-	assert.Empty(t, f, "a shutdown is not a transcription failure: the row stays for FailInterruptedUploads to mark interrupted")
-	assert.Empty(t, r.leftovers(t), "but the audio is still deleted")
+	assert.Equal(t, domain.UploadErrInterrupted, f["a"], "the row is recorded interrupted by the dying process, not left for a sweep")
+	assert.Empty(t, r.leftovers(t), "and the audio is still deleted")
 }
 
 func TestWorkerProcess_AJobThatOutlivesItsTimeoutIsFailedNotStuck(t *testing.T) {