Detect and alert on stuck jobs

internal/alert/rules_test.go

@@ -3,6 +3,7 @@ package alert
 import (
 	"context"
 	"path/filepath"
+	"strings"
 	"testing"
 	"time"
 
@@ -69,6 +70,65 @@ func TestEngineBackupFailedRaisesThenResolves(t *testing.T) {
 	}
 }
 
+func TestEngineStuckJobRaisesDeduplicatesAndResolves(t *testing.T) {
+	t.Parallel()
+	eng, st, hostID := setupEngine(t)
+	ctx := context.Background()
+	now := time.Now().UTC().Truncate(time.Second)
+	started := now.Add(-7 * time.Hour)
+	if err := st.CreateJob(ctx, store.Job{ID: "stuck-job", HostID: hostID, Kind: "prune", ActorKind: "user", CreatedAt: started}); err != nil {
+		t.Fatalf("create job: %v", err)
+	}
+	if err := st.MarkJobStarted(ctx, "stuck-job", started); err != nil {
+		t.Fatalf("start job: %v", err)
+	}
+
+	eng.evaluateStuckJobs(ctx, now)
+	eng.evaluateStuckJobs(ctx, now.Add(time.Minute))
+	open, err := st.ListAlerts(ctx, store.AlertFilter{Status: "open", HostID: hostID})
+	if err != nil {
+		t.Fatalf("list alerts: %v", err)
+	}
+	if len(open) != 1 || open[0].Kind != KindJobStuck || open[0].DedupKey != "stuck-job" {
+		t.Fatalf("expected one deduplicated stuck alert, got %+v", open)
+	}
+	if !strings.Contains(open[0].Message, started.Format(time.RFC3339)) {
+		t.Errorf("alert does not identify start/activity time: %q", open[0].Message)
+	}
+
+	if err := st.MarkJobFinished(ctx, "stuck-job", "succeeded", 0, nil, "", now); err != nil {
+		t.Fatalf("finish job: %v", err)
+	}
+	eng.evaluateStuckJobs(ctx, now.Add(2*time.Minute))
+	open, _ = st.ListAlerts(ctx, store.AlertFilter{Status: "open", HostID: hostID})
+	if len(open) != 0 {
+		t.Fatalf("expected terminal job alert resolved, got %+v", open)
+	}
+}
+
+func TestEngineStuckJobUsesLatestLogActivity(t *testing.T) {
+	t.Parallel()
+	eng, st, hostID := setupEngine(t)
+	ctx := context.Background()
+	now := time.Now().UTC().Truncate(time.Second)
+	started := now.Add(-7 * time.Hour)
+	if err := st.CreateJob(ctx, store.Job{ID: "active-job", HostID: hostID, Kind: "forget", ActorKind: "user", CreatedAt: started}); err != nil {
+		t.Fatalf("create job: %v", err)
+	}
+	if err := st.MarkJobStarted(ctx, "active-job", started); err != nil {
+		t.Fatalf("start job: %v", err)
+	}
+	if err := st.AppendJobLog(ctx, "active-job", 1, now.Add(-time.Hour), "stdout", "active"); err != nil {
+		t.Fatalf("append log: %v", err)
+	}
+
+	eng.evaluateStuckJobs(ctx, now)
+	open, _ := st.ListAlerts(ctx, store.AlertFilter{Status: "open", HostID: hostID})
+	if len(open) != 0 {
+		t.Fatalf("recent activity should suppress stuck alert, got %+v", open)
+	}
+}
+
 func TestEngineCheckFailedSeverityCritical(t *testing.T) {
 	t.Parallel()
 	eng, st, hostID := setupEngine(t)