fix: add more logging to blixt readiness test utils

internal/test/utils/utils.go

@@ -6,18 +6,21 @@ import (
 	"fmt"
 	"log"
 	"testing"
+	"time"
 
 	"github.com/go-logr/logr"
 	"github.com/go-logr/stdr"
 	"github.com/kong/kubernetes-testing-framework/pkg/clusters"
 	"github.com/kong/kubernetes-testing-framework/pkg/environments"
 	"github.com/stretchr/testify/assert"
+	corev1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/runtime"
 	utilruntime "k8s.io/apimachinery/pkg/util/runtime"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/client/fake"
 	gatewayv1beta1 "sigs.k8s.io/gateway-api/apis/v1beta1"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
 
 	"github.com/kong/blixt/pkg/vars"
 )
@@ -73,9 +76,13 @@ func NewFakeClientWithGatewayClasses(initObjects ...client.Object) (gatewayv1bet
 // environment (but deploying Blixt is expected to have already been handled
 // elsewhere).
 func WaitForBlixtReadiness(ctx context.Context, env environments.Environment) error {
+	ticker := time.NewTicker(time.Minute * 3) // TODO: glob
 	for {
 		select {
+		case <-ticker.C:
+			simpleDiagDump(ctx, env)
 		case <-ctx.Done():
+			simpleDiagDump(ctx, env)
 			if err := ctx.Err(); err != nil {
 				return fmt.Errorf("context completed while waiting for components: %w", err)
 			}
@@ -85,6 +92,7 @@ func WaitForBlixtReadiness(ctx context.Context, env environments.Environment) er
 
 			controlplane, err := env.Cluster().Client().AppsV1().Deployments(vars.DefaultNamespace).Get(ctx, vars.DefaultControlPlaneDeploymentName, metav1.GetOptions{})
 			if err != nil {
+				fmt.Printf("Error while checking controlplane components: %s\n", err)
 				return err
 			}
 			if controlplane.Status.AvailableReplicas > 0 {
@@ -93,6 +101,7 @@ func WaitForBlixtReadiness(ctx context.Context, env environments.Environment) er
 
 			dataplane, err := env.Cluster().Client().AppsV1().DaemonSets(vars.DefaultNamespace).Get(ctx, vars.DefaultDataPlaneDaemonSetName, metav1.GetOptions{})
 			if err != nil {
+				fmt.Printf("Error while checking dataplane components: %s\n", err)
 				return err
 			}
 			if dataplane.Status.NumberAvailable > 0 {
@@ -116,3 +125,42 @@ func DumpDiagnosticsIfFailed(ctx context.Context, t *testing.T, clusters cluster
 		assert.NoError(t, err)
 	}
 }
+
+// simpleDiagDump is something more brief than a full cluster diagnostic,
+// mainly intended to help quickly diagnose Pod issues.
+func simpleDiagDump(ctx context.Context, env environments.Environment) {
+	fmt.Println("INFO: dumping cluster details")
+
+	deployments, err := env.Cluster().Client().AppsV1().Deployments(corev1.NamespaceAll).List(ctx, corev1.ListOptions{})
+	if err == nil {
+		b, err := yaml.Marshal(deployments)
+		if err != nil {
+			fmt.Printf("Warning: failed to marshal YAML report of current deployment status on shutdown: %s\n", err)
+		}
+		fmt.Printf("Deployments:\n---\n%s\n", string(b))
+	} else {
+		fmt.Printf("Warning: failed to report current deployment status on shutdown: %s\n", err)
+	}
+
+	daemonsets, err := env.Cluster().Client().AppsV1().DaemonSets(corev1.NamespaceAll).List(ctx, corev1.ListOptions{})
+	if err == nil {
+		b, err := yaml.Marshal(daemonsets)
+		if err != nil {
+			fmt.Printf("Warning: failed to marshal YAML report of current daemonset status on shutdown: %s\n", err)
+		}
+		fmt.Printf("Daemonsets:\n---\n%s\n", string(b))
+	} else {
+		fmt.Printf("Warning: failed to report current daemonset status on shutdown: %s\n", err)
+	}
+
+	pods, err := env.Cluster().Client().CoreV1().Pods(corev1.NamespaceAll).List(ctx, corev1.ListOptions{})
+	if err == nil {
+		b, err := yaml.Marshal(pods)
+		if err != nil {
+			fmt.Printf("Warning: failed to marshal YAML report of current pod status on shutdown: %s\n", err)
+		}
+		fmt.Printf("Pods:\n---\n%s\n", string(b))
+	} else {
+		fmt.Printf("Warning: failed to report current pod status on shutdown: %s\n", err)
+	}
+}