From 5fb91d35d0ecc86b4f99aa94796834aa7b3726f2 Mon Sep 17 00:00:00 2001
From: HarshwardhanPatil07 <harshpat@redhat.com>
Date: Thu, 6 Aug 2026 10:36:30 +0530
Subject: [PATCH] Fix CoreDNS readiness race in integration test

Wait for CoreDNS pods to be ready before attempting DNS
resolution, preventing flaky "Connection refused" failures.

Signed-off-by: HarshwardhanPatil07 <harshpat@redhat.com>
---
 internal/cluster/init.go   |  7 +++++++
 internal/kube/resources.go | 25 +++++++++++++++++++++++++
 2 files changed, 32 insertions(+)

diff --git a/internal/cluster/init.go b/internal/cluster/init.go
index 69c2aca..26acf3d 100644
--- a/internal/cluster/init.go
+++ b/internal/cluster/init.go
@@ -152,6 +152,13 @@ func (c *Cluster) Init(ctx context.Context, opts InitOptions) error {
 		return fmt.Errorf("failed to patch CoreDNS: %w", err)
 	}
 
+	c.logger.Info("")
+	c.logger.Info("Waiting for CoreDNS to be ready...")
+	if err := kubeClient.WaitForDeploymentReady(ctx, "kube-system", "coredns", 3*time.Minute); err != nil {
+		return fmt.Errorf("CoreDNS not ready: %w", err)
+	}
+	c.logger.Info("✓ CoreDNS is ready")
+
 	c.logger.Info("")
 	c.logger.Infof("✅ Cluster initialized on %s with Calico CNI", nodeName)
 
diff --git a/internal/kube/resources.go b/internal/kube/resources.go
index b10e2cb..e45f3fd 100644
--- a/internal/kube/resources.go
+++ b/internal/kube/resources.go
@@ -156,6 +156,31 @@ func (c *Client) EnableCoreDNSFallthrough(ctx context.Context) error {
 	return nil
 }
 
+// WaitForDeploymentReady polls until the named deployment has at least one
+// ready replica, or the timeout expires.
+func (c *Client) WaitForDeploymentReady(ctx context.Context, namespace, name string, timeout time.Duration) error {
+	deadline := time.After(timeout)
+	ticker := time.NewTicker(2 * time.Second)
+	defer ticker.Stop()
+
+	for {
+		select {
+		case <-ctx.Done():
+			return ctx.Err()
+		case <-deadline:
+			return fmt.Errorf("timed out waiting for deployment %s/%s to be ready", namespace, name)
+		case <-ticker.C:
+			deploy, err := c.clientset.AppsV1().Deployments(namespace).Get(ctx, name, metav1.GetOptions{})
+			if err != nil {
+				continue
+			}
+			if deploy.Status.ReadyReplicas >= 1 {
+				return nil
+			}
+		}
+	}
+}
+
 // LabelNode adds the given labels to a node, overwriting any that already exist.
 func (c *Client) LabelNode(ctx context.Context, nodeName string, labels map[string]string) error {
 	patch := map[string]interface{}{