OCPBUGS-59354: E2E add test to verify guaranteed pod is running after kubelet restart (#1361)

* verify Guranteed pod is running after kubelet restart

This PR addresses issue where we are verifying
if the cpu manager state file is same after kubelet restart
while we are verifying the above, we are not checking
if Guranteed pod started before kubelet restart is also
still running.

Refer: https://issues.redhat.com/browse/OCPBUGS-43280

Signed-off-by: Niranjan M.R <mrniranjan@redhat.com>

* avoid using indirect references and test negative pod status condition

Signed-off-by: Niranjan M.R <mrniranjan@redhat.com>

* typo fix and add more debug when pod fails

Signed-off-by: Niranjan M.R <mrniranjan@redhat.com>

---------

Signed-off-by: Niranjan M.R <mrniranjan@redhat.com>
Co-authored-by: Niranjan M.R <mrniranjan@redhat.com>

Author: mrniranjan

test/e2e/performanceprofile/functests/1_performance/cpu_management.go

@@ -346,6 +346,11 @@ var _ = Describe("[rfe_id:27363][performance] CPU Management", Ordered, func() {
 				cpuManagerCpusetBeforeRestart, err := nodes.CpuManagerCpuSet(ctx, workerRTNode)
 				Expect(err).ToNot(HaveOccurred())
 				testlog.Infof("pre kubelet restart default cpuset: %v", cpuManagerCpusetBeforeRestart.String())
+
+				By("capturing test pod state before restart")
+				originalPodUID := testpod.UID
+				testlog.Infof("pre kubelet restart pod UID: %v", originalPodUID)
+
 				kubeletRestartCmd := []string{
 					"chroot",
 					"/rootfs",
@@ -362,6 +367,33 @@ var _ = Describe("[rfe_id:27363][performance] CPU Management", Ordered, func() {
 
 				testlog.Infof("post restart: finished cooldown time: %v", restartCooldownTime)
 
+				By("verify test pod comes back after kubelet restart")
+				Eventually(func() error {
+					var updatedPod corev1.Pod
+					err := testclient.DataPlaneClient.Get(ctx, client.ObjectKeyFromObject(testpod), &updatedPod)
+					if err != nil {
+						return fmt.Errorf("failed to get pod after restart: %v", err)
+					}
+
+					// Verify it's the same pod (same UID)
+					if updatedPod.UID != originalPodUID {
+						return fmt.Errorf("pod UID changed after restart: original=%v, current=%v", originalPodUID, updatedPod.UID)
+					}
+
+					// Verify pod is ready
+					if updatedPod.Status.Phase != corev1.PodRunning {
+						return fmt.Errorf("pod is not running after restart: phase=%v", updatedPod.Status.Phase)
+					}
+					// Check pod ready condition
+					for _, condition := range updatedPod.Status.Conditions {
+						if condition.Type == corev1.PodReady && condition.Status != corev1.ConditionTrue {
+							return fmt.Errorf("Pod condition is not in Ready state after kubelet restart: reason: %v, message: %v", condition.Reason, condition.Message)
+
+						}
+					}
+					return nil
+				}).WithTimeout(5*time.Minute).WithPolling(10*time.Second).Should(Succeed(), "test pod should come back after kubelet restart")
+
 				By("fetch Default cpuset from cpu manager state after restart")
 				cpuManagerCpusetAfterRestart, err := nodes.CpuManagerCpuSet(ctx, workerRTNode)
 				Expect(err).ToNot(HaveOccurred())