fix(tests,kubevirt_vm): Make waiting for VM more robust

This changes the runme.sh of the kubevirt_vm integration tests to retry
the connection to the VM until a login is possible. This is necessary
since it is not possible with Ansible alone to retry a task in case the
connection failed with the unreachable status. This can happen when the
sshd of the VM already accepts connections but a login is not yet
possible because the VM is still booting up.

Signed-off-by: Felix Matouschek <fmatouschek@redhat.com>

tests/integration/targets/kubevirt_vm/runme.sh

@@ -13,4 +13,18 @@ ansible-playbook playbook.yml "$@"
 
 ansible-inventory -i test.kubevirt.yml -y --list "$@"
 
-ansible-playbook verify.yml -i test.kubevirt.yml --private-key=files/testkey "$@"
+# Retry connection to VM until a login is possible
+# This is necessary since wait_for is not enough to wait for logins to be possible.
+# wait_for is only able to wait until sshd accepts connections.
+retries=0
+while ! ansible-playbook wait_for_vm.yml -i test.kubevirt.yml --private-key=files/testkey "$@"; do
+  if [ "$retries" -ge "10" ]; then
+    echo "Maximum retries reached, giving up"
+    exit 1
+  fi
+  echo "Failed to wait for VM, retrying..."
+  sleep 10
+  ((retries+=1))
+done
+
+ansible-playbook verify.yml --diff -i test.kubevirt.yml --private-key=files/testkey "$@"

tests/integration/targets/kubevirt_vm/verify.yml

@@ -1,27 +1,4 @@
 ---
-- name: Wait for SSH
-  connection: local
-  gather_facts: false
-  hosts: localhost
-  tasks:
-    - name: Wait up to 900 seconds for port 22 to become open
-      ansible.builtin.wait_for:
-        port: 22
-        host: "{{ hostvars['default-testvm'].ansible_host }}"
-        delay: 30
-        timeout: 900
-
-- name: Connect to VM
-  gather_facts: true
-  hosts: default-testvm
-  remote_user: cloud-user
-  vars:
-    ansible_python_interpreter: /usr/bin/python3
-  tasks:
-    - name: Print VM facts
-      ansible.builtin.debug:
-        var: ansible_facts
-
 - name: Verify creation with existing VM
   connection: local
   gather_facts: false

tests/integration/targets/kubevirt_vm/wait_for_vm.yml

@@ -0,0 +1,24 @@
+---
+- name: Wait for SSH
+  connection: local
+  gather_facts: false
+  hosts: localhost
+  tasks:
+    - name: Wait up to 900 seconds for port 22 to become open
+      ansible.builtin.wait_for:
+        port: 22
+        host: "{{ hostvars['default-testvm'].ansible_host }}"
+        search_regex: OpenSSH
+        delay: 10
+        timeout: 900
+
+- name: Connect to VM
+  gather_facts: true
+  hosts: default-testvm
+  remote_user: cloud-user
+  vars:
+    ansible_python_interpreter: /usr/bin/python3
+  tasks:
+    - name: Print VM facts
+      ansible.builtin.debug:
+        var: ansible_facts