feat(reboot): support staggered reboots of cluster nodes (#693)

- Add serial to the reboot play so concurrent_reboots controls how many nodes
  reboot at a time, defaulting to 100% (reboot all at once) for backward
  compatibility
- Add a per-node test_command that verifies the node is healthy after reboot
- Add an optional wait_seconds_after_reboot pause between staggered batches so
  pods can settle before the next batch reboots
- Document the new concurrent_reboots and wait_seconds_after_reboot variables

Co-authored-by: Felix Seifert <mail@felix-seifert.com>

reboot.yml

@@ -2,9 +2,29 @@
 - name: Reboot k3s_cluster
   hosts: k3s_cluster
   gather_facts: true
+
+  # Stagger the reboot across the cluster when concurrent_reboots is set.
+  # Defaults to '100%' so the whole cluster reboots at once (backward compatible).
+  serial: "{{ concurrent_reboots | default('100%') }}"
+
   tasks:
-    - name: Reboot the nodes (and Wait upto 5 mins max)
+    - name: >-
+        {{
+          'Reboot all nodes at once'
+          if (concurrent_reboots is not defined)
+          else 'Reboot nodes with concurrency of ' ~ concurrent_reboots
+        }}
       become: true
       ansible.builtin.reboot:
         reboot_command: "{{ custom_reboot_command | default(omit) }}"
         reboot_timeout: 300
+        test_command: >-
+          {{ 'kubectl get nodes' if 'master' in group_names else 'whoami' }}
+
+    - name: Optional wait before rebooting the next batch of nodes
+      ansible.builtin.pause:
+        seconds: "{{ wait_seconds_after_reboot | int }}"
+      when: >-
+        concurrent_reboots is defined and
+        wait_seconds_after_reboot is defined and
+        wait_seconds_after_reboot | int > 0