From 1debc443b12931defb29c690066ca413105cc29b Mon Sep 17 00:00:00 2001
From: Felix Seifert <mail@felix-seifert.com>
Date: Fri, 12 Sep 2025 21:48:19 +0200
Subject: [PATCH] feat: allow staggered reboot of K3s cluster nodes

---
 README.md  | 10 ++++++++++
 reboot.yml | 22 ++++++++++++++++++++--
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 37ba59b..dd0adf7 100644
--- a/README.md
+++ b/README.md
@@ -91,6 +91,16 @@ ansible-playbook reset.yml -i inventory/my-cluster/hosts.ini
 
 >You should also reboot these nodes due to the VIP not being destroyed
 
+### ⏻️ Reboot Cluster Nodes
+
+The cluster nodes can all be rebooted at once, or staggered. For a staggered reboot, you can use `concurrent_reboots` to specify
+how many nodes can be rebooted simultaneously. You can also use `wait_seconds_after_reboot` to specify how many seconds wait
+time there should be between a successful reboot and starting the next reboot; this could be helpful for waiting to restart pods.
+
+```bash
+ansible-playbook reboot.yml -i inventory/my-cluster/hosts.ini --extra-vars 'concurrent_reboots=2 wait_seconds_after_reboot=30'
+```
+
 ## ⚙️ Kube Config
 
 To copy your `kube config` locally so that you can access your **Kubernetes** cluster run:
diff --git a/reboot.yml b/reboot.yml
index e0fa8b9..fa98b06 100644
--- a/reboot.yml
+++ b/reboot.yml
@@ -2,9 +2,27 @@
 - name: Reboot k3s_cluster
   hosts: k3s_cluster
   gather_facts: true
+
+  # concurrent_reboots defines how many hosts to reboot concurrently, if not defined, all hosts rebooted at once
+  serial: "{{ concurrent_reboots | default('100%') }}"
+
   tasks:
-    - name: Reboot the nodes (and Wait upto 5 mins max)
-      become: true
+    - name: >-
+        {{
+          'Reboot all nodes at once'
+          if (concurrent_reboots is not defined)
+          else 'Reboot nodes with concurrency of ' ~ concurrent_reboots
+        }}
       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 after reboot before next rebooting next node
+      ansible.builtin.pause:
+        seconds: "{{ wait_seconds_after_reboot | default(0) }}"
+      when: >-
+        concurrent_reboots is defined and
+        wait_seconds_after_reboot is defined and
+        wait_seconds_after_reboot | int > 0