fix crio restart while switching runtime (#12008)

fixed kubelet condition

CRI-O: fix for handling of container runtime switching

refactored kubelet start condition

stop/start kubelet and crio only when default runtime is changed

fixed condition for runtime_matches fact variable

fixed set facts for existing container runtime

added crio runtime switch variable

changed condition to use runtime switch variable

added comment for not-found for readers

roles/container-engine/cri-o/defaults/main.yml

@@ -4,6 +4,7 @@ crio_cgroup_manager: "{{ kubelet_cgroup_driver | default('systemd') }}"
 crio_conmon: "{{ bin_dir }}/conmon"
 crio_default_runtime: "crun"
 crio_libexec_dir: "/usr/libexec/crio"
+crio_runtime_switch: false
 crio_enable_metrics: false
 crio_log_level: "info"
 crio_metrics_port: "9090"

roles/container-engine/cri-o/tasks/main.yaml

@@ -55,6 +55,46 @@
   when:
     - youki_enabled
 
+- name: Cri-o | Stop kubelet service if running
+  service:
+    name: kubelet
+    state: stopped
+  when:
+    - crio_runtime_switch
+    - ansible_facts.services['kubelet.service'] is defined and ansible_facts.services['kubelet.service'].state == 'running'
+
+- name: Cri-o | Get all pods
+  ansible.builtin.command: "{{ bin_dir }}/crictl pods -o json"
+  changed_when: false
+  register: crio_pods
+  when:
+    - crio_runtime_switch
+    - ansible_facts.services['crio.service'] is defined
+
+- name: Cri-o | Stop and remove pods not on host network
+  ansible.builtin.command: "{{ bin_dir }}/crictl rmp -f {{ item.id }}"
+  loop: "{{ (crio_pods.stdout | from_json).items | default([]) | selectattr('metadata.namespace', 'ne', 'NODE') }}"
+  changed_when: true
+  when:
+    - crio_runtime_switch
+    - ansible_facts.services['crio.service'] is defined
+    - crio_pods.stdout is defined
+
+- name: Cri-o | Stop and remove all remaining pods
+  ansible.builtin.command: "{{ bin_dir }}/crictl rmp -fa"
+  changed_when: true
+  when:
+    - crio_runtime_switch
+    - ansible_facts.services['crio.service'] is defined
+
+- name: Cri-o | stop crio service if running
+  service:
+    name: crio
+    state: stopped
+  when:
+    - crio_runtime_switch
+    - ansible_facts.services['crio.service'] is defined and ansible_facts.services['crio.service'].state == 'running'
+
 - name: Cri-o | make sure needed folders exist in the system
   with_items:
     - /etc/crio
@@ -250,3 +290,16 @@
   changed_when: false
   retries: 5
   delay: "{{ retry_stagger | random + 3 }}"
+
+# The kubelet service status can be 'not-found' if something depends on it.
+# This check prevents failures when the service is in this indeterminate state,
+# which can occur when adding new nodes to a cluster.
+# See: https://superuser.com/questions/1755211/cleaning-debugging-services/1755215#1755215
+
+- name: Cri-o | ensure kubelet service is started if present and stopped
+  service:
+    name: kubelet
+    state: started
+  when:
+    - crio_runtime_switch
+    - ansible_facts.services['kubelet.service'] is defined and ansible_facts.services['kubelet.service']['status'] != 'not-found'