Remove ignore_errors from drain tasks and enable retires (#7151)

* Remove ignore_errors from drain tasks and enable retires

* Fix lint error by checking if stdout length is not 0, ie string is not empty.

roles/remove-node/pre-remove/defaults/main.yml

@@ -2,3 +2,5 @@
 allow_ungraceful_removal: false
 drain_grace_period: 300
 drain_timeout: 360s
+drain_retries: 3
+drain_retry_delay_seconds: 10

roles/remove-node/pre-remove/tasks/main.yml

@@ -1,14 +1,26 @@
 ---
-- name: cordon-node | Mark all nodes as unschedulable before drain  # noqa 301
+- name: remove-node | Set `nodes_to_drain` as empty list
-  command: >-
+  set_fact:
-    {{ bin_dir }}/kubectl cordon {{ hostvars[item]['kube_override_hostname']|default(item) }}
+    nodes_to_drain: []
-  with_items:
+
-    - "{{ node.split(',') | default(groups['kube-node']) }}"
+- name: remove-node | Identify nodes to drain, ignore non-cluster nodes
-  register: result
+  shell: |
-  failed_when: result.rc != 0 and not allow_ungraceful_removal
+    set -o pipefail
+    {{ bin_dir }}/kubectl get nodes -o json \
+                  | jq .items[].metadata.name \
+                  | jq "select(. | test(\"^{{ hostvars[item]['kube_override_hostname']|default(item) }}$\"))"
+  loop: "{{ node.split(',') | default(groups['kube-node']) }}"
+  register: nodes
   delegate_to: "{{ groups['kube-master']|first }}"
+  changed_when: false
+  run_once: true
+
+- name: remove-node | Generate list of nodes to drain
+  set_fact:
+    nodes_to_drain: "{{  nodes_to_drain }} + [ '{{ item.stdout  | regex_replace('\"', '') }}' ]"
+  loop: "{{ nodes.results }}"
+  when: item.stdout | length != 0
   run_once: true
-  ignore_errors: yes
 
 - name: remove-node | Drain node except daemonsets resource  # noqa 301
   command: >-
@@ -18,10 +30,11 @@
       --grace-period {{ drain_grace_period }}
       --timeout {{ drain_timeout }}
       --delete-local-data {{ hostvars[item]['kube_override_hostname']|default(item) }}
-  with_items:
+  loop: "{{ nodes_to_drain }}"
-    - "{{ node.split(',') | default(groups['kube-node']) }}"
   register: result
   failed_when: result.rc != 0 and not allow_ungraceful_removal
   delegate_to: "{{ groups['kube-master']|first }}"
   run_once: true
-  ignore_errors: yes
+  until: result.rc == 0 or allow_ungraceful_removal
+  retries: "{{ drain_retries }}"
+  delay: "{{ drain_retry_delay_seconds }}"