ac2135e450
* Fix recover-control-plane to work with etcd 3.3.x and add CI * Set default values for testcase * Add actual test jobs * Attempt to satisty gitlab ci linter * Fix ansible targets * Set etcd_member_name as stated in the docs... * Recovering from 0 masters is not supported yet * Add other master to broken_kube-master group as well * Increase number of retries to see if etcd needs more time to heal * Make number of retries for ETCD loops configurable, increase it for recovery CI and document it
30 lines
983 B
YAML
30 lines
983 B
YAML
---
|
|
- name: Wait for apiserver
|
|
shell: "{{ bin_dir }}/kubectl get nodes"
|
|
environment:
|
|
- KUBECONFIG: "{{ ansible_env.HOME | default('/root') }}/.kube/config"
|
|
register: apiserver_is_ready
|
|
until: apiserver_is_ready.rc == 0
|
|
retries: 6
|
|
delay: 10
|
|
changed_when: false
|
|
when: groups['broken_kube-master']
|
|
|
|
- name: Delete broken kube-master nodes from cluster
|
|
shell: "{{ bin_dir }}/kubectl delete node {{ item }}"
|
|
environment:
|
|
- KUBECONFIG: "{{ ansible_env.HOME | default('/root') }}/.kube/config"
|
|
with_items: "{{ groups['broken_kube-master'] }}"
|
|
register: delete_broken_kube_masters
|
|
failed_when: false
|
|
when: groups['broken_kube-master']
|
|
|
|
- name: Fail if unable to delete broken kube-master nodes from cluster
|
|
fail:
|
|
msg: "Unable to delete broken kube-master node: {{ item.item }}"
|
|
loop: "{{ delete_broken_kube_masters.results }}"
|
|
changed_when: false
|
|
when:
|
|
- groups['broken_kube-master']
|
|
- "item.rc != 0 and not 'NotFound' in item.stderr"
|