c12s-kubespray/roles/recover_control_plane/etcd/tasks/main.yml
qvicksilver ac2135e450
Fix recover-control-plane to work with etcd 3.3.x and add CI (#5500)
* 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
2020-02-11 01:38:01 -08:00

78 lines
2.7 KiB
YAML

---
- name: Get etcd endpoint health
shell: "{{ bin_dir }}/etcdctl --cacert {{ etcd_cert_dir }}/ca.pem --cert {{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem --key {{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem --endpoints={{ etcd_access_addresses }} endpoint health"
register: etcd_endpoint_health
ignore_errors: true
changed_when: false
check_mode: no
environment:
- ETCDCTL_API: 3
when:
- groups['broken_etcd']
- name: Set healthy fact
set_fact:
healthy: "{{ etcd_endpoint_health.stderr | match('Error: unhealthy cluster') }}"
when:
- groups['broken_etcd']
- name: Set has_quorum fact
set_fact:
has_quorum: "{{ etcd_endpoint_health.stdout_lines | select('match', '.*is healthy.*') | list | length >= etcd_endpoint_health.stderr_lines | select('match', '.*is unhealthy.*') | list | length }}"
- include_tasks: recover_lost_quorum.yml
when:
- groups['broken_etcd']
- not has_quorum
- name: Remove etcd data dir
file:
path: "{{ etcd_data_dir }}"
state: absent
delegate_to: "{{ item }}"
with_items: "{{ groups['broken_etcd'] }}"
when:
- groups['broken_etcd']
- has_quorum
- name: Delete old certificates
# noqa 302 - rm is ok here for now
shell: "rm {{ etcd_cert_dir }}/*{{ item }}*"
with_items: "{{ groups['broken_etcd'] }}"
register: delete_old_cerificates
ignore_errors: true
when: groups['broken_etcd']
- name: Fail if unable to delete old certificates
fail:
msg: "Unable to delete old certificates for: {{ item.item }}"
loop: "{{ delete_old_cerificates.results }}"
changed_when: false
when:
- groups['broken_etcd']
- "item.rc != 0 and not 'No such file or directory' in item.stderr"
- name: Get etcd cluster members
shell: "{{ bin_dir }}/etcdctl --cacert {{ etcd_cert_dir }}/ca.pem --cert {{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem --key {{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem member list"
register: member_list
changed_when: false
check_mode: no
environment:
- ETCDCTL_API: 3
when:
- groups['broken_etcd']
- not healthy
- has_quorum
- name: Remove broken cluster members
shell: "{{ bin_dir }}/etcdctl --cacert {{ etcd_cert_dir }}/ca.pem --cert {{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem --key {{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem --endpoints={{ etcd_access_addresses }} member remove {{ item[1].replace(' ','').split(',')[0] }}"
environment:
- ETCDCTL_API: 3
with_nested:
- "{{ groups['broken_etcd'] }}"
- "{{ member_list.stdout_lines }}"
when:
- groups['broken_etcd']
- not healthy
- has_quorum
- hostvars[item[0]]['etcd_member_name'] == item[1].replace(' ','').split(',')[2]