c12s-kubespray/roles/etcd/tasks/configure.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

149 lines
5.4 KiB
YAML

---
- name: Configure | Check if etcd cluster is healthy
shell: "{{ bin_dir }}/etcdctl --endpoints={{ etcd_access_addresses }} cluster-health | grep -q 'cluster is healthy'"
register: etcd_cluster_is_healthy
ignore_errors: true
changed_when: false
check_mode: no
when: is_etcd_master and etcd_cluster_setup
tags:
- facts
environment:
ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
ETCDCTL_CA_FILE: "{{ etcd_cert_dir }}/ca.pem"
- name: Configure | Check if etcd-events cluster is healthy
shell: "{{ bin_dir }}/etcdctl --endpoints={{ etcd_events_access_addresses }} cluster-health | grep -q 'cluster is healthy'"
register: etcd_events_cluster_is_healthy
ignore_errors: true
changed_when: false
check_mode: no
when: is_etcd_master and etcd_events_cluster_setup
tags:
- facts
environment:
ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
ETCDCTL_CA_FILE: "{{ etcd_cert_dir }}/ca.pem"
- include_tasks: refresh_config.yml
when: is_etcd_master
- name: Configure | Copy etcd.service systemd file
template:
src: "etcd-{{ etcd_deployment_type }}.service.j2"
dest: /etc/systemd/system/etcd.service
backup: yes
when: is_etcd_master and etcd_cluster_setup
- name: Configure | Copy etcd-events.service systemd file
template:
src: "etcd-events-{{ etcd_deployment_type }}.service.j2"
dest: /etc/systemd/system/etcd-events.service
backup: yes
when: is_etcd_master and etcd_events_cluster_setup
- name: Configure | reload systemd
systemd:
daemon_reload: true
when: is_etcd_master
- name: Configure | Ensure etcd is running
service:
name: etcd
state: started
enabled: yes
when: is_etcd_master and etcd_cluster_setup
- name: Configure | Ensure etcd-events is running
service:
name: etcd-events
state: started
enabled: yes
when: is_etcd_master and etcd_events_cluster_setup
- name: Configure | Check if etcd cluster is healthy
shell: "{{ bin_dir }}/etcdctl --no-sync --endpoints={{ etcd_client_url }} cluster-health | grep -q 'cluster is healthy'"
register: etcd_cluster_is_healthy
until: etcd_cluster_is_healthy.rc == 0
retries: "{{ etcd_retries }}"
delay: "{{ retry_stagger | random + 3 }}"
ignore_errors: false
changed_when: false
check_mode: no
delegate_to: "{{ groups['etcd'][0] }}"
run_once: yes
when:
- is_etcd_master
- etcd_cluster_setup
tags:
- facts
environment:
ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
ETCDCTL_CA_FILE: "{{ etcd_cert_dir }}/ca.pem"
- name: Configure | Check if etcd-events cluster is healthy
shell: "{{ bin_dir }}/etcdctl --no-sync --endpoints={{ etcd_events_client_url }} cluster-health | grep -q 'cluster is healthy'"
register: etcd_events_cluster_is_healthy
until: etcd_events_cluster_is_healthy.rc == 0
retries: "{{ etcd_retries }}"
delay: "{{ retry_stagger | random + 3 }}"
ignore_errors: false
changed_when: false
check_mode: no
delegate_to: "{{ groups['etcd'][0] }}"
run_once: yes
when:
- is_etcd_master
- etcd_events_cluster_setup
- etcd_cluster_setup
tags:
- facts
environment:
ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
ETCDCTL_CA_FILE: "{{ etcd_cert_dir }}/ca.pem"
- name: Configure | Check if member is in etcd cluster
shell: "{{ bin_dir }}/etcdctl --no-sync --endpoints={{ etcd_access_addresses }} member list | grep -q {{ etcd_access_address }}"
register: etcd_member_in_cluster
ignore_errors: true
changed_when: false
check_mode: no
when: is_etcd_master and etcd_cluster_setup
tags:
- facts
environment:
ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
ETCDCTL_CA_FILE: "{{ etcd_cert_dir }}/ca.pem"
- name: Configure | Check if member is in etcd-events cluster
shell: "{{ bin_dir }}/etcdctl --no-sync --endpoints={{ etcd_events_access_addresses }} member list | grep -q {{ etcd_access_address }}"
register: etcd_events_member_in_cluster
ignore_errors: true
changed_when: false
check_mode: no
when: is_etcd_master and etcd_events_cluster_setup
tags:
- facts
environment:
ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
ETCDCTL_CA_FILE: "{{ etcd_cert_dir }}/ca.pem"
- name: Configure | Join member(s) to etcd cluster one at a time
include_tasks: join_etcd_member.yml
vars:
target_node: "{{ item }}"
with_items: "{{ groups['etcd'] }}"
when: inventory_hostname == item and etcd_cluster_setup and etcd_member_in_cluster.rc != 0 and etcd_cluster_is_healthy.rc == 0
- name: Configure | Join member(s) to etcd-events cluster one at a time
include_tasks: join_etcd-events_member.yml
vars:
target_node: "{{ item }}"
with_items: "{{ groups['etcd'] }}"
when: inventory_hostname == item and etcd_events_cluster_setup and etcd_events_member_in_cluster.rc != 0 and etcd_events_cluster_is_healthy.rc == 0