kubespray/roles/etcd/tasks/configure.yml

---
- name: Configure | Check if etcd cluster is healthy
  shell: "set -o pipefail && {{ bin_dir }}/etcdctl endpoint --cluster status && {{ bin_dir }}/etcdctl endpoint --cluster health  2>&1 | grep -v 'Error: unhealthy cluster' >/dev/null"
  args:
    executable: /bin/bash
  register: etcd_cluster_is_healthy
  failed_when: false
  changed_when: false
  check_mode: false
  run_once: true
  when:
    - is_etcd_master
    - etcd_cluster_setup
  tags:
    - facts
  environment:
    ETCDCTL_API: "3"
    ETCDCTL_CERT: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
    ETCDCTL_KEY: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
    ETCDCTL_CACERT: "{{ etcd_cert_dir }}/ca.pem"
    ETCDCTL_ENDPOINTS: "{{ etcd_access_addresses }}"

- name: Configure | Check if etcd-events cluster is healthy
  shell: "set -o pipefail && {{ bin_dir }}/etcdctl endpoint --cluster status && {{ bin_dir }}/etcdctl endpoint --cluster health  2>&1 | grep -v 'Error: unhealthy cluster' >/dev/null"
  args:
    executable: /bin/bash
  register: etcd_events_cluster_is_healthy
  failed_when: false
  changed_when: false
  check_mode: false
  run_once: true
  when:
    - is_etcd_master
    - etcd_events_cluster_setup
  tags:
    - facts
  environment:
    ETCDCTL_API: "3"
    ETCDCTL_CERT: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
    ETCDCTL_KEY: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
    ETCDCTL_CACERT: "{{ etcd_cert_dir }}/ca.pem"
    ETCDCTL_ENDPOINTS: "{{ etcd_events_access_addresses }}"

- name: Configure | Refresh etcd config
  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: true
    mode: "0644"
    # FIXME: check that systemd version >= 250 (factory-reset.target was introduced in that release)
    # Remove once we drop support for systemd < 250
    validate: "sh -c '[ -f /usr/bin/systemd/system/factory-reset.target ] || exit 0 && systemd-analyze verify %s:etcd-{{ etcd_deployment_type }}.service'"
  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: true
    mode: "0644"
    validate: "sh -c '[ -f /usr/bin/systemd/system/factory-reset.target ] || exit 0 && systemd-analyze verify %s:etcd-events-{{ etcd_deployment_type }}.service'"
    # FIXME: check that systemd version >= 250 (factory-reset.target was introduced in that release)
    # Remove once we drop support for systemd < 250
  when: is_etcd_master and etcd_events_cluster_setup

- name: Configure | reload systemd
  systemd_service:
    daemon_reload: true
  when: is_etcd_master

# when scaling new etcd will fail to start
- name: Configure | Ensure etcd is running
  service:
    name: etcd
    state: started
    enabled: true
  ignore_errors: "{{ etcd_cluster_is_healthy.rc == 0 }}"  # noqa ignore-errors
  when: is_etcd_master and etcd_cluster_setup

# when scaling new etcd will fail to start
- name: Configure | Ensure etcd-events is running
  service:
    name: etcd-events
    state: started
    enabled: true
  ignore_errors: "{{ etcd_events_cluster_is_healthy.rc != 0 }}"  # noqa ignore-errors
  when: is_etcd_master and etcd_events_cluster_setup

- name: Configure | Wait for etcd cluster to be healthy
  shell: "set -o pipefail && {{ bin_dir }}/etcdctl endpoint --cluster status && {{ bin_dir }}/etcdctl endpoint --cluster health 2>&1 | grep -v 'Error: unhealthy cluster' >/dev/null"
  args:
    executable: /bin/bash
  register: etcd_cluster_is_healthy
  until: etcd_cluster_is_healthy.rc == 0
  retries: "{{ etcd_retries }}"
  delay: "{{ retry_stagger | random + 3 }}"
  changed_when: false
  check_mode: false
  run_once: true
  when:
    - is_etcd_master
    - etcd_cluster_setup
  tags:
    - facts
  environment:
    ETCDCTL_API: "3"
    ETCDCTL_CERT: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
    ETCDCTL_KEY: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
    ETCDCTL_CACERT: "{{ etcd_cert_dir }}/ca.pem"
    ETCDCTL_ENDPOINTS: "{{ etcd_access_addresses }}"

- name: Configure | Wait for etcd-events cluster to be healthy
  shell: "set -o pipefail && {{ bin_dir }}/etcdctl endpoint --cluster status && {{ bin_dir }}/etcdctl endpoint --cluster health 2>&1 | grep -v 'Error: unhealthy cluster' >/dev/null"
  args:
    executable: /bin/bash
  register: etcd_events_cluster_is_healthy
  until: etcd_events_cluster_is_healthy.rc == 0
  retries: "{{ etcd_retries }}"
  delay: "{{ retry_stagger | random + 3 }}"
  changed_when: false
  check_mode: false
  run_once: true
  when:
    - is_etcd_master
    - etcd_events_cluster_setup
  tags:
    - facts
  environment:
    ETCDCTL_API: "3"
    ETCDCTL_CERT: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
    ETCDCTL_KEY: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
    ETCDCTL_CACERT: "{{ etcd_cert_dir }}/ca.pem"
    ETCDCTL_ENDPOINTS: "{{ etcd_events_access_addresses }}"

- name: Configure | Check if member is in etcd cluster
  shell: "{{ bin_dir }}/etcdctl member list | grep -w -q {{ etcd_access_address }}"
  register: etcd_member_in_cluster
  ignore_errors: true  # noqa ignore-errors
  changed_when: false
  check_mode: false
  when: is_etcd_master and etcd_cluster_setup
  tags:
    - facts
  environment:
    ETCDCTL_API: "3"
    ETCDCTL_CERT: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
    ETCDCTL_KEY: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
    ETCDCTL_CACERT: "{{ etcd_cert_dir }}/ca.pem"
    ETCDCTL_ENDPOINTS: "{{ etcd_access_addresses }}"

- name: Configure | Check if member is in etcd-events cluster
  shell: "{{ bin_dir }}/etcdctl member list | grep -w -q {{ etcd_access_address }}"
  register: etcd_events_member_in_cluster
  ignore_errors: true  # noqa ignore-errors
  changed_when: false
  check_mode: false
  when: is_etcd_master and etcd_events_cluster_setup
  tags:
    - facts
  environment:
    ETCDCTL_API: "3"
    ETCDCTL_CERT: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
    ETCDCTL_KEY: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
    ETCDCTL_CACERT: "{{ etcd_cert_dir }}/ca.pem"
    ETCDCTL_ENDPOINTS: "{{ etcd_events_access_addresses }}"

- name: Configure | Join member(s) to etcd cluster one at a time
  include_tasks: join_etcd_member.yml
  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
  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