feat: 声明 sandbox 双节点 K3s 集群

2026-09-17 14:57:48 +00:00
parent cadfee0aea
commit 6585d8c46a
25 changed files with 1132 additions and 0 deletions
@@ -0,0 +1,50 @@
+---
+- name: Validate sandbox PostgreSQL inputs
+  ansible.builtin.assert:
+    that:
+      - sandbox_postgresql_k3s_password | length >= 32
+      - sandbox_postgresql_replication_password | length >= 32
+      - inventory_hostname in groups['postgres_primary'] or inventory_hostname in groups['postgres_standby']
+    fail_msg: Missing Bao-provided PostgreSQL credentials or invalid inventory role
+  no_log: true
+
+- name: Install PostgreSQL packages
+  ansible.builtin.apt:
+    name:
+      - postgresql-{{ sandbox_postgresql_version }}
+      - postgresql-client-{{ sandbox_postgresql_version }}
+      - python3-psycopg2
+    state: present
+    update_cache: true
+    cache_valid_time: 3600
+
+- name: Check whether synchronous replication has completed bootstrap
+  ansible.builtin.stat:
+    path: /etc/postgresql/{{ sandbox_postgresql_version }}/main/sandbox-synchronous-ready
+  register: sandbox_postgresql_synchronous_marker
+
+- name: Install sandbox PostgreSQL access policy
+  ansible.builtin.template:
+    src: pg_hba.conf.j2
+    dest: /etc/postgresql/{{ sandbox_postgresql_version }}/main/pg_hba.conf
+    owner: postgres
+    group: postgres
+    mode: "0640"
+  notify: Restart sandbox PostgreSQL
+
+- name: Install sandbox PostgreSQL server settings
+  ansible.builtin.template:
+    src: sandbox.conf.j2
+    dest: /etc/postgresql/{{ sandbox_postgresql_version }}/main/conf.d/99-sandbox.conf
+    owner: postgres
+    group: postgres
+    mode: "0644"
+  notify: Restart sandbox PostgreSQL
+
+- name: Configure sandbox PostgreSQL primary
+  ansible.builtin.include_tasks: primary.yml
+  when: inventory_hostname in groups['postgres_primary']
+
+- name: Configure sandbox PostgreSQL standby
+  ansible.builtin.include_tasks: standby.yml
+  when: inventory_hostname in groups['postgres_standby']
@@ -0,0 +1,45 @@
+---
+- name: Apply primary PostgreSQL configuration before replication setup
+  ansible.builtin.meta: flush_handlers
+
+- name: Create K3s PostgreSQL login role
+  community.postgresql.postgresql_user:
+    name: "{{ sandbox_postgresql_user }}"
+    password: "{{ sandbox_postgresql_k3s_password }}"
+    no_password_changes: "{{ not sandbox_postgresql_rotate_passwords }}"
+    role_attr_flags: LOGIN,NOSUPERUSER,NOCREATEDB,NOCREATEROLE,NOREPLICATION
+    state: present
+  become: true
+  become_user: postgres
+  no_log: true
+  environment:
+    PGOPTIONS: -c password_encryption=scram-sha-256
+
+- name: Create K3s PostgreSQL database
+  community.postgresql.postgresql_db:
+    name: "{{ sandbox_postgresql_database }}"
+    owner: "{{ sandbox_postgresql_user }}"
+    state: present
+  become: true
+  become_user: postgres
+
+- name: Create PostgreSQL replication login role
+  community.postgresql.postgresql_user:
+    name: "{{ sandbox_postgresql_replication_user }}"
+    password: "{{ sandbox_postgresql_replication_password }}"
+    no_password_changes: "{{ not sandbox_postgresql_rotate_passwords }}"
+    role_attr_flags: LOGIN,REPLICATION,NOSUPERUSER,NOCREATEDB,NOCREATEROLE
+    state: present
+  become: true
+  become_user: postgres
+  no_log: true
+  environment:
+    PGOPTIONS: -c password_encryption=scram-sha-256
+
+- name: Create physical replication slot for sandbox2
+  community.postgresql.postgresql_slot:
+    name: "{{ sandbox_postgresql_replication_slot }}"
+    slot_type: physical
+    state: present
+  become: true
+  become_user: postgres
@@ -0,0 +1,114 @@
+---
+- name: Detect whether sandbox2 is already a standby
+  community.postgresql.postgresql_query:
+    login_db: postgres
+    query: SELECT pg_is_in_recovery() AS in_recovery
+  become: true
+  become_user: postgres
+  register: sandbox_postgresql_recovery_state
+
+- name: Inspect databases before the initial standby seed
+  community.postgresql.postgresql_query:
+    login_db: postgres
+    query: >-
+      SELECT datname FROM pg_database
+      WHERE NOT datistemplate AND datname <> 'postgres'
+  become: true
+  become_user: postgres
+  register: sandbox_postgresql_existing_databases
+  when: not sandbox_postgresql_recovery_state.query_result[0].in_recovery
+
+- name: Refuse to overwrite a non-empty PostgreSQL node
+  ansible.builtin.assert:
+    that:
+      - sandbox_postgresql_existing_databases.query_result | length == 0
+    fail_msg: Refusing to reseed sandbox2 because it contains non-system databases
+  when: not sandbox_postgresql_recovery_state.query_result[0].in_recovery
+
+- name: Stop PostgreSQL before the initial standby seed
+  ansible.builtin.service:
+    name: postgresql
+    state: stopped
+  when: not sandbox_postgresql_recovery_state.query_result[0].in_recovery
+
+- name: Remove the verified-empty standby data directory
+  ansible.builtin.file:
+    path: /var/lib/postgresql/{{ sandbox_postgresql_version }}/main
+    state: absent
+  when: not sandbox_postgresql_recovery_state.query_result[0].in_recovery
+
+- name: Recreate the standby data directory
+  ansible.builtin.file:
+    path: /var/lib/postgresql/{{ sandbox_postgresql_version }}/main
+    state: directory
+    owner: postgres
+    group: postgres
+    mode: "0700"
+  when: not sandbox_postgresql_recovery_state.query_result[0].in_recovery
+
+- name: Install standby replication password file
+  ansible.builtin.copy:
+    dest: /var/lib/postgresql/.pgpass
+    content: >-
+      {{ sandbox_postgresql_primary_address }}:5432:*:{{ sandbox_postgresql_replication_user }}:{{ sandbox_postgresql_replication_password }}
+    owner: postgres
+    group: postgres
+    mode: "0600"
+  no_log: true
+
+- name: Seed sandbox2 from the PostgreSQL primary
+  ansible.builtin.command:
+    argv:
+      - /usr/bin/pg_basebackup
+      - --host={{ sandbox_postgresql_primary_address }}
+      - --username={{ sandbox_postgresql_replication_user }}
+      - --pgdata=/var/lib/postgresql/{{ sandbox_postgresql_version }}/main
+      - --format=plain
+      - --wal-method=stream
+      - --write-recovery-conf
+      - --slot={{ sandbox_postgresql_replication_slot }}
+  become: true
+  become_user: postgres
+  environment:
+    PGPASSFILE: /var/lib/postgresql/.pgpass
+  when: not sandbox_postgresql_recovery_state.query_result[0].in_recovery
+  no_log: true
+
+- name: Set the standby connection identity
+  ansible.builtin.lineinfile:
+    path: /var/lib/postgresql/{{ sandbox_postgresql_version }}/main/postgresql.auto.conf
+    regexp: ^primary_conninfo =
+    line: >-
+      primary_conninfo = 'host={{ sandbox_postgresql_primary_address }} port=5432
+      user={{ sandbox_postgresql_replication_user }} application_name=sandbox2
+      passfile=/var/lib/postgresql/.pgpass'
+    owner: postgres
+    group: postgres
+    mode: "0600"
+  no_log: true
+
+- name: Start PostgreSQL standby
+  ansible.builtin.service:
+    name: postgresql
+    enabled: true
+    state: started
+
+- name: Wait for sandbox2 to enter recovery
+  community.postgresql.postgresql_query:
+    login_db: postgres
+    query: SELECT pg_is_in_recovery() AS in_recovery
+  become: true
+  become_user: postgres
+  register: sandbox_postgresql_standby_ready
+  retries: 12
+  delay: 5
+  until: sandbox_postgresql_standby_ready.query_result[0].in_recovery
+
+- name: Mark synchronous replication bootstrap complete on the primary
+  ansible.builtin.copy:
+    dest: /etc/postgresql/{{ sandbox_postgresql_version }}/main/sandbox-synchronous-ready
+    content: "sandbox2\n"
+    owner: postgres
+    group: postgres
+    mode: "0644"
+  delegate_to: "{{ groups['postgres_primary'][0] }}"