feat: 纳管共享 etcd 与 k3s 外 PostgreSQL 高可用及备份
yaml / yaml (pull_request) Successful in 41s
ansible / collection-test (pull_request) Successful in 2m41s
terraform / validate (pull_request) Successful in 2m41s
ansible / lint (pull_request) Successful in 4m36s

This commit is contained in:
2026-09-25 19:34:48 +00:00
parent acd4b55722
commit 3a2fe5fa0c
92 changed files with 4211 additions and 0 deletions
+6
View File
@@ -0,0 +1,6 @@
[defaults]
inventory = inventory/hosts.yml
roles_path = roles
retry_files_enabled = False
host_key_checking = True
interpreter_python = auto_silent
@@ -0,0 +1,60 @@
---
# 与常规 site 分离,防止重建/恢复时默默创建新的认证域。
- name: 初始化共享 etcd 认证
hosts: etcd[0]
become: true
gather_facts: false
pre_tasks:
- name: 加载共享默认参数
ansible.builtin.import_role:
name: shared_etcd
tasks_from: context
environment:
ETCDCTL_ENDPOINTS: "https://{{ etcd_address }}:{{ etcd_client_port }}"
ETCDCTL_CACERT: "{{ etcd_config_dir }}/ca.crt"
ETCDCTL_CERT: "{{ etcd_config_dir }}/admin.crt"
ETCDCTL_KEY: "{{ etcd_config_dir }}/admin.key"
tasks:
- name: 读取认证状态
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", --write-out=json, auth, status]
changed_when: false
register: etcd_auth_status
check_mode: false
- name: 初始化管理员与认证
when: not ((etcd_auth_status.stdout | from_json).enabled | default(false))
block:
- name: 要求显式初始化参数
ansible.builtin.assert:
that: etcd_bootstrap_auth | default(false) | bool
fail_msg: 首次初始化需要 -e etcd_bootstrap_auth=true;常规运行不能重建认证。
- name: 读取现有用户
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", --write-out=json, user, list]
changed_when: false
register: etcd_users
- name: 创建仅证书认证的 root 用户
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", user, add, root, --no-password]
when: "'root' not in ((etcd_users.stdout | from_json).users | default([], true))"
changed_when: true
- name: 读取管理员角色
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", --write-out=json, user, get, root]
changed_when: false
register: etcd_root_roles
- name: 授予 root 管理角色
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", user, grant-role, root, root]
when: "'root' not in ((etcd_root_roles.stdout | from_json).roles | default([], true))"
changed_when: true
- name: 开启认证
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", auth, enable]
changed_when: true
+37
View File
@@ -0,0 +1,37 @@
---
- name: 收敛消费者账号及独立 prefix
hosts: etcd[0]
become: true
gather_facts: false
pre_tasks:
- name: 加载共享默认参数
ansible.builtin.import_role:
name: shared_etcd
tasks_from: context
environment:
ETCDCTL_ENDPOINTS: "https://{{ etcd_address }}:{{ etcd_client_port }}"
ETCDCTL_CACERT: "{{ etcd_config_dir }}/ca.crt"
ETCDCTL_CERT: "{{ etcd_config_dir }}/admin.crt"
ETCDCTL_KEY: "{{ etcd_config_dir }}/admin.key"
tasks:
- name: 检查认证状态
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", --write-out=json, auth, status]
register: etcd_auth_status
changed_when: false
check_mode: false
- name: 要求认证已启用
ansible.builtin.assert:
that:
- ((etcd_auth_status.stdout | from_json).enabled | default(false))
- etcd_consumers | map(attribute='name') | unique | length == etcd_consumers | length
- etcd_bao_token | length > 0
no_log: true
- name: 逐个收敛消费者
ansible.builtin.include_tasks: tasks/consumer.yml
loop: "{{ etcd_consumers }}"
loop_control:
loop_var: etcd_consumer
label: "{{ etcd_consumer.name }}"
@@ -0,0 +1,74 @@
---
# 仅在 Terraform 身份配置完成后部署;预检失败不启用定时器。
- name: 安装独立于人工会话的续签调度
hosts: etcd-laptop
become: true
gather_facts: false
tasks:
- name: 创建 root 管理的程序目录
ansible.builtin.file:
path: /opt/homelab-etcd-controller
state: directory
mode: '0755'
- name: 安装证书登录与调度程序
ansible.builtin.copy:
src: "../controller/{{ item }}"
dest: "/opt/homelab-etcd-controller/{{ item }}"
owner: root
group: root
mode: '0755'
loop: [login.py, renew.py]
- name: 以机器身份预检(不输出 token)
ansible.builtin.command:
argv: [/usr/bin/python3, /opt/homelab-etcd-controller/login.py]
changed_when: false
no_log: true
- name: 安装固定的 Ansible 配置副本
ansible.builtin.copy:
src: "{{ playbook_dir }}/"
dest: /opt/homelab-etcd-controller/ansible/
owner: root
group: root
mode: preserve
- name: 创建调度状态目录
ansible.builtin.file:
path: /var/lib/homelab-etcd-controller
state: directory
owner: panxiao81
group: panxiao81
mode: '0700'
- name: 安装续签 oneshot unit
ansible.builtin.copy:
dest: /etc/systemd/system/homelab-etcd-renew.service
mode: '0644'
content: |
[Unit]
Description=Renew shared etcd certificates through Bao machine identity
After=network-online.target
[Service]
Type=oneshot
User=panxiao81
Environment=HOME=/home/panxiao81
Environment=PATH=/home/panxiao81/.local/bin:/usr/local/bin:/usr/bin:/bin
ExecStart=/usr/bin/python3 /opt/homelab-etcd-controller/renew.py
TimeoutStartSec=30min
UMask=0077
- name: 安装每日续签 timer
ansible.builtin.copy:
dest: /etc/systemd/system/homelab-etcd-renew.timer
mode: '0644'
content: |
[Unit]
Description=Daily shared etcd certificate renewal check
[Timer]
OnCalendar=*-*-* 04:10:00 UTC
RandomizedDelaySec=15min
Persistent=true
[Install]
WantedBy=timers.target
- name: 启用续签调度
ansible.builtin.systemd_service:
name: homelab-etcd-renew.timer
daemon_reload: true
enabled: true
state: started
@@ -0,0 +1,20 @@
---
etcd_bao_url: https://bao.ad.ddupan.top:8200
etcd_bao_pki_mount: pki
etcd_bao_kv_mount: kv
etcd_bao_secret_base: infra/etcd/consumers
# 只在控制端使用,不下发 Bao token。也不读取或复制历史 .vault_pass。
etcd_bao_token: "{{ lookup('env', 'BAO_TOKEN') }}"
etcd_consumers:
- name: patroni-pg-prod
prefix: /homelab/patroni/pg-prod/
etcd_lxc_template: laptop:vztmpl/ubuntu-24.04-standard_24.04-2_amd64.tar.zst
etcd_lxc_storage: pve-rg
etcd_lxc_bridge: labnet
etcd_lxc_gateway: 10.60.0.1
etcd_lxc_memory: 512
etcd_lxc_disk_gb: 8
etcd_lxc_pubkey: "{{ lookup('file', '~/.ssh/id_ed25519.pub') }}"
# 与现有 LAN exporter 相同的内网采集边界;禁止映射到公网。
etcd_metrics_urls: "http://127.0.0.1:2381,http://{{ etcd_address }}:2381"
@@ -0,0 +1,33 @@
---
# 已部署成员;共置 PG standby/备份的承载预算,数据库数据用独立 HDD mp0。
all:
vars:
ansible_user: root
children:
etcd:
hosts:
etcd-laptop:
ansible_connection: local
ansible_host: 192.168.10.127
ansible_user: panxiao81
etcd_address: 192.168.10.127
etcd-pve1:
ansible_host: 10.60.0.20
etcd_address: 10.60.0.20
etcd-pve2:
ansible_host: 10.60.0.21
etcd_address: 10.60.0.21
etcd_pve:
hosts:
pve1:
ansible_host: 192.168.10.4
etcd_lxc_vmid: 150
etcd_lxc_hostname: etcd-pve1
etcd_lxc_address: 10.60.0.20/24
etcd_lxc_memory: 1536
pve2:
ansible_host: 192.168.10.7
etcd_lxc_vmid: 151
etcd_lxc_hostname: etcd-pve2
etcd_lxc_address: 10.60.0.21/24
etcd_lxc_memory: 768
+126
View File
@@ -0,0 +1,126 @@
---
# 只创建已声明且尚不存在的 LXC;不接管未知 VMID,不重启现有容器。
- name: 创建独立 etcd LXC
hosts: etcd_pve
become: true
gather_facts: false
tasks:
- name: 读取全局资源,避免 VMID 在其他节点已占用
ansible.builtin.command:
argv: [pvesh, get, /cluster/resources, --type, vm, --output-format, json]
register: etcd_pve_resources
changed_when: false
check_mode: false
- name: 保存同号资源
ansible.builtin.set_fact:
etcd_lxc_existing: >-
{{ etcd_pve_resources.stdout
| from_json
| selectattr('vmid', 'equalto', etcd_lxc_vmid)
| list }}
- name: 拒绝接管未知资源
ansible.builtin.assert:
that:
- >-
etcd_lxc_existing | length == 0 or
(etcd_lxc_existing[0].type == 'lxc' and etcd_lxc_existing[0].node == inventory_hostname
and etcd_lxc_existing[0].name == etcd_lxc_hostname
and 'shared-etcd' in (etcd_lxc_existing[0].tags | default('')))
- name: 新建无特权 LXC
when: etcd_lxc_existing | length == 0 and not ansible_check_mode
block:
- name: 暂存 SSH 公钥
ansible.builtin.copy:
content: "{{ etcd_lxc_pubkey }}\n"
dest: /run/shared-etcd-bootstrap.pub
mode: '0600'
- name: 创建声明的容器
ansible.builtin.command:
argv:
- pct
- create
- "{{ etcd_lxc_vmid }}"
- "{{ etcd_lxc_template }}"
- --hostname
- "{{ etcd_lxc_hostname }}"
- --unprivileged
- '1'
- --cores
- '1'
- --memory
- "{{ etcd_lxc_memory }}"
- --swap
- '0'
- --rootfs
- "{{ etcd_lxc_storage }}:{{ etcd_lxc_disk_gb }}"
- --net0
- "name=eth0,bridge={{ etcd_lxc_bridge }},ip={{ etcd_lxc_address }},gw={{ etcd_lxc_gateway }},type=veth"
- --nameserver
- 192.168.10.5
- --searchdomain
- ad.ddupan.top
- --ssh-public-keys
- /run/shared-etcd-bootstrap.pub
- --onboot
- '1'
- --tags
- ansible;shared-etcd
changed_when: true
always:
- name: 删除暂存公钥
ansible.builtin.file:
path: /run/shared-etcd-bootstrap.pub
state: absent
- name: 读取容器配置
ansible.builtin.command:
argv: [pct, config, "{{ etcd_lxc_vmid }}"]
changed_when: false
register: etcd_lxc_config
when: not ansible_check_mode or etcd_lxc_existing | length > 0
- name: 配置漂移先报错,不直接改运行中的网络/资源
ansible.builtin.assert:
that:
- >-
('ip=' ~ etcd_lxc_address ~ ',') in etcd_lxc_config.stdout or
('ip=' ~ etcd_lxc_address ~ '\n') in etcd_lxc_config.stdout
- "('bridge=' ~ etcd_lxc_bridge ~ ',') in etcd_lxc_config.stdout"
- "'unprivileged: 1' in etcd_lxc_config.stdout"
- "('memory: ' ~ etcd_lxc_memory) in etcd_lxc_config.stdout"
- "('rootfs: ' ~ etcd_lxc_storage ~ ':') in etcd_lxc_config.stdout"
when: etcd_lxc_config is not skipped
- name: 读取容器运行状态
ansible.builtin.command:
argv: [pct, status, "{{ etcd_lxc_vmid }}"]
changed_when: false
register: etcd_lxc_status
when: not ansible_check_mode
- name: 启动容器
ansible.builtin.command:
argv: [pct, start, "{{ etcd_lxc_vmid }}"]
changed_when: true
when: not ansible_check_mode and 'running' not in etcd_lxc_status.stdout
- name: 通过可信宿主机取得容器 SSH 公钥
ansible.builtin.command:
argv: [pct, exec, "{{ etcd_lxc_vmid }}", --, cat, /etc/ssh/ssh_host_ed25519_key.pub]
register: etcd_lxc_hostkey
changed_when: false
retries: 12
delay: 5
until: etcd_lxc_hostkey.rc == 0
when: not ansible_check_mode
- name: 保存经宿主机验证的 SSH host key
ansible.builtin.known_hosts:
name: "{{ etcd_lxc_address.split('/')[0] }}"
key: "{{ etcd_lxc_address.split('/')[0] }} {{ etcd_lxc_hostkey.stdout }}"
delegate_to: localhost
become: false
when: not ansible_check_mode
@@ -0,0 +1,90 @@
---
# 首次部署承载调整,逐节点迁移;普通 lxc.yml 不自动移动磁盘。
- name: 逐个将新 etcd 容器迁入声明的 SSD 池
hosts: etcd_pve
become: true
gather_facts: false
serial: 1
any_errors_fatal: true
vars:
etcd_move_health_command:
- /opt/homelab-etcd/etcdctl
- --endpoints=https://192.168.10.127:2379,https://10.60.0.20:2379,https://10.60.0.21:2379
- --cacert=/etc/homelab-etcd/ca.crt
- --cert=/etc/homelab-etcd/admin.crt
- --key=/etc/homelab-etcd/admin.key
- endpoint
- health
tasks:
- name: 核对容器配置
ansible.builtin.command:
argv: [pct, config, "{{ etcd_lxc_vmid }}"]
register: etcd_move_config
changed_when: false
check_mode: false
- name: 限定本项目新建容器与允许的源池
ansible.builtin.assert:
that:
- etcd_lxc_vmid in [150, 151]
- "('hostname: ' ~ etcd_lxc_hostname) in etcd_move_config.stdout"
- "'shared-etcd' in etcd_move_config.stdout"
- "'rootfs: local-lvm:' in etcd_move_config.stdout or 'rootfs: pve-rg:' in etcd_move_config.stdout"
- etcd_lxc_storage == 'pve-rg'
- name: 验证迁移前全部端点健康
ansible.builtin.command:
argv: "{{ etcd_move_health_command }}"
delegate_to: localhost
changed_when: false
check_mode: false
- name: 迁移当前尚在本地池的根卷
when: "'rootfs: local-lvm:' in etcd_move_config.stdout and not ansible_check_mode"
block:
- name: 创建已验证的集群快照
ansible.builtin.command:
argv: [systemctl, start, homelab-etcd-snapshot.service]
delegate_to: localhost
changed_when: true
- name: 正常关闭一个容器
ansible.builtin.command:
argv: [pct, shutdown, "{{ etcd_lxc_vmid }}", --timeout, '60']
changed_when: true
- name: 复制成功后移除该新建容器的原卷
ansible.builtin.command:
argv:
- pct
- move-volume
- "{{ etcd_lxc_vmid }}"
- rootfs
- "{{ etcd_lxc_storage }}"
- --delete
- '1'
- --bwlimit
- '32768'
changed_when: true
always:
- name: 核对容器运行状态
ansible.builtin.command:
argv: [pct, status, "{{ etcd_lxc_vmid }}"]
register: etcd_move_status
changed_when: false
- name: 重新启动容器
ansible.builtin.command:
argv: [pct, start, "{{ etcd_lxc_vmid }}"]
when: "'running' not in etcd_move_status.stdout"
changed_when: true
- name: 等待当前成员回归
ansible.builtin.command:
argv: "{{ etcd_move_health_command }}"
delegate_to: localhost
changed_when: false
register: etcd_move_health
retries: 18
delay: 5
until: etcd_move_health.rc == 0
when: not ansible_check_mode
@@ -0,0 +1,4 @@
---
collections:
- name: community.crypto
version: 3.2.1
@@ -0,0 +1,17 @@
---
etcd_version: 3.7.2
etcd_archive_checksum: sha256:3a3679bc51a4ee9d30bccea1da7cd4fe62c6fc1d2ca1255068d2c53bf3026135
etcd_install_dir: /opt/homelab-etcd
etcd_config_dir: /etc/homelab-etcd
etcd_data_dir: /var/lib/homelab-etcd
etcd_cluster_token: homelab-shared-etcd-v1
etcd_client_port: 2379
etcd_peer_port: 2380
etcd_metrics_port: 2381
etcd_quota_bytes: 268435456
etcd_memory_high: 256M
etcd_memory_max: 384M
etcd_certificate_ttl: 1440h
etcd_renew_before: +14d
etcd_snapshot_dir: /var/backups/homelab-etcd
etcd_snapshot_keep: 3
@@ -0,0 +1,93 @@
---
- name: 在成员本地生成私钥
community.crypto.openssl_privatekey:
path: "{{ etcd_config_dir }}/{{ etcd_cert.name }}.key"
type: ECC
curve: secp256r1
owner: root
group: "{{ etcd_cert.group }}"
mode: '0640'
- name: 本地生成 CSR
community.crypto.openssl_csr:
path: "{{ etcd_config_dir }}/{{ etcd_cert.name }}.csr"
privatekey_path: "{{ etcd_config_dir }}/{{ etcd_cert.name }}.key"
common_name: "{{ etcd_cert.cn | default(omit, true) }}"
subject_alt_name: >-
{{ ['IP:' ~ etcd_address, 'DNS:' ~ inventory_hostname] if etcd_cert.name in ['server', 'peer']
else (['DNS:' ~ inventory_hostname] if etcd_cert.name == 'gateway' else []) }}
use_common_name_for_san: false
extended_key_usage: "{{ etcd_cert.eku }}"
key_usage: [digitalSignature]
mode: '0644'
register: etcd_csr_state
- name: 检查已有证书
ansible.builtin.stat:
path: "{{ etcd_config_dir }}/{{ etcd_cert.name }}.crt"
register: etcd_cert_file
- name: 检查续签窗口
community.crypto.x509_certificate_info:
path: "{{ etcd_config_dir }}/{{ etcd_cert.name }}.crt"
valid_at:
renewal: "{{ etcd_renew_before }}"
register: etcd_cert_info
when: etcd_cert_file.stat.exists
- name: 通过中央 CA 签发需更新的证书
when: >-
not etcd_cert_file.stat.exists or etcd_csr_state is changed or
not (etcd_cert_info.valid_at.renewal | default(false))
block:
- name: 仅在确需签发时要求 Bao 凭据
ansible.builtin.assert:
that: etcd_bao_token | length > 0
no_log: true
- name: 读取 CSR 公共内容
ansible.builtin.slurp:
src: "{{ etcd_config_dir }}/{{ etcd_cert.name }}.csr"
register: etcd_csr
- name: 控制端提交 Bao 签名请求
ansible.builtin.uri:
url: "{{ etcd_bao_url }}/v1/{{ etcd_bao_pki_mount }}/sign/{{ etcd_cert.role }}"
method: POST
headers:
X-Vault-Token: "{{ etcd_bao_token }}"
body_format: json
body:
csr: "{{ etcd_csr.content | b64decode }}"
ttl: "{{ etcd_certificate_ttl }}"
status_code: 200
delegate_to: localhost
become: false
register: etcd_signed
no_log: true
when: not ansible_check_mode
- name: 保存签发的证书链
ansible.builtin.copy:
content: |
{{ etcd_signed.json.data.certificate }}
{{ etcd_signed.json.data.ca_chain | join('\n') }}
dest: "{{ etcd_config_dir }}/{{ etcd_cert.name }}.crt"
owner: root
group: "{{ etcd_cert.group }}"
mode: '0644'
when: not ansible_check_mode
- name: 保存中央 CA 信任链
ansible.builtin.copy:
content: |
{{ etcd_signed.json.data.ca_chain | join('\n') }}
dest: "{{ etcd_config_dir }}/ca.crt"
owner: root
group: homelab-etcd
mode: '0644'
when: not ansible_check_mode
- name: 标记证书已更新
ansible.builtin.set_fact:
etcd_certificates_changed: true
@@ -0,0 +1,3 @@
---
# 只加载 role defaults,供运维入口复用。
[]
@@ -0,0 +1,134 @@
---
- name: 验证拓扑和签发配置
ansible.builtin.assert:
that:
- groups['etcd'] | length == 3
- groups['etcd'] | map('extract', hostvars, 'etcd_address') | unique | length == 3
- ansible_facts['architecture'] == 'x86_64'
- etcd_bao_url is match('^https://')
- etcd_archive_checksum is match('^sha256:[a-f0-9]{64}$')
no_log: true
- name: 安装证书处理依赖
ansible.builtin.package:
name: [python3-cryptography, openssl]
state: present
- name: 创建独立 etcd 组
ansible.builtin.group:
name: homelab-etcd
system: true
- name: 创建独立 etcd 用户
ansible.builtin.user:
name: homelab-etcd
group: homelab-etcd
system: true
shell: /usr/sbin/nologin
create_home: false
- name: 创建受管目录
ansible.builtin.file:
path: "{{ item.path }}"
state: directory
owner: "{{ item.owner }}"
group: homelab-etcd
mode: "{{ item.mode }}"
loop:
- {path: "{{ etcd_config_dir }}", owner: root, mode: '0750'}
- {path: "{{ etcd_data_dir }}", owner: homelab-etcd, mode: '0700'}
- {path: "{{ etcd_install_dir }}", owner: root, mode: '0755'}
- name: 下载固定版本及校验归档
ansible.builtin.get_url:
url: >-
https://github.com/etcd-io/etcd/releases/download/v{{ etcd_version }}/etcd-v{{ etcd_version }}-linux-amd64.tar.gz
dest: "{{ etcd_install_dir }}/etcd-v{{ etcd_version }}.tar.gz"
checksum: "{{ etcd_archive_checksum }}"
mode: '0644'
register: etcd_download
retries: 3
delay: 5
until: etcd_download is succeeded
- name: 展开固定版本
ansible.builtin.unarchive:
src: "{{ etcd_install_dir }}/etcd-v{{ etcd_version }}.tar.gz"
dest: "{{ etcd_install_dir }}"
remote_src: true
creates: "{{ etcd_install_dir }}/etcd-v{{ etcd_version }}-linux-amd64/etcd"
- name: 安装版本链接
ansible.builtin.file:
src: "{{ etcd_install_dir }}/etcd-v{{ etcd_version }}-linux-amd64/{{ item }}"
dest: "{{ etcd_install_dir }}/{{ item }}"
state: link
loop: [etcd, etcdctl, etcdutl]
register: etcd_binary_links
- name: 签发成员与管理员证书
ansible.builtin.include_tasks: certificate.yml
loop:
- {name: server, role: homelab-etcd-server, cn: "{{ inventory_hostname }}", eku: [serverAuth], group: homelab-etcd}
- {name: peer, role: homelab-etcd-peer, cn: homelab-etcd-peer, eku: [serverAuth, clientAuth], group: homelab-etcd}
- {name: gateway, role: homelab-etcd-gateway, cn: "", eku: [clientAuth], group: homelab-etcd}
- {name: admin, role: homelab-etcd-admin, cn: root, eku: [clientAuth], group: root}
loop_control:
loop_var: etcd_cert
- name: 写入独立 etcd 配置
ansible.builtin.template:
src: etcd.yml.j2
dest: "{{ etcd_config_dir }}/etcd.yml"
owner: root
group: homelab-etcd
mode: '0640'
register: etcd_config_file
- name: 写入独立 systemd unit
ansible.builtin.template:
src: homelab-etcd.service.j2
dest: /etc/systemd/system/homelab-etcd.service
mode: '0644'
register: etcd_unit
# 跨失败重跑记录激活状态,防止上一轮写文件后中断导致漏掉必要重启。
- name: 计算受管文件校验和
ansible.builtin.stat:
path: "{{ item }}"
checksum_algorithm: sha256
loop:
- "{{ etcd_config_dir }}/etcd.yml"
- "{{ etcd_config_dir }}/server.crt"
- "{{ etcd_config_dir }}/peer.crt"
- "{{ etcd_config_dir }}/gateway.crt"
- "{{ etcd_config_dir }}/ca.crt"
- /etc/systemd/system/homelab-etcd.service
register: etcd_managed_files
- name: 计算期望激活指纹
ansible.builtin.set_fact:
etcd_config_fingerprint: >-
{{ ((etcd_managed_files.results | map(attribute='stat.checksum') | list | join(':'))
~ ':' ~ etcd_version) | hash('sha256') }}
when: not ansible_check_mode
- name: 检查已激活指纹
ansible.builtin.stat:
path: "{{ etcd_config_dir }}/activated.sha256"
register: etcd_activated_file
- name: 读取已激活指纹
ansible.builtin.slurp:
src: "{{ etcd_config_dir }}/activated.sha256"
register: etcd_activated
when: etcd_activated_file.stat.exists
- name: 判断是否需要滚动激活
ansible.builtin.set_fact:
etcd_config_changed: >-
{{ not etcd_activated_file.stat.exists or
(etcd_activated.content | default('') | b64decode | trim) != etcd_config_fingerprint | default('check-mode') }}
- name: 管理本地快照任务
ansible.builtin.import_tasks: snapshot.yml
@@ -0,0 +1,26 @@
---
- name: 创建仅 root 可访问的快照目录
ansible.builtin.file:
path: "{{ etcd_snapshot_dir }}"
state: directory
owner: root
group: root
mode: '0700'
- name: 写入快照脚本和 systemd 任务
ansible.builtin.template:
src: "{{ item.src }}"
dest: "{{ item.dest }}"
mode: "{{ item.mode }}"
loop:
- {src: snapshot.sh.j2, dest: "{{ etcd_install_dir }}/snapshot", mode: '0700'}
- {src: snapshot.service.j2, dest: /etc/systemd/system/homelab-etcd-snapshot.service, mode: '0644'}
- {src: snapshot.timer.j2, dest: /etc/systemd/system/homelab-etcd-snapshot.timer, mode: '0644'}
register: etcd_snapshot_units
- name: 启用本地快照计划
ansible.builtin.systemd_service:
name: homelab-etcd-snapshot.timer
daemon_reload: "{{ etcd_snapshot_units is changed }}"
enabled: true
state: started
@@ -0,0 +1,33 @@
# Ansible 管理;与 k3s、数据库生命周期独立。
name: {{ inventory_hostname | to_json }}
data-dir: {{ etcd_data_dir | to_json }}
listen-client-urls: https://{{ etcd_address }}:{{ etcd_client_port }}
advertise-client-urls: https://{{ etcd_address }}:{{ etcd_client_port }}
listen-peer-urls: https://{{ etcd_address }}:{{ etcd_peer_port }}
initial-advertise-peer-urls: https://{{ etcd_address }}:{{ etcd_peer_port }}
initial-cluster: "{% for member in groups['etcd'] %}{{ member }}=https://{{ hostvars[member].etcd_address }}:{{ etcd_peer_port }}{{ ',' if not loop.last else '' }}{% endfor %}"
initial-cluster-token: {{ etcd_cluster_token | to_json }}
initial-cluster-state: new
# 已存在的数据目录优先;成员替换必须走单独 runbook,不删除数据重建。
client-transport-security:
cert-file: {{ etcd_config_dir }}/server.crt
key-file: {{ etcd_config_dir }}/server.key
client-cert-file: {{ etcd_config_dir }}/gateway.crt
client-key-file: {{ etcd_config_dir }}/gateway.key
trusted-ca-file: {{ etcd_config_dir }}/ca.crt
client-cert-auth: true
peer-transport-security:
cert-file: {{ etcd_config_dir }}/peer.crt
key-file: {{ etcd_config_dir }}/peer.key
trusted-ca-file: {{ etcd_config_dir }}/ca.crt
client-cert-auth: true
allowed-cn: [homelab-etcd-peer]
# 独立 metrics listener 仅提供指标/健康,不开放 KV API;只绑定受管内网地址。
listen-metrics-urls: {{ etcd_metrics_urls | default("http://127.0.0.1:" ~ etcd_metrics_port) | to_json }}
quota-backend-bytes: {{ etcd_quota_bytes }}
auto-compaction-mode: periodic
auto-compaction-retention: '1h'
heartbeat-interval: 100
election-timeout: 1000
logger: zap
log-level: info
@@ -0,0 +1,23 @@
[Unit]
Description=Homelab shared etcd
Wants=network-online.target
After=network-online.target
[Service]
User=homelab-etcd
Group=homelab-etcd
ExecStart={{ etcd_install_dir }}/etcd --config-file={{ etcd_config_dir }}/etcd.yml
Restart=on-failure
RestartSec=5
TimeoutStopSec=60
MemoryHigh={{ etcd_memory_high }}
MemoryMax={{ etcd_memory_max }}
UMask=0077
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths={{ etcd_data_dir }}
[Install]
WantedBy=multi-user.target
@@ -0,0 +1,11 @@
[Unit]
Description=Snapshot homelab shared etcd
After=homelab-etcd.service
[Service]
Type=oneshot
ExecStart={{ etcd_install_dir }}/snapshot
User=root
UMask=0077
TimeoutStartSec=300
Nice=10
@@ -0,0 +1,20 @@
#!/bin/bash
set -euo pipefail
umask 077
export ETCDCTL_ENDPOINTS="https://{{ etcd_address }}:{{ etcd_client_port }}"
export ETCDCTL_CACERT="{{ etcd_config_dir }}/ca.crt"
export ETCDCTL_CERT="{{ etcd_config_dir }}/admin.crt"
export ETCDCTL_KEY="{{ etcd_config_dir }}/admin.key"
repo="{{ etcd_snapshot_dir }}"
exec 9>"$repo/.lock"
flock -n 9 || exit 0
output="$repo/$(date -u +%Y%m%dT%H%M%SZ).db"
trap 'rm -f "$output.partial" "$output.partial.part"' EXIT
{{ etcd_install_dir }}/etcdctl snapshot save "$output.partial"
{{ etcd_install_dir }}/etcdutl snapshot status "$output.partial" >/dev/null
mv "$output.partial" "$output"
# 只有新快照成功且验证可读才清理旧备份。目录仅由此任务管理。
mapfile -t snapshots < <(find "$repo" -maxdepth 1 -type f -name '????????T??????Z.db' -printf '%f\n' | sort -r)
for old in "${snapshots[@]:{{ etcd_snapshot_keep }}}"; do
rm -- "$repo/$old"
done
@@ -0,0 +1,10 @@
[Unit]
Description=Daily homelab etcd snapshot
[Timer]
OnCalendar=*-*-* 03:20:00 UTC
RandomizedDelaySec=300
Persistent=true
[Install]
WantedBy=timers.target
+66
View File
@@ -0,0 +1,66 @@
---
# 先配置全体,再滚动启动:首次集群形成不能在第一个节点等待 quorum。
- name: 配置 shared etcd 成员
hosts: etcd
become: true
roles:
- shared_etcd
- name: 滚动启动并验证 shared etcd
hosts: etcd
become: true
serial: 1
pre_tasks:
- name: 加载共享默认参数
ansible.builtin.import_role:
name: shared_etcd
tasks_from: context
tasks:
- name: 启动已配置的成员
ansible.builtin.systemd_service:
name: homelab-etcd
enabled: true
daemon_reload: true
state: "{{ 'restarted' if etcd_config_changed | bool else 'started' }}"
- name: 等待本机客户端端口
ansible.builtin.wait_for:
host: "{{ etcd_address }}"
port: "{{ etcd_client_port }}"
timeout: 60
when: not ansible_check_mode
- name: 已有集群每次激活后等待本成员恢复 quorum 通信
ansible.builtin.command:
argv:
- "{{ etcd_install_dir }}/etcdctl"
- --endpoints=https://{{ etcd_address }}:{{ etcd_client_port }}
- --cacert={{ etcd_config_dir }}/ca.crt
- --cert={{ etcd_config_dir }}/admin.crt
- --key={{ etcd_config_dir }}/admin.key
- endpoint
- health
changed_when: false
register: etcd_member_health
retries: 12
delay: 5
until: etcd_member_health.rc == 0
when: etcd_activated_file.stat.exists and not ansible_check_mode
- name: 核对全部成员
ansible.builtin.import_playbook: verify.yml
- name: 记录已成功激活的配置
hosts: etcd
become: true
pre_tasks:
- name: 加载共享默认参数
ansible.builtin.import_role:
name: shared_etcd
tasks_from: context
tasks:
- name: 写入激活指纹(全体健康检查通过后)
ansible.builtin.copy:
content: "{{ etcd_config_fingerprint }}\n"
dest: "{{ etcd_config_dir }}/activated.sha256"
mode: '0644'
when: not ansible_check_mode
@@ -0,0 +1,170 @@
---
- name: 验证消费者范围
ansible.builtin.assert:
that:
- etcd_consumer.name is match('^[a-z][a-z0-9-]+$')
- etcd_consumer.name != 'root'
- etcd_consumer.prefix is match('^/homelab/[a-zA-Z0-9/_-]+/$')
- etcd_consumer.prefix | length > 10
- name: 读取已有用户和角色
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", --write-out=json, "{{ item }}", list]
loop: [user, role]
register: etcd_identities
changed_when: false
check_mode: false
# 404 data 也可能代表被删除/销毁的旧秘密;只有 metadata 不存在才允许生成。
- name: 控制端读取 Bao 秘密元数据
ansible.builtin.uri:
url: "{{ etcd_bao_url }}/v1/{{ etcd_bao_kv_mount }}/metadata/{{ etcd_bao_secret_base }}/{{ etcd_consumer.name }}"
headers:
X-Vault-Token: "{{ etcd_bao_token }}"
status_code: [200, 404]
delegate_to: localhost
become: false
no_log: true
register: etcd_secret_metadata
check_mode: false
- name: 禁止已有用户丢失秘密后自动换密码
ansible.builtin.assert:
that: >-
etcd_secret_metadata.status == 200 or
etcd_consumer.name not in ((etcd_identities.results[0].stdout | from_json).users | default([], true))
fail_msg: etcd 用户已存在但 Bao 秘密缺失;需恢复原秘密或执行显式轮换。
- name: 首次创建随机秘密且禁止覆盖已有版本
ansible.builtin.uri:
url: "{{ etcd_bao_url }}/v1/{{ etcd_bao_kv_mount }}/data/{{ etcd_bao_secret_base }}/{{ etcd_consumer.name }}"
method: POST
headers:
X-Vault-Token: "{{ etcd_bao_token }}"
body_format: json
body:
options: {cas: 0}
data:
username: "{{ etcd_consumer.name }}"
password: "{{ lookup('ansible.builtin.password', '/dev/null', length=48, chars=['ascii_letters', 'digits']) }}"
prefix: "{{ etcd_consumer.prefix }}"
status_code: 200
delegate_to: localhost
become: false
no_log: true
changed_when: true
when:
- etcd_secret_metadata.status == 404
- not ansible_check_mode
- name: 控制端读取既有秘密
ansible.builtin.uri:
url: "{{ etcd_bao_url }}/v1/{{ etcd_bao_kv_mount }}/data/{{ etcd_bao_secret_base }}/{{ etcd_consumer.name }}"
headers:
X-Vault-Token: "{{ etcd_bao_token }}"
status_code: 200
delegate_to: localhost
become: false
register: etcd_consumer_secret
no_log: true
when: etcd_secret_metadata.status == 200 or not ansible_check_mode
check_mode: false
- name: 核对已保存秘密归属
ansible.builtin.assert:
that:
- etcd_consumer_secret.json.data.data.username == etcd_consumer.name
- etcd_consumer_secret.json.data.data.prefix == etcd_consumer.prefix
- etcd_consumer_secret.json.data.data.password | length >= 32
no_log: true
when: etcd_secret_metadata.status == 200 or not ansible_check_mode
- name: 新建消费者用户(密码只通过 stdin 传递)
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", user, add, "{{ etcd_consumer.name }}", --interactive=false]
stdin: "{{ etcd_consumer_secret.json.data.data.password }}"
no_log: true
changed_when: true
when:
- etcd_consumer.name not in ((etcd_identities.results[0].stdout | from_json).users | default([], true))
- not ansible_check_mode
- name: 新建消费者角色
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", role, add, "{{ etcd_consumer.name }}"]
changed_when: true
when: etcd_consumer.name not in ((etcd_identities.results[1].stdout | from_json).roles | default([], true))
- name: 读取角色权限
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", --write-out=json, role, get, "{{ etcd_consumer.name }}"]
register: etcd_role_state
changed_when: false
when: >-
not ansible_check_mode or
etcd_consumer.name in ((etcd_identities.results[1].stdout | from_json).roles | default([], true))
- name: 拒绝不符合声明的既有权限(不自动扩大或删除)
ansible.builtin.assert:
that:
- >-
((etcd_role_state.stdout | from_json).perm | default([], true)) in
[[], [{'permType': 2, 'key': etcd_consumer.prefix | b64encode,
'range_end': (etcd_consumer.prefix[:-1] ~ '0') | b64encode}]]
fail_msg: 既有角色权限与声明不同,请显式审查权限迁移。
when: etcd_role_state is not skipped
- name: 授予唯一 prefix 读写权限
ansible.builtin.command:
argv:
- "{{ etcd_install_dir }}/etcdctl"
- role
- grant-permission
- "{{ etcd_consumer.name }}"
- readwrite
- "{{ etcd_consumer.prefix }}"
- --prefix=true
changed_when: true
when:
- etcd_role_state is not skipped
- ((etcd_role_state.stdout | from_json).perm | default([], true)) | length == 0
- name: 读取用户角色
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", --write-out=json, user, get, "{{ etcd_consumer.name }}"]
register: etcd_user_state
changed_when: false
when: >-
not ansible_check_mode or
etcd_consumer.name in ((etcd_identities.results[0].stdout | from_json).users | default([], true))
- name: 拒绝消费者已有额外角色
ansible.builtin.assert:
that: >-
((etcd_user_state.stdout | from_json).roles | default([], true))
| difference([etcd_consumer.name]) | length == 0
when: etcd_user_state is not skipped
- name: 绑定消费者角色
ansible.builtin.command:
argv: ["{{ etcd_install_dir }}/etcdctl", user, grant-role, "{{ etcd_consumer.name }}", "{{ etcd_consumer.name }}"]
changed_when: true
when:
- etcd_user_state is not skipped
- etcd_consumer.name not in ((etcd_user_state.stdout | from_json).roles | default([], true))
# 使用 gateway 的真实密码登录来核对 Bao 与 etcd 一致性,不能只看用户已存在。
- name: 验证消费者密码可经 gateway 登录
ansible.builtin.uri:
url: "https://{{ etcd_address }}:{{ etcd_client_port }}/v3/auth/authenticate"
method: POST
client_cert: "{{ etcd_config_dir }}/gateway.crt"
client_key: "{{ etcd_config_dir }}/gateway.key"
ca_path: "{{ etcd_config_dir }}/ca.crt"
body_format: json
body:
name: "{{ etcd_consumer.name }}"
password: "{{ etcd_consumer_secret.json.data.data.password }}"
status_code: 200
no_log: true
when: not ansible_check_mode
+29
View File
@@ -0,0 +1,29 @@
---
- name: 验证 shared etcd 全部端点
hosts: etcd[0]
become: true
gather_facts: false
pre_tasks:
- name: 加载共享默认参数
ansible.builtin.import_role:
name: shared_etcd
tasks_from: context
tasks:
- name: 通过管理员 mTLS 检查所有端点健康
ansible.builtin.command:
argv:
- "{{ etcd_install_dir }}/etcdctl"
- >-
--endpoints={{ groups['etcd'] | map('extract', hostvars, 'etcd_address')
| map('regex_replace', '^(.*)$', 'https://\1:' ~ etcd_client_port) | join(',') }}
- --cacert={{ etcd_config_dir }}/ca.crt
- --cert={{ etcd_config_dir }}/admin.crt
- --key={{ etcd_config_dir }}/admin.key
- endpoint
- health
changed_when: false
register: etcd_health
retries: 12
delay: 5
until: etcd_health.rc == 0
when: not ansible_check_mode