ben/mgmt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 添加Nomad集群监控与配置更新

Browse Source 
fix(nomad): 修复服务器网络配置和重复配置问题
perf: 优化Podman与Nomad集成配置
refactor: 重构inventory文件结构
docs: 添加Telegraf监控部署文档
chore: 清理旧配置文件和脚本
This commit is contained in:
Houzhong Xu
2025-09-25 14:07:55 +00:00
parent d0e7f64c1d
commit 79b721e165
49 changed files with 2699 additions and 457 deletions
Download Patch File Download Diff File Expand all files Collapse all files

202
configuration/playbooks/add-warden-to-nomad-cluster.yml Normal file
View File

@@ -0,0 +1,202 @@
---
- name: Add Warden Server as Nomad Client to Cluster
hosts: warden
become: yes
gather_facts: yes
vars:
nomad_plugin_dir: "/opt/nomad/plugins"
nomad_datacenter: "dc1"
nomad_region: "global"
nomad_servers:
- "100.117.106.136:4647"
- "100.116.80.94:4647"
- "100.97.62.111:4647"
- "100.116.112.45:4647"
- "100.84.197.26:4647"
tasks:
- name: 显示当前处理的节点
debug:
msg: "🔧 将 warden 服务器添加为 Nomad 客户端: {{ inventory_hostname }}"
- name: 检查 Nomad 是否已安装
shell: which nomad || echo "not_found"
register: nomad_check
changed_when: false
- name: 下载并安装 Nomad
block:
- name: 下载 Nomad 1.10.5
get_url:
url: "https://releases.hashicorp.com/nomad/1.10.5/nomad_1.10.5_linux_amd64.zip"
dest: "/tmp/nomad.zip"
mode: '0644'
- name: 解压并安装 Nomad
unarchive:
src: "/tmp/nomad.zip"
dest: "/usr/local/bin/"
remote_src: yes
owner: root
group: root
mode: '0755'
- name: 清理临时文件
file:
path: "/tmp/nomad.zip"
state: absent
when: nomad_check.stdout == "not_found"
- name: 验证 Nomad 安装
shell: nomad version
register: nomad_version_output
- name: 创建 Nomad 配置目录
file:
path: /etc/nomad.d
state: directory
owner: root
group: root
mode: '0755'
- name: 创建 Nomad 数据目录
file:
path: /opt/nomad/data
state: directory
owner: nomad
group: nomad
mode: '0755'
ignore_errors: yes
- name: 创建 Nomad 插件目录
file:
path: "{{ nomad_plugin_dir }}"
state: directory
owner: nomad
group: nomad
mode: '0755'
ignore_errors: yes
- name: 获取服务器 IP 地址
shell: |
ip route get 1.1.1.1 | grep -oP 'src \K\S+'
register: server_ip_result
changed_when: false
- name: 设置服务器 IP 变量
set_fact:
server_ip: "{{ server_ip_result.stdout }}"
- name: 停止 Nomad 服务（如果正在运行）
systemd:
name: nomad
state: stopped
ignore_errors: yes
- name: 创建 Nomad 客户端配置文件
copy:
content: |
# Nomad Client Configuration for warden
datacenter = "{{ nomad_datacenter }}"
data_dir = "/opt/nomad/data"
log_level = "INFO"
bind_addr = "{{ server_ip }}"
server {
enabled = false
}
client {
enabled = true
servers = [
{% for server in nomad_servers %}"{{ server }}"{% if not loop.last %}, {% endif %}{% endfor %}
]
}
plugin_dir = "{{ nomad_plugin_dir }}"
plugin "podman" {
config {
socket_path = "unix:///run/podman/podman.sock"
volumes {
enabled = true
}
}
}
consul {
address = "127.0.0.1:8500"
}
dest: /etc/nomad.d/nomad.hcl
owner: root
group: root
mode: '0644'
- name: 验证 Nomad 配置
shell: nomad config validate /etc/nomad.d/nomad.hcl
register: nomad_validate
failed_when: nomad_validate.rc != 0
- name: 创建 Nomad systemd 服务文件
copy:
content: |
[Unit]
Description=Nomad
Documentation=https://www.nomadproject.io/docs/
Wants=network-online.target
After=network-online.target
[Service]
Type=notify
User=root
Group=root
ExecStart=/usr/local/bin/nomad agent -config=/etc/nomad.d
ExecReload=/bin/kill -HUP $MAINPID
KillMode=process
KillSignal=SIGINT
TimeoutStopSec=5
LimitNOFILE=65536
LimitNPROC=32768
Restart=on-failure
RestartSec=2
[Install]
WantedBy=multi-user.target
dest: /etc/systemd/system/nomad.service
mode: '0644'
- name: 重新加载 systemd 配置
systemd:
daemon_reload: yes
- name: 启动并启用 Nomad 服务
systemd:
name: nomad
state: started
enabled: yes
- name: 等待 Nomad 服务启动
wait_for:
port: 4646
host: "{{ server_ip }}"
delay: 5
timeout: 60
- name: 检查 Nomad 客户端状态
shell: nomad node status -self
register: nomad_node_status
retries: 5
delay: 5
until: nomad_node_status.rc == 0
ignore_errors: yes
- name: 显示 Nomad 客户端配置结果
debug:
msg: |
✅ warden 服务器已成功配置为 Nomad 客户端
📦 Nomad 版本: {{ nomad_version_output.stdout.split('\n')[0] }}
🌐 服务器 IP: {{ server_ip }}
🏗️ 数据中心: {{ nomad_datacenter }}
📊 客户端状态: {{ 'SUCCESS' if nomad_node_status.rc == 0 else 'PENDING' }}
🚀 warden 现在是 Nomad 集群的一部分

15
configuration/playbooks/check-podman-version.yml Normal file
View File

@@ -0,0 +1,15 @@
---
- name: 检查 Podman 版本
hosts: warden
become: yes
gather_facts: yes
tasks:
- name: 检查当前 Podman 版本
shell: podman --version
register: current_podman_version
ignore_errors: yes
- name: 显示当前版本
debug:
msg: "当前 Podman 版本: {{ current_podman_version.stdout if current_podman_version.rc == 0 else '未安装或无法获取' }}"

22
configuration/playbooks/check-podman-versions.yml Normal file
View File

@@ -0,0 +1,22 @@
- name: Check podman version on semaphore (local)
hosts: semaphore
connection: local
gather_facts: false
tasks:
- name: Check podman version
command: /usr/local/bin/podman --version
register: podman_version
- name: Display podman version
debug:
msg: "Podman version on {{ inventory_hostname }} is: {{ podman_version.stdout }}"
- name: Check podman version on other beijing nodes
hosts: beijing:!semaphore
gather_facts: false
tasks:
- name: Check podman version
command: /usr/local/bin/podman --version
register: podman_version
- name: Display podman version
debug:
msg: "Podman version on {{ inventory_hostname }} is: {{ podman_version.stdout }}"

38
configuration/playbooks/clear-aliases.yml
View File

@@ -56,21 +56,29 @@
loop: "{{ alias_files.files }}"
when: alias_files.files is defined
- name: Clear shell history to remove alias commands
shell: |
> /root/.bash_history
> /root/.zsh_history
history -c
ignore_errors: yes
- name: Unalias all current aliases
shell: unalias -a
ignore_errors: yes
- name: Restart shell services
shell: |
pkill -f bash || true
pkill -f zsh || true
- name: Clear aliases from /etc/profile.d/aliases.sh
ansible.builtin.file:
path: /etc/profile.d/aliases.sh
state: absent
- name: Clear aliases from /root/.bashrc
ansible.builtin.lineinfile:
path: /root/.bashrc
state: absent
regexp: "^alias "
- name: Clear aliases from /root/.bash_aliases
ansible.builtin.file:
path: /root/.bash_aliases
state: absent
- name: Clear history
ansible.builtin.command:
cmd: > /root/.bash_history
- name: Restart shell to apply changes
ansible.builtin.command:
cmd: pkill -f bash || true
- name: Test network connectivity after clearing aliases
shell: ping -c 2 8.8.8.8 || echo "Ping failed"

32
configuration/playbooks/clear-all-aliases.yml Normal file
View File

@@ -0,0 +1,32 @@
---
- name: Remove all aliases from user shell configuration files
hosts: all
become: yes
gather_facts: false
tasks:
- name: Find all relevant shell configuration files
find:
paths: /home
patterns: .bashrc, .bash_aliases, .profile
register: shell_config_files
- name: Remove aliases from shell configuration files
replace:
path: "{{ item.path }}"
regexp: '^alias .*'
replace: ''
loop: "{{ shell_config_files.files }}"
when: shell_config_files.files is defined
- name: Remove functions from shell configuration files
replace:
path: "{{ item.path }}"
regexp: '^function .*'
replace: ''
loop: "{{ shell_config_files.files }}"
when: shell_config_files.files is defined
- name: Display completion message
debug:
msg: "All aliases and functions have been removed from user shell configuration files."

47
configuration/playbooks/clear-proxy-settings.yml Normal file
View File

@@ -0,0 +1,47 @@
---
- name: Clear proxy settings from the system
hosts: all
become: yes
gather_facts: false
tasks:
- name: Remove proxy environment file
file:
path: /root/mgmt/configuration/proxy.env
state: absent
ignore_errors: yes
- name: Unset proxy environment variables
shell: |
unset http_proxy
unset https_proxy
unset HTTP_PROXY
unset HTTPS_PROXY
unset no_proxy
unset NO_PROXY
unset ALL_PROXY
unset all_proxy
unset DOCKER_BUILDKIT
unset BUILDKIT_PROGRESS
unset GIT_HTTP_PROXY
unset GIT_HTTPS_PROXY
unset CURL_PROXY
unset WGET_PROXY
ignore_errors: yes
- name: Remove proxy settings from /etc/environment
lineinfile:
path: /etc/environment
state: absent
regexp: '^(http_proxy|https_proxy|no_proxy|ALL_PROXY|DOCKER_BUILDKIT|BUILDKIT_PROGRESS|GIT_HTTP_PROXY|GIT_HTTPS_PROXY|CURL_PROXY|WGET_PROXY)='
ignore_errors: yes
- name: Remove proxy settings from /etc/apt/apt.conf.d/proxy.conf
file:
path: /etc/apt/apt.conf.d/proxy.conf
state: absent
ignore_errors: yes
- name: Display completion message
debug:
msg: "Proxy settings have been cleared from the system."

22
configuration/playbooks/configure-nomad-sudo.yml Normal file
View File

@@ -0,0 +1,22 @@
---
- name: Configure NOPASSWD sudo for nomad user
hosts: nomad_clients
become: yes
tasks:
- name: Ensure sudoers.d directory exists
file:
path: /etc/sudoers.d
state: directory
owner: root
group: root
mode: '0750'
- name: Allow nomad user passwordless sudo for required commands
copy:
dest: /etc/sudoers.d/nomad
content: |
nomad ALL=(ALL) NOPASSWD: /usr/bin/apt, /usr/bin/systemctl, /bin/mkdir, /bin/chown, /bin/chmod, /bin/mv, /bin/sed, /usr/bin/tee, /usr/sbin/usermod, /usr/bin/unzip, /usr/bin/wget
owner: root
group: root
mode: '0440'
validate: 'visudo -cf %s'

36
configuration/playbooks/configure-nomad-tailscale.yml
View File

@@ -11,7 +11,12 @@
- name: 获取当前节点的 Tailscale IP
shell: tailscale ip | head -1
register: current_tailscale_ip
failed_when: current_tailscale_ip.rc != 0
changed_when: false
ignore_errors: yes
- name: 计算用于 Nomad 的地址（优先 Tailscale，回退到 inventory 或 ansible_host）
set_fact:
node_addr: "{{ (current_tailscale_ip.stdout | default('')) is match('^100\\.') | ternary((current_tailscale_ip.stdout | trim), (hostvars[inventory_hostname].tailscale_ip | default(ansible_host))) }}"
- name: 确保 Nomad 配置目录存在
file:
@@ -32,12 +37,12 @@
data_dir = "/opt/nomad/data"
log_level = "INFO"
bind_addr = "{{ current_tailscale_ip.stdout }}"
bind_addr = "{{ node_addr }}"
addresses {
http = "0.0.0.0"
rpc = "{{ current_tailscale_ip.stdout }}"
serf = "{{ current_tailscale_ip.stdout }}"
http = "{{ node_addr }}"
rpc = "{{ node_addr }}"
serf = "{{ node_addr }}"
}
ports {
@@ -74,9 +79,10 @@
}
consul {
address = "{{ current_tailscale_ip.stdout }}:8500"
address = "{{ node_addr }}:8500"
}
when: nomad_role == "server"
notify: restart nomad
- name: 生成 Nomad 客户端配置（使用 Tailscale）
copy:
@@ -89,12 +95,12 @@
data_dir = "/opt/nomad/data"
log_level = "INFO"
bind_addr = "{{ current_tailscale_ip.stdout }}"
bind_addr = "{{ node_addr }}"
addresses {
http = "0.0.0.0"
rpc = "{{ current_tailscale_ip.stdout }}"
serf = "{{ current_tailscale_ip.stdout }}"
http = "{{ node_addr }}"
rpc = "{{ node_addr }}"
serf = "{{ node_addr }}"
}
ports {
@@ -109,6 +115,7 @@
client {
enabled = true
network_interface = "tailscale0"
servers = [
"100.116.158.95:4647", # semaphore
@@ -128,9 +135,10 @@
}
consul {
address = "{{ current_tailscale_ip.stdout }}:8500"
address = "{{ node_addr }}:8500"
}
when: nomad_role == "client"
notify: restart nomad
- name: 检查 Nomad 二进制文件位置
shell: which nomad || find /usr -name nomad 2>/dev/null | head -1
@@ -154,7 +162,7 @@
Type=notify
User=root
Group=root
ExecStart={{ nomad_binary_path.stdout }} agent -config=/etc/nomad.d/nomad.hcl
ExecStart=/snap/bin/nomad agent -config=/etc/nomad.d/nomad.hcl
ExecReload=/bin/kill -HUP $MAINPID
KillMode=process
Restart=on-failure
@@ -185,7 +193,7 @@
- name: 等待 Nomad 服务启动
wait_for:
port: 4646
host: "{{ current_tailscale_ip.stdout }}"
host: "{{ node_addr }}"
delay: 5
timeout: 30
ignore_errors: yes
@@ -199,7 +207,7 @@
debug:
msg: |
✅ 节点 {{ inventory_hostname }} 配置完成
🌐 Tailscale IP: {{ current_tailscale_ip.stdout }}
🌐 使用地址: {{ node_addr }}
🎯 角色: {{ nomad_role }}
🔧 Nomad 二进制: {{ nomad_binary_path.stdout }}
📊 服务状态: {{ 'active' if nomad_status.rc == 0 else 'failed' }}

115
configuration/playbooks/configure-podman-for-nomad.yml Normal file
View File

@@ -0,0 +1,115 @@
---
- name: Configure Podman for Nomad Integration
hosts: all
become: yes
gather_facts: yes
tasks:
- name: 显示当前处理的节点
debug:
msg: "🔧 正在为 Nomad 配置 Podman: {{ inventory_hostname }}"
- name: 确保 Podman 已安装
package:
name: podman
state: present
- name: 启用并启动 Podman socket 服务
systemd:
name: podman.socket
enabled: yes
state: started
- name: 创建 Podman 系统配置目录
file:
path: /etc/containers
state: directory
mode: '0755'
- name: 配置 Podman 使用系统 socket
copy:
content: |
[engine]
# 使用系统级 socket 而不是用户级 socket
active_service = "system"
[engine.service_destinations]
[engine.service_destinations.system]
uri = "unix:///run/podman/podman.sock"
dest: /etc/containers/containers.conf
mode: '0644'
- name: 检查是否存在 nomad 用户
getent:
database: passwd
key: nomad
register: nomad_user_check
ignore_errors: yes
- name: 为 nomad 用户创建配置目录
file:
path: "/home/nomad/.config/containers"
state: directory
owner: nomad
group: nomad
mode: '0755'
when: nomad_user_check is succeeded
- name: 为 nomad 用户配置 Podman
copy:
content: |
[engine]
active_service = "system"
[engine.service_destinations]
[engine.service_destinations.system]
uri = "unix:///run/podman/podman.sock"
dest: /home/nomad/.config/containers/containers.conf
owner: nomad
group: nomad
mode: '0644'
when: nomad_user_check is succeeded
- name: 将 nomad 用户添加到 podman 组
user:
name: nomad
groups: podman
append: yes
when: nomad_user_check is succeeded
ignore_errors: yes
- name: 创建 podman 组（如果不存在）
group:
name: podman
state: present
ignore_errors: yes
- name: 设置 podman socket 目录权限
file:
path: /run/podman
state: directory
mode: '0755'
group: podman
ignore_errors: yes
- name: 验证 Podman socket 权限
file:
path: /run/podman/podman.sock
mode: '066'
when: nomad_user_check is succeeded
ignore_errors: yes
- name: 验证 Podman 安装
shell: podman --version
register: podman_version
- name: 测试 Podman 功能
shell: podman info
register: podman_info
ignore_errors: yes
- name: 显示配置结果
debug:
msg: |
✅ 节点 {{ inventory_hostname }} Podman 配置完成
📦 Podman 版本: {{ podman_version.stdout }}
🐳 Podman 状态: {{ 'SUCCESS' if podman_info.rc == 0 else 'WARNING' }}
👤 Nomad 用户: {{ 'FOUND' if nomad_user_check is succeeded else 'NOT FOUND' }}

24
configuration/playbooks/debug-nomad-germany.yml Normal file
View File

@@ -0,0 +1,24 @@
- name: Debug Nomad service on germany
hosts: germany
gather_facts: false
tasks:
- name: Get Nomad service status
command: systemctl status nomad.service --no-pager -l
register: nomad_status
ignore_errors: true
- name: Get Nomad service journal
command: journalctl -xeu nomad.service --no-pager -n 100
register: nomad_journal
ignore_errors: true
- name: Display debug information
debug:
msg: |
--- Nomad Service Status ---
{{ nomad_status.stdout }}
{{ nomad_status.stderr }}
--- Nomad Service Journal ---
{{ nomad_journal.stdout }}
{{ nomad_journal.stderr }}

12
configuration/playbooks/debug-syd.yml Normal file
View File

@@ -0,0 +1,12 @@
- name: Distribute new podman binary to syd
hosts: syd
gather_facts: false
tasks:
- name: Copy new podman binary to /usr/local/bin
copy:
src: /root/mgmt/configuration/podman-remote-static-linux_amd64
dest: /usr/local/bin/podman
owner: root
group: root
mode: '0755'
become: yes

76
configuration/playbooks/distribute-podman-driver.yml Normal file
View File

@@ -0,0 +1,76 @@
---
- name: Distribute Nomad Podman Driver to all nodes
hosts: nomad_cluster
become: yes
vars:
nomad_user: nomad
nomad_data_dir: /opt/nomad/data
nomad_plugins_dir: "{{ nomad_data_dir }}/plugins"
tasks:
- name: Stop Nomad service
systemd:
name: nomad
state: stopped
- name: Create plugins directory
file:
path: "{{ nomad_plugins_dir }}"
state: directory
owner: "{{ nomad_user }}"
group: "{{ nomad_user }}"
mode: '0755'
- name: Copy Nomad Podman driver from local
copy:
src: /tmp/nomad-driver-podman
dest: "{{ nomad_plugins_dir }}/nomad-driver-podman"
owner: "{{ nomad_user }}"
group: "{{ nomad_user }}"
mode: '0755'
- name: Update Nomad configuration for plugin directory
lineinfile:
path: /etc/nomad.d/nomad.hcl
regexp: '^plugin_dir'
line: 'plugin_dir = "{{ nomad_plugins_dir }}"'
insertafter: 'data_dir = "/opt/nomad/data"'
- name: Ensure Podman is installed
package:
name: podman
state: present
- name: Enable Podman socket
systemd:
name: podman.socket
enabled: yes
state: started
ignore_errors: yes
- name: Start Nomad service
systemd:
name: nomad
state: started
enabled: yes
- name: Wait for Nomad to be ready
wait_for:
port: 4646
host: localhost
delay: 10
timeout: 60
- name: Wait for plugins to load
pause:
seconds: 15
- name: Check driver status
shell: |
/usr/local/bin/nomad node status -self | grep -A 10 "Driver Status" || /usr/bin/nomad node status -self | grep -A 10 "Driver Status"
register: driver_status
failed_when: false
- name: Display driver status
debug:
var: driver_status.stdout_lines

12
configuration/playbooks/distribute-podman-germany.yml Normal file
View File

@@ -0,0 +1,12 @@
- name: Distribute new podman binary to germany
hosts: germany
gather_facts: false
tasks:
- name: Copy new podman binary to /usr/local/bin
copy:
src: /root/mgmt/configuration/podman-remote-static-linux_amd64
dest: /usr/local/bin/podman
owner: root
group: root
mode: '0755'
become: yes

12
configuration/playbooks/distribute-podman.yml Normal file
View File

@@ -0,0 +1,12 @@
- name: Distribute new podman binary to specified nomad_clients
hosts: nomadlxc,hcp,huawei,ditigalocean
gather_facts: false
tasks:
- name: Copy new podman binary to /usr/local/bin
copy:
src: /root/mgmt/configuration/podman-remote-static-linux_amd64
dest: /usr/local/bin/podman
owner: root
group: root
mode: '0755'
become: yes

25
configuration/playbooks/ensure-nomad-user.yml Normal file
View File

@@ -0,0 +1,25 @@
---
- name: Ensure nomad user and plugin directory exist
hosts: nomad_clients
become: yes
tasks:
- name: Ensure nomad group exists
group:
name: nomad
state: present
- name: Ensure nomad user exists
user:
name: nomad
group: nomad
shell: /usr/sbin/nologin
system: yes
create_home: no
- name: Ensure plugin directory exists with correct ownership
file:
path: /opt/nomad/data/plugins
state: directory
owner: nomad
group: nomad
mode: '0755'

16
configuration/playbooks/fix-apt-errors.yml Normal file
View File

@@ -0,0 +1,16 @@
---
- name: Debug apt repository issues
hosts: beijing:children
become: yes
ignore_unreachable: yes
tasks:
- name: Run apt-get update to capture error
ansible.builtin.shell: apt-get update
register: apt_update_result
failed_when: false
changed_when: false
- name: Display apt-get update stderr
ansible.builtin.debug:
var: apt_update_result.stderr
verbosity: 2

126
configuration/playbooks/fix-duplicate-podman-config.yml Normal file
View File

@@ -0,0 +1,126 @@
---
- name: Fix duplicate Podman configuration in Nomad
hosts: nomad_cluster
become: yes
tasks:
- name: Stop Nomad service
systemd:
name: nomad
state: stopped
- name: Backup current configuration
copy:
src: /etc/nomad.d/nomad.hcl
dest: /etc/nomad.d/nomad.hcl.backup-duplicate-fix
remote_src: yes
- name: Read current configuration
slurp:
src: /etc/nomad.d/nomad.hcl
register: current_config
- name: Create clean configuration for clients
copy:
content: |
datacenter = "{{ nomad_datacenter }}"
region = "{{ nomad_region }}"
data_dir = "/opt/nomad/data"
bind_addr = "{{ tailscale_ip }}"
server {
enabled = false
}
client {
enabled = true
servers = ["100.116.158.95:4647", "100.117.106.136:4647", "100.86.141.112:4647", "100.81.26.3:4647", "100.103.147.94:4647"]
}
ui {
enabled = true
}
addresses {
http = "0.0.0.0"
rpc = "{{ tailscale_ip }}"
serf = "{{ tailscale_ip }}"
}
ports {
http = 4646
rpc = 4647
serf = 4648
}
plugin "podman" {
config {
socket_path = "unix:///run/podman/podman.sock"
volumes {
enabled = true
}
recover_stopped = true
}
}
consul {
auto_advertise = false
server_auto_join = false
client_auto_join = false
}
log_level = "INFO"
enable_syslog = true
dest: /etc/nomad.d/nomad.hcl
owner: nomad
group: nomad
mode: '0640'
when: nomad_role == "client"
- name: Ensure Podman is installed
package:
name: podman
state: present
- name: Enable and start Podman socket
systemd:
name: podman.socket
enabled: yes
state: started
- name: Set proper permissions on Podman socket
file:
path: /run/podman/podman.sock
mode: '0666'
ignore_errors: yes
- name: Validate Nomad configuration
shell: /usr/local/bin/nomad config validate /etc/nomad.d/nomad.hcl || /usr/bin/nomad config validate /etc/nomad.d/nomad.hcl
register: config_validation
failed_when: config_validation.rc != 0
- name: Start Nomad service
systemd:
name: nomad
state: started
enabled: yes
- name: Wait for Nomad to be ready
wait_for:
port: 4646
host: localhost
delay: 10
timeout: 60
- name: Wait for drivers to load
pause:
seconds: 20
- name: Check driver status
shell: |
/usr/local/bin/nomad node status -self | grep -A 10 "Driver Status" || /usr/bin/nomad node status -self | grep -A 10 "Driver Status"
register: driver_status
failed_when: false
- name: Display driver status
debug:
var: driver_status.stdout_lines

34
configuration/playbooks/fix-hashicorp-apt-source.yml Normal file
View File

@@ -0,0 +1,34 @@
---
- name: 直接复制正确的 HashiCorp APT 源配置
hosts: nomad_cluster
become: yes
tasks:
- name: 备份现有的 HashiCorp APT 源配置（如果存在）
copy:
src: "/etc/apt/sources.list.d/hashicorp.list"
dest: "/etc/apt/sources.list.d/hashicorp.list.backup-{{ ansible_date_time.epoch }}"
remote_src: yes
ignore_errors: yes
- name: 创建正确的 HashiCorp APT 源配置
copy:
content: "deb [trusted=yes] http://apt.releases.hashicorp.com bookworm main\n"
dest: "/etc/apt/sources.list.d/hashicorp.list"
owner: root
group: root
mode: '0644'
- name: 更新 APT 缓存
apt:
update_cache: yes
ignore_errors: yes
- name: 验证配置
command: cat /etc/apt/sources.list.d/hashicorp.list
register: config_check
changed_when: false
- name: 显示配置内容
debug:
msg: "HashiCorp APT 源配置: {{ config_check.stdout }}"

98
configuration/playbooks/fix-nomad-cluster.yml Normal file
View File

@@ -0,0 +1,98 @@
---
- name: Fix Nomad Cluster Configuration
hosts: nomad_servers
become: yes
vars:
nomad_servers_list:
- "100.116.158.95" # semaphore
- "100.103.147.94" # ash2e
- "100.81.26.3" # ash1d
- "100.90.159.68" # ch2
- "{{ ansible_default_ipv4.address }}" # ch3 (will be determined dynamically)
tasks:
- name: Stop Nomad service
systemd:
name: nomad
state: stopped
ignore_errors: yes
- name: Create nomad user
user:
name: nomad
system: yes
shell: /bin/false
home: /opt/nomad
create_home: no
- name: Create Nomad configuration directory
file:
path: /etc/nomad.d
state: directory
mode: '0755'
- name: Create Nomad data directory
file:
path: /opt/nomad/data
state: directory
mode: '0755'
owner: nomad
group: nomad
ignore_errors: yes
- name: Create Nomad log directory
file:
path: /var/log/nomad
state: directory
mode: '0755'
owner: nomad
group: nomad
ignore_errors: yes
- name: Generate Nomad server configuration
template:
src: nomad-server.hcl.j2
dest: /etc/nomad.d/nomad.hcl
mode: '0644'
notify: restart nomad
- name: Create Nomad systemd service file
copy:
content: |
[Unit]
Description=Nomad
Documentation=https://www.nomadproject.io/
Requires=network-online.target
After=network-online.target
ConditionFileNotEmpty=/etc/nomad.d/nomad.hcl
[Service]
Type=notify
User=nomad
Group=nomad
ExecStart=/usr/bin/nomad agent -config=/etc/nomad.d/nomad.hcl
ExecReload=/bin/kill -HUP $MAINPID
KillMode=process
Restart=on-failure
LimitNOFILE=65536
[Install]
WantedBy=multi-user.target
dest: /etc/systemd/system/nomad.service
mode: '0644'
- name: Reload systemd daemon
systemd:
daemon_reload: yes
- name: Enable and start Nomad service
systemd:
name: nomad
enabled: yes
state: started
handlers:
- name: restart nomad
systemd:
name: nomad
state: restarted

109
configuration/playbooks/fix-server-config.yml Normal file
View File

@@ -0,0 +1,109 @@
---
- name: Fix Nomad server configuration
hosts: nomad_servers
become: yes
tasks:
- name: Stop Nomad service
systemd:
name: nomad
state: stopped
- name: Backup current configuration
copy:
src: /etc/nomad.d/nomad.hcl
dest: /etc/nomad.d/nomad.hcl.backup-server-fix
remote_src: yes
- name: Create clean server configuration
copy:
content: |
datacenter = "{{ nomad_datacenter }}"
region = "{{ nomad_region }}"
data_dir = "/opt/nomad/data"
bind_addr = "{{ ansible_default_ipv4.address }}"
server {
enabled = true
bootstrap_expect = {{ nomad_bootstrap_expect }}
encrypt = "{{ nomad_encrypt_key }}"
retry_join = [
"100.116.158.95",
"100.103.147.94",
"100.81.26.3",
"100.90.159.68",
"100.86.141.112"
]
}
client {
enabled = true
}
ui {
enabled = true
}
addresses {
http = "0.0.0.0"
rpc = "{{ ansible_default_ipv4.address }}"
serf = "{{ ansible_default_ipv4.address }}"
}
ports {
http = 4646
rpc = 4647
serf = 4648
}
plugin "podman" {
config {
socket_path = "unix:///run/podman/podman.sock"
volumes {
enabled = true
}
recover_stopped = true
}
}
consul {
auto_advertise = false
server_auto_join = false
client_auto_join = false
}
log_level = "INFO"
log_file = "/var/log/nomad/nomad.log"
dest: /etc/nomad.d/nomad.hcl
owner: nomad
group: nomad
mode: '0640'
- name: Ensure Podman is installed
package:
name: podman
state: present
- name: Enable and start Podman socket
systemd:
name: podman.socket
enabled: yes
state: started
- name: Validate Nomad configuration
shell: /usr/local/bin/nomad config validate /etc/nomad.d/nomad.hcl || /usr/bin/nomad config validate /etc/nomad.d/nomad.hcl
register: config_validation
failed_when: config_validation.rc != 0
- name: Start Nomad service
systemd:
name: nomad
state: started
enabled: yes
- name: Wait for Nomad to be ready
wait_for:
port: 4646
host: localhost
delay: 10
timeout: 60

103
configuration/playbooks/fix-server-network-config.yml Normal file
View File

@@ -0,0 +1,103 @@
---
- name: Fix Nomad server network configuration
hosts: nomad_servers
become: yes
vars:
server_ips:
semaphore: "100.116.158.95"
ash2e: "100.103.147.94"
ash1d: "100.81.26.3"
ch2: "100.90.159.68"
ch3: "100.86.141.112"
tasks:
- name: Stop Nomad service
systemd:
name: nomad
state: stopped
- name: Get server IP for this host
set_fact:
server_ip: "{{ server_ips[inventory_hostname] }}"
- name: Create corrected server configuration
copy:
content: |
datacenter = "{{ nomad_datacenter }}"
region = "{{ nomad_region }}"
data_dir = "/opt/nomad/data"
bind_addr = "{{ server_ip }}"
server {
enabled = true
bootstrap_expect = {{ nomad_bootstrap_expect }}
encrypt = "{{ nomad_encrypt_key }}"
retry_join = [
"100.116.158.95",
"100.103.147.94",
"100.81.26.3",
"100.90.159.68",
"100.86.141.112"
]
}
client {
enabled = true
}
ui {
enabled = true
}
addresses {
http = "0.0.0.0"
rpc = "{{ server_ip }}"
serf = "{{ server_ip }}"
}
ports {
http = 4646
rpc = 4647
serf = 4648
}
plugin "podman" {
config {
socket_path = "unix:///run/podman/podman.sock"
volumes {
enabled = true
}
recover_stopped = true
}
}
consul {
auto_advertise = false
server_auto_join = false
client_auto_join = false
}
log_level = "INFO"
log_file = "/var/log/nomad/nomad.log"
dest: /etc/nomad.d/nomad.hcl
owner: nomad
group: nomad
mode: '0640'
- name: Validate Nomad configuration
shell: /usr/local/bin/nomad config validate /etc/nomad.d/nomad.hcl || /usr/bin/nomad config validate /etc/nomad.d/nomad.hcl
register: config_validation
failed_when: config_validation.rc != 0
- name: Start Nomad service
systemd:
name: nomad
state: started
enabled: yes
- name: Wait for Nomad to be ready
wait_for:
port: 4646
host: localhost
delay: 10
timeout: 60

39
configuration/playbooks/fix-warden-compose.yml Normal file
View File

@@ -0,0 +1,39 @@
---
- name: Fix Warden docker-compose.yml
hosts: warden
become: yes
gather_facts: no
tasks:
- name: Ensure /opt/warden directory exists
file:
path: /opt/warden
state: directory
owner: root
group: root
mode: '0755'
- name: Create or update docker-compose.yml with correct indentation
copy:
dest: /opt/warden/docker-compose.yml
content: |
services:
vaultwarden:
image: hub.git4ta.fun/vaultwarden/server:latest
security_opt:
- "seccomp=unconfined"
env_file:
- .env
volumes:
- ./data:/data
ports:
- "980:80"
restart: always
networks:
- vaultwarden_network
networks:
vaultwarden_network:
owner: root
group: root
mode: '0644'

67
configuration/playbooks/hack-podman-upgrade.yml Normal file
View File

@@ -0,0 +1,67 @@
---
- name: 强制升级 Podman 到最新版本
hosts: warden
become: yes
gather_facts: yes
tasks:
- name: 检查当前 Podman 版本
shell: podman --version
register: current_podman_version
ignore_errors: yes
- name: 显示当前版本
debug:
msg: "升级前版本: {{ current_podman_version.stdout if current_podman_version.rc == 0 else '未安装' }}"
- name: 卸载现有 Podman
shell: apt-get remove -y --purge podman* containerd* runc*
ignore_errors: yes
- name: 清理残留配置
shell: |
rm -rf /etc/containers
rm -rf /usr/share/containers
rm -rf /var/lib/containers
ignore_errors: yes
- name: 直接下载并安装最新版Podman二进制文件
shell: |
# 清理可能存在的旧版本
rm -f /tmp/podman-latest.tar.gz
rm -f /usr/local/bin/podman
# 获取最新版本号
LATEST_VERSION="v5.6.1" # 硬编码最新版本避免网络问题
echo "安装版本: $LATEST_VERSION"
# 使用GitHub镜像站点下载二进制文件
echo "使用GitHub镜像站点下载..."
wget -O /tmp/podman-latest.tar.gz "https://gh.git4ta.fun/github.com/containers/podman/releases/download/${LATEST_VERSION}/podman-linux-static-amd64.tar.gz"
# 检查文件是否下载成功，如果失败尝试直接下载
if [ ! -f /tmp/podman-latest.tar.gz ]; then
echo "镜像下载失败，尝试直接下载..."
wget -O /tmp/podman-latest.tar.gz "https://github.com/containers/podman/releases/download/${LATEST_VERSION}/podman-linux-static-amd64.tar.gz"
fi
# 解压并安装
tar -xzf /tmp/podman-latest.tar.gz -C /usr/local/bin/ --strip-components=1
chmod +x /usr/local/bin/podman
# 更新PATH
echo 'export PATH=/usr/local/bin:$PATH' >> /etc/profile
. /etc/profile
# 验证安装
/usr/local/bin/podman --version
ignore_errors: yes
- name: 验证安装结果
shell: podman --version
register: new_podman_version
ignore_errors: yes
- name: 显示最终版本
debug:
msg: "升级后版本: {{ new_podman_version.stdout if new_podman_version.rc == 0 else '安装失败' }}"

161
configuration/playbooks/install-configure-nomad-podman-driver.yml Normal file
View File

@@ -0,0 +1,161 @@
---
- name: Install and Configure Nomad Podman Driver on Client Nodes
hosts: nomad_clients
become: yes
vars:
nomad_plugin_dir: "/opt/nomad/plugins"
tasks:
- name: Create backup directory with timestamp
set_fact:
backup_dir: "/root/backup/{{ ansible_date_time.date }}_{{ ansible_date_time.hour }}{{ ansible_date_time.minute }}{{ ansible_date_time.second }}"
- name: Create backup directory
file:
path: "{{ backup_dir }}"
state: directory
mode: '0755'
- name: Backup current Nomad configuration
copy:
src: /etc/nomad.d/nomad.hcl
dest: "{{ backup_dir }}/nomad.hcl.backup"
remote_src: yes
ignore_errors: yes
- name: Backup current apt sources
shell: |
cp -r /etc/apt/sources.list* {{ backup_dir }}/
dpkg --get-selections > {{ backup_dir }}/installed_packages.txt
ignore_errors: yes
- name: Create temporary directory for apt
file:
path: /tmp/apt-temp
state: directory
mode: '1777'
- name: Download HashiCorp GPG key
get_url:
url: https://apt.releases.hashicorp.com/gpg
dest: /tmp/hashicorp.gpg
mode: '0644'
environment:
TMPDIR: /tmp/apt-temp
- name: Install HashiCorp GPG key
shell: |
gpg --dearmor < /tmp/hashicorp.gpg > /usr/share/keyrings/hashicorp-archive-keyring.gpg
environment:
TMPDIR: /tmp/apt-temp
- name: Add HashiCorp repository
lineinfile:
path: /etc/apt/sources.list.d/hashicorp.list
line: "deb [signed-by=/usr/share/keyrings/hashicorp-archive-keyring.gpg] https://apt.releases.hashicorp.com {{ ansible_distribution_release }} main"
create: yes
mode: '0644'
- name: Update apt cache
apt:
update_cache: yes
environment:
TMPDIR: /tmp/apt-temp
ignore_errors: yes
- name: Install nomad-driver-podman
apt:
name: nomad-driver-podman
state: present
environment:
TMPDIR: /tmp/apt-temp
- name: Create Nomad plugin directory
file:
path: "{{ nomad_plugin_dir }}"
state: directory
owner: nomad
group: nomad
mode: '0755'
- name: Create symlink for nomad-driver-podman in plugin directory
file:
src: /usr/bin/nomad-driver-podman
dest: "{{ nomad_plugin_dir }}/nomad-driver-podman"
state: link
owner: nomad
group: nomad
- name: Get server IP address
shell: |
ip route get 1.1.1.1 | grep -oP 'src \K\S+'
register: server_ip_result
changed_when: false
- name: Set server IP fact
set_fact:
server_ip: "{{ server_ip_result.stdout }}"
- name: Stop Nomad service
systemd:
name: nomad
state: stopped
- name: Create updated Nomad client configuration
copy:
content: |
datacenter = "{{ nomad_datacenter }}"
data_dir = "/opt/nomad/data"
log_level = "INFO"
bind_addr = "{{ server_ip }}"
server {
enabled = false
}
client {
enabled = true
servers = ["100.117.106.136:4647", "100.116.80.94:4647", "100.97.62.111:4647", "100.116.112.45:4647", "100.84.197.26:4647"]
}
plugin_dir = "{{ nomad_plugin_dir }}"
plugin "nomad-driver-podman" {
config {
volumes {
enabled = true
}
recover_stopped = true
}
}
consul {
address = "127.0.0.1:8500"
}
dest: /etc/nomad.d/nomad.hcl
owner: nomad
group: nomad
mode: '0640'
backup: yes
- name: Validate Nomad configuration
shell: nomad config validate /etc/nomad.d/nomad.hcl
register: nomad_validate
failed_when: nomad_validate.rc != 0
- name: Start Nomad service
systemd:
name: nomad
state: started
enabled: yes
- name: Wait for Nomad to be ready
wait_for:
port: 4646
host: "{{ server_ip }}"
delay: 5
timeout: 60
- name: Display backup location
debug:
msg: "Backup created at: {{ backup_dir }}"

218
configuration/playbooks/integrated-podman-setup.yml Normal file
View File

@@ -0,0 +1,218 @@
---
- name: Integrated Podman Setup - Remove Docker, Install and Configure Podman with Compose for Nomad
hosts: all
become: yes
gather_facts: yes
tasks:
- name: 显示当前处理的节点
debug:
msg: "🔧 开始集成 Podman 设置: {{ inventory_hostname }}"
- name: 检查 Docker 服务状态
shell: systemctl is-active docker 2>/dev/null || echo "inactive"
register: docker_status
changed_when: false
- name: 停止 Docker 服务
systemd:
name: docker
state: stopped
enabled: no
ignore_errors: yes
when: docker_status.stdout == "active"
- name: 停止 Docker socket
systemd:
name: docker.socket
state: stopped
enabled: no
ignore_errors: yes
- name: 移除 Docker 相关包
apt:
name:
- docker-ce
- docker-ce-cli
- containerd.io
- docker-buildx-plugin
- docker-compose-plugin
- docker.io
- docker-doc
- docker-compose
- docker-registry
- containerd
- runc
state: absent
purge: yes
ignore_errors: yes
- name: 清理 Docker 数据目录
file:
path: "{{ item }}"
state: absent
loop:
- /var/lib/docker
- /var/lib/containerd
- /etc/docker
- /etc/containerd
ignore_errors: yes
- name: 清理 Docker 用户组
group:
name: docker
state: absent
ignore_errors: yes
- name: 更新包缓存
apt:
update_cache: yes
cache_valid_time: 3600
- name: 安装 Podman 及相关工具
apt:
name:
- podman
- buildah
- skopeo
- python3-pip
- python3-setuptools
state: present
retries: 3
delay: 10
- name: 安装 Podman Compose via pip
pip:
name: podman-compose
state: present
ignore_errors: yes
- name: 启用 Podman socket 服务
systemd:
name: podman.socket
enabled: yes
state: started
ignore_errors: yes
- name: 创建 Podman 用户服务目录
file:
path: /etc/systemd/user
state: directory
mode: '0755'
- name: 验证 Podman 安装
shell: podman --version
register: podman_version
- name: 验证 Podman Compose 安装
shell: podman-compose --version 2>/dev/null || echo "未安装"
register: podman_compose_version
- name: 检查 Docker 清理状态
shell: systemctl is-active docker 2>/dev/null || echo "已移除"
register: final_docker_status
- name: 显示 Docker 移除和 Podman 安装结果
debug:
msg: |
✅ 节点 {{ inventory_hostname }} Docker 移除和 Podman 安装完成
🐳 Docker 状态: {{ final_docker_status.stdout }}
📦 Podman 版本: {{ podman_version.stdout }}
🔧 Compose 状态: {{ podman_compose_version.stdout }}
- name: 创建 Podman 系统配置目录
file:
path: /etc/containers
state: directory
mode: '0755'
- name: 配置 Podman 使用系统 socket
copy:
content: |
[engine]
# 使用系统级 socket 而不是用户级 socket
active_service = "system"
[engine.service_destinations]
[engine.service_destinations.system]
uri = "unix:///run/podman/podman.sock"
dest: /etc/containers/containers.conf
mode: '0644'
- name: 检查是否存在 nomad 用户
getent:
database: passwd
key: nomad
register: nomad_user_check
ignore_errors: yes
- name: 为 nomad 用户创建配置目录
file:
path: "/home/nomad/.config/containers"
state: directory
owner: nomad
group: nomad
mode: '0755'
when: nomad_user_check is succeeded
- name: 为 nomad 用户配置 Podman
copy:
content: |
[engine]
active_service = "system"
[engine.service_destinations]
[engine.service_destinations.system]
uri = "unix:///run/podman/podman.sock"
dest: /home/nomad/.config/containers/containers.conf
owner: nomad
group: nomad
mode: '0644'
when: nomad_user_check is succeeded
- name: 将 nomad 用户添加到 podman 组
user:
name: nomad
groups: podman
append: yes
when: nomad_user_check is succeeded
ignore_errors: yes
- name: 创建 podman 组（如果不存在）
group:
name: podman
state: present
ignore_errors: yes
- name: 设置 podman socket 目录权限
file:
path: /run/podman
state: directory
mode: '0755'
group: podman
ignore_errors: yes
- name: 验证 Podman socket 权限
file:
path: /run/podman/podman.sock
mode: '0666'
when: nomad_user_check is succeeded
ignore_errors: yes
- name: 测试 Podman 功能
shell: podman info
register: podman_info
ignore_errors: yes
- name: 清理 apt 缓存
apt:
autoclean: yes
autoremove: yes
- name: 显示最终配置结果
debug:
msg: |
🎉 节点 {{ inventory_hostname }} 集成 Podman 设置完成！
📦 Podman 版本: {{ podman_version.stdout }}
🐳 Podman Compose: {{ podman_compose_version.stdout }}
👤 Nomad 用户: {{ 'FOUND' if nomad_user_check is succeeded else 'NOT FOUND' }}
🔧 Podman 状态: {{ 'SUCCESS' if podman_info.rc == 0 else 'WARNING' }}
🚀 Docker 已移除，Podman 已配置为与 Nomad 集成

17
configuration/playbooks/manual-run-nomad-germany.yml Normal file
View File

@@ -0,0 +1,17 @@
- name: Manually run Nomad agent to capture output
hosts: germany
gather_facts: false
tasks:
- name: Run nomad agent directly
command: /snap/bin/nomad agent -config=/etc/nomad.d/nomad.hcl
register: nomad_agent_output
ignore_errors: true
- name: Display agent output
debug:
msg: |
--- Nomad Agent STDOUT ---
{{ nomad_agent_output.stdout }}
--- Nomad Agent STDERR ---
{{ nomad_agent_output.stderr }}

12
configuration/playbooks/read-nomad-config-germany.yml Normal file
View File

@@ -0,0 +1,12 @@
- name: Read Nomad config on germany
hosts: germany
gather_facts: false
tasks:
- name: Read nomad.hcl
command: cat /etc/nomad.d/nomad.hcl
register: nomad_config
ignore_errors: true
- name: Display config
debug:
msg: "{{ nomad_config.stdout }}"

126
configuration/playbooks/remove-docker-install-podman-with-compose.yml Normal file
View File

@@ -0,0 +1,126 @@
---
- name: 移除 Docker 并安装带 Compose 功能的 Podman
hosts: all
become: yes
gather_facts: yes
tasks:
- name: 显示当前处理的节点
debug:
msg: "🔧 正在处理节点: {{ inventory_hostname }}"
- name: 检查 Docker 服务状态
shell: systemctl is-active docker 2>/dev/null || echo "inactive"
register: docker_status
changed_when: false
- name: 停止 Docker 服务
systemd:
name: docker
state: stopped
enabled: no
ignore_errors: yes
when: docker_status.stdout == "active"
- name: 停止 Docker socket
systemd:
name: docker.socket
state: stopped
enabled: no
ignore_errors: yes
- name: 移除 Docker 相关包
apt:
name:
- docker-ce
- docker-ce-cli
- containerd.io
- docker-buildx-plugin
- docker-compose-plugin
- docker.io
- docker-doc
- docker-compose
- docker-registry
- containerd
- runc
state: absent
purge: yes
ignore_errors: yes
- name: 清理 Docker 数据目录
file:
path: "{{ item }}"
state: absent
loop:
- /var/lib/docker
- /var/lib/containerd
- /etc/docker
- /etc/containerd
ignore_errors: yes
- name: 清理 Docker 用户组
group:
name: docker
state: absent
ignore_errors: yes
- name: 更新包缓存
apt:
update_cache: yes
cache_valid_time: 3600
- name: 安装 Podman 及相关工具
apt:
name:
- podman
- buildah
- skopeo
- python3-pip
- python3-setuptools
state: present
retries: 3
delay: 10
- name: 安装 Podman Compose via pip
pip:
name: podman-compose
state: present
ignore_errors: yes
- name: 启用 Podman socket 服务
systemd:
name: podman.socket
enabled: yes
state: started
ignore_errors: yes
- name: 创建 Podman 用户服务目录
file:
path: /etc/systemd/user
state: directory
mode: '0755'
- name: 验证 Podman 安装
shell: podman --version
register: podman_version
- name: 验证 Podman Compose 安装
shell: podman-compose --version 2>/dev/null || echo "未安装"
register: podman_compose_version
- name: 检查 Docker 清理状态
shell: systemctl is-active docker 2>/dev/null || echo "已移除"
register: final_docker_status
- name: 显示节点处理结果
debug:
msg: |
✅ 节点 {{ inventory_hostname }} 处理完成
🐳 Docker 状态: {{ final_docker_status.stdout }}
📦 Podman 版本: {{ podman_version.stdout }}
🔧 Compose 状态: {{ podman_compose_version.stdout }}
- name: 清理 apt 缓存
apt:
autoclean: yes
autoremove: yes

2
configuration/playbooks/setup-new-nomad-nodes.yml
View File

@@ -1,6 +1,6 @@
---
- name: 安装并配置新的 Nomad Server 节点
hosts: ash2e,ash1d,ch2
hosts: influxdb1
become: yes
gather_facts: no

100
configuration/playbooks/test-podman-snap-migration.yml Normal file
View File

@@ -0,0 +1,100 @@
---
- name: 测试将 Podman 切换到 Snap 版本 (ch2 节点)
hosts: ch2
become: yes
gather_facts: yes
tasks:
- name: 检查当前 Podman 版本和安装方式
shell: |
echo "=== 当前 Podman 信息 ==="
podman --version
echo "安装路径: $(which podman)"
echo "=== Snap 状态 ==="
which snap || echo "snap 未安装"
snap list podman 2>/dev/null || echo "Podman snap 未安装"
echo "=== 包管理器状态 ==="
dpkg -l | grep podman || echo "未通过 apt 安装"
register: current_status
- name: 显示当前状态
debug:
msg: "{{ current_status.stdout }}"
- name: 检查 snap 是否已安装
shell: which snap
register: snap_check
ignore_errors: yes
changed_when: false
- name: 安装 snapd (如果未安装)
apt:
name: snapd
state: present
when: snap_check.rc != 0
- name: 确保 snapd 服务运行
systemd:
name: snapd
state: started
enabled: yes
- name: 检查当前 Podman snap 版本
shell: snap info podman
register: snap_podman_info
ignore_errors: yes
- name: 显示可用的 Podman snap 版本
debug:
msg: "{{ snap_podman_info.stdout if snap_podman_info.rc == 0 else '无法获取 snap podman 信息' }}"
- name: 停止当前 Podman 相关服务
systemd:
name: podman
state: stopped
ignore_errors: yes
- name: 移除通过包管理器安装的 Podman
apt:
name: podman
state: absent
purge: yes
ignore_errors: yes
- name: 安装 Podman snap (edge 通道)
snap:
name: podman
state: present
classic: yes
channel: edge
- name: 创建符号链接 (确保 podman 命令可用)
file:
src: /snap/bin/podman
dest: /usr/local/bin/podman
state: link
force: yes
- name: 验证 Snap Podman 安装
shell: |
/snap/bin/podman --version
which podman
register: snap_podman_verify
- name: 显示安装结果
debug:
msg: |
✅ Snap Podman 安装完成
🚀 版本: {{ snap_podman_verify.stdout_lines[0] }}
📍 路径: {{ snap_podman_verify.stdout_lines[1] }}
- name: 测试 Podman 基本功能
shell: |
/snap/bin/podman version
/snap/bin/podman info --format json | jq -r '.host.arch'
register: podman_test
ignore_errors: yes
- name: 显示测试结果
debug:
msg: "Podman 测试结果: {{ podman_test.stdout if podman_test.rc == 0 else '测试失败' }}"

77
configuration/playbooks/upgrade-podman-to-5.yml Normal file
View File

@@ -0,0 +1,77 @@
---
- name: 升级 Podman 到最新版本 (warden 节点测试)
hosts: warden
become: yes
gather_facts: yes
tasks:
- name: 检查当前 Podman 版本
shell: podman --version
register: current_podman_version
ignore_errors: yes
- name: 显示当前版本
debug:
msg: "当前 Podman 版本: {{ current_podman_version.stdout if current_podman_version.rc == 0 else '未安装或无法获取' }}"
- name: 备份现有 Podman 配置
shell: |
if [ -d /etc/containers ]; then
cp -r /etc/containers /etc/containers.backup.$(date +%Y%m%d)
fi
if [ -d /usr/share/containers ]; then
cp -r /usr/share/containers /usr/share/containers.backup.$(date +%Y%m%d)
fi
ignore_errors: yes
- name: 添加 Kubic 仓库 (HTTP 跳过签名)
shell: |
# 添加仓库并跳过签名验证
echo "deb [trusted=yes] http://download.opensuse.org/repositories/devel:/kubic:/libcontainers:/stable/xUbuntu_22.04/ /" > /etc/apt/sources.list.d/kubic-containers.list
- name: 更新包列表 (跳过签名验证)
shell: apt-get update -o Acquire::AllowInsecureRepositories=true -o Acquire::AllowDowngradeToInsecureRepositories=true
- name: 检查仓库中可用的 Podman 版本
shell: apt-cache policy podman
register: podman_versions
- name: 显示可用的 Podman 版本
debug:
msg: "{{ podman_versions.stdout }}"
- name: 安装 Podman 5.x (强制跳过签名)
shell: apt-get install -y --allow-unauthenticated --allow-downgrades --allow-remove-essential --allow-change-held-packages podman
- name: 验证 Podman 5.x 安装
shell: |
podman --version
podman info --format json | jq -r '.Version.Version'
register: podman_5_verify
- name: 显示升级结果
debug:
msg: |
✅ Podman 升级完成
🚀 新版本: {{ podman_5_verify.stdout_lines[0] }}
📊 详细版本: {{ podman_5_verify.stdout_lines[1] }}
- name: 测试基本功能
shell: |
podman run --rm hello-world
register: podman_test
ignore_errors: yes
- name: 显示测试结果
debug:
msg: "Podman 功能测试: {{ '成功' if podman_test.rc == 0 else '失败 - ' + podman_test.stderr }}"
- name: 检查相关服务状态
shell: |
systemctl status podman.socket 2>/dev/null || echo "podman.socket 未运行"
systemctl status containerd 2>/dev/null || echo "containerd 未运行"
register: service_status
- name: 显示服务状态
debug:
msg: "{{ service_status.stdout }}"