Skip to Content
文档服务器高可用基础

高可用基础

高可用（High Availability，HA）确保服务在单点故障时仍可持续运行。本文介绍三种常用的高可用方案：keepalived（VIP 漂移）、HAProxy（负载均衡）和 Pacemaker/Corosync（集群资源管理）。

keepalived（虚拟 IP 漂移）

keepalived 基于 VRRP 协议实现虚拟 IP 地址的自动漂移，当主节点故障时，备用节点自动接管 VIP。

安装

# 在所有节点安装
sudo apt update
sudo apt install keepalived -y

架构示例

节点 1 (MASTER): 192.168.1.11
节点 2 (BACKUP): 192.168.1.12
虚拟 IP (VIP):   192.168.1.100

主节点配置

sudo tee /etc/keepalived/keepalived.conf << 'EOF'
global_defs {
    router_id LVS_NODE1
    script_user root
    enable_script_security
}
 
# 健康检查脚本
vrrp_script check_nginx {
    script "/usr/bin/curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1 | grep -q 200"
    interval 5
    weight -20
    fall 3
    rise 2
}
 
vrrp_instance VI_1 {
    state MASTER
    interface eth0
    virtual_router_id 51
    priority 100
    advert_int 1
 
    authentication {
        auth_type PASS
        auth_pass MyS3cretP@ss
    }
 
    virtual_ipaddress {
        192.168.1.100/24 dev eth0
    }
 
    track_script {
        check_nginx
    }
 
    # 通知脚本（可选）
    notify_master "/etc/keepalived/notify.sh master"
    notify_backup "/etc/keepalived/notify.sh backup"
    notify_fault  "/etc/keepalived/notify.sh fault"
}
EOF

备用节点配置

sudo tee /etc/keepalived/keepalived.conf << 'EOF'
global_defs {
    router_id LVS_NODE2
    script_user root
    enable_script_security
}
 
vrrp_script check_nginx {
    script "/usr/bin/curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1 | grep -q 200"
    interval 5
    weight -20
    fall 3
    rise 2
}
 
vrrp_instance VI_1 {
    state BACKUP
    interface eth0
    virtual_router_id 51
    priority 90
    advert_int 1
 
    authentication {
        auth_type PASS
        auth_pass MyS3cretP@ss
    }
 
    virtual_ipaddress {
        192.168.1.100/24 dev eth0
    }
 
    track_script {
        check_nginx
    }
}
EOF

通知脚本

sudo tee /etc/keepalived/notify.sh << 'SCRIPT'
#!/bin/bash
STATE=$1
DATETIME=$(date '+%Y-%m-%d %H:%M:%S')
echo "${DATETIME} - 状态变更为: ${STATE}" >> /var/log/keepalived-notify.log
 
case $STATE in
    master)
        echo "${DATETIME} - 当前节点成为 MASTER" >> /var/log/keepalived-notify.log
        # 可在此发送告警通知
        ;;
    backup)
        echo "${DATETIME} - 当前节点成为 BACKUP" >> /var/log/keepalived-notify.log
        ;;
    fault)
        echo "${DATETIME} - 当前节点进入 FAULT 状态" >> /var/log/keepalived-notify.log
        ;;
esac
SCRIPT
 
sudo chmod +x /etc/keepalived/notify.sh

启动服务

# 在所有节点启动
sudo systemctl enable --now keepalived
 
# 查看状态
sudo systemctl status keepalived
 
# 查看 VIP
ip addr show eth0 | grep 192.168.1.100
 
# 查看日志
sudo journalctl -u keepalived -f
 
# 测试故障转移
# 在主节点停止 keepalived
sudo systemctl stop keepalived
# 观察备用节点是否接管 VIP

HAProxy（负载均衡）

HAProxy 是高性能的 TCP/HTTP 负载均衡器，支持多种调度算法和健康检查。

安装

sudo apt update
sudo apt install haproxy -y
 
# 查看版本
haproxy -v

基本配置

sudo tee /etc/haproxy/haproxy.cfg << 'EOF'
global
    log /dev/log local0
    log /dev/log local1 notice
    chroot /var/lib/haproxy
    stats socket /run/haproxy/admin.sock mode 660 level admin
    stats timeout 30s
    user haproxy
    group haproxy
    daemon
 
    # 性能调优
    maxconn 50000
    tune.ssl.default-dh-param 2048
 
defaults
    log     global
    mode    http
    option  httplog
    option  dontlognull
    option  forwardfor
    option  http-server-close
    timeout connect 5000
    timeout client  50000
    timeout server  50000
    errorfile 400 /etc/haproxy/errors/400.http
    errorfile 403 /etc/haproxy/errors/403.http
    errorfile 408 /etc/haproxy/errors/408.http
    errorfile 500 /etc/haproxy/errors/500.http
    errorfile 502 /etc/haproxy/errors/502.http
    errorfile 503 /etc/haproxy/errors/503.http
    errorfile 504 /etc/haproxy/errors/504.http
 
# 统计页面
listen stats
    bind *:8404
    stats enable
    stats uri /stats
    stats refresh 10s
    stats admin if LOCALHOST
    stats auth admin:haproxy_pass
 
# HTTP 前端
frontend http_front
    bind *:80
    # HTTPS 重定向
    # redirect scheme https code 301 if !{ ssl_fc }
    default_backend http_back
 
# HTTPS 前端
frontend https_front
    bind *:443 ssl crt /etc/haproxy/certs/example.com.pem
    http-request set-header X-Forwarded-Proto https
 
    # 基于域名路由
    acl host_app1 hdr(host) -i app1.example.com
    acl host_app2 hdr(host) -i app2.example.com
 
    use_backend app1_back if host_app1
    use_backend app2_back if host_app2
    default_backend http_back
 
# 后端服务器组
backend http_back
    balance roundrobin
    option httpchk GET /health
    http-check expect status 200
 
    server web1 192.168.1.21:80 check inter 5s fall 3 rise 2
    server web2 192.168.1.22:80 check inter 5s fall 3 rise 2
    server web3 192.168.1.23:80 check inter 5s fall 3 rise 2 backup
 
backend app1_back
    balance leastconn
    option httpchk GET /health
    server app1a 192.168.1.31:8080 check
    server app1b 192.168.1.32:8080 check
 
backend app2_back
    balance source
    server app2a 192.168.1.41:8080 check
    server app2b 192.168.1.42:8080 check
EOF

TCP 负载均衡（数据库等）

# 在 haproxy.cfg 中添加
cat << 'EOF' | sudo tee -a /etc/haproxy/haproxy.cfg
 
# MySQL 负载均衡
listen mysql_cluster
    bind *:3306
    mode tcp
    option mysql-check user haproxy
    balance roundrobin
    server mysql1 192.168.1.51:3306 check inter 5s
    server mysql2 192.168.1.52:3306 check inter 5s backup
 
# Redis Sentinel
listen redis
    bind *:6379
    mode tcp
    option tcp-check
    balance first
    server redis1 192.168.1.61:6379 check inter 3s
    server redis2 192.168.1.62:6379 check inter 3s
EOF

负载均衡算法

算法说明适用场景
roundrobin轮询默认，服务器性能相近
leastconn最少连接长连接、处理时间不均
source源 IP 哈希需要会话保持
uriURI 哈希缓存服务器
first填满第一个再用第二个节约资源

启动与验证

# 检查配置
sudo haproxy -c -f /etc/haproxy/haproxy.cfg
 
# 启动服务
sudo systemctl enable --now haproxy
 
# 查看状态页面
curl http://localhost:8404/stats
 
# 防火墙
sudo ufw allow 80/tcp
sudo ufw allow 443/tcp
sudo ufw allow 8404/tcp

keepalived + HAProxy 组合

最常见的高可用方案是 keepalived + HAProxy：两台 HAProxy 互为主备，通过 keepalived 管理 VIP。

# keepalived 配置中检查 HAProxy 状态
sudo tee /etc/keepalived/keepalived.conf << 'EOF'
global_defs {
    router_id HAPROXY_NODE1
    script_user root
    enable_script_security
}
 
vrrp_script check_haproxy {
    script "/usr/bin/killall -0 haproxy"
    interval 2
    weight -30
    fall 3
    rise 2
}
 
vrrp_instance VI_1 {
    state MASTER
    interface eth0
    virtual_router_id 51
    priority 100
    advert_int 1
 
    authentication {
        auth_type PASS
        auth_pass HAProxy_HA
    }
 
    virtual_ipaddress {
        192.168.1.100/24
    }
 
    track_script {
        check_haproxy
    }
}
EOF

Pacemaker / Corosync（集群资源管理）

Pacemaker 和 Corosync 提供企业级的集群资源管理，支持复杂的资源依赖和故障策略。

安装

# 在所有节点安装
sudo apt update
sudo apt install pacemaker corosync pcs resource-agents -y
 
# 设置 hacluster 用户密码（所有节点相同）
sudo passwd hacluster
 
# 启动 pcs 管理服务
sudo systemctl enable --now pcsd

配置集群

# 在一个节点上执行认证（所有节点）
sudo pcs host auth node1 node2 -u hacluster -p yourpassword
 
# 创建集群
sudo pcs cluster setup ha-cluster node1 node2
 
# 启动集群
sudo pcs cluster start --all
sudo pcs cluster enable --all
 
# 查看集群状态
sudo pcs cluster status
sudo pcs status
 
# 对于两节点集群，禁用 quorum 策略
sudo pcs property set no-quorum-policy=ignore
# 禁用 STONITH（测试环境，生产环境应配置 fencing 设备）
sudo pcs property set stonith-enabled=false

配置集群资源

# 添加虚拟 IP 资源
sudo pcs resource create cluster_vip ocf:heartbeat:IPaddr2 \
  ip=192.168.1.100 \
  cidr_netmask=24 \
  nic=eth0 \
  op monitor interval=10s
 
# 添加 Nginx 资源
sudo pcs resource create web_server ocf:heartbeat:nginx \
  configfile=/etc/nginx/nginx.conf \
  op monitor interval=10s timeout=30s \
  op start timeout=60s \
  op stop timeout=60s
 
# 确保 VIP 和 Nginx 在同一节点
sudo pcs constraint colocation add web_server with cluster_vip INFINITY
 
# 确保 VIP 先于 Nginx 启动
sudo pcs constraint order cluster_vip then web_server
 
# 创建资源组（更简单的方式）
sudo pcs resource group add web_group cluster_vip web_server
 
# 查看资源状态
sudo pcs resource status
sudo pcs constraint show

资源管理

# 手动迁移资源
sudo pcs resource move web_group node2
 
# 清除迁移约束（迁移后必须执行）
sudo pcs resource clear web_group
 
# 启用/禁用资源
sudo pcs resource disable web_server
sudo pcs resource enable web_server
 
# 清除资源错误状态
sudo pcs resource cleanup web_server
 
# 维护模式
sudo pcs node standby node1       # 将节点置为待机
sudo pcs node unstandby node1     # 恢复节点
sudo pcs property set maintenance-mode=true   # 全局维护模式
sudo pcs property set maintenance-mode=false

集群监控

# 实时监控集群状态
sudo crm_mon -1
 
# 查看集群配置
sudo pcs config show
 
# 查看集群日志
sudo journalctl -u pacemaker -f
sudo journalctl -u corosync -f
 
# Corosync 成员状态
sudo corosync-cmapctl | grep members

方案对比

特性keepalivedHAProxyPacemaker/Corosync
主要功能VIP 漂移负载均衡集群资源管理
配置复杂度简单中等较复杂
资源类型仅 VIPHTTP/TCP 均衡任意（VIP、服务、文件系统等）
健康检查基于脚本丰富的协议检查基于资源代理
适用规模2 节点大规模2-32 节点
典型用途主备切换流量分发企业级 HA

选择建议

  • 简单主备：keepalived 即可满足
  • Web 负载均衡：HAProxy（可配合 keepalived 实现 HA）
  • 复杂集群：Pacemaker/Corosync（多种资源、复杂依赖关系）
  • 最常见组合：keepalived + HAProxy，简单高效
Last updated on
虚拟化与容器Kubernetes 入门