load-balancing

负载均衡

将流量分发到应用服务器，以实现高可用性、可扩展性和容错能力。

适用场景

• 将 HTTP/HTTPS 流量分发到多台后端服务器。
• 实施运行状况检查，以绕过运行异常的实例。
• 在负载均衡器处终止 TLS，简化证书管理。
• 通过流量切换实现蓝绿部署或金丝雀部署。
• 在单一入口后进行水平扩展。

前置条件

• 两台或更多运行相同应用的后端服务器。
• 用于终止 HTTPS 的 TLS 证书（ACM、Let's Encrypt，或供内部使用的自签名证书）。
• 对于 AWS：在多个可用区中包含公有和私有子网的 VPC。
• 对于 nginx/HAProxy：拥有 root 访问权限的 Linux 服务器。

nginx 负载均衡器

基本轮询

# /etc/nginx/conf.d/loadbalancer.conf
upstream app_backend {
    server 10.0.1.10:8080;
    server 10.0.1.11:8080;
    server 10.0.1.12:8080;
}

server {
    listen 80;
    server_name app.example.com;
    return 301 https://$host$request_uri;
}

server {
    listen 443 ssl http2;
    server_name app.example.com;

    ssl_certificate     /etc/ssl/certs/app.example.com.pem;
    ssl_certificate_key /etc/ssl/private/app.example.com-key.pem;
    ssl_protocols       TLSv1.2 TLSv1.3;
    ssl_ciphers         HIGH:!aNULL:!MD5;

    location / {
        proxy_pass http://app_backend;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;

        proxy_connect_timeout 5s;
        proxy_read_timeout 30s;
        proxy_send_timeout 30s;
    }

    location /health {
        access_log off;
        return 200 "OK";
    }
}

加权和备用服务器

upstream app_backend {
    least_conn;  # Route to server with fewest active connections

    server 10.0.1.10:8080 weight=5;      # Gets 5x traffic
    server 10.0.1.11:8080 weight=3;      # Gets 3x traffic
    server 10.0.1.12:8080 weight=1;      # Gets 1x traffic
    server 10.0.1.20:8080 backup;        # Only used when others are down
    server 10.0.1.21:8080 down;          # Temporarily removed from pool
}

运行状况检查（nginx Plus / OpenResty）

upstream app_backend {
    zone backend 64k;  # Shared memory zone for health data

    server 10.0.1.10:8080;
    server 10.0.1.11:8080;
    server 10.0.1.12:8080;
}

# Health check (requires nginx Plus or third-party module)
# match healthy {
#     status 200;
#     body ~ "OK";
# }
# health_check interval=5s fails=3 passes=2 match=healthy;

粘性会话（IP 哈希）

upstream app_backend {
    ip_hash;  # Same client IP always goes to the same server
    server 10.0.1.10:8080;
    server 10.0.1.11:8080;
    server 10.0.1.12:8080;
}

HAProxy 配置

完整的生产环境配置

# /etc/haproxy/haproxy.cfg
global
    log /dev/log local0
    maxconn 4096
    daemon
    ssl-default-bind-ciphers ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES128-GCM-SHA256
    ssl-default-bind-options no-sslv3 no-tlsv10 no-tlsv11
    tune.ssl.default-dh-param 2048

defaults
    mode http
    log global
    option httplog
    option dontlognull
    option forwardfor
    timeout connect 5s
    timeout client  30s
    timeout server  30s
    timeout http-request 10s
    timeout http-keep-alive 5s
    retries 3

frontend http_front
    bind *:80
    redirect scheme https code 301 if !{ ssl_fc }

frontend https_front
    bind *:443 ssl crt /etc/ssl/certs/app.example.com.pem
    http-request set-header X-Forwarded-Proto https

    # Route based on path
    acl is_api path_beg /api/
    acl is_ws  path_beg /ws/

    use_backend api_servers if is_api
    use_backend ws_servers  if is_ws
    default_backend web_servers

backend web_servers
    balance roundrobin
    option httpchk GET /health HTTP/1.1\r\nHost:\ app.example.com
    http-check expect status 200

    cookie SERVERID insert indirect nocache
    server web1 10.0.1.10:8080 check inter 5s fall 3 rise 2 cookie web1
    server web2 10.0.1.11:8080 check inter 5s fall 3 rise 2 cookie web2
    server web3 10.0.1.12:8080 check inter 5s fall 3 rise 2 cookie web3

backend api_servers
    balance leastconn
    option httpchk GET /api/health
    http-check expect status 200

    server api1 10.0.2.10:8080 check inter 5s fall 3 rise 2
    server api2 10.0.2.11:8080 check inter 5s fall 3 rise 2

backend ws_servers
    balance source
    option httpchk GET /health
    timeout tunnel 1h

    server ws1 10.0.3.10:8080 check inter 5s fall 3 rise 2
    server ws2 10.0.3.11:8080 check inter 5s fall 3 rise 2

listen stats
    bind *:8404
    stats enable
    stats uri /stats
    stats refresh 10s
    stats admin if LOCALHOST

HAProxy 管理

# Test config before reloading
haproxy -c -f /etc/haproxy/haproxy.cfg

# Reload without dropping connections
sudo systemctl reload haproxy

# View stats from CLI
echo "show stat" | sudo socat stdio /var/run/haproxy/admin.sock

# Drain a server (stop new connections, let existing finish)
echo "set server web_servers/web1 state drain" | sudo socat stdio /var/run/haproxy/admin.sock

# Set server to maintenance
echo "set server web_servers/web1 state maint" | sudo socat stdio /var/run/haproxy/admin.sock

# Re-enable server
echo "set server web_servers/web1 state ready" | sudo socat stdio /var/run/haproxy/admin.sock

AWS 应用程序负载均衡器（ALB）

通过 CLI 创建 ALB

# Create the load balancer
aws elbv2 create-load-balancer \
  --name my-app-alb \
  --subnets subnet-aaa111 subnet-bbb222 \
  --security-groups sg-xxx123 \
  --type application \
  --scheme internet-facing

# Create a target group
aws elbv2 create-target-group \
  --name my-app-targets \
  --protocol HTTP \
  --port 8080 \
  --vpc-id vpc-xxx123 \
  --health-check-protocol HTTP \
  --health-check-path /health \
  --health-check-interval-seconds 15 \
  --healthy-threshold-count 2 \
  --unhealthy-threshold-count 3 \
  --target-type instance

# Register targets
aws elbv2 register-targets \
  --target-group-arn arn:aws:elasticloadbalancing:us-east-1:123456:targetgroup/my-app-targets/abc123 \
  --targets Id=i-0123456789abc Id=i-0987654321def

# Create HTTPS listener
aws elbv2 create-listener \
  --load-balancer-arn arn:aws:elasticloadbalancing:us-east-1:123456:loadbalancer/app/my-app-alb/abc123 \
  --protocol HTTPS \
  --port 443 \
  --certificates CertificateArn=arn:aws:acm:us-east-1:123456:certificate/abc-123 \
  --default-actions Type=forward,TargetGroupArn=arn:aws:elasticloadbalancing:us-east-1:123456:targetgroup/my-app-targets/abc123

# Create HTTP redirect listener
aws elbv2 create-listener \
  --load-balancer-arn arn:aws:elasticloadbalancing:us-east-1:123456:loadbalancer/app/my-app-alb/abc123 \
  --protocol HTTP \
  --port 80 \
  --default-actions Type=redirect,RedirectConfig='{Protocol=HTTPS,Port=443,StatusCode=HTTP_301}'

检查目标运行状况

# Check health of registered targets
aws elbv2 describe-target-health \
  --target-group-arn arn:aws:elasticloadbalancing:us-east-1:123456:targetgroup/my-app-targets/abc123

AWS 网络负载均衡器（NLB）

# Create NLB (for TCP, UDP, or TLS traffic)
aws elbv2 create-load-balancer \
  --name my-tcp-nlb \
  --subnets subnet-aaa111 subnet-bbb222 \
  --type network \
  --scheme internet-facing

# Create TCP target group
aws elbv2 create-target-group \
  --name my-tcp-targets \
  --protocol TCP \
  --port 5432 \
  --vpc-id vpc-xxx123 \
  --health-check-protocol TCP \
  --target-type ip

使用 Terraform 配置 ALB

resource "aws_lb" "app" {
  name               = "my-app-alb"
  internal           = false
  load_balancer_type = "application"
  security_groups    = [aws_security_group.alb.id]
  subnets            = var.public_subnet_ids

  enable_deletion_protection = true
}

resource "aws_lb_target_group" "app" {
  name     = "my-app-tg"
  port     = 8080
  protocol = "HTTP"
  vpc_id   = var.vpc_id

  health_check {
    path                = "/health"
    port                = "traffic-port"
    healthy_threshold   = 2
    unhealthy_threshold = 3
    timeout             = 5
    interval            = 15
    matcher             = "200"
  }

  deregistration_delay = 30

  stickiness {
    type            = "lb_cookie"
    cookie_duration = 86400
    enabled         = true
  }
}

resource "aws_lb_listener" "https" {
  load_balancer_arn = aws_lb.app.arn
  port              = 443
  protocol          = "HTTPS"
  ssl_policy        = "ELBSecurityPolicy-TLS13-1-2-2021-06"
  certificate_arn   = aws_acm_certificate.cert.arn

  default_action {
    type             = "forward"
    target_group_arn = aws_lb_target_group.app.arn
  }
}

resource "aws_lb_listener" "http_redirect" {
  load_balancer_arn = aws_lb.app.arn
  port              = 80
  protocol          = "HTTP"

  default_action {
    type = "redirect"
    redirect {
      port        = "443"
      protocol    = "HTTPS"
      status_code = "HTTP_301"
    }
  }
}

负载均衡算法

算法	使用场景	nginx	HAProxy
轮询	默认模式，服务器权重相同	(default)	balance roundrobin
最少连接数	请求时长不一	least_conn	balance leastconn
IP 哈希	无需 Cookie 的会话持久性	ip_hash	balance source
URI 哈希	按 URL 实现缓存局部性	hash $request_uri	balance uri
两次随机选择	大型服务器池	random two least_conn	balance random(2)

故障排查

症状	原因	解决方法
所有后端均显示“unhealthy”	运行状况检查路径返回非 200 状态码	确认 /health 端点返回 200；检查安全组
502 Bad Gateway	后端未运行或端口错误	确认后端正在配置的端口上监听
流量分配不均	粘性会话或加权配置	检查会话亲和性设置；检查服务器权重
连接超时	后端响应过慢或超时时间过短	增大 proxy_read_timeout 或 HAProxy 的 timeout server
TLS 握手失败	证书不匹配或已过期	确认证书与域名匹配；若已过期则续期
ALB 返回 503	未注册健康目标	检查目标组运行状况；确认目标位于正确的子网中
WebSocket 连接断开	代理未配置升级	添加 proxy_set_header Upgrade 和 Connection "upgrade"

相关技能

• reverse-proxy - 反向代理配置模式
• dns-management - 指向负载均衡器的 DNS 记录
• cdn-setup - 在负载均衡源站前部署 CDN
• service-mesh - Kubernetes 中的服务级负载均衡