Nginx反向代理出现502与504错误问题详解及排查指南

# 检查服务是否运行
systemctl status php-fpm  # 以PHP-FPM为例
 
# 尝试直接访问上游服务
curl http://127.0.0.1:9000  # PHP-FPM默认端口

# 关键配置检查示例
upstream backend {
    server 192.168.1.100:8080;  # 确认IP和端口是否正确
}
 
server {
    location / {
        proxy_pass http://backend;  # 确认协议和路径
        proxy_set_header Host $host;
    }
}

# 通常位于/var/log/nginx/error.log
tail -f /var/log/nginx/error.log

# 查看内存使用情况
free -h
 
# 查看CPU使用情况
top
 
# 检查文件描述符限制
ulimit -n

# 使用curl测试上游服务响应时间
time curl -I http://127.0.0.1:8080  # 替换为实际上游地址

# 关键超时参数示例
location / {
    proxy_connect_timeout 60s;  # 连接超时时间
    proxy_send_timeout 60s;     # 发送请求超时时间
    proxy_read_timeout 120s;    # 读取响应超时时间
    proxy_buffer_size 16k;
    proxy_buffers 4 32k;
}

# 检查网络延迟
ping 192.168.1.100  # 上游服务器IP
 
# 检查网络带宽使用情况
iftop -i eth0

# 优化代理配置
http {
    proxy_connect_timeout 30s;
    proxy_send_timeout 60s;
    proxy_read_timeout 60s;
    proxy_buffer_size 32k;
    proxy_buffers 4 32k;
    proxy_busy_buffers_size 64k;
    proxy_temp_file_write_size 64k;
    proxy_next_upstream error timeout invalid_header http_500 http_502 http_503 http_504;
}

# /etc/php-fpm.d/www.conf
pm.max_children = 50
pm.start_servers = 10
pm.min_spare_servers = 5
pm.max_spare_servers = 20

upstream backend {
    least_conn;  # 最少连接算法
    server backend1.example.com weight=5;
    server backend2.example.com weight=5;
    server backend3.example.com backup;  # 备份服务器
}

upstream backend {
    server backend1.example.com;
    server backend2.example.com;
    check interval=3000 rise=2 fall=5 timeout=1000 type=http;
    check_http_send "HEAD /health HTTP/1.0\r\n\r\n";
    check_http_expect_alive http_2xx http_3xx;
}

#!/bin/bash
 
# Nginx 502/504错误快速诊断脚本
 
# 颜色定义
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[0;33m'
NC='\033[0m' # No Color
 
echo -e "${YELLOW}=== Nginx 502/504错误诊断工具 ===${NC}"
 
# 检查Nginx服务状态
echo -e "\n${YELLOW}[1/5] 检查Nginx服务状态:${NC}"
if systemctl is-active --quiet nginx; then
    echo -e "${GREEN}✓ Nginx服务正在运行${NC}"
else
    echo -e "${RED}✗ Nginx服务未运行${NC}"
    systemctl status nginx --no-pager
fi
 
# 检查Nginx配置
echo -e "\n${YELLOW}[2/5] 检查Nginx配置语法:${NC}"
nginx -t
NGINX_CONFIG_STATUS=$?
 
# 检查上游服务器连通性
echo -e "\n${YELLOW}[3/5] 检查上游服务器连通性:${NC}"
UPSTREAM=$(grep -r "proxy_pass" /etc/nginx/ | awk -F'[ ;]' '{print $3}' | sort -u)
for server in $UPSTREAM; do
    echo -e "\n测试上游服务器: ${server}"
    IP=$(echo $server | cut -d':' -f1)
    PORT=$(echo $server | cut -d':' -f2)
    
    if ping -c 1 $IP &>/dev/null; then
        echo -e "${GREEN}✓ ${IP} 网络可达${NC}"
    else
        echo -e "${RED}✗ ${IP} 网络不可达${NC}"
    fi
    
    if nc -z -w 2 $IP $PORT &>/dev/null; then
        echo -e "${GREEN}✓ ${IP}:${PORT} 端口可访问${NC}"
    else
        echo -e "${RED}✗ ${IP}:${PORT} 端口不可访问${NC}"
    fi
done
 
# 检查Nginx错误日志
echo -e "\n${YELLOW}[4/5] 检查最近的Nginx错误日志:${NC}"
if [ -f "/var/log/nginx/error.log" ]; then
    tail -n 20 /var/log/nginx/error.log | grep -iE "502|504|connect|refused|timeout" || echo "未发现最近的502/504相关错误"
else
    echo "错误日志文件不存在"
fi
 
# 检查系统资源
echo -e "\n${YELLOW}[5/5] 检查系统资源使用情况:${NC}"
echo -e "\n内存使用:"
free -h
echo -e "\nCPU使用:"
top -bn1 | head -n 5
echo -e "\n磁盘使用:"
df -h
 
echo -e "\n${YELLOW}=== 诊断完成 ===${NC}"