MySQL多表查询进阶实战：连接与子查询深度解析
一、多表连接核心原理
1. 七种JOIN操作
-- 创建测试数据
CREATE TABLE departments (
dept_id INT PRIMARY KEY,
dept_name VARCHAR(50)
);
CREATE TABLE employees (
emp_id INT PRIMARY KEY,
emp_name VARCHAR(50),
dept_id INT
);
-- 1. 内连接（INNER JOIN）
SELECT e.emp_name, d.dept_name
FROM employees e
INNER JOIN departments d ON e.dept_id = d.dept_id;
-- 2. 左连接（LEFT JOIN）
SELECT e.emp_name, d.dept_name
FROM employees e
LEFT JOIN departments d ON e.dept_id = d.dept_id;
-- 3. 右连接（RIGHT JOIN）
SELECT e.emp_name, d.dept_name
FROM employees e
RIGHT JOIN departments d ON e.dept_id = d.dept_id;
-- 4. 全外连接（FULL OUTER JOIN）MySQL需用UNION模拟
SELECT e.emp_name, d.dept_name
FROM employees e LEFT JOIN departments d ON e.dept_id = d.dept_id
UNION
SELECT e.emp_name, d.dept_name
FROM employees e RIGHT JOIN departments d ON e.dept_id = d.dept_id
WHERE e.dept_id IS NULL;二、连接查询性能优化
1. 执行计划分析
-- 查看连接查询的执行计划
EXPLAIN
SELECT e.emp_name, d.dept_name
FROM employees e
JOIN departments d ON e.dept_id = d.dept_id;关键指标解读：
-
type：eq_ref为最佳连接类型 -
key：确认连接字段使用索引 -
rows：乘积值越小越好
2. 索引策略
-- 为连接字段创建索引
ALTER TABLE employees ADD INDEX idx_dept (dept_id);
-- 多列连接索引优化
ALTER TABLE orders ADD INDEX idx_customer_product (customer_id, product_id);3. 连接顺序控制
-- 使用STRAIGHT_JOIN强制连接顺序
SELECT /*+ STRAIGHT_JOIN */ e.emp_name, d.dept_name
FROM employees e
JOIN departments d ON e.dept_id = d.dept_id;三、子查询高级技巧
1. 子查询类型对比
| 类型 | 示例 | 执行特点 |
|---|---|---|
| 标量子查询 | SELECT (SELECT MAX(salary) FROM emp) |
返回单个值 |
| 列子查询 | WHERE id IN (SELECT id FROM temp) |
返回单列多行 |
| 行子查询 | WHERE (id,name) = (SELECT 1,'Alice') |
返回单行多列 |
| EXISTS子查询 | WHERE EXISTS (SELECT 1 FROM dept...) |
只返回布尔值 |
2. IN vs EXISTS性能对决
-- IN子查询（适合小结果集）
SELECT * FROM employees
WHERE dept_id IN (SELECT dept_id FROM departments WHERE location = '北京');
-- EXISTS子查询（适合大表关联）
SELECT e.* FROM employees e
WHERE EXISTS (
SELECT 1 FROM departments d
WHERE d.dept_id = e.dept_id AND d.location = '北京'
);优化建议：
-
外表大内表小用IN
-
外表小内表大用EXISTS
-
MySQL 8.0+ 会自动优化为JOIN
3. 派生表优化
-- 原始低效写法
SELECT * FROM (
SELECT * FROM employees WHERE salary > 10000
) AS high_salary_emp
WHERE dept_id = 5;
-- 优化写法（条件下推）
SELECT * FROM employees
WHERE salary > 10000 AND dept_id = 5;
-- 必须使用派生表时（添加索引提示）
SELECT * FROM (
SELECT /*+ INDEX(emp idx_salary) */ *
FROM employees
WHERE salary > 10000
) AS emp_with_index;
四、实战案例：电商数据分析
1. 多层级联查询
-- 查询购买了"电子产品"类商品的VIP用户
SELECT DISTINCT u.user_name, u.phone
FROM users u
JOIN orders o ON u.user_id = o.user_id
JOIN order_items oi ON o.order_id = oi.order_id
JOIN products p ON oi.product_id = p.product_id
JOIN categories c ON p.category_id = c.category_id
WHERE u.is_vip = 1
AND c.category_name = '电子产品'
AND o.create_time > DATE_SUB(NOW(), INTERVAL 30 DAY);2. 复杂聚合分析
-- 每个月的商品销售TOP3
SELECT month, product_name, sales_amount FROM (
SELECT
DATE_FORMAT(o.create_time, '%Y-%m') AS month,
p.product_name,
SUM(oi.quantity * oi.price) AS sales_amount,
RANK() OVER (PARTITION BY DATE_FORMAT(o.create_time, '%Y-%m')
ORDER BY SUM(oi.quantity * oi.price) DESC) AS sales_rank
FROM orders o
JOIN order_items oi ON o.order_id = oi.order_id
JOIN products p ON oi.product_id = p.product_id
GROUP BY month, p.product_id
) AS ranked_sales
WHERE sales_rank <= 3;五、性能陷阱与解决方案
1. N+1查询问题
反模式：
-- 应用程序中循环执行（伪代码）
for dept in departments:
emps = execute("SELECT * FROM employees WHERE dept_id = ?", dept.id)解决方案：
-- 一次性JOIN查询
SELECT d.dept_name, e.emp_name
FROM departments d
LEFT JOIN employees e ON d.dept_id = e.dept_id;
2. 临时表过大
症状：
-
Using temporary出现在EXPLAIN结果中 -
查询速度随数据量急剧下降
优化方案：
-- 增加临时表内存大小
SET tmp_table_size = 256M;
SET max_heap_table_size = 256M;
-- 优化GROUP BY字段顺序（与索引一致）
SELECT dept_id, COUNT(*)
FROM employees
GROUP BY dept_id; -- 确保dept_id有索引