如何在 SQL Server 中提示多对多连接？

我有 3 个“大”表，它们连接在一对列（两者int）上。

• 表 1 有约 2 亿行
• 表 2 有约 150 万行
• Table3 有大约 600 万行

每个表在 , 上都有一个聚集索引Key1，Key2然后是一列。Key1具有低基数并且非常偏斜。它总是在WHERE子句中引用。Key2条款中从未提及WHERE。每个连接都是多对多的。

问题在于基数估计。每个连接的输出估计变得更小而不是更大。当实际结果达到数百万时，这导致最终估计为低数百。

我有什么办法可以让行政长官做出更好的估计吗？

SELECT 1
FROM Table1 t1
     JOIN Table2 t2
       ON t1.Key1 = t2.Key1
          AND t1.Key2 = t2.Key2
     JOIN Table3 t3
       ON t1.Key1 = t3.Key1
          AND t1.Key2 = t3.Key2
WHERE t1.Key1 = 1;

我尝试过的解决方案：

• 在 上创建多列统计信息Key1，Key2
• 创建大量过滤后的统计信息Key1（这很有帮助，但我最终会在数据库中获得数千个用户创建的统计信息。）

屏蔽的执行计划（抱歉屏蔽不好）

在我正在查看的情况下，结果有 900 万行。新的 CE 估计有 180 行；旧版 CE 估计有 6100 行。

这是一个可重现的示例：

DROP TABLE IF EXISTS #Table1, #Table2, #Table3;
CREATE TABLE #Table1 (Key1 INT NOT NULL, Key2 INT NOT NULL, T1Key3 INT NOT NULL, CONSTRAINT pk_t1 PRIMARY KEY CLUSTERED (Key1, Key2, T1Key3));
CREATE TABLE #Table2 (Key1 INT NOT NULL, Key2 INT NOT NULL, T2Key3 INT NOT NULL, CONSTRAINT pk_t2 PRIMARY KEY CLUSTERED (Key1, Key2, T2Key3));
CREATE TABLE #Table3 (Key1 INT NOT NULL, Key2 INT NOT NULL, T3Key3 INT NOT NULL, CONSTRAINT pk_t3 PRIMARY KEY CLUSTERED (Key1, Key2, T3Key3));

-- Table1 
WITH Numbers
     AS (SELECT TOP (1000000) Number = ROW_NUMBER() OVER(ORDER BY t1.number)
         FROM master..spt_values t1
              CROSS JOIN master..spt_values t2),
     DataSize (Key1, NumberOfRows)
     AS (SELECT 1, 2000 UNION
         SELECT 2, 10000 UNION
         SELECT 3, 25000 UNION
         SELECT 4, 50000 UNION
         SELECT 5, 200000)
INSERT INTO #Table1
SELECT Key1
     , Key2 = ROW_NUMBER() OVER (PARTITION BY Key1, T1Key3 ORDER BY Number)
     , T1Key3
FROM DataSize
     CROSS APPLY (SELECT TOP(NumberOfRows) 
                         Number
                       , T1Key3 = Number%(Key1*Key1) + 1 
                  FROM Numbers
                  ORDER BY Number) size;

-- Table2 (same Key1, Key2 values; smaller number of distinct third Key)
WITH Numbers
     AS (SELECT TOP (1000000) Number = ROW_NUMBER() OVER(ORDER BY t1.number)
         FROM master..spt_values t1
              CROSS JOIN master..spt_values t2)
INSERT INTO #Table2
SELECT DISTINCT 
       Key1
     , Key2
     , T2Key3
FROM #Table1
     CROSS APPLY (SELECT TOP (Key1*10) 
                         T2Key3 = Number
                  FROM Numbers
                  ORDER BY Number) size;

-- Table2 (same Key1, Key2 values; smallest number of distinct third Key)
WITH Numbers
     AS (SELECT TOP (1000000) Number = ROW_NUMBER() OVER(ORDER BY t1.number)
         FROM master..spt_values t1
              CROSS JOIN master..spt_values t2)
INSERT INTO #Table3
SELECT DISTINCT 
       Key1
     , Key2
     , T3Key3
FROM #Table1
     CROSS APPLY (SELECT TOP (Key1) 
                         T3Key3 = Number
                  FROM Numbers
                  ORDER BY Number) size;


DROP TABLE IF EXISTS #a;
SELECT col = 1 
INTO #a
FROM #Table1 t1
     JOIN #Table2 t2
       ON t1.Key1 = t2.Key1
          AND t1.Key2 = t2.Key2
WHERE t1.Key1 = 1;

DROP TABLE IF EXISTS #b;
SELECT col = 1 
INTO #b
FROM #Table1 t1
     JOIN #Table2 t2
       ON t1.Key1 = t2.Key1
          AND t1.Key2 = t2.Key2
     JOIN #Table3 t3
       ON t1.Key1 = t3.Key1
          AND t1.Key2 = t3.Key2
WHERE t1.Key1 = 1;