Percona MySQL 5.7

表格方案:

CREATE TABLE Developer.Rate (
  ID bigint(20) UNSIGNED NOT NULL AUTO_INCREMENT,
  TIME datetime NOT NULL,
  BASE varchar(3) NOT NULL,
  QUOTE varchar(3) NOT NULL,
  BID double NOT NULL,
  ASK double NOT NULL,
  PRIMARY KEY (ID),
  INDEX IDX_TIME (TIME),
  UNIQUE INDEX IDX_UK (BASE, QUOTE, TIME)
)
ENGINE = INNODB
ROW_FORMAT = COMPRESSED;

我尝试在选定时间段之前请求最新数据。优化器使用不完整的唯一键，只有 2 列，每列 3。

如果我以普通方式请求:

EXPLAIN FORMAT=JSON
SELECT
  BID
FROM 
  Rate
WHERE 
  BASE = 'EUR' 
  AND QUOTE = 'USD' 
  AND `TIME` <= (NOW() - INTERVAL 1 MONTH) 
ORDER BY 
  `TIME` DESC 
LIMIT 1
;

“解释”显示仅使用了索引的前 2 列:BASE、QUOTE

{
  "query_block": {
    "select_id": 1,
    "cost_info": {
      "query_cost": "10231052.40"
    },
    "ordering_operation": {
      "using_filesort": false,
      "table": {
        "table_name": "Rate",
        "access_type": "ref",
        "possible_keys": [
          "IDX_UK",
          "IDX_TIME"
        ],
        "key": "IDX_UK",
        "used_key_parts": [
          "BASE",
          "QUOTE"
        ],
        "key_length": "22",
        "ref": [
          "const",
          "const"
        ],
        "rows_examined_per_scan": 45966462,
        "rows_produced_per_join": 22983231,
        "filtered": "50.00",
        "cost_info": {
          "read_cost": "1037760.00",
          "eval_cost": "4596646.20",
          "prefix_cost": "10231052.40",
          "data_read_per_join": "1G"
        },
        "used_columns": [
          "ID",
          "TIME",
          "BASE",
          "QUOTE",
          "BID"
        ],
        "attached_condition": "((`Developer`.`Rate`.`BASE` <=> 'EUR') and (`Developer`.`Rate`.`QUOTE` <=> 'USD') and (`Developer`.`Rate`.`TIME` <= <cache>((now() - interval 1 month))))"
      }
    }
  }
}

但是如果您强制优化器使用 IDX_UK，MySQL 将使用请求中的所有 3 列:

EXPLAIN FORMAT=JSON
SELECT
  BID
FROM 
  Rate FORCE INDEX(IDX_UK)
WHERE 
  BASE = 'EUR' 
  AND QUOTE = 'USD' 
  AND `TIME` <= (NOW() - INTERVAL 1 MONTH) 
ORDER BY 
  `TIME` DESC 
LIMIT 1

{
  "query_block": {
    "select_id": 1,
    "cost_info": {
      "query_cost": "10231052.40"
    },
    "ordering_operation": {
      "using_filesort": false,
      "table": {
        "table_name": "Rate",
        "access_type": "range",
        "possible_keys": [
          "IDX_UK"
        ],
        "key": "IDX_UK",
        "used_key_parts": [
          "BASE",
          "QUOTE",
          "TIME"
        ],
        "key_length": "27",
        "rows_examined_per_scan": 45966462,
        "rows_produced_per_join": 15320621,
        "filtered": "100.00",
        "index_condition": "((`Developer`.`Rate`.`BASE` = 'EUR') and (`Developer`.`Rate`.`QUOTE` = 'USD') and (`Developer`.`Rate`.`TIME` <= <cache>((now() - interval 1 month))))",
        "cost_info": {
          "read_cost": "1037760.00",
          "eval_cost": "3064124.31",
          "prefix_cost": "10231052.40",
          "data_read_per_join": "818M"
        },
        "used_columns": [
          "ID",
          "TIME",
          "BASE",
          "QUOTE",
          "BID"
        ]
      }
    }
  }
}

为什么优化器在没有明确声明索引的情况下不使用所有 3 列？

Added:

我的理解对吗，我应该像这样使用请求吗？

Reuest example:

EXPLAIN FORMAT=JSON
SELECT
  BID
FROM 
  Rate
WHERE 
  BASE = 'EUR' 
  AND QUOTE = 'USD' 
  AND `TIME` <= (NOW() - INTERVAL 1 MONTH) 
ORDER BY 
  BASE DESC, QUOTE DESC, TIME DESC
LIMIT 1

如果我理解正确，Explain 的输出不会更好。仍然只有 2 列没有使用 TIME

Explain Output

{ "query_block": { "select_id": 1, "cost_info": { "query_cost": "10384642.20" }, "ordering_operation": { "using_filesort": false, "table": { "table_name": "Rate", "access_type": "ref", "possible_keys": [ "IDX_UK", "IDX_TIME" ], "key": "IDX_UK", "used_key_parts": [ "BASE", "QUOTE" ], "key_length": "22", "ref": [ "const", "const" ], "rows_examined_per_scan": 46734411, "rows_produced_per_join": 23367205, "filtered": "50.00", "index_condition": "((<code>Developer</code>.<code>Rate</code>.<code>BASE</code> <=> 'EUR') and (<code>Developer</code>.<code>Rate</code>.<code>QUOTE</code> <=> 'USD') and (<code>Developer</code>.<code>Rate</code>.<code>TIME</code> <= ((now() - interval 1 month))))", "cost_info": { "read_cost": "1037760.00", "eval_cost": "4673441.10", "prefix_cost": "10384642.20", "data_read_per_join": "1G" }, "used_columns": [ "ID", "TIME", "BASE", "QUOTE", "BID" ] } } } }


Added 2:

我提出了这 4 个要求:

— 1 —


<code>FLUSH STATUS;
SELECT
  BID
FROM 
  Rate
WHERE 
  BASE = 'EUR' 
  AND QUOTE = 'USD' 
  AND `TIME` <= (NOW() - INTERVAL 1 MONTH) 
LIMIT 1;
SHOW SESSION STATUS LIKE 'Handler%';</code>

— 2 —

<code>FLUSH STATUS;
SELECT
  BID
FROM 
  Rate FORCE INDEX (IDX_UK)
WHERE 
  BASE = 'EUR' 
  AND QUOTE = 'USD' 
  AND `TIME` <= (NOW() - INTERVAL 1 MONTH) 
LIMIT 1;
SHOW SESSION STATUS LIKE 'Handler%';
</code>

— 3 —

<code>FLUSH STATUS;
SELECT
  BID
FROM 
  Rate
WHERE 
  BASE = 'EUR' 
  AND QUOTE = 'USD' 
  AND `TIME` <= (NOW() - INTERVAL 1 MONTH) 
ORDER BY 
  `TIME` DESC 
LIMIT 1;
SHOW SESSION STATUS LIKE 'Handler%';</code>

— 4 —

<code>
FLUSH STATUS;
SELECT
  BID
FROM 
  Rate FORCE INDEX (IDX_UK)
WHERE 
  BASE = 'EUR' 
  AND QUOTE = 'USD' 
  AND `TIME` <= (NOW() - INTERVAL 1 MONTH) 
ORDER BY 
  `TIME` DESC 
LIMIT 1;
SHOW SESSION STATUS LIKE 'Handler%';</code>

session_status的输出在除了请求3之外的所有请求中都是一样的。在请求3的输出中:Handler_read_prev = 486474; 在所有其他请求的输出中:Handler_read_prev = 0;

Added 3:

我复制了一张表，删除了 Id 字段，将 UNIQUE 键提升为 PRIMARY。

方案:

CREATE TABLE Developer.Rate2 (
  TIME datetime NOT NULL,
  BASE varchar(3) NOT NULL,
  QUOTE varchar(3) NOT NULL,
  BID double NOT NULL,
  ASK double NOT NULL,
  PRIMARY KEY (BASE, QUOTE, TIME),
  INDEX IDX_BID_ASK (BID, ASK)
)
ENGINE = INNODB
AVG_ROW_LENGTH = 26
CHARACTER SET utf8
COLLATE utf8_general_ci
ROW_FORMAT = COMPRESSED;

{
  "query_block": {
    "select_id": 1,
    "cost_info": {
      "query_cost": "9673452.20"
    },
    "ordering_operation": {
      "using_filesort": false,
      "table": {
        "table_name": "Rate2",
        "access_type": "range",
        "possible_keys": [
          "PRIMARY"
        ],
        "key": "PRIMARY",
        "used_key_parts": [
          "BASE",
          "QUOTE",
          "TIME"
        ],
        "key_length": "27",
        "rows_examined_per_scan": 48023345,
        "rows_produced_per_join": 16006180,
        "filtered": "100.00",
        "cost_info": {
          "read_cost": "68783.20",
          "eval_cost": "3201236.12",
          "prefix_cost": "9673452.20",
          "data_read_per_join": "732M"
        },
        "used_columns": [
          "TIME",
          "BASE",
          "QUOTE",
          "BID"
        ],
        "attached_condition": "((`Developer`.`Rate2`.`BASE` = 'EUR') and (`Developer`.`Rate2`.`QUOTE` = 'USD') and (`Developer`.`Rate2`.`TIME` <= <cache>((now() - interval 1 month))))"
      }
    }
  }
}

现在请求确实有效，Explain 显示所有 3 列都已使用。此变体有效。

最佳答案

去掉ID，没用的。将您的 UNIQUE 键提升为 PRIMARY。现在，神奇的是，查询速度会更快，您提出的问题也会变得毫无意义。 (您可能还需要洛林建议的 DESC 技巧。)

这是另一种比较性能的技术:

FLUSH STATUS;
SELECT ...;
SHOW SESSION STATUS LIKE 'Handler%';

我有兴趣查看使用和不使用 DESC 技巧时 SHOW 的输出。有/没有你提到的 FORCE INDEX。

为什么更快？您的查询使用的是二级索引，但它需要 bid，而索引未“涵盖”它。要获得 bid，需要在“数据”中向下钻取 PRIMARY KEY。通过更改它以便使用 PK，可以避免这种额外的向下钻取。

关于mysql - 为什么 MySQL 优化器不使用所有列索引？，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/49083626/