【发布时间】：2019-10-14 09:06:57
【问题描述】：
我正在设计一个新的数据库，并注意到我的查询没有像应有的那样扩展。当我的聚合涉及数百条记录时，我发现响应时间显着增加。我想知道我的查询是否存在严重缺陷，或者我只是没有使用正确的索引。
我对我的查询做了很多调整，但还没有想出一种方法来消除全表扫描，而是使用索引。当我在查询中使用类似于 EXPLAIN 的工具时，我看到以下内容：
- 全表扫描通常效率低下，请避免使用它们。
- 您的查询使用 MySQL 的“文件排序”操作。这往往会减慢查询速度。
- 您的查询使用 MySQL 的临时表。这可能需要额外的 I/O，并且往往会减慢查询速度。
表：
CREATE TABLE `indexTable` (
`id` int(10) unsigned NOT NULL,
`userId` int(10) unsigned NOT NULL,
`col1` varbinary(320) NOT NULL,
`col2` tinyint(3) unsigned NOT NULL,
`col3` tinyint(3) unsigned NOT NULL,
`createdAt` bigint(20) unsigned NOT NULL,
`updatedAt` bigint(20) unsigned NOT NULL,
`metadata` json NOT NULL,
PRIMARY KEY (`id`,`userId`,`col1`,`col2`,`col3`),
KEY `createdAt` (`createdAt`),
KEY `id_userId_col1_col2_createdAt` (`id`,`userId`,`col1`,`col2`,`createdAt`),
KEY `col1_col2_createdAt` (`col1`,`col2`,`createdAt`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 ROW_FORMAT=COMPRESSED KEY_BLOCK_SIZE=8
查询：
SELECT t1.id, t1.userId, t1.col1, t1.col2, t1.col3, t1.metadata
FROM indexTable as t1
INNER JOIN(
SELECT col1, col2, MAX(createdAt) AS maxCreatedAt
FROM indexTable
WHERE id = ? AND userId = ?
GROUP BY col1, col2
ORDER BY maxCreatedAt
LIMIT 10 OFFSET 0) AS sub
ON t1.col1 = sub.col1
AND t1.col2 = sub.col2
AND t1.createdAt = sub.maxCreatedAt
WHERE t1.id = ? AND t1.userId = ?
ORDER BY t1.createdAt;
PK：id, userId, col1, col2, col3
索引：createdAt
解释：
{
"query_block": {
"select_id": 1,
"cost_info": {
"query_cost": "34.50"
},
"ordering_operation": {
"using_temporary_table": true,
"using_filesort": true,
"cost_info": {
"sort_cost": "10.00"
},
"nested_loop": [
{
"table": {
"table_name": "sub",
"access_type": "ALL",
"rows_examined_per_scan": 10,
"rows_produced_per_join": 10,
"filtered": "100.00",
"cost_info": {
"read_cost": "10.50",
"eval_cost": "2.00",
"prefix_cost": "12.50",
"data_read_per_join": "3K"
},
"used_columns": [
"col1",
"col2",
"maxCreatedAt"
],
"attached_condition": "(`sub`.`maxCreatedAt` is not null)",
"materialized_from_subquery": {
"using_temporary_table": true,
"dependent": false,
"cacheable": true,
"query_block": {
"select_id": 2,
"cost_info": {
"query_cost": "10.27"
},
"ordering_operation": {
"using_filesort": true,
"grouping_operation": {
"using_temporary_table": true,
"using_filesort": false,
"table": {
"table_name": "indexTable",
"access_type": "ref",
"possible_keys": [
"PRIMARY",
"createdAt",
"id_userId_col1_col2_createdAt",
"col1_col2_createdAt"
],
"key": "PRIMARY",
"used_key_parts": [
"id",
"userId"
],
"key_length": "8",
"ref": [
"const",
"const"
],
"rows_examined_per_scan": 46,
"rows_produced_per_join": 46,
"filtered": "100.00",
"cost_info": {
"read_cost": "1.07",
"eval_cost": "9.20",
"prefix_cost": "10.27",
"data_read_per_join": "16K"
},
"used_columns": [
"id",
"userId",
"createdAt",
"col1",
"col2",
"col3"
],
"attached_condition": "((`MyDB`.`indexTable`.`id` <=> 53) and (`MyDB`.`indexTable`.`userId` <=> 549814))"
}
}
}
}
}
}
},
{
"table": {
"table_name": "t1",
"access_type": "ref",
"possible_keys": [
"PRIMARY",
"createdAt",
"id_userId_col1_col2_createdAt",
"col1_col2_createdAt"
],
"key": "id_userId_col1_col2_createdAt",
"used_key_parts": [
"id",
"userId",
"col1",
"col2",
"createdAt"
],
"key_length": "339",
"ref": [
"const",
"const",
"sub.col1",
"sub.col2",
"sub.maxCreatedAt"
],
"rows_examined_per_scan": 1,
"rows_produced_per_join": 10,
"filtered": "100.00",
"cost_info": {
"read_cost": "10.00",
"eval_cost": "2.00",
"prefix_cost": "24.50",
"data_read_per_join": "3K"
},
"used_columns": [
"id",
"userId",
"createdAt",
"updatedAt",
"col1",
"col2",
"col3",
"metadata",
]
}
}
]
}
}
}
此查询在col1 和col2 的分组中查找最新记录，按createdAt 排序，并将条目限制为10 个。
【问题讨论】：
-
尝试在
(id, userId, col1, col2, createdAt)上创建索引。 -
根据数据的分区方式，
(id, userId, createdAt)的复合索引也可能有效。 -
我尝试了上述索引并没有看到任何改进。事实上，查询似乎执行得较慢。
-
与所有相关表的 SHOW CREATE TABLE 语句一样，有关查询性能的问题需要对给定查询的 EXPLAIN
-
您尝试过 FORCE INDEX 吗？有时MYSQL不使用索引，而是使用全表扫描。