五、如何建立合适的索引
Posted
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了五、如何建立合适的索引相关的知识，希望对你有一定的参考价值。
参考技术A 1.查询频繁2.区分度高（离散度）
3.长度小
4.尽可能覆盖常用的查询字段
区分度高（离散度）：100万用户，性别基本为男/女各50万，区分度就很低了.
索引长度直接影响索引文件的大小，影响增删改的速度，并间接影响查询速度（占用内存多）。联合索引中，区分度大的字段放前面
对于一些较长但又需要经常查询的字段，可以截取前面部分作为索引
例子：比如成语表的成语字段长度为4-20左右。
针对该列中的值，从左往右截取部分来建索引
1：截的越短，重复度越高，区分度越小，索引效果越不好
2：截取的越长，重复度越低，区分度越高，索引效果越好，但是索引长度越大，带来的影响也越大-增删改慢，间接影响查询。
所以，需要再区分度+长度 两者取一个平衡。
方法：截取不同长度，并测试区分度,取一个合适的长度
select ( (select count(distinct left(`word`,1)) from dict)/( select count(*) from dict) )
select ( (select count(distinct left(`word`,2)) from dict)/( select count(*) from dict) )
select ( (select count(distinct left(`word`,3)) from dict)/( select count(*) from dict) )
因为innodb 的左前缀原则，xxx%有效，而%xxx则无效。
对于左前缀区分度不高的字段，该如何建立索引
比如网址，前缀都是http://www
http://www.baidu.com
http://www.php.cn
http://www.w3school.com
技巧一：
将数据反过来存储，比如moc.udiab.www:ptth;
技巧二：
使用伪哈希
添加一个url_crc32字段，
使用crc32算法将网址转为整形存储，查询的时候查询该网址的crc32值。
crc32是一种哈希算法，能把字符串算为32为整数。
crc32的计算结果可能有重复，但是概率不高，可以在查询后再做相应过滤
多列索引
考虑因素，列的查询效率，区分度，同时还要结合具体业务。
MySQL如何选择合适的索引
先来看一个栗子
EXPLAIN select * from employees where name > 'a';
如果用name索引查找数据需要遍历name字段联合索引树，然后根据遍历出来的主键值去主键索引树里再去查出最终数据，成本比全表扫描还高。
可以用覆盖索引优化，这样只需要遍历name字段的联合索引树就可以拿到所有的结果。
EXPLAIN select name,age,position from employees where name > 'a';
可以看到通过select出的字段是覆盖索引，MySQL底层使用了索引优化。
在看另一个case：
EXPLAIN select * from employees where name > 'zzz';
对于上面的这两种 name>‘a‘ 和 name>‘zzz‘的执行结果， mysql最终是否选择走索引或者一张表涉及多个索引， mysql最终如何选择索引，可以通过trace工具来一查究竟，开启trace工具会影响mysql性能，所以只能临时分析sql使用，用完之后需要立即关闭。
SET SESSION optimizer_trace="enabled=on",end_markers_in_json=on; --开启trace
SELECT * FROM employees WHERE name > 'a' ORDER BY position;
SELECT * FROM information_schema.OPTIMIZER_TRACE;
查看trace字段：
"steps": [
"join_preparation": --第一阶段：SQl准备阶段
"select#": 1,
"steps": [
"expanded_query": "/* select#1 */ select `employees`.`id` AS `id`,`employees`.`name` AS `name`,`employees`.`age` AS `age`,`employees`.`position` AS `position`,`employees`.`hire_time` AS `hire_time` from `employees` where (`employees`.`name` > 'a') order by `employees`.`position`"
] /* steps */
/* join_preparation */
,
"join_optimization": --第二阶段：SQL优化阶段
"select#": 1,
"steps": [
"condition_processing": --条件处理
"condition": "WHERE",
"original_condition": "(`employees`.`name` > 'a')",
"steps": [
"transformation": "equality_propagation",
"resulting_condition": "(`employees`.`name` > 'a')"
,
"transformation": "constant_propagation",
"resulting_condition": "(`employees`.`name` > 'a')"
,
"transformation": "trivial_condition_removal",
"resulting_condition": "(`employees`.`name` > 'a')"
] /* steps */
/* condition_processing */
,
"table_dependencies": [ --表依赖详情
"table": "`employees`",
"row_may_be_null": false,
"map_bit": 0,
"depends_on_map_bits": [
] /* depends_on_map_bits */
] /* table_dependencies */
,
"ref_optimizer_key_uses": [
] /* ref_optimizer_key_uses */
,
"rows_estimation": [ --预估标的访问成本
"table": "`employees`",
"range_analysis":
"table_scan": --全表扫描情况
"rows": 3, --扫描行数
"cost": 3.7 --查询成本
/* table_scan */,
"potential_range_indices": [ --查询可能使用的索引
"index": "PRIMARY", --主键索引
"usable": false,
"cause": "not_applicable"
,
"index": "idx_name_age_position", --辅助索引
"usable": true,
"key_parts": [
"name",
"age",
"position",
"id"
] /* key_parts */
,
"index": "idx_age",
"usable": false,
"cause": "not_applicable"
] /* potential_range_indices */,
"setup_range_conditions": [
] /* setup_range_conditions */,
"group_index_range":
"chosen": false,
"cause": "not_group_by_or_distinct"
/* group_index_range */,
"analyzing_range_alternatives": ‐‐分析各个索引使用成本
"range_scan_alternatives": [
"index": "idx_name_age_position",
"ranges": [
"a < name"
] /* ranges */,
"index_dives_for_eq_ranges": true,
"rowid_ordered": false,
"using_mrr": false,
"index_only": false, ‐‐是否使用覆盖索引
"rows": 3, --‐‐索引扫描行数
"cost": 4.61, --索引使用成本
"chosen": false, ‐‐是否选择该索引
"cause": "cost"
] /* range_scan_alternatives */,
"analyzing_roworder_intersect":
"usable": false,
"cause": "too_few_roworder_scans"
/* analyzing_roworder_intersect */
/* analyzing_range_alternatives */
/* range_analysis */
] /* rows_estimation */
,
"considered_execution_plans": [
"plan_prefix": [
] /* plan_prefix */,
"table": "`employees`",
"best_access_path":
"considered_access_paths": [
"access_type": "scan",
"rows": 3,
"cost": 1.6,
"chosen": true,
"use_tmp_table": true
] /* considered_access_paths */
/* best_access_path */,
"cost_for_plan": 1.6,
"rows_for_plan": 3,
"sort_cost": 3,
"new_cost_for_plan": 4.6,
"chosen": true
] /* considered_execution_plans */
,
"attaching_conditions_to_tables":
"original_condition": "(`employees`.`name` > 'a')",
"attached_conditions_computation": [
] /* attached_conditions_computation */,
"attached_conditions_summary": [
"table": "`employees`",
"attached": "(`employees`.`name` > 'a')"
] /* attached_conditions_summary */
/* attaching_conditions_to_tables */
,
"clause_processing":
"clause": "ORDER BY",
"original_clause": "`employees`.`position`",
"items": [
"item": "`employees`.`position`"
] /* items */,
"resulting_clause_is_simple": true,
"resulting_clause": "`employees`.`position`"
/* clause_processing */
,
"refine_plan": [
"table": "`employees`",
"access_type": "table_scan"
] /* refine_plan */
,
"reconsidering_access_paths_for_index_ordering":
"clause": "ORDER BY",
"index_order_summary":
"table": "`employees`",
"index_provides_order": false,
"order_direction": "undefined",
"index": "unknown",
"plan_changed": false
/* index_order_summary */
/* reconsidering_access_paths_for_index_ordering */
] /* steps */
/* join_optimization */
,
"join_execution": --第三阶段：SQL执行阶段
"select#": 1,
"steps": [
"filesort_information": [
"direction": "asc",
"table": "`employees`",
"field": "position"
] /* filesort_information */,
"filesort_priority_queue_optimization":
"usable": false,
"cause": "not applicable (no LIMIT)"
/* filesort_priority_queue_optimization */,
"filesort_execution": [
] /* filesort_execution */,
"filesort_summary":
"rows": 3,
"examined_rows": 3,
"number_of_tmp_files": 0,
"sort_buffer_size": 200704,
"sort_mode": "<sort_key, additional_fields>"
/* filesort_summary */
] /* steps */
/* join_execution */
] /* steps */
全表扫描的成本低于索引扫描， 索引MySQL最终会选择全表扫描。
SELECT * FROM employees WHERE name > 'zzz' ORDER BY position;
SELECT * FROM information_schema.OPTIMIZER_TRACE;
"steps": [
"join_preparation":
"select#": 1,
"steps": [
"expanded_query": "/* select#1 */ select `employees`.`id` AS `id`,`employees`.`name` AS `name`,`employees`.`age` AS `age`,`employees`.`position` AS `position`,`employees`.`hire_time` AS `hire_time` from `employees` where (`employees`.`name` > 'zzz') order by `employees`.`position`"
] /* steps */
/* join_preparation */
,
"join_optimization":
"select#": 1,
"steps": [
"condition_processing":
"condition": "WHERE",
"original_condition": "(`employees`.`name` > 'zzz')",
"steps": [
"transformation": "equality_propagation",
"resulting_condition": "(`employees`.`name` > 'zzz')"
,
"transformation": "constant_propagation",
"resulting_condition": "(`employees`.`name` > 'zzz')"
,
"transformation": "trivial_condition_removal",
"resulting_condition": "(`employees`.`name` > 'zzz')"
] /* steps */
/* condition_processing */
,
"table_dependencies": [
"table": "`employees`",
"row_may_be_null": false,
"map_bit": 0,
"depends_on_map_bits": [
] /* depends_on_map_bits */
] /* table_dependencies */
,
"ref_optimizer_key_uses": [
] /* ref_optimizer_key_uses */
,
"rows_estimation": [
"table": "`employees`",
"range_analysis":
"table_scan":
"rows": 3,
"cost": 3.7
/* table_scan */,
"potential_range_indices": [
"index": "PRIMARY",
"usable": false,
"cause": "not_applicable"
,
"index": "idx_name_age_position",
"usable": true,
"key_parts": [
"name",
"age",
"position",
"id"
] /* key_parts */
,
"index": "idx_age",
"usable": false,
"cause": "not_applicable"
] /* potential_range_indices */,
"setup_range_conditions": [
] /* setup_range_conditions */,
"group_index_range":
"chosen": false,
"cause": "not_group_by_or_distinct"
/* group_index_range */,
"analyzing_range_alternatives":
"range_scan_alternatives": [
"index": "idx_name_age_position",
"ranges": [
"zzz < name"
] /* ranges */,
"index_dives_for_eq_ranges": true,
"rowid_ordered": false,
"using_mrr": false,
"index_only": false,
"rows": 1,
"cost": 2.21,
"chosen": true
] /* range_scan_alternatives */,
"analyzing_roworder_intersect":
"usable": false,
"cause": "too_few_roworder_scans"
/* analyzing_roworder_intersect */
/* analyzing_range_alternatives */,
"chosen_range_access_summary":
"range_access_plan":
"type": "range_scan",
"index": "idx_name_age_position",
"rows": 1,
"ranges": [
"zzz < name"
] /* ranges */
/* range_access_plan */,
"rows_for_plan": 1,
"cost_for_plan": 2.21,
"chosen": true
/* chosen_range_access_summary */
/* range_analysis */
] /* rows_estimation */
,
"considered_execution_plans": [
"plan_prefix": [
] /* plan_prefix */,
"table": "`employees`",
"best_access_path":
"considered_access_paths": [
"access_type": "range",
"rows": 1,
"cost": 2.41,
"chosen": true,
"use_tmp_table": true
] /* considered_access_paths */
/* best_access_path */,
"cost_for_plan": 2.41,
"rows_for_plan": 1,
"sort_cost": 1,
"new_cost_for_plan": 3.41,
"chosen": true
] /* considered_execution_plans */
,
"attaching_conditions_to_tables":
"original_condition": "(`employees`.`name` > 'zzz')",
"attached_conditions_computation": [
] /* attached_conditions_computation */,
"attached_conditions_summary": [
"table": "`employees`",
"attached": "(`employees`.`name` > 'zzz')"
] /* attached_conditions_summary */
/* attaching_conditions_to_tables */
,
"clause_processing":
"clause": "ORDER BY",
"original_clause": "`employees`.`position`",
"items": [
"item": "`employees`.`position`"
] /* items */,
"resulting_clause_is_simple": true,
"resulting_clause": "`employees`.`position`"
/* clause_processing */
,
"refine_plan": [
"table": "`employees`",
"pushed_index_condition": "(`employees`.`name` > 'zzz')",
"table_condition_attached": null,
"access_type": "range"
] /* refine_plan */
,
"reconsidering_access_paths_for_index_ordering":
"clause": "ORDER BY",
"index_order_summary":
"table": "`employees`",
"index_provides_order": false,
"order_direction": "undefined",
"index": "idx_name_age_position",
"plan_changed": false
/* index_order_summary */
/* reconsidering_access_paths_for_index_ordering */
] /* steps */
/* join_optimization */
,
"join_execution":
"select#": 1,
"steps": [
"filesort_information": [
"direction": "asc",
"table": "`employees`",
"field": "position"
] /* filesort_information */,
"filesort_priority_queue_optimization":
"usable": false,
"cause": "not applicable (no LIMIT)"
/* filesort_priority_queue_optimization */,
"filesort_execution": [
] /* filesort_execution */,
"filesort_summary":
"rows": 0,
"examined_rows": 0,
"number_of_tmp_files": 0,
"sort_buffer_size": 200704,
"sort_mode": "<sort_key, additional_fields>"
/* filesort_summary */
] /* steps */
/* join_execution */
] /* steps */
查看trace字段可知索引扫描的成本低于全表扫描的成本，所以MySQL最终选择索引扫描。
SET SESSION optimizer_trace="enabled=off"; -- 关闭trace还没关注我的公众号？
- 扫文末二维码关注公众号【小强的进阶之路】可领取如下:
- 学习资料： 1T视频教程：涵盖Javaweb前后端教学视频、机器学习/人工智能教学视频、Linux系统教程视频、雅思考试视频教程；
- 100多本书：包含C/C++、Java、Python三门编程语言的经典必看图书、LeetCode题解大全；
- 软件工具：几乎包括你在编程道路上的可能会用到的大部分软件；
- 项目源码：20个JavaWeb项目源码。
以上是关于五、如何建立合适的索引的主要内容，如果未能解决你的问题，请参考以下文章