一 表結構如下:
CREATE TABLE t_audit_operate_log (
Fid bigint(16) AUTO_INCREMENT,
Fcreate_time int(10) unsigned NOT NULL DEFAULT '0',
Fuser varchar(50) DEFAULT '',
Fip bigint(16) DEFAULT NULL,
Foperate_object_id bigint(20) DEFAULT '0',
PRIMARY KEY (Fid),
KEY indx_ctime (Fcreate_time),
KEY indx_user (Fuser),
KEY indx_objid (Foperate_object_id),
KEY indx_ip (Fip)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;
執行查詢:
mysql> explain select count(*) from t_audit_operate_log where Fuser='XX@XX.com' and Fcreate_time>=1407081600 and Fcreate_time<=1407427199\G
*************************** 1. row ***************************
id: 1
select_type: SIMPLE
table: t_audit_operate_log
type: ref
possible_keys: indx_ctime,indx_user
key: indx_user
key_len: 153
ref: const
rows: 2007326
Extra: Using where
發現,使用了一個不合適的索引, 不是很理想,於是改成指定索引:
mysql> explain select count(*) from t_audit_operate_log use index(indx_ctime) where Fuser='CY6016@cyou-inc.com' and Fcreate_time>=1407081600 and Fcreate_time<=1407427199\G
*************************** 1. row ***************************
id: 1
select_type: SIMPLE
table: t_audit_operate_log
type: range
possible_keys: indx_ctime
key: indx_ctime
key_len: 5
ref: NULL
rows: 670092
Extra: Using where
實際執行耗時,后者比前者快了接近10
問題: 很奇怪,優化器為何不選擇使用 indx_ctime 索引,而選擇了明顯會掃描更多行的 indx_user 索引。
分析2個索引的數據量如下: 兩個條件的唯一性對比:
select count(*) from t_audit_operate_log where Fuser='XX@XX.com';
+----------+
| count(*) |
+----------+
| 1238382 |
+----------+
select count(*) from t_audit_operate_log where Fcreate_time>=1407254400 and Fcreate_time<=1407427199;
+----------+
| count(*) |
+----------+
| 198920 |
+----------+
顯然,使用索引indx_ctime好於indx_user,但MySQL卻選擇了indx_user. 為什么?
於是,使用 OPTIMIZER_TRACE進一步探索.
二 OPTIMIZER_TRACE的過程說明
以本處事例簡要說明OPTIMIZER_TRACE的過程.
查看OPTIMIZER_TRACE方法:
1.set optimizer_trace='enabled=on'; --- 開啟trace
2.set optimizer_trace_max_mem_size=1000000; --- 設置trace大小
3.set end_markers_in_json=on; --- 增加trace中注釋
4.select * from information_schema.optimizer_trace\G;
{\
"steps": [\ {\ "join_preparation": {\ ---優化准備工作 "select#": 1,\ "steps": [\ {\ "expanded_query": "/* select#1 */ select count(0) AS `count(*)` from `t_audit_operate_log` where ((`t_audit_operate_log`.`Fuser` = 'XX@XX.com') and (`t_audit_operate_log`.`Fcreate_time` >= 1407081600) and (`t_audit_operate_log`.`Fcreate_time` <= 1407427199))"\ }\ ] /* steps */\ } /* join_preparation */\ },\ {\ "join_optimization": {\ ---優化工作的主要階段,包括邏輯優化和物理優化兩個階段 "select#": 1,\ "steps": [\ ---優化工作的主要階段, 邏輯優化階段 {\ "condition_processing": {\ ---邏輯優化,條件化簡 "condition": "WHERE",\ "original_condition": "((`t_audit_operate_log`.`Fuser` = 'XX@XX.com') and (`t_audit_operate_log`.`Fcreate_time` >= 1407081600) and (`t_audit_operate_log`.`Fcreate_time` <= 1407427199))",\ "steps": [\ {\ "transformation": "equality_propagation",\ ---邏輯優化,條件化簡,等式處理 "resulting_condition": "((`t_audit_operate_log`.`Fuser` = 'XX@XX.com') and (`t_audit_operate_log`.`Fcreate_time` >= 1407081600) and (`t_audit_operate_log`.`Fcreate_time` <= 1407427199))"\ },\ {\ "transformation": "constant_propagation",\ ---邏輯優化,條件化簡,常量處理 "resulting_condition": "((`t_audit_operate_log`.`Fuser` = 'XX@XX.com') and (`t_audit_operate_log`.`Fcreate_time` >= 1407081600) and (`t_audit_operate_log`.`Fcreate_time` <= 1407427199))"\ },\ {\ "transformation": "trivial_condition_removal",\ ---邏輯優化,條件化簡,條件去除 "resulting_condition": "((`t_audit_operate_log`.`Fuser` = 'XX@XX.com') and (`t_audit_operate_log`.`Fcreate_time` >= 1407081600) and (`t_audit_operate_log`.`Fcreate_time` <= 1407427199))"\ }\ ] /* steps */\ } /* condition_processing */\ },\ ---邏輯優化,條件化簡,結束 {\ "table_dependencies": [\ ---邏輯優化, 找出表之間的相互依賴關系. 非直接可用的優化方式. {\ "table": "`t_audit_operate_log`",\ "row_may_be_null": false,\ "map_bit": 0,\ "depends_on_map_bits": [\ ] /* depends_on_map_bits */\ }\ ] /* table_dependencies */\ },\ {\ "ref_optimizer_key_uses": [\ ---邏輯優化, 找出備選的索引 {\ "table": "`t_audit_operate_log`",\ "field": "Fuser",\ "equals": "'XX@XX.com'",\ "null_rejecting": false\ }\ ] /* ref_optimizer_key_uses */\ },\ {\ "rows_estimation": [\ ---邏輯優化, 估算每個表的元組個數. 單表上進行全表掃描和索引掃描的代價估算. 每個索引都估算索引掃描代價 {\ "table": "`t_audit_operate_log`",\ "range_analysis": {\ "table_scan": {\---邏輯優化, 估算每個表的元組個數. 單表上進行全表掃描的代價 "rows": 8150516,\ "cost": 1.73e6\ } /* table_scan */,\ "potential_range_indices": [\ ---邏輯優化, 列出備選的索引. 后續版本字符串變為potential_range_indexes {\ "index": "PRIMARY",\---邏輯優化, 本行表明主鍵索引不可用 "usable": false,\ "cause": "not_applicable"\ },\ {\ "index": "indx_ctime",\---邏輯優化, 索引indx_ctime "usable": true,\ "key_parts": [\ "Fcreate_time",\ "Fid"\ ] /* key_parts */\ },\ {\ "index": "indx_user",\---邏輯優化, 索引indx_user "usable": true,\ "key_parts": [\ "Fuser",\ "Fid"\ ] /* key_parts */\ },\ {\ "index": "indx_objid",\---邏輯優化, 索引 "usable": false,\ "cause": "not_applicable"\ },\ {\ "index": "indx_ip",\---邏輯優化, 索引 "usable": false,\ "cause": "not_applicable"\ }\ ] /* potential_range_indices */,\ "setup_range_conditions": [\ ---邏輯優化, 如果有可下推的條件,則帶條件考慮范圍查詢 ] /* setup_range_conditions */,\ "group_index_range": {\---邏輯優化, 如帶有GROUPBY或DISTINCT,則考慮是否有索引可優化這種操作. 並考慮帶有MIN/MAX的情況 "chosen": false,\ "cause": "not_group_by_or_distinct"\ } /* group_index_range */,\ "analyzing_range_alternatives": {\---邏輯優化,開始計算每個索引做范圍掃描的花費(等值比較是范圍掃描的特例) "range_scan_alternatives": [\ {\ "index": "indx_ctime",\ ---[A] "ranges": [\ "1407081600 <= Fcreate_time <= 1407427199"\ ] /* ranges */,\ "index_dives_for_eq_ranges": true,\ "rowid_ordered": false,\ "using_mrr": true,\ "index_only": false,\ "rows": 688362,\ "cost": 564553,\ ---邏輯優化,這個索引的代價最小 "chosen": true\ ---邏輯優化,這個索引的代價最小,被選中. (比前面的table_scan 和其他索引的代價都小) },\ {\ "index": "indx_user",\ "ranges": [\ "XX@XX.com <= Fuser <= XX@XX.com"\ ] /* ranges */,\ "index_dives_for_eq_ranges": true,\ "rowid_ordered": true,\ "using_mrr": true,\ "index_only": false,\ "rows": 1945894,\ "cost": 1.18e6,\ "chosen": false,\ "cause": "cost"\ }\ ] /* range_scan_alternatives */,\ "analyzing_roworder_intersect": {\ "usable": false,\ "cause": "too_few_roworder_scans"\ } /* analyzing_roworder_intersect */\ } /* analyzing_range_alternatives */,\---邏輯優化,開始計算每個索引做范圍掃描的花費. 這項工作結算 "chosen_range_access_summary": {\---邏輯優化,開始計算每個索引做范圍掃描的花費. 總結本階段最優的. "range_access_plan": {\ "type": "range_scan",\ "index": "indx_ctime",\ "rows": 688362,\ "ranges": [\ "1407081600 <= Fcreate_time <= 1407427199"\ ] /* ranges */\ } /* range_access_plan */,\ "rows_for_plan": 688362,\ "cost_for_plan": 564553,\ "chosen": true\ -- 這里看到的cost和rows都比 indx_user 要來的小很多---這個和[A]處是一樣的,是信息匯總. } /* chosen_range_access_summary */\ } /* range_analysis */\ }\ ] /* rows_estimation */\ ---邏輯優化, 估算每個表的元組個數. 行估算結束 },\ {\ "considered_execution_plans": [\ ---物理優化, 開始多表連接的物理優化計算 {\ "plan_prefix": [\ ] /* plan_prefix */,\ "table": "`t_audit_operate_log`",\ "best_access_path": {\ "considered_access_paths": [\ {\ "access_type": "ref",\ ---物理優化, 計算indx_user索引上使用ref方查找的花費, "index": "indx_user",\ "rows": 1.95e6,\ "cost": 683515,\ "chosen": true\ },\ ---物理優化, 本應該比較所有的可用索引,即打印出多個格式相同的但索引名不同的內容,這里卻沒有。推測是bug--沒有遍歷每一個索引. {\ "access_type": "range",\---物理優化,猜測對應的是indx_time(沒有實例可進行調試,對比5.7的跟蹤信息猜測而得) "rows": 516272,\ "cost": 702225,\---物理優化,代價大於了ref方式的683515,所以沒有被選擇 "chosen": false\ -- cost比上面看到的增加了很多,但rows沒什么變化 ---物理優化,此索引沒有被選擇 }\ ] /* considered_access_paths */\ } /* best_access_path */,\ "cost_for_plan": 683515,\ ---物理優化,匯總在best_access_path 階段得到的結果 "rows_for_plan": 1.95e6,\ "chosen": true\ -- cost比上面看到的竟然小了很多?雖然rows沒啥變化 ---物理優化,匯總在best_access_path 階段得到的結果 }\ ] /* considered_execution_plans */\ },\ {\ "attaching_conditions_to_tables": {\---邏輯優化,盡量把條件綁定到對應的表上 } /* attaching_conditions_to_tables */\ },\ {\ "refine_plan": [\ {\ "table": "`t_audit_operate_log`",\---邏輯優化,下推索引條件"pushed_index_condition";其他條件附加到表上做為過濾條件"table_condition_attached" }\ ] /* refine_plan */\ }\ ] /* steps */\ } /* join_optimization */\ \---邏輯優化和物理優化結束 },\ {\ "join_explain": {} /* join_explain */\ }\ ] /* steps */\
optimizer_trace有兩個字段:
offset=-5,limit=5 將最近的5次trace打印出來
當offset小於0時,則會顯示最新的-offset開始的limit個trace,也就是說,只顯示新的trace
注意重設變量會導致trace被清空
mysql> show variables like ‘optimizer_trace_features';
http://jorgenloland.blogspot.com/2011/10/optimizer-tracing-query-execution-plan.html