以下是查询：
SELECT p.name p_name,
c.name c_name,
p.line1,
p.zip,
c.line1,
p.zip
FROM
(SELECT c.name,
ad.line1,
ad.zip
FROM customer c
JOIN account a ON a.customer_id = c.id
JOIN account_address aa ON aa.account_id = a.id
JOIN address ad ON aa.address_id = ad.id
JOIN account_import ai ON a.account_import_id = ai.id
JOIN generic_import gi ON ai.generic_import_id = gi.id
JOIN import_bundle ib ON gi.import_bundle_id = ib.id
WHERE gi.active = 1
AND ib.active = 1
AND ib.bank_id = 8
LIMIT 1000) c
JOIN
(SELECT p.name,
a.line1,
a.zip
FROM prospect p
JOIN address a ON p.address_id = a.id) p
ON
0
OR (p.zip = c.zip AND SUBSTRING(p.name, 1, 12) = SUBSTRING(c.name, 1, 12))
OR (p.zip = c.zip AND p.name = c.name)
OR (p.zip = c.zip
AND SUBSTRING(p.name, 1, 4) = SUBSTRING(c.name, 1, 4)
AND SUBSTRING(SUBSTRING_INDEX(p.name, ' ', -1), 1, 4) = SUBSTRING(SUBSTRING_INDEX(c.name, ' ', -1), 1, 4))
OR (p.zip = c.zip
AND SUBSTRING(p.name, 1, 3) = SUBSTRING(c.name, 1, 3)
AND SUBSTRING(SUBSTRING_INDEX(p.name, ' ', -1), 1, 3) = SUBSTRING(SUBSTRING_INDEX(c.name, ' ', -1), 1, 3)
AND SUBSTRING(p.line1, 1, 4) = SUBSTRING(c.line1, 1, 4))
这是EXPLAIN：
*************************** 1. row ***************************
id: 1
select_type: PRIMARY
table: <derived2>
type: ALL
possible_keys: NULL
key: NULL
key_len: NULL
ref: NULL
rows: 1000
Extra:
*************************** 2. row ***************************
id: 1
select_type: PRIMARY
table: <derived3>
type: ALL
possible_keys: NULL
key: NULL
key_len: NULL
ref: NULL
rows: 15030
Extra: Using where; Using join buffer
*************************** 3. row ***************************
id: 3
select_type: DERIVED
table: p
type: ALL
possible_keys: address_id
key: NULL
key_len: NULL
ref: NULL
rows: 15067
Extra:
*************************** 4. row ***************************
id: 3
select_type: DERIVED
table: a
type: eq_ref
possible_keys: PRIMARY,index_address_id
key: PRIMARY
key_len: 8
ref: mcif.p.address_id
rows: 1
Extra:
*************************** 5. row ***************************
id: 2
select_type: DERIVED
table: ib
type: index_merge
possible_keys: PRIMARY,bank_id,fk_bank_id,index_import_bundle_id,index_import_bundle_bank_id,index_import_bundle_active
key: index_import_bundle_active,fk_bank_id
key_len: 1,8
ref: NULL
rows: 1
Extra: Using intersect(index_import_bundle_active,fk_bank_id); Using where; Using index
*************************** 6. row ***************************
id: 2
select_type: DERIVED
table: gi
type: ref
possible_keys: PRIMARY,import_bundle_id,index_generic_import_id,index_generic_import_import_bundle_id,index_generic_import_active
key: import_bundle_id
key_len: 8
ref: mcif.ib.id
rows: 34
Extra: Using where
*************************** 7. row ***************************
id: 2
select_type: DERIVED
table: ai
type: ref
possible_keys: PRIMARY,generic_import_id,index_account_import_generic_import_id
key: generic_import_id
key_len: 8
ref: mcif.gi.id
rows: 1
Extra: Using index
*************************** 8. row ***************************
id: 2
select_type: DERIVED
table: a
type: ref
possible_keys: PRIMARY,fk_account_customer_id,index_account_customer_id,index_account_id,index_account_account_import_id
key: index_account_account_import_id
key_len: 9
ref: mcif.ai.id
rows: 1482
Extra: Using where
*************************** 9. row ***************************
id: 2
select_type: DERIVED
table: c
type: eq_ref
possible_keys: PRIMARY,index_customer_id
key: PRIMARY
key_len: 8
ref: mcif.a.customer_id
rows: 1
Extra:
*************************** 10. row ***************************
id: 2
select_type: DERIVED
table: aa
type: ref
possible_keys: fk_account_address_account_id,fk_account_address_address_id,index_account_address_account_id,index_account_address_address_id
key: fk_account_address_account_id
key_len: 8
ref: mcif.a.id
rows: 1
Extra:
*************************** 11. row ***************************
id: 2
select_type: DERIVED
table: ad
type: eq_ref
possible_keys: PRIMARY,index_address_id
key: PRIMARY
key_len: 8
ref: mcif.aa.address_id
rows: 1
Extra:
11 rows in set (0.10 sec)
我不知道从哪里开始。我想主要是我只需要有人来解释EXPLAIN。
答案 0 :(得分：1)
这些子字符串会破坏您使用索引的可能性，是否可以删除它们并加入全名？如果没有，你可以在包含名称子串的表中添加一个额外的索引列，然后加入这些列吗？
答案 1 :(得分：0)
数据库引擎会尝试尽快使用where子句删除行。但是，在您的第一个子选择中，在您加入表6表之前，不可能开始使用where子句删除行。您在where子句中引用的第一个表应始终是您选择的第一个表，而您在where子句中引用的第二个表应该是您加入的第一个表。
所以尝试在大内部选择中切换表的顺序：）
这是我的尝试，但当然未经测试，因为我没有数据库：
SELECT
p.name AS p_name,
c.name AS c_name,
p.line1,
p.zip,
c.line1,
p.zip
FROM (
SELECT
c.name,
ad.line1,
ad.zip
FROM generic_import AS gi
JOIN import_bundle AS ib ON gi.import_bundle_id = ib.id
JOIN account_import AS ai ON ai.generic_import_id = gi.id
JOIN account AS a ON a.account_import_id = ai.id
JOIN account_address AS aa ON aa.account_id = a.id
JOIN address AS ad ON aa.address_id = ad.id
JOIN customer AS c ON a.customer_id = c.id
WHERE gi.active = 1
AND ib.active = 1
AND ib.bank_id = 8
LIMIT 1000) AS c
JOIN
(SELECT
p.name,
a.line1,
a.zip
FROM prospect AS p
JOIN address AS a ON p.address_id = a.id
) AS p
ON (p.zip = c.zip
AND SUBSTRING(p.name, 1, 12) = SUBSTRING(c.name, 1, 12)
)
OR (p.zip = c.zip AND p.name = c.name)
OR
(p.zip = c.zip AND SUBSTRING(p.name, 1, 4) = SUBSTRING(c.name, 1, 4)
AND SUBSTRING(SUBSTRING_INDEX(p.name, ' ', -1), 1, 4) =
SUBSTRING(SUBSTRING_INDEX(c.name, ' ', -1), 1, 4)
)
OR
(p.zip = c.zip AND SUBSTRING(p.name, 1, 3) = SUBSTRING(c.name, 1, 3)
AND SUBSTRING(SUBSTRING_INDEX(p.name, ' ', -1), 1, 3) =
SUBSTRING(SUBSTRING_INDEX(c.name, ' ', -1), 1, 3)
AND SUBSTRING(p.line1, 1, 4) = SUBSTRING(c.line1, 1, 4)
)
它更快吗？ d：
答案 2 :(得分：0)
您可以尝试将prospect.name添加到prospect.address_id上的索引，这样您就可以在address_id,name上找到索引。它应该稍微改善性能（至少来自explain的第3行）。
也是行
OR (p.zip = c.zip AND p.name = c.name)似乎是多余的 -
(p.zip = c.zip AND SUBSTRING(p.name, 1, 12) = SUBSTRING(c.name, 1, 12))包含p.name = c.name的所有行。
答案 3 :(得分：0)
解决方案是取出子查询并仅使用连接重写查询。