为了增加涵盖两种发动机之间机械差异的广泛响应选择，我提出了一项经验速度比较研究。
就纯速度而言，MyISAM 并不总是比 InnoDB 快，但根据我的经验，PURE READ 工作环境的速度往往快 2.0-2.5 倍。显然，这并不适合所有环境——正如其他人所写的那样，MyISAM 缺少诸如事务和外键之类的东西。
我在下面做了一些基准测试——我使用 python 进行循环，使用 timeit 库进行时间比较。出于兴趣，我还包括了内存引擎，尽管它只适用于较小的表（The table 'tbl' is full当您超过 MySQL 内存限制时，您会不断遇到），但它提供了全面的最佳性能。我看到的四种选择是：
- 香草选择
- 计数
- 条件选择
- 索引和非索引子选择
首先，我使用以下 SQL 创建了三个表
CREATE TABLE
data_interrogation.test_table_myisam
(
index_col BIGINT NOT NULL AUTO_INCREMENT,
value1 DOUBLE,
value2 DOUBLE,
value3 DOUBLE,
value4 DOUBLE,
PRIMARY KEY (index_col)
)
ENGINE=MyISAM DEFAULT CHARSET=utf8
在第二个和第三个表中，用“MyISAM”替换了“InnoDB”和“memory”。
1) 香草精选
询问：SELECT * FROM tbl WHERE index_col = xx
结果：平局
这些的速度大致相同，并且正如预期的那样，与要选择的列数呈线性关系。InnoDB 似乎比 MyISAM稍快，但这确实是微不足道的。
代码：
import timeit
import MySQLdb
import MySQLdb.cursors
import random
from random import randint
db = MySQLdb.connect(host="...", user="...", passwd="...", db="...", cursorclass=MySQLdb.cursors.DictCursor)
cur = db.cursor()
lengthOfTable = 100000
# Fill up the tables with random data
for x in xrange(lengthOfTable):
rand1 = random.random()
rand2 = random.random()
rand3 = random.random()
rand4 = random.random()
insertString = "INSERT INTO test_table_innodb (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
insertString2 = "INSERT INTO test_table_myisam (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
insertString3 = "INSERT INTO test_table_memory (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
cur.execute(insertString)
cur.execute(insertString2)
cur.execute(insertString3)
db.commit()
# Define a function to pull a certain number of records from these tables
def selectRandomRecords(testTable,numberOfRecords):
for x in xrange(numberOfRecords):
rand1 = randint(0,lengthOfTable)
selectString = "SELECT * FROM " + testTable + " WHERE index_col = " + str(rand1)
cur.execute(selectString)
setupString = "from __main__ import selectRandomRecords"
# Test time taken using timeit
myisam_times = []
innodb_times = []
memory_times = []
for theLength in [3,10,30,100,300,1000,3000,10000]:
innodb_times.append( timeit.timeit('selectRandomRecords("test_table_innodb",' + str(theLength) + ')', number=100, setup=setupString) )
myisam_times.append( timeit.timeit('selectRandomRecords("test_table_myisam",' + str(theLength) + ')', number=100, setup=setupString) )
memory_times.append( timeit.timeit('selectRandomRecords("test_table_memory",' + str(theLength) + ')', number=100, setup=setupString) )
2) 计数
询问：SELECT count(*) FROM tbl
结果：MyISAM 获胜
这展示了 MyISAM 和 InnoDB 之间的一个很大区别——MyISAM（和内存）跟踪表中的记录数，所以这个事务很快并且 O(1)。InnoDB 计数所需的时间量随着表大小在我调查的范围内呈超线性增加。我怀疑在实践中观察到的 MyISAM 查询的许多加速是由于类似的影响。
代码：
myisam_times = []
innodb_times = []
memory_times = []
# Define a function to count the records
def countRecords(testTable):
selectString = "SELECT count(*) FROM " + testTable
cur.execute(selectString)
setupString = "from __main__ import countRecords"
# Truncate the tables and re-fill with a set amount of data
for theLength in [3,10,30,100,300,1000,3000,10000,30000,100000]:
truncateString = "TRUNCATE test_table_innodb"
truncateString2 = "TRUNCATE test_table_myisam"
truncateString3 = "TRUNCATE test_table_memory"
cur.execute(truncateString)
cur.execute(truncateString2)
cur.execute(truncateString3)
for x in xrange(theLength):
rand1 = random.random()
rand2 = random.random()
rand3 = random.random()
rand4 = random.random()
insertString = "INSERT INTO test_table_innodb (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
insertString2 = "INSERT INTO test_table_myisam (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
insertString3 = "INSERT INTO test_table_memory (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
cur.execute(insertString)
cur.execute(insertString2)
cur.execute(insertString3)
db.commit()
# Count and time the query
innodb_times.append( timeit.timeit('countRecords("test_table_innodb")', number=100, setup=setupString) )
myisam_times.append( timeit.timeit('countRecords("test_table_myisam")', number=100, setup=setupString) )
memory_times.append( timeit.timeit('countRecords("test_table_memory")', number=100, setup=setupString) )
3) 条件选择
询问：SELECT * FROM tbl WHERE value1<0.5 AND value2<0.5 AND value3<0.5 AND value4<0.5
结果：MyISAM 获胜
在这里，MyISAM 和内存的性能大致相同，在更大的表上比 InnoDB 高出约 50%。这是 MyISAM 的好处似乎被最大化的那种查询。
代码：
myisam_times = []
innodb_times = []
memory_times = []
# Define a function to perform conditional selects
def conditionalSelect(testTable):
selectString = "SELECT * FROM " + testTable + " WHERE value1 < 0.5 AND value2 < 0.5 AND value3 < 0.5 AND value4 < 0.5"
cur.execute(selectString)
setupString = "from __main__ import conditionalSelect"
# Truncate the tables and re-fill with a set amount of data
for theLength in [3,10,30,100,300,1000,3000,10000,30000,100000]:
truncateString = "TRUNCATE test_table_innodb"
truncateString2 = "TRUNCATE test_table_myisam"
truncateString3 = "TRUNCATE test_table_memory"
cur.execute(truncateString)
cur.execute(truncateString2)
cur.execute(truncateString3)
for x in xrange(theLength):
rand1 = random.random()
rand2 = random.random()
rand3 = random.random()
rand4 = random.random()
insertString = "INSERT INTO test_table_innodb (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
insertString2 = "INSERT INTO test_table_myisam (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
insertString3 = "INSERT INTO test_table_memory (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
cur.execute(insertString)
cur.execute(insertString2)
cur.execute(insertString3)
db.commit()
# Count and time the query
innodb_times.append( timeit.timeit('conditionalSelect("test_table_innodb")', number=100, setup=setupString) )
myisam_times.append( timeit.timeit('conditionalSelect("test_table_myisam")', number=100, setup=setupString) )
memory_times.append( timeit.timeit('conditionalSelect("test_table_memory")', number=100, setup=setupString) )
4) 子选择
结果：InnoDB 获胜
对于这个查询，我为子选择创建了一组额外的表。每一个都只是两列 BIGINT，一列有主键索引，另一列没有任何索引。由于表很大，我没有测试内存引擎。SQL 表创建命令是
CREATE TABLE
subselect_myisam
(
index_col bigint NOT NULL,
non_index_col bigint,
PRIMARY KEY (index_col)
)
ENGINE=MyISAM DEFAULT CHARSET=utf8;
在第二个表中，“MyISAM”再次替换了“InnoDB”。
在此查询中，我将选择表的大小保留为 1000000，而是改变子选择列的大小。
在这里，InnoDB 轻松获胜。在我们得到一个合理的大小表之后，两个引擎都随着子选择的大小线性缩放。索引加快了 MyISAM 命令的速度，但有趣的是对 InnoDB 速度几乎没有影响。子选择.png
代码：
myisam_times = []
innodb_times = []
myisam_times_2 = []
innodb_times_2 = []
def subSelectRecordsIndexed(testTable,testSubSelect):
selectString = "SELECT * FROM " + testTable + " WHERE index_col in ( SELECT index_col FROM " + testSubSelect + " )"
cur.execute(selectString)
setupString = "from __main__ import subSelectRecordsIndexed"
def subSelectRecordsNotIndexed(testTable,testSubSelect):
selectString = "SELECT * FROM " + testTable + " WHERE index_col in ( SELECT non_index_col FROM " + testSubSelect + " )"
cur.execute(selectString)
setupString2 = "from __main__ import subSelectRecordsNotIndexed"
# Truncate the old tables, and re-fill with 1000000 records
truncateString = "TRUNCATE test_table_innodb"
truncateString2 = "TRUNCATE test_table_myisam"
cur.execute(truncateString)
cur.execute(truncateString2)
lengthOfTable = 1000000
# Fill up the tables with random data
for x in xrange(lengthOfTable):
rand1 = random.random()
rand2 = random.random()
rand3 = random.random()
rand4 = random.random()
insertString = "INSERT INTO test_table_innodb (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
insertString2 = "INSERT INTO test_table_myisam (value1,value2,value3,value4) VALUES (" + str(rand1) + "," + str(rand2) + "," + str(rand3) + "," + str(rand4) + ")"
cur.execute(insertString)
cur.execute(insertString2)
for theLength in [3,10,30,100,300,1000,3000,10000,30000,100000]:
truncateString = "TRUNCATE subselect_innodb"
truncateString2 = "TRUNCATE subselect_myisam"
cur.execute(truncateString)
cur.execute(truncateString2)
# For each length, empty the table and re-fill it with random data
rand_sample = sorted(random.sample(xrange(lengthOfTable), theLength))
rand_sample_2 = random.sample(xrange(lengthOfTable), theLength)
for (the_value_1,the_value_2) in zip(rand_sample,rand_sample_2):
insertString = "INSERT INTO subselect_innodb (index_col,non_index_col) VALUES (" + str(the_value_1) + "," + str(the_value_2) + ")"
insertString2 = "INSERT INTO subselect_myisam (index_col,non_index_col) VALUES (" + str(the_value_1) + "," + str(the_value_2) + ")"
cur.execute(insertString)
cur.execute(insertString2)
db.commit()
# Finally, time the queries
innodb_times.append( timeit.timeit('subSelectRecordsIndexed("test_table_innodb","subselect_innodb")', number=100, setup=setupString) )
myisam_times.append( timeit.timeit('subSelectRecordsIndexed("test_table_myisam","subselect_myisam")', number=100, setup=setupString) )
innodb_times_2.append( timeit.timeit('subSelectRecordsNotIndexed("test_table_innodb","subselect_innodb")', number=100, setup=setupString2) )
myisam_times_2.append( timeit.timeit('subSelectRecordsNotIndexed("test_table_myisam","subselect_myisam")', number=100, setup=setupString2) )
我认为所有这一切的关键信息是，如果您真的关心速度，您需要对正在执行的查询进行基准测试，而不是对哪个引擎更合适做出任何假设。