85

为什么这个简单的测试用例使用 SQLAlchemy 插入 100,000 行比直接使用 sqlite3 驱动程序慢 25 倍？我在现实世界的应用程序中看到了类似的减速。难道我做错了什么？

#!/usr/bin/env python
# Why is SQLAlchemy with SQLite so slow?
# Output from this program:
# SqlAlchemy: Total time for 100000 records 10.74 secs
# sqlite3:    Total time for 100000 records  0.40 secs


import time
import sqlite3

from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy import Column, Integer, String,  create_engine 
from sqlalchemy.orm import scoped_session, sessionmaker

Base = declarative_base()
DBSession = scoped_session(sessionmaker())

class Customer(Base):
    __tablename__ = "customer"
    id = Column(Integer, primary_key=True)
    name = Column(String(255))

def init_sqlalchemy(dbname = 'sqlite:///sqlalchemy.db'):
    engine  = create_engine(dbname, echo=False)
    DBSession.configure(bind=engine, autoflush=False, expire_on_commit=False)
    Base.metadata.drop_all(engine)
    Base.metadata.create_all(engine)

def test_sqlalchemy(n=100000):
    init_sqlalchemy()
    t0 = time.time()
    for i in range(n):
        customer = Customer()
        customer.name = 'NAME ' + str(i)
        DBSession.add(customer)
    DBSession.commit()
    print "SqlAlchemy: Total time for " + str(n) + " records " + str(time.time() - t0) + " secs"

def init_sqlite3(dbname):
    conn = sqlite3.connect(dbname)
    c = conn.cursor()
    c.execute("DROP TABLE IF EXISTS customer")
    c.execute("CREATE TABLE customer (id INTEGER NOT NULL, name VARCHAR(255), PRIMARY KEY(id))")
    conn.commit()
    return conn

def test_sqlite3(n=100000, dbname = 'sqlite3.db'):
    conn = init_sqlite3(dbname)
    c = conn.cursor()
    t0 = time.time()
    for i in range(n):
        row = ('NAME ' + str(i),)
        c.execute("INSERT INTO customer (name) VALUES (?)", row)
    conn.commit()
    print "sqlite3: Total time for " + str(n) + " records " + str(time.time() - t0) + " sec"

if __name__ == '__main__':
    test_sqlalchemy(100000)
    test_sqlite3(100000)

我尝试了许多变体（请参阅http://pastebin.com/zCmzDraU）

4

3 回答 3

194

SQLAlchemy ORM在同步对数据库的更改时使用工作单元模式。这种模式远远超出了简单的数据“插入”。它包括使用属性检测系统接收分配给对象的属性，该系统跟踪对象所做的更改，包括在身份映射中跟踪插入的所有行其效果是，对于每一行 SQLAlchemy 必须检索其“最后插入的 id”（如果尚未给出），并且还涉及根据需要对要插入的行进行扫描和排序以查找依赖项。对象还需要进行相当程度的簿记，以保持所有这些运行，对于大量行来说，一次会产生大量的时间花费在大型数据结构上，因此最好将它们分块。

基本上，工作单元是高度自动化的，目的是自动化将复杂对象图持久化到关系数据库中的任务，而无需显式持久化代码，这种自动化是有代价的。

所以 ORM 基本上不适合高性能批量插入。这就是为什么 SQLAlchemy 有两个独立的库的全部原因，如果你查看http://docs.sqlalchemy.org/en/latest/index.html你会注意到索引页面有两个不同的部分 -一个用于 ORM，一个用于核心。如果不了解两者，就无法有效地使用 SQLAlchemy。

对于快速批量插入的用例，SQLAlchemy 提供了核心，即 ORM 在其之上构建的 SQL 生成和执行系统。有效地使用这个系统，我们可以生成一个与原始 SQLite 版本竞争的 INSERT。下面的脚本说明了这一点，以及一个预先分配主键标识符的 ORM 版本，以便 ORM 可以使用 executemany() 插入行。两个 ORM 版本都一次将刷新分块为 1000 条记录，这会对性能产生重大影响。

这里观察到的运行时是：

SqlAlchemy ORM: Total time for 100000 records 16.4133379459 secs
SqlAlchemy ORM pk given: Total time for 100000 records 9.77570986748 secs
SqlAlchemy Core: Total time for 100000 records 0.568737983704 secs
sqlite3: Total time for 100000 records 0.595796823502 sec

脚本：

import time
import sqlite3

from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy import Column, Integer, String,  create_engine
from sqlalchemy.orm import scoped_session, sessionmaker

Base = declarative_base()
DBSession = scoped_session(sessionmaker())

class Customer(Base):
    __tablename__ = "customer"
    id = Column(Integer, primary_key=True)
    name = Column(String(255))

def init_sqlalchemy(dbname = 'sqlite:///sqlalchemy.db'):
    global engine
    engine = create_engine(dbname, echo=False)
    DBSession.remove()
    DBSession.configure(bind=engine, autoflush=False, expire_on_commit=False)
    Base.metadata.drop_all(engine)
    Base.metadata.create_all(engine)

def test_sqlalchemy_orm(n=100000):
    init_sqlalchemy()
    t0 = time.time()
    for i in range(n):
        customer = Customer()
        customer.name = 'NAME ' + str(i)
        DBSession.add(customer)
        if i % 1000 == 0:
            DBSession.flush()
    DBSession.commit()
    print "SqlAlchemy ORM: Total time for " + str(n) + " records " + str(time.time() - t0) + " secs"

def test_sqlalchemy_orm_pk_given(n=100000):
    init_sqlalchemy()
    t0 = time.time()
    for i in range(n):
        customer = Customer(id=i+1, name="NAME " + str(i))
        DBSession.add(customer)
        if i % 1000 == 0:
            DBSession.flush()
    DBSession.commit()
    print "SqlAlchemy ORM pk given: Total time for " + str(n) + " records " + str(time.time() - t0) + " secs"

def test_sqlalchemy_core(n=100000):
    init_sqlalchemy()
    t0 = time.time()
    engine.execute(
        Customer.__table__.insert(),
        [{"name":'NAME ' + str(i)} for i in range(n)]
    )
    print "SqlAlchemy Core: Total time for " + str(n) + " records " + str(time.time() - t0) + " secs"

def init_sqlite3(dbname):
    conn = sqlite3.connect(dbname)
    c = conn.cursor()
    c.execute("DROP TABLE IF EXISTS customer")
    c.execute("CREATE TABLE customer (id INTEGER NOT NULL, name VARCHAR(255), PRIMARY KEY(id))")
    conn.commit()
    return conn

def test_sqlite3(n=100000, dbname = 'sqlite3.db'):
    conn = init_sqlite3(dbname)
    c = conn.cursor()
    t0 = time.time()
    for i in range(n):
        row = ('NAME ' + str(i),)
        c.execute("INSERT INTO customer (name) VALUES (?)", row)
    conn.commit()
    print "sqlite3: Total time for " + str(n) + " records " + str(time.time() - t0) + " sec"

if __name__ == '__main__':
    test_sqlalchemy_orm(100000)
    test_sqlalchemy_orm_pk_given(100000)
    test_sqlalchemy_core(100000)
    test_sqlite3(100000)

另见： http ://docs.sqlalchemy.org/en/latest/faq/performance.html

于 2012-08-02T01:17:27.380 回答
24

@zzzeek 的出色回答。对于那些想知道查询的相同统计信息的人，我稍微修改了@zzzeek 代码以在插入它们后立即查询这些相同的记录，然后将这些记录转换为字典列表。

这是结果

SqlAlchemy ORM: Total time for 100000 records 11.9210000038 secs
SqlAlchemy ORM query: Total time for 100000 records 2.94099998474 secs
SqlAlchemy ORM pk given: Total time for 100000 records 7.51800012589 secs
SqlAlchemy ORM pk given query: Total time for 100000 records 3.07699990273 secs
SqlAlchemy Core: Total time for 100000 records 0.431999921799 secs
SqlAlchemy Core query: Total time for 100000 records 0.389000177383 secs
sqlite3: Total time for 100000 records 0.459000110626 sec
sqlite3 query: Total time for 100000 records 0.103999853134 secs

有趣的是，使用裸 sqlite3 进行查询仍然比使用 SQLAlchemy Core 快 3 倍。我想这就是你为返回一个ResultProxy而不是一个裸的 sqlite3 行而付出的代价。

SQLAlchemy Core 比使用 ORM 快大约 8 倍。所以无论如何使用 ORM 查询都会慢很多。

这是我使用的代码：

import time
import sqlite3

from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy import Column, Integer, String,  create_engine
from sqlalchemy.orm import scoped_session, sessionmaker
from sqlalchemy.sql import select

Base = declarative_base()
DBSession = scoped_session(sessionmaker())

class Customer(Base):
    __tablename__ = "customer"
    id = Column(Integer, primary_key=True)
    name = Column(String(255))

def init_sqlalchemy(dbname = 'sqlite:///sqlalchemy.db'):
    global engine
    engine = create_engine(dbname, echo=False)
    DBSession.remove()
    DBSession.configure(bind=engine, autoflush=False, expire_on_commit=False)
    Base.metadata.drop_all(engine)
    Base.metadata.create_all(engine)

def test_sqlalchemy_orm(n=100000):
    init_sqlalchemy()
    t0 = time.time()
    for i in range(n):
        customer = Customer()
        customer.name = 'NAME ' + str(i)
        DBSession.add(customer)
        if i % 1000 == 0:
            DBSession.flush()
    DBSession.commit()
    print "SqlAlchemy ORM: Total time for " + str(n) + " records " + str(time.time() - t0) + " secs"
    t0 = time.time()
    q = DBSession.query(Customer)
    dict = [{'id':r.id, 'name':r.name} for r in q]
    print "SqlAlchemy ORM query: Total time for " + str(len(dict)) + " records " + str(time.time() - t0) + " secs"


def test_sqlalchemy_orm_pk_given(n=100000):
    init_sqlalchemy()
    t0 = time.time()
    for i in range(n):
        customer = Customer(id=i+1, name="NAME " + str(i))
        DBSession.add(customer)
        if i % 1000 == 0:
            DBSession.flush()
    DBSession.commit()
    print "SqlAlchemy ORM pk given: Total time for " + str(n) + " records " + str(time.time() - t0) + " secs"
    t0 = time.time()
    q = DBSession.query(Customer)
    dict = [{'id':r.id, 'name':r.name} for r in q]
    print "SqlAlchemy ORM pk given query: Total time for " + str(len(dict)) + " records " + str(time.time() - t0) + " secs"

def test_sqlalchemy_core(n=100000):
    init_sqlalchemy()
    t0 = time.time()
    engine.execute(
        Customer.__table__.insert(),
        [{"name":'NAME ' + str(i)} for i in range(n)]
    )
    print "SqlAlchemy Core: Total time for " + str(n) + " records " + str(time.time() - t0) + " secs"
    conn = engine.connect()
    t0 = time.time()
    sql = select([Customer.__table__])
    q = conn.execute(sql)
    dict = [{'id':r[0], 'name':r[0]} for r in q]
    print "SqlAlchemy Core query: Total time for " + str(len(dict)) + " records " + str(time.time() - t0) + " secs"

def init_sqlite3(dbname):
    conn = sqlite3.connect(dbname)
    c = conn.cursor()
    c.execute("DROP TABLE IF EXISTS customer")
    c.execute("CREATE TABLE customer (id INTEGER NOT NULL, name VARCHAR(255), PRIMARY KEY(id))")
    conn.commit()
    return conn

def test_sqlite3(n=100000, dbname = 'sqlite3.db'):
    conn = init_sqlite3(dbname)
    c = conn.cursor()
    t0 = time.time()
    for i in range(n):
        row = ('NAME ' + str(i),)
        c.execute("INSERT INTO customer (name) VALUES (?)", row)
    conn.commit()
    print "sqlite3: Total time for " + str(n) + " records " + str(time.time() - t0) + " sec"
    t0 = time.time()
    q = conn.execute("SELECT * FROM customer").fetchall()
    dict = [{'id':r[0], 'name':r[0]} for r in q]
    print "sqlite3 query: Total time for " + str(len(dict)) + " records " + str(time.time() - t0) + " secs"


if __name__ == '__main__':
    test_sqlalchemy_orm(100000)
    test_sqlalchemy_orm_pk_given(100000)
    test_sqlalchemy_core(100000)
    test_sqlite3(100000)

我还测试了没有将查询结果转换为 dicts 并且统计信息相似：

SqlAlchemy ORM: Total time for 100000 records 11.9189999104 secs
SqlAlchemy ORM query: Total time for 100000 records 2.78500008583 secs
SqlAlchemy ORM pk given: Total time for 100000 records 7.67199993134 secs
SqlAlchemy ORM pk given query: Total time for 100000 records 2.94000005722 secs
SqlAlchemy Core: Total time for 100000 records 0.43700003624 secs
SqlAlchemy Core query: Total time for 100000 records 0.131000041962 secs
sqlite3: Total time for 100000 records 0.500999927521 sec
sqlite3 query: Total time for 100000 records 0.0859999656677 secs

与 ORM 相比，使用 SQLAlchemy Core 查询大约快 20 倍。

需要注意的是，这些测试非常肤浅，不应过于认真。我可能会遗漏一些可以完全改变统计数据的明显技巧。

衡量性能改进的最佳方法是直接在您自己的应用程序中。不要把我的统计数据视为理所当然。

于 2014-02-23T12:33:13.573 回答
0

我会尝试插入表达式测试，然后进行基准测试。

由于 OR 映射器开销，它可能仍然会更慢，但我希望不会那么慢。

您介意尝试并发布结果吗？这是非常有趣的东西。

于 2012-08-02T00:42:27.567 回答