ORM基本上不是用于高性能批量插入的-这是SQLAlchemy除了将ORM作为一流组件之外还提供Core的全部原因。
对于快速批量插入的用例,ORM所基于的SQL生成和执行系统是Core的一部分。直接使用该系统,我们可以产生与直接使用原始数据库API相比具有竞争力的INSERT。
另外,SQLAlchemy ORM提供了Bulk Operations方法套件,该套件提供了到工作单元过程各部分的挂钩,以便发出基于ORM的自动化程度较低的Core级INSERT和UPDATE构造。
下面的示例说明了基于时间的测试,该测试针对从自动程度最高到最少的几种不同的行插入方法。使用cPython 2.7,可以观察到运行时:
classics-MacBook-Pro:sqlalchemy classic$ python test.py
SQLAlchemy ORM: Total time for 100000 records 12.0471920967 secs
SQLAlchemy ORM pk given: Total time for 100000 records 7.06283402443 secs
SQLAlchemy ORM bulk_save_objects(): Total time for 100000 records 0.856323003769 secs
SQLAlchemy Core: Total time for 100000 records 0.485800027847 secs
sqlite3: Total time for 100000 records 0.487842082977 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())
engine = None
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 xrange(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 xrange(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_orm_bulk_insert(n=100000):
init_sqlalchemy()
t0 = time.time()
n1 = n
while n1 > 0:
n1 = n1 - 10000
DBSession.bulk_insert_mappings(
Customer,
[
dict(name="NAME " + str(i))
for i in xrange(min(10000, n1))
]
)
DBSession.commit()
print(
"SQLAlchemy ORM bulk_save_objects(): 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 xrange(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 xrange(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_orm_bulk_insert(100000)
test_sqlalchemy_core(100000)
test_sqlite3(100000)