summaryrefslogtreecommitdiff
path: root/test/perf/orm2010.py
blob: de63a36c84f947387477588b941bc117a09d7c6e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
import warnings
warnings.filterwarnings("ignore", r".*Decimal objects natively")  # noqa

# speed up cdecimal if available
try:
    import cdecimal
    import sys
    sys.modules['decimal'] = cdecimal
except ImportError:
    pass

from sqlalchemy import __version__
from sqlalchemy import Column, Integer, create_engine, ForeignKey, \
    String, Numeric

from sqlalchemy.orm import Session, relationship

from sqlalchemy.ext.declarative import declarative_base
import random
import os
from decimal import Decimal

Base = declarative_base()


class Employee(Base):
    __tablename__ = 'employee'

    id = Column(Integer, primary_key=True)
    name = Column(String(100), nullable=False)
    type = Column(String(50), nullable=False)

    __mapper_args__ = {'polymorphic_on': type}


class Boss(Employee):
    __tablename__ = 'boss'

    id = Column(Integer, ForeignKey('employee.id'), primary_key=True)
    golf_average = Column(Numeric)

    __mapper_args__ = {'polymorphic_identity': 'boss'}


class Grunt(Employee):
    __tablename__ = 'grunt'

    id = Column(Integer, ForeignKey('employee.id'), primary_key=True)
    savings = Column(Numeric)

    employer_id = Column(Integer, ForeignKey('boss.id'))

    employer = relationship("Boss", backref="employees",
                            primaryjoin=Boss.id == employer_id)

    __mapper_args__ = {'polymorphic_identity': 'grunt'}


if os.path.exists('orm2010.db'):
    os.remove('orm2010.db')
# use a file based database so that cursor.execute() has some
# palpable overhead.
engine = create_engine('sqlite:///orm2010.db')

Base.metadata.create_all(engine)

sess = Session(engine)


def runit(status, factor=1, query_runs=5):
    num_bosses = 100 * factor
    num_grunts = num_bosses * 100

    bosses = [
        Boss(
            name="Boss %d" % i,
            golf_average=Decimal(random.randint(40, 150))
        )
        for i in range(num_bosses)
    ]

    sess.add_all(bosses)
    status("Added %d boss objects" % num_bosses)

    grunts = [
        Grunt(
            name="Grunt %d" % i,
            savings=Decimal(random.randint(5000000, 15000000) / 100)
        )
        for i in range(num_grunts)
    ]
    status("Added %d grunt objects" % num_grunts)

    while grunts:
        # this doesn't associate grunts with bosses evenly,
        # just associates lots of them with a relatively small
        # handful of bosses
        batch_size = 100
        batch_num = (num_grunts - len(grunts)) / batch_size
        boss = sess.query(Boss).filter_by(name="Boss %d" % batch_num).first()
        for grunt in grunts[0:batch_size]:
            grunt.employer = boss

        grunts = grunts[batch_size:]

    sess.commit()
    status("Associated grunts w/ bosses and committed")

    # do some heavier reading
    for i in range(query_runs):
        status("Heavy query run #%d" % (i + 1))

        report = []

        # load all the Grunts, print a report with their name, stats,
        # and their bosses' stats.
        for grunt in sess.query(Grunt):
            report.append((
                            grunt.name,
                            grunt.savings,
                            grunt.employer.name,
                            grunt.employer.golf_average
                        ))

        sess.close()  # close out the session


def run_with_profile(runsnake=False, dump=False):
    import cProfile
    import pstats
    filename = "orm2010.profile"

    if os.path.exists("orm2010.profile"):
        os.remove("orm2010.profile")

    def status(msg):
        print(msg)

    cProfile.runctx('runit(status)', globals(), locals(), filename)
    stats = pstats.Stats(filename)

    counts_by_methname = dict((key[2],
                               stats.stats[key][0]) for key in stats.stats)

    print("SQLA Version: %s" % __version__)
    print("Total calls %d" % stats.total_calls)
    print("Total cpu seconds: %.2f" % stats.total_tt)
    print('Total execute calls: %d'
          % counts_by_methname["<method 'execute' of 'sqlite3.Cursor' "
                               "objects>"])
    print('Total executemany calls: %d'
          % counts_by_methname.get("<method 'executemany' of 'sqlite3.Cursor' "
                                   "objects>", 0))

    if dump:
        stats.sort_stats('time', 'calls')
        stats.print_stats()

    if runsnake:
        os.system("runsnake %s" % filename)


def run_with_time():
    import time
    now = time.time()

    def status(msg):
        print("%d - %s" % (time.time() - now, msg))

    runit(status, 10)
    print("Total time: %d" % (time.time() - now))


if __name__ == '__main__':
    import argparse

    parser = argparse.ArgumentParser()
    parser.add_argument('--profile', action='store_true',
                        help='run shorter test suite w/ cprofilng')
    parser.add_argument('--dump', action='store_true',
                        help='dump full call profile (implies --profile)')
    parser.add_argument('--runsnake', action='store_true',
                        help='invoke runsnakerun (implies --profile)')

    args = parser.parse_args()

    args.profile = args.profile or args.dump or args.runsnake

    if args.profile:
        run_with_profile(runsnake=args.runsnake, dump=args.dump)
    else:
        run_with_time()