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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
|
# flake8: noqa
import json
import logging
import os
import sys
from io import BytesIO
from io import StringIO
import py
import pytest
from freezegun import freeze_time
from pytest_benchmark import plugin
from pytest_benchmark.plugin import BenchmarkSession
from pytest_benchmark.plugin import pytest_benchmark_compare_machine_info
from pytest_benchmark.plugin import pytest_benchmark_generate_json
from pytest_benchmark.plugin import pytest_benchmark_group_stats
from pytest_benchmark.plugin import pytest_benchmark_scale_unit
from pytest_benchmark.session import PerformanceRegression
from pytest_benchmark.stats import normalize_stats
from pytest_benchmark.storage.file import FileStorage
from pytest_benchmark.utils import NAME_FORMATTERS
from pytest_benchmark.utils import DifferenceRegressionCheck
from pathlib import Path
from pytest_benchmark.utils import PercentageRegressionCheck
from pytest_benchmark.utils import get_machine_id
pytest_plugins = 'pytester'
THIS = Path(__file__)
STORAGE = THIS.with_suffix('')
JSON_DATA = json.loads(next(STORAGE.glob('0030_*.json')).read_text(encoding='utf8'))
JSON_DATA['machine_info'] = {'foo': 'bar'}
JSON_DATA['commit_info'] = {'foo': 'bar'}
list(normalize_stats(bench['stats']) for bench in JSON_DATA['benchmarks'])
class Namespace(object):
def __init__(self, **kwargs):
self.__dict__.update(kwargs)
def __getitem__(self, item):
return self.__dict__[item]
def getoption(self, item, default=None):
try:
return self[item]
except KeyError:
return default
class LooseFileLike(BytesIO):
def close(self):
value = self.getvalue()
super().close()
self.getvalue = lambda: value
class MockSession(BenchmarkSession):
def __init__(self, name_format):
self.histogram = True
self.verbose = False
self.quiet = False
self.benchmarks = []
self.performance_regressions = []
self.sort = 'min'
self.compare = '0001'
logger = logging.getLogger(__name__)
self.logger = Namespace(
debug=lambda *args, **_kwargs: logger.debug(*args),
info=lambda *args, **_kwargs: logger.info(*args),
warning=lambda *args, **_kwargs: logger.warning(*args),
error=lambda *args, **_kwargs: logger.error(*args),
)
self.machine_id = 'FoobarOS'
self.machine_info = {'foo': 'bar'}
self.save = self.autosave = self.json = False
self.name_format = NAME_FORMATTERS[name_format]
self.options = {
'min_rounds': 123,
'min_time': 234,
'max_time': 345,
'cprofile': False,
}
self.cprofile_sort_by = 'cumtime'
self.cprofile_loops = 1
self.cprofile_top = 25
self.compare_fail = []
self.config = Namespace(
hook=Namespace(
pytest_benchmark_scale_unit=pytest_benchmark_scale_unit,
pytest_benchmark_group_stats=pytest_benchmark_group_stats,
pytest_benchmark_generate_machine_info=lambda **kwargs: {'foo': 'bar'},
pytest_benchmark_update_machine_info=lambda **kwargs: None,
pytest_benchmark_compare_machine_info=pytest_benchmark_compare_machine_info,
pytest_benchmark_generate_json=pytest_benchmark_generate_json,
pytest_benchmark_update_json=lambda **kwargs: None,
pytest_benchmark_generate_commit_info=lambda **kwargs: {'foo': 'bar'},
pytest_benchmark_update_commit_info=lambda **kwargs: None,
)
)
self.storage = FileStorage(str(STORAGE), default_machine_id=get_machine_id(), logger=self.logger)
self.group_by = 'group'
self.columns = ['min', 'max', 'mean', 'stddev', 'median', 'iqr', 'outliers', 'rounds', 'iterations', 'ops']
for bench_file, data in reversed(list(self.storage.load('[0-9][0-9][0-9][0-9]_*'))):
self.benchmarks.extend(
Namespace(
as_dict=lambda include_data=False, stats=True, flat=False, _bench=bench, cprofile='cumtime': dict(
_bench, **_bench['stats']
)
if flat
else dict(_bench),
name=bench['name'],
fullname=bench['fullname'],
group=bench['group'],
options=bench['options'],
has_error=False,
params=None,
**bench['stats'],
)
for bench in data['benchmarks']
)
break
try:
text_type = unicode
except NameError:
text_type = str
def force_text(text):
if isinstance(text, text_type):
return text
else:
return text.decode('utf-8')
def force_bytes(text):
if isinstance(text, text_type):
return text.encode('utf-8')
else:
return text
@pytest.fixture(params=['short', 'normal', 'long', 'trial'])
def name_format(request):
return request.param
@pytest.fixture
def sess(request, name_format):
return MockSession(name_format)
def make_logger(sess):
output = StringIO()
sess.logger = sess.storage.logger = Namespace(
warning=lambda text, **opts: output.write(force_text(text) + '\n'),
info=lambda text, **opts: output.write(force_text(text) + '\n'),
error=lambda text: output.write(force_text(text) + '\n'),
)
return output
def test_rendering(sess):
output = make_logger(sess)
sess.histogram = os.path.join('docs', 'sample')
sess.compare = '*/*'
sess.sort = 'name'
sess.handle_loading()
sess.finish()
sess.display(
Namespace(
ensure_newline=lambda: None,
write_line=lambda line, **opts: output.write(force_text(line) + '\n'),
write=lambda text, **opts: output.write(force_text(text)),
rewrite=lambda text, **opts: output.write(force_text(text)),
)
)
def test_regression_checks(sess, name_format):
output = make_logger(sess)
sess.handle_loading()
sess.performance_regressions = []
sess.compare_fail = [PercentageRegressionCheck('stddev', 5), DifferenceRegressionCheck('max', 0.000001)]
sess.finish()
pytest.raises(
PerformanceRegression,
sess.display,
Namespace(
ensure_newline=lambda: None,
write_line=lambda line, **opts: output.write(force_text(line) + '\n'),
write=lambda text, **opts: output.write(force_text(text)),
rewrite=lambda text, **opts: output.write(force_text(text)),
),
)
print(output.getvalue())
assert (
sess.performance_regressions
== {
'normal': [
(
'test_xfast_parametrized[0] (0001_b87b9aa)',
"Field 'stddev' has failed PercentageRegressionCheck: 23.331641765 > 5.000000000",
),
(
'test_xfast_parametrized[0] (0001_b87b9aa)',
"Field 'max' has failed DifferenceRegressionCheck: 0.000001843 > 0.000001000",
),
],
'short': [
('xfast_parametrized[0] (0001)', "Field 'stddev' has failed PercentageRegressionCheck: 23.331641765 > 5.000000000"),
('xfast_parametrized[0] (0001)', "Field 'max' has failed DifferenceRegressionCheck: 0.000001843 > 0.000001000"),
],
'long': [
(
'tests/test_normal.py::test_xfast_parametrized[0] (0001_b87b9aae14ff14a7887a6bbaa9731b9a8760555d_20150814_190343_uncommitted-changes)',
"Field 'stddev' has failed PercentageRegressionCheck: 23.331641765 > 5.000000000",
),
(
'tests/test_normal.py::test_xfast_parametrized[0] (0001_b87b9aae14ff14a7887a6bbaa9731b9a8760555d_20150814_190343_uncommitted-changes)',
"Field 'max' has failed DifferenceRegressionCheck: 0.000001843 > 0.000001000",
),
],
'trial': [
('0001', "Field 'stddev' has failed PercentageRegressionCheck: 23.331641765 > 5.000000000"),
('0001', "Field 'max' has failed DifferenceRegressionCheck: 0.000001843 > 0.000001000"),
],
}[name_format]
)
output = make_logger(sess)
pytest.raises(PerformanceRegression, sess.check_regressions)
print(output.getvalue())
assert (
output.getvalue()
== {
'short': """Performance has regressed:
\txfast_parametrized[0] (0001) - Field 'stddev' has failed PercentageRegressionCheck: 23.331641765 > 5.000000000
\txfast_parametrized[0] (0001) - Field 'max' has failed DifferenceRegressionCheck: 0.000001843 > 0.000001000
""",
'normal': """Performance has regressed:
\ttest_xfast_parametrized[0] (0001_b87b9aa) - Field 'stddev' has failed PercentageRegressionCheck: 23.331641765 > 5.000000000
\ttest_xfast_parametrized[0] (0001_b87b9aa) - Field 'max' has failed DifferenceRegressionCheck: 0.000001843 > 0.000001000
""",
'long': """Performance has regressed:
\ttests/test_normal.py::test_xfast_parametrized[0] (0001_b87b9aae14ff14a7887a6bbaa9731b9a8760555d_20150814_190343_uncommitted-changes) - Field 'stddev' has failed PercentageRegressionCheck: 23.331641765 > 5.000000000
\ttests/test_normal.py::test_xfast_parametrized[0] (0001_b87b9aae14ff14a7887a6bbaa9731b9a8760555d_20150814_190343_uncommitted-changes) - Field 'max' has failed DifferenceRegressionCheck: 0.000001843 > 0.000001000
""",
'trial': """Performance has regressed:
\t0001 - Field 'stddev' has failed PercentageRegressionCheck: 23.331641765 > 5.000000000
\t0001 - Field 'max' has failed DifferenceRegressionCheck: 0.000001843 > 0.000001000
""",
}[name_format]
)
@pytest.mark.skipif(sys.version_info[:2] < (2, 7), reason='Something weird going on, see: https://bugs.python.org/issue4482')
def test_regression_checks_inf(sess, name_format):
output = make_logger(sess)
sess.compare = '0002'
sess.handle_loading()
sess.performance_regressions = []
sess.compare_fail = [PercentageRegressionCheck('stddev', 5), DifferenceRegressionCheck('max', 0.000001)]
sess.finish()
pytest.raises(
PerformanceRegression,
sess.display,
Namespace(
ensure_newline=lambda: None,
write_line=lambda line, **opts: output.write(force_text(line) + '\n'),
write=lambda text, **opts: output.write(force_text(text)),
rewrite=lambda text, **opts: output.write(force_text(text)),
),
)
print(output.getvalue())
assert (
sess.performance_regressions
== {
'normal': [
('test_xfast_parametrized[0] (0002_b87b9aa)', "Field 'stddev' has failed PercentageRegressionCheck: inf > 5.000000000"),
(
'test_xfast_parametrized[0] (0002_b87b9aa)',
"Field 'max' has failed DifferenceRegressionCheck: 0.000005551 > 0.000001000",
),
],
'short': [
('xfast_parametrized[0] (0002)', "Field 'stddev' has failed PercentageRegressionCheck: inf > 5.000000000"),
('xfast_parametrized[0] (0002)', "Field 'max' has failed DifferenceRegressionCheck: 0.000005551 > 0.000001000"),
],
'long': [
(
'tests/test_normal.py::test_xfast_parametrized[0] '
'(0002_b87b9aae14ff14a7887a6bbaa9731b9a8760555d_20150814_190348_uncommitted-changes)',
"Field 'stddev' has failed PercentageRegressionCheck: inf > 5.000000000",
),
(
'tests/test_normal.py::test_xfast_parametrized[0] '
'(0002_b87b9aae14ff14a7887a6bbaa9731b9a8760555d_20150814_190348_uncommitted-changes)',
"Field 'max' has failed DifferenceRegressionCheck: 0.000005551 > " '0.000001000',
),
],
'trial': [
('0002', "Field 'stddev' has failed PercentageRegressionCheck: inf > 5.000000000"),
('0002', "Field 'max' has failed DifferenceRegressionCheck: 0.000005551 > 0.000001000"),
],
}[name_format]
)
output = make_logger(sess)
pytest.raises(PerformanceRegression, sess.check_regressions)
print(output.getvalue())
assert (
output.getvalue()
== {
'short': """Performance has regressed:
\txfast_parametrized[0] (0002) - Field 'stddev' has failed PercentageRegressionCheck: inf > 5.000000000
\txfast_parametrized[0] (0002) - Field 'max' has failed DifferenceRegressionCheck: 0.000005551 > 0.000001000
""",
'normal': """Performance has regressed:
\ttest_xfast_parametrized[0] (0002_b87b9aa) - Field 'stddev' has failed PercentageRegressionCheck: inf > 5.000000000
\ttest_xfast_parametrized[0] (0002_b87b9aa) - Field 'max' has failed DifferenceRegressionCheck: 0.000005551 > 0.000001000
""",
'long': """Performance has regressed:
\ttests/test_normal.py::test_xfast_parametrized[0] (0002_b87b9aae14ff14a7887a6bbaa9731b9a8760555d_20150814_190348_uncommitted-changes) - Field 'stddev' has failed PercentageRegressionCheck: inf > 5.000000000
\ttests/test_normal.py::test_xfast_parametrized[0] (0002_b87b9aae14ff14a7887a6bbaa9731b9a8760555d_20150814_190348_uncommitted-changes) - Field 'max' has failed DifferenceRegressionCheck: 0.000005551 > 0.000001000
""",
'trial': """Performance has regressed:
\t0002 - Field 'stddev' has failed PercentageRegressionCheck: inf > 5.000000000
\t0002 - Field 'max' has failed DifferenceRegressionCheck: 0.000005551 > 0.000001000
""",
}[name_format]
)
def test_compare_1(sess, LineMatcher):
output = make_logger(sess)
sess.handle_loading()
sess.finish()
sess.display(
Namespace(
ensure_newline=lambda: None,
write_line=lambda line, **opts: output.write(force_text(line) + '\n'),
write=lambda text, **opts: output.write(force_text(text)),
rewrite=lambda text, **opts: output.write(force_text(text)),
)
)
print(output.getvalue())
LineMatcher(output.getvalue().splitlines()).fnmatch_lines(
[
'Benchmark machine_info is different. Current: {"foo": "bar"} VS saved: {"machine": "x86_64", "node": "minibox", "processor": "x86_64", "python_compiler": "GCC 4.6.3", "python_implementation": "CPython", "python_version": "2.7.3", "release": "3.13.0-55-generic", "system": "Linux"} (location: tests/test_storage).',
'Comparing against benchmarks from: 0001_b87b9aae14ff14a7887a6bbaa9731b9a8760555d_20150814_190343_uncommitted' '-changes.json',
'',
'*------------------------------------------------------------------------ benchmark: 2 tests -----------------------------------------------------------------------*',
'Name (time in ns) * Min * Max Mean StdDev Median IQR Outliers Rounds Iterations OPS (Mops/s) *',
'-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------*',
'*0001* 217.3145 (1.0) 11*447.3891 (1.0) 262.2408 (1.00) 214.0442 (1.0) 220.1664 (1.00) 38.2154 (2.03) 90;1878 9987 418 3.8133 (1.00)*',
'*NOW* 217.9511 (1.00) 13*290.0380 (1.16) 261.2051 (1.0) 263.9842 (1.23) 220.1638 (1.0) 18.8080 (1.0) 160;1726 9710 431 3.8284 (1.0)*',
'--------------------------------------------------------------------------------------------------------------------------------------------------------------------*',
'Legend:',
' Outliers: 1 Standard Deviation from Mean; 1.5 IQR (InterQuartile Range) from 1st Quartile and 3rd Quartile.',
' OPS: Operations Per Second, computed as 1 / Mean',
]
)
def test_compare_2(sess, LineMatcher):
output = make_logger(sess)
sess.compare = '0002'
sess.handle_loading()
sess.finish()
sess.display(
Namespace(
ensure_newline=lambda: None,
write_line=lambda line, **opts: output.write(force_text(line) + '\n'),
section=lambda line, **opts: output.write(force_text(line) + '\n'),
write=lambda text, **opts: output.write(force_text(text)),
rewrite=lambda text, **opts: output.write(force_text(text)),
)
)
print(output.getvalue())
LineMatcher(output.getvalue().splitlines()).fnmatch_lines(
[
'Benchmark machine_info is different. Current: {"foo": "bar"} VS saved: {"machine": "x86_64", "node": "minibox", "processor": "x86_64", "python_compiler": "GCC 4.6.3", "python_implementation": "CPython", "python_version": "2.7.3", "release": "3.13.0-55-generic", "system": "Linux"} (location: tests/test_storage).',
'Comparing against benchmarks from: 0002_b87b9aae14ff14a7887a6bbaa9731b9a8760555d_20150814_190348_uncommitted-changes.json',
'',
'*------------------------------------------------------------------------ benchmark: 2 tests -----------------------------------------------------------------------*',
'Name (time in ns) * Min *Max Mean StdDev Median IQR Outliers Rounds Iterations OPS (Mops/s)*',
'--------------------------------------------------------------------------------------------------------------------------------------------------------------------*',
'*0002* 216.9028 (1.0) 7*739.2997 (1.0) 254.0585 (1.0) 0.0000 (1.0) 219.8103 (1.0) 27.3309 (1.45) 235;1688 11009 410 3.9361 (1.0)*',
'*NOW* 217.9511 (1.00) 13*290.0380 (1.72) 261.2051 (1.03) 263.9842 (inf) 220.1638 (1.00) 18.8080 (1.0) 160;1726 9710 431 3.8284 (0.97)*',
'--------------------------------------------------------------------------------------------------------------------------------------------------------------------*',
'Legend:',
' Outliers: 1 Standard Deviation from Mean; 1.5 IQR (InterQuartile Range) from 1st Quartile and 3rd Quartile.',
' OPS: Operations Per Second, computed as 1 / Mean',
]
)
@freeze_time('2015-08-15T00:04:18.687119')
def test_save_json(sess, tmpdir, monkeypatch):
monkeypatch.setattr(plugin, '__version__', '2.5.0')
sess.save = False
sess.autosave = False
sess.json = LooseFileLike()
sess.save_data = False
sess.handle_saving()
assert tmpdir.listdir() == []
assert json.loads(sess.json.getvalue().decode()) == JSON_DATA
@freeze_time('2015-08-15T00:04:18.687119')
def test_save_with_name(sess, tmpdir, monkeypatch):
monkeypatch.setattr(plugin, '__version__', '2.5.0')
sess.save = 'foobar'
sess.autosave = True
sess.json = None
sess.save_data = False
sess.storage.path = Path(str(tmpdir))
sess.handle_saving()
files = list(Path(str(tmpdir)).rglob('*.json'))
print(files)
assert len(files) == 1
assert json.loads(files[0].read_text(encoding='utf8')) == JSON_DATA
@freeze_time('2015-08-15T00:04:18.687119')
def test_save_no_name(sess, tmpdir, monkeypatch):
monkeypatch.setattr(plugin, '__version__', '2.5.0')
sess.save = True
sess.autosave = True
sess.json = None
sess.save_data = False
sess.storage.path = Path(str(tmpdir))
sess.handle_saving()
files = list(Path(str(tmpdir)).rglob('*.json'))
assert len(files) == 1
assert json.loads(files[0].read_text(encoding='utf8')) == JSON_DATA
@freeze_time('2015-08-15T00:04:18.687119')
def test_save_with_error(sess, tmpdir, monkeypatch):
monkeypatch.setattr(plugin, '__version__', '2.5.0')
sess.save = True
sess.autosave = True
sess.json = None
sess.save_data = False
sess.storage.path = Path(str(tmpdir))
for bench in sess.benchmarks:
bench.has_error = True
sess.handle_saving()
files = list(Path(str(tmpdir)).rglob('*.json'))
assert len(files) == 1
assert json.loads(files[0].read_text(encoding='utf8')) == {
'benchmarks': [],
'commit_info': {'foo': 'bar'},
'datetime': '2015-08-15T00:04:18.687119+00:00',
'machine_info': {'foo': 'bar'},
'version': '2.5.0',
}
@freeze_time('2015-08-15T00:04:18.687119')
def test_autosave(sess, tmpdir, monkeypatch):
monkeypatch.setattr(plugin, '__version__', '2.5.0')
sess.save = False
sess.autosave = True
sess.json = None
sess.save_data = False
sess.storage.path = Path(str(tmpdir))
sess.handle_saving()
files = list(Path(str(tmpdir)).rglob('*.json'))
assert len(files) == 1
assert json.loads(files[0].read_text(encoding='utf8')) == JSON_DATA
|
