forked from aws/sagemaker-python-sdk
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtest_profiler.py
More file actions
476 lines (403 loc) · 19.2 KB
/
test_profiler.py
File metadata and controls
476 lines (403 loc) · 19.2 KB
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
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License"). You
# may not use this file except in compliance with the License. A copy of
# the License is located at
#
# http://aws.amazon.com/apache2.0/
#
# or in the "license" file accompanying this file. This file is
# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
# ANY KIND, either express or implied. See the License for the specific
# language governing permissions and limitations under the License.
from __future__ import absolute_import
import os
import re
import time
import uuid
import pytest
from sagemaker.debugger import (
DebuggerHookConfig,
FrameworkProfile,
get_rule_container_image_uri,
ProfilerConfig,
ProfilerRule,
Rule,
rule_configs,
)
from sagemaker.debugger.metrics_config import DetailedProfilingConfig
from sagemaker.mxnet.estimator import MXNet
from sagemaker.utils import unique_name_from_base
from tests.integ import DATA_DIR, TRAINING_DEFAULT_TIMEOUT_MINUTES
from tests.integ.timeout import timeout
TRAINING_STATUS = "Training"
ALGO_PULL_FINISHED_MESSAGE = "Training image download completed. Training in progress."
def _wait_until_training_can_be_updated(sagemaker_client, job_name, poll=5):
ready_for_updating = _check_secondary_status(sagemaker_client, job_name)
while not ready_for_updating:
time.sleep(poll)
ready_for_updating = _check_secondary_status(sagemaker_client, job_name)
def _check_secondary_status(sagemaker_client, job_name):
desc = sagemaker_client.describe_training_job(TrainingJobName=job_name)
secondary_status_transitions = desc.get("SecondaryStatusTransitions")
if not secondary_status_transitions:
return False
latest_secondary_status_transition = secondary_status_transitions[-1]
secondary_status = latest_secondary_status_transition.get("Status")
status_message = latest_secondary_status_transition.get("StatusMessage")
return TRAINING_STATUS == secondary_status and ALGO_PULL_FINISHED_MESSAGE == status_message
def test_mxnet_with_default_profiler_config_and_profiler_rule(
sagemaker_session,
mxnet_training_latest_version,
mxnet_training_latest_py_version,
cpu_instance_type,
):
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist_gluon.py")
data_path = os.path.join(DATA_DIR, "mxnet_mnist")
mx = MXNet(
entry_point=script_path,
role="SageMakerRole",
framework_version=mxnet_training_latest_version,
py_version=mxnet_training_latest_py_version,
instance_count=1,
instance_type=cpu_instance_type,
sagemaker_session=sagemaker_session,
)
train_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "train"), key_prefix="integ-test-data/mxnet_mnist/train"
)
test_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "test"), key_prefix="integ-test-data/mxnet_mnist/test"
)
training_job_name = unique_name_from_base("test-profiler-mxnet-training")
mx.fit(
inputs={"train": train_input, "test": test_input},
job_name=training_job_name,
wait=False,
)
job_description = mx.latest_training_job.describe()
assert (
job_description["ProfilerConfig"]
== ProfilerConfig(
s3_output_path=mx.output_path, system_monitor_interval_millis=500
)._to_request_dict()
)
assert job_description.get("ProfilingStatus") == "Enabled"
profiler_rule_configuration = job_description.get("ProfilerRuleConfigurations")[0]
assert re.match(r"ProfilerReport-\d*", profiler_rule_configuration["RuleConfigurationName"])
assert profiler_rule_configuration["RuleEvaluatorImage"] == get_rule_container_image_uri(
mx.sagemaker_session.boto_region_name
)
assert profiler_rule_configuration["RuleParameters"] == {"rule_to_invoke": "ProfilerReport"}
with pytest.raises(ValueError) as error:
mx.enable_default_profiling()
assert "Debugger monitoring is already enabled." in str(error)
def test_mxnet_with_custom_profiler_config_then_update_rule_and_config(
sagemaker_session,
mxnet_training_latest_version,
mxnet_training_latest_py_version,
cpu_instance_type,
):
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
profiler_config = ProfilerConfig(
s3_output_path=f"s3://{sagemaker_session.default_bucket()}/{str(uuid.uuid4())}/system",
system_monitor_interval_millis=1000,
)
script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist_gluon.py")
data_path = os.path.join(DATA_DIR, "mxnet_mnist")
mx = MXNet(
entry_point=script_path,
role="SageMakerRole",
framework_version=mxnet_training_latest_version,
py_version=mxnet_training_latest_py_version,
instance_count=1,
instance_type=cpu_instance_type,
sagemaker_session=sagemaker_session,
profiler_config=profiler_config,
)
train_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "train"), key_prefix="integ-test-data/mxnet_mnist/train"
)
test_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "test"), key_prefix="integ-test-data/mxnet_mnist/test"
)
training_job_name = unique_name_from_base("test-profiler-mxnet-training")
mx.fit(
inputs={"train": train_input, "test": test_input},
job_name=training_job_name,
wait=False,
)
job_description = mx.latest_training_job.describe()
assert job_description.get("ProfilerConfig") == profiler_config._to_request_dict()
assert job_description.get("ProfilingStatus") == "Enabled"
profiler_rule_configuration = job_description.get("ProfilerRuleConfigurations")[0]
assert re.match(r"ProfilerReport-\d*", profiler_rule_configuration["RuleConfigurationName"])
assert profiler_rule_configuration["RuleEvaluatorImage"] == get_rule_container_image_uri(
mx.sagemaker_session.boto_region_name
)
assert profiler_rule_configuration["RuleParameters"] == {"rule_to_invoke": "ProfilerReport"}
_wait_until_training_can_be_updated(sagemaker_session.sagemaker_client, training_job_name)
mx.update_profiler(
rules=[ProfilerRule.sagemaker(rule_configs.CPUBottleneck())],
system_monitor_interval_millis=500,
)
job_description = mx.latest_training_job.describe()
assert job_description["ProfilerConfig"]["S3OutputPath"] == profiler_config.s3_output_path
assert job_description["ProfilerConfig"]["ProfilingIntervalInMilliseconds"] == 500
profiler_report_rule_config = job_description.get("ProfilerRuleConfigurations")[0]
assert re.match(r"ProfilerReport-\d*", profiler_report_rule_config["RuleConfigurationName"])
assert profiler_report_rule_config["RuleEvaluatorImage"] == get_rule_container_image_uri(
mx.sagemaker_session.boto_region_name
)
assert profiler_report_rule_config["RuleParameters"] == {"rule_to_invoke": "ProfilerReport"}
def test_mxnet_with_built_in_profiler_rule_with_custom_parameters(
sagemaker_session,
mxnet_training_latest_version,
mxnet_training_latest_py_version,
cpu_instance_type,
):
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
custom_profiler_report_rule = ProfilerRule.sagemaker(
rule_configs.ProfilerReport(CPUBottleneck_threshold=90), name="CustomProfilerReportRule"
)
script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist_gluon.py")
data_path = os.path.join(DATA_DIR, "mxnet_mnist")
mx = MXNet(
entry_point=script_path,
role="SageMakerRole",
framework_version=mxnet_training_latest_version,
py_version=mxnet_training_latest_py_version,
instance_count=1,
instance_type=cpu_instance_type,
sagemaker_session=sagemaker_session,
rules=[custom_profiler_report_rule],
)
train_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "train"), key_prefix="integ-test-data/mxnet_mnist/train"
)
test_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "test"), key_prefix="integ-test-data/mxnet_mnist/test"
)
training_job_name = unique_name_from_base("test-profiler-mxnet-training")
mx.fit(
inputs={"train": train_input, "test": test_input},
job_name=training_job_name,
wait=False,
)
job_description = mx.latest_training_job.describe()
assert job_description.get("ProfilingStatus") == "Enabled"
assert (
job_description.get("ProfilerConfig")
== ProfilerConfig(
s3_output_path=mx.output_path, system_monitor_interval_millis=500
)._to_request_dict()
)
profiler_rule_configuration = job_description.get("ProfilerRuleConfigurations")[0]
assert profiler_rule_configuration["RuleConfigurationName"] == "CustomProfilerReportRule"
assert profiler_rule_configuration["RuleEvaluatorImage"] == mx.rules[0].image_uri
assert profiler_rule_configuration["RuleParameters"] == {
"rule_to_invoke": "ProfilerReport",
"CPUBottleneck_threshold": "90",
}
def test_mxnet_with_profiler_and_debugger_then_disable_framework_metrics(
sagemaker_session,
mxnet_training_latest_version,
mxnet_training_latest_py_version,
cpu_instance_type,
):
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
rules = [
Rule.sagemaker(rule_configs.vanishing_gradient()),
Rule.sagemaker(
base_config=rule_configs.all_zero(), rule_parameters={"tensor_regex": ".*"}
),
ProfilerRule.sagemaker(rule_configs.ProfilerReport(), name="CustomProfilerReportRule"),
]
debugger_hook_config = DebuggerHookConfig(
s3_output_path=f"s3://{sagemaker_session.default_bucket()}/{str(uuid.uuid4())}/tensors",
)
profiler_config = ProfilerConfig(
s3_output_path=f"s3://{sagemaker_session.default_bucket()}/{str(uuid.uuid4())}/system",
system_monitor_interval_millis=1000,
framework_profile_params=FrameworkProfile(),
)
script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist_gluon.py")
data_path = os.path.join(DATA_DIR, "mxnet_mnist")
mx = MXNet(
entry_point=script_path,
role="SageMakerRole",
framework_version=mxnet_training_latest_version,
py_version=mxnet_training_latest_py_version,
instance_count=1,
instance_type=cpu_instance_type,
sagemaker_session=sagemaker_session,
rules=rules,
debugger_hook_config=debugger_hook_config,
profiler_config=profiler_config,
)
train_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "train"), key_prefix="integ-test-data/mxnet_mnist/train"
)
test_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "test"), key_prefix="integ-test-data/mxnet_mnist/test"
)
training_job_name = unique_name_from_base("test-profiler-mxnet-training")
mx.fit(
inputs={"train": train_input, "test": test_input},
job_name=training_job_name,
wait=False,
)
job_description = mx.latest_training_job.describe()
assert job_description["ProfilerConfig"] == profiler_config._to_request_dict()
assert job_description["DebugHookConfig"] == debugger_hook_config._to_request_dict()
assert job_description.get("ProfilingStatus") == "Enabled"
profiler_rule_configuration = job_description.get("ProfilerRuleConfigurations")[0]
assert profiler_rule_configuration["RuleConfigurationName"] == "CustomProfilerReportRule"
assert profiler_rule_configuration["RuleEvaluatorImage"] == mx.rules[0].image_uri
assert profiler_rule_configuration["RuleParameters"] == {
"rule_to_invoke": "ProfilerReport",
}
for index, rule in enumerate(mx.debugger_rules):
assert (
job_description["DebugRuleConfigurations"][index]["RuleConfigurationName"]
== rule.name
)
assert (
job_description["DebugRuleConfigurations"][index]["RuleEvaluatorImage"]
== rule.image_uri
)
_wait_until_training_can_be_updated(sagemaker_session.sagemaker_client, training_job_name)
mx.update_profiler(disable_framework_metrics=True)
job_description = mx.latest_training_job.describe()
assert job_description["ProfilerConfig"]["ProfilingParameters"] == {}
def test_mxnet_with_enable_framework_metrics_then_update_framework_metrics(
sagemaker_session,
mxnet_training_latest_version,
mxnet_training_latest_py_version,
cpu_instance_type,
):
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
profiler_config = ProfilerConfig(
framework_profile_params=FrameworkProfile(start_step=1, num_steps=5)
)
script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist_gluon.py")
data_path = os.path.join(DATA_DIR, "mxnet_mnist")
mx = MXNet(
entry_point=script_path,
role="SageMakerRole",
framework_version=mxnet_training_latest_version,
py_version=mxnet_training_latest_py_version,
instance_count=1,
instance_type=cpu_instance_type,
sagemaker_session=sagemaker_session,
profiler_config=profiler_config,
)
train_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "train"), key_prefix="integ-test-data/mxnet_mnist/train"
)
test_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "test"), key_prefix="integ-test-data/mxnet_mnist/test"
)
training_job_name = unique_name_from_base("test-profiler-mxnet-training")
mx.fit(
inputs={"train": train_input, "test": test_input},
job_name=training_job_name,
wait=False,
)
job_description = mx.latest_training_job.describe()
assert (
job_description["ProfilerConfig"]["ProfilingParameters"]
== profiler_config._to_request_dict()["ProfilingParameters"]
)
assert job_description.get("ProfilingStatus") == "Enabled"
_wait_until_training_can_be_updated(sagemaker_session.sagemaker_client, training_job_name)
updated_framework_profile = FrameworkProfile(
detailed_profiling_config=DetailedProfilingConfig(profile_default_steps=True)
)
mx.update_profiler(framework_profile_params=updated_framework_profile)
job_description = mx.latest_training_job.describe()
assert (
job_description["ProfilerConfig"]["ProfilingParameters"]
== updated_framework_profile.profiling_parameters
)
profiler_rule_configuration = job_description.get("ProfilerRuleConfigurations")[0]
assert re.match(r"ProfilerReport-\d*", profiler_rule_configuration["RuleConfigurationName"])
assert profiler_rule_configuration["RuleEvaluatorImage"] == get_rule_container_image_uri(
mx.sagemaker_session.boto_region_name
)
assert profiler_rule_configuration["RuleParameters"] == {"rule_to_invoke": "ProfilerReport"}
def test_mxnet_with_disable_profiler_then_enable_default_profiling(
sagemaker_session,
mxnet_training_latest_version,
mxnet_training_latest_py_version,
cpu_instance_type,
):
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist_gluon.py")
data_path = os.path.join(DATA_DIR, "mxnet_mnist")
mx = MXNet(
entry_point=script_path,
role="SageMakerRole",
framework_version=mxnet_training_latest_version,
py_version=mxnet_training_latest_py_version,
instance_count=1,
instance_type=cpu_instance_type,
sagemaker_session=sagemaker_session,
disable_profiler=True,
)
train_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "train"), key_prefix="integ-test-data/mxnet_mnist/train"
)
test_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "test"), key_prefix="integ-test-data/mxnet_mnist/test"
)
training_job_name = unique_name_from_base("test-profiler-mxnet-training")
mx.fit(
inputs={"train": train_input, "test": test_input},
job_name=training_job_name,
wait=False,
)
job_description = mx.latest_training_job.describe()
assert job_description.get("ProfilerConfig") is None
assert job_description.get("ProfilerRuleConfigurations") is None
assert job_description.get("ProfilingStatus") == "Disabled"
_wait_until_training_can_be_updated(sagemaker_session.sagemaker_client, training_job_name)
mx.enable_default_profiling()
job_description = mx.latest_training_job.describe()
assert job_description["ProfilerConfig"]["S3OutputPath"] == mx.output_path
def test_mxnet_profiling_with_disable_debugger_hook(
sagemaker_session,
mxnet_training_latest_version,
mxnet_training_latest_py_version,
cpu_instance_type,
):
with timeout(minutes=TRAINING_DEFAULT_TIMEOUT_MINUTES):
script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist_gluon.py")
data_path = os.path.join(DATA_DIR, "mxnet_mnist")
mx = MXNet(
entry_point=script_path,
role="SageMakerRole",
framework_version=mxnet_training_latest_version,
py_version=mxnet_training_latest_py_version,
instance_count=1,
instance_type=cpu_instance_type,
sagemaker_session=sagemaker_session,
debugger_hook_config=False,
)
train_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "train"), key_prefix="integ-test-data/mxnet_mnist/train"
)
test_input = mx.sagemaker_session.upload_data(
path=os.path.join(data_path, "test"), key_prefix="integ-test-data/mxnet_mnist/test"
)
training_job_name = unique_name_from_base("test-profiler-mxnet-training")
mx.fit(
inputs={"train": train_input, "test": test_input},
job_name=training_job_name,
wait=False,
)
job_description = mx.latest_training_job.describe()
# setting debugger_hook_config to false would not disable profiling
# https://docs.aws.amazon.com/sagemaker/latest/dg/debugger-turn-off.html
assert job_description.get("ProfilingStatus") == "Enabled"