-
Notifications
You must be signed in to change notification settings - Fork 4.3k
/
job_LoadTests_Combine_Python.groovy
154 lines (144 loc) · 6.24 KB
/
job_LoadTests_Combine_Python.groovy
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
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License 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.
*/
import CommonJobProperties as commonJobProperties
import LoadTestsBuilder as loadTestsBuilder
import PhraseTriggeringPostCommitBuilder
import InfluxDBCredentialsHelper
def now = new Date().format("MMddHHmmss", TimeZone.getTimeZone('UTC'))
def loadTestConfigurations = { datasetName, mode ->
[
[
title : 'Combine Python Load test: 2GB 10 byte records',
test : 'apache_beam.testing.load_tests.combine_test',
runner : CommonTestProperties.Runner.DATAFLOW,
pipelineOptions: [
job_name : "load-tests-python-dataflow-${mode}-combine-1-${now}",
project : 'apache-beam-testing',
region : 'us-central1',
temp_location : 'gs://temp-storage-for-perf-tests/smoketests',
publish_to_big_query : true,
metrics_dataset : datasetName,
metrics_table : "python_dataflow_${mode}_combine_1",
influx_measurement : "python_${mode}_combine_1",
input_options : '\'{' +
'"num_records": 200000000,' +
'"key_size": 1,' +
'"value_size": 9,' +
'"algorithm": "lcg"}\'',
num_workers : 5,
autoscaling_algorithm: "NONE",
top_count : 20,
]
],
[
title : 'Combine Python Load test: 2GB Fanout 4',
test : 'apache_beam.testing.load_tests.combine_test',
runner : CommonTestProperties.Runner.DATAFLOW,
pipelineOptions: [
job_name : "load-tests-python-dataflow-${mode}-combine-4-${now}",
project : 'apache-beam-testing',
region : 'us-central1',
temp_location : 'gs://temp-storage-for-perf-tests/smoketests',
publish_to_big_query : true,
metrics_dataset : datasetName,
metrics_table : "python_dataflow_${mode}_combine_4",
influx_measurement : "python_${mode}_combine_4",
input_options : '\'{' +
'"num_records": 5000000,' +
'"key_size": 10,' +
'"value_size": 90,' +
'"algorithm": "lcg"}\'',
num_workers : 16,
autoscaling_algorithm: "NONE",
fanout : 4,
top_count : 20,
]
],
[
title : 'Combine Python Load test: 2GB Fanout 8',
test : 'apache_beam.testing.load_tests.combine_test',
runner : CommonTestProperties.Runner.DATAFLOW,
pipelineOptions: [
job_name : "load-tests-python-dataflow-${mode}-combine-5-${now}",
project : 'apache-beam-testing',
region : 'us-central1',
temp_location : 'gs://temp-storage-for-perf-tests/smoketests',
publish_to_big_query : true,
metrics_dataset : datasetName,
metrics_table : "python_dataflow_${mode}_combine_5",
influx_measurement : "python_${mode}_combine_5",
input_options : '\'{' +
'"num_records": 2500000,' +
'"key_size": 10,' +
'"value_size": 90,' +
'"algorithm": "lcg"}\'',
num_workers : 16,
autoscaling_algorithm: "NONE",
fanout : 8,
top_count : 20,
]
],
]
.each { test -> test.pipelineOptions.putAll(additionalPipelineArgs) }
.each{ test -> (mode != 'streaming') ?: addStreamingOptions(test) }
}
def addStreamingOptions(test){
test.pipelineOptions << [streaming: null,
experiments: "use_runner_v2"
]
}
def loadTestJob = { scope, triggeringContext, jobType ->
scope.description("Runs Python Combine load tests on Dataflow runner in ${jobType} mode")
commonJobProperties.setTopLevelMainJobProperties(scope, 'master', 720)
def datasetName = loadTestsBuilder.getBigQueryDataset('load_test', triggeringContext)
for (testConfiguration in loadTestConfigurations(datasetName, jobType)) {
loadTestsBuilder.loadTest(scope, testConfiguration.title, testConfiguration.runner, CommonTestProperties.SDK.PYTHON, testConfiguration.pipelineOptions, testConfiguration.test)
}
}
PhraseTriggeringPostCommitBuilder.postCommitJob(
'beam_LoadTests_Python_Combine_Dataflow_Batch',
'Run Load Tests Python Combine Dataflow Batch',
'Load Tests Python Combine Dataflow Batch suite',
this
) {
additionalPipelineArgs = [:]
loadTestJob(delegate, CommonTestProperties.TriggeringContext.PR, "batch")
}
CronJobBuilder.cronJob('beam_LoadTests_Python_Combine_Dataflow_Batch', 'H H * * *', this) {
additionalPipelineArgs = [
influx_db_name: InfluxDBCredentialsHelper.InfluxDBDatabaseName,
influx_hostname: InfluxDBCredentialsHelper.InfluxDBHostUrl,
]
loadTestJob(delegate, CommonTestProperties.TriggeringContext.POST_COMMIT, "batch")
}
PhraseTriggeringPostCommitBuilder.postCommitJob(
'beam_LoadTests_Python_Combine_Dataflow_Streaming',
'Run Load Tests Python Combine Dataflow Streaming',
'Load Tests Python Combine Dataflow Streaming suite',
this
) {
additionalPipelineArgs = [:]
loadTestJob(delegate, CommonTestProperties.TriggeringContext.PR, "streaming")
}
CronJobBuilder.cronJob('beam_LoadTests_Python_Combine_Dataflow_Streaming', 'H H * * *', this) {
additionalPipelineArgs = [
influx_db_name: InfluxDBCredentialsHelper.InfluxDBDatabaseName,
influx_hostname: InfluxDBCredentialsHelper.InfluxDBHostUrl,
]
loadTestJob(delegate, CommonTestProperties.TriggeringContext.POST_COMMIT, "streaming")
}