[BEAM-10675] Add Python GBK Load Tests for streaming on Dataflow #12612
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -25,7 +25,7 @@ import InfluxDBCredentialsHelper | |
|
|
||
| def now = new Date().format("MMddHHmmss", TimeZone.getTimeZone('UTC')) | ||
|
|
||
| def loadTestConfigurations = { mode, datasetName -> | ||
| [ | ||
| [ | ||
| title : 'GroupByKey Python Load test: reiterate 4 times 10kB values', | ||
|
|
@@ -34,21 +34,21 @@ def loadTestConfigurations = { datasetName -> | |
| pipelineOptions: [ | ||
| project : 'apache-beam-testing', | ||
| region : 'us-central1', | ||
| job_name : "load-tests-python-dataflow-${mode}-gbk-6-${now}", | ||
| temp_location : 'gs://temp-storage-for-perf-tests/loadtests', | ||
| publish_to_big_query : true, | ||
| metrics_dataset : datasetName, | ||
| metrics_table : "python_dataflow_${mode}_gbk_6", | ||
| influx_measurement : "python_${mode}_gbk_6", | ||
| input_options : '\'{"num_records": 20000000,' + | ||
| '"key_size": 10,' + | ||
| '"value_size": 90,' + | ||
| '"num_hot_keys": 200,' + | ||
| '"hot_key_fraction": 1}\'', | ||
| iterations : 4, | ||
| fanout : 1, | ||
| num_workers : 5, | ||
| autoscaling_algorithm: 'NONE', | ||
| ] | ||
| ], | ||
| [ | ||
|
|
@@ -58,43 +58,52 @@ def loadTestConfigurations = { datasetName -> | |
| pipelineOptions: [ | ||
| project : 'apache-beam-testing', | ||
| region : 'us-central1', | ||
| job_name : "load-tests-python-dataflow-${mode}-gbk-7-${now}", | ||
| temp_location : 'gs://temp-storage-for-perf-tests/loadtests', | ||
| publish_to_big_query : true, | ||
| metrics_dataset : datasetName, | ||
| metrics_table : "python_dataflow_${mode}_gbk_7", | ||
| influx_measurement : "python_${mode}_gbk_7", | ||
| input_options : '\'{"num_records": 20000000,' + | ||
| '"key_size": 10,' + | ||
| '"value_size": 90,' + | ||
| '"num_hot_keys": 10,' + | ||
| '"hot_key_fraction": 1}\'', | ||
| iterations : 4, | ||
| fanout : 1, | ||
| num_workers : 5, | ||
| autoscaling_algorithm: 'NONE', | ||
| ] | ||
| ] | ||
| ] | ||
| .each { test -> test.pipelineOptions.putAll(additionalPipelineArgs) } | ||
| .each { test -> (mode != 'streaming') ?: addStreamingOptions(test) } | ||
| } | ||
|
|
||
| def addStreamingOptions(test) { | ||
| test.pipelineOptions << [ | ||
| streaming: null, | ||
| // Use the new Dataflow runner, which offers improved efficiency of Dataflow jobs. | ||
| // See https://cloud.google.com/dataflow/docs/guides/deploying-a-pipeline#dataflow-runner-v2 | ||
| // for more details. | ||
| experiments: 'use_runner_v2', | ||
| ] | ||
| } | ||
|
|
||
| def loadTestJob = { scope, triggeringContext, mode -> | ||
| def datasetName = loadTestsBuilder.getBigQueryDataset('load_test', triggeringContext) | ||
| loadTestsBuilder.loadTests(scope, CommonTestProperties.SDK.PYTHON_37, | ||
| loadTestConfigurations(mode, datasetName), 'GBK reiterate', mode) | ||
| } | ||
|
|
||
| CronJobBuilder.cronJob('beam_LoadTests_Python_GBK_reiterate_Dataflow_Batch', | ||
| 'H 14 * * *', this) { | ||
|
There was a problem hiding this comment. What's the methodology for picking the time to trigger these? Is it documented anywhere? There was a problem hiding this comment. Ideally, each test suite (GBK, ParDo, IO tests, etc.) should has its own, unique time in order no to flood Jenkins with many tests that are triggered at the same time. When adding a new test suite, a contributor has to take a look at what time slots are already occupied and avoid using them. I think this is not documented. I'll add some information here: https://cwiki.apache.org/confluence/display/BEAM/Contribution+Testing+Guide#ContributionTestingGuide |
||
| additionalPipelineArgs = [ | ||
| influx_db_name: InfluxDBCredentialsHelper.InfluxDBDatabaseName, | ||
| influx_hostname: InfluxDBCredentialsHelper.InfluxDBHostname, | ||
| ] | ||
| loadTestJob(delegate, CommonTestProperties.TriggeringContext.POST_COMMIT, 'batch') | ||
| } | ||
|
|
||
| PhraseTriggeringPostCommitBuilder.postCommitJob( | ||
| 'beam_LoadTests_Python_GBK_reiterate_Dataflow_Batch', | ||
|
|
@@ -103,5 +112,24 @@ PhraseTriggeringPostCommitBuilder.postCommitJob( | |
| this | ||
| ) { | ||
| additionalPipelineArgs = [:] | ||
| loadTestJob(delegate, CommonTestProperties.TriggeringContext.PR, 'batch') | ||
| } | ||
|
|
||
| CronJobBuilder.cronJob('beam_LoadTests_Python_GBK_reiterate_Dataflow_Streaming', | ||
| 'H 14 * * *', this) { | ||
| additionalPipelineArgs = [ | ||
| influx_db_name: InfluxDBCredentialsHelper.InfluxDBDatabaseName, | ||
| influx_hostname: InfluxDBCredentialsHelper.InfluxDBHostname, | ||
| ] | ||
| loadTestJob(delegate, CommonTestProperties.TriggeringContext.POST_COMMIT, 'streaming') | ||
| } | ||
|
|
||
| PhraseTriggeringPostCommitBuilder.postCommitJob( | ||
| 'beam_LoadTests_Python_GBK_reiterate_Dataflow_Streaming', | ||
| 'Run Load Tests Python GBK reiterate Dataflow Streaming', | ||
| 'Load Tests Python GBK reiterate Dataflow Streaming suite', | ||
| this | ||
| ) { | ||
| additionalPipelineArgs = [:] | ||
| loadTestJob(delegate, CommonTestProperties.TriggeringContext.PR, 'streaming') | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Same here, please add a comment.