[
https://issues.apache.org/jira/browse/BEAM-7005?focusedWorklogId=226171&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-226171
]
ASF GitHub Bot logged work on BEAM-7005:
----------------------------------------
Author: ASF GitHub Bot
Created on: 11/Apr/19 17:05
Start Date: 11/Apr/19 17:05
Worklog Time Spent: 10m
Work Description: markflyhigh commented on pull request #8247:
[BEAM-7005] Added a set of Jenkins load tests with GBK for Java in streaming
mode
URL: https://github.com/apache/beam/pull/8247#discussion_r274526945
##########
File path: .test-infra/jenkins/job_LoadTests_Java.groovy
##########
@@ -22,203 +22,225 @@ import LoadTestsBuilder as loadTestsBuilder
import PhraseTriggeringPostCommitBuilder
import CronJobBuilder
-def loadTestConfigurations = [
- [
- title : 'Load test: 2GB of 10B records',
- itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
- runner : CommonTestProperties.Runner.DATAFLOW,
- jobProperties: [
- project : 'apache-beam-testing',
- appName :
'load_tests_Java_Dataflow_Batch_GBK_1',
- tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
- publishToBigQuery : true,
- bigQueryDataset : 'load_test',
- bigQueryTable : 'java_dataflow_batch_GBK_1',
- sourceOptions : """
- {
- "numRecords": 200000000,
- "keySizeBytes": 1,
- "valueSizeBytes": 9
- }
- """.trim().replaceAll("\\s", ""),
- fanout : 1,
- iterations : 1,
- maxNumWorkers : 5,
- numWorkers : 5,
- autoscalingAlgorithm: "NONE"
- ]
- ],
- [
- title : 'Load test: 2GB of 100B records',
- itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
- runner : CommonTestProperties.Runner.DATAFLOW,
- jobProperties: [
- project : 'apache-beam-testing',
- appName :
'load_tests_Java_Dataflow_Batch_GBK_2',
- tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
- publishToBigQuery : true,
- bigQueryDataset : 'load_test',
- bigQueryTable : 'java_dataflow_batch_GBK_2',
- sourceOptions : """
- {
- "numRecords": 20000000,
- "keySizeBytes": 10,
- "valueSizeBytes": 90
- }
- """.trim().replaceAll("\\s", ""),
- fanout : 1,
- iterations : 1,
- maxNumWorkers : 5,
- numWorkers : 5,
- autoscalingAlgorithm: "NONE"
- ]
- ],
+def loadTestConfigurations =
+ { jobType, isStreaming ->
[
+ [
+ title : 'Load test: 2GB of 10B records',
+ itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
+ runner : CommonTestProperties.Runner.DATAFLOW,
+ jobProperties: [
+ project : 'apache-beam-testing',
+ appName :
"load_tests_Java_Dataflow_${jobType}_GBK_1",
+ tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
+ publishToBigQuery : true,
+ bigQueryDataset : 'load_test',
+ bigQueryTable :
"java_dataflow_${jobType}_GBK_1",
+ sourceOptions : """
+ {
+ "numRecords": 200000000,
+ "keySizeBytes": 1,
+ "valueSizeBytes": 9
+ }
+ """.trim().replaceAll("\\s", ""),
+ fanout : 1,
+ iterations : 1,
+ maxNumWorkers : 5,
+ numWorkers : 5,
+ autoscalingAlgorithm: "NONE",
+ streaming : isStreaming
+ ]
+ ],
+ [
+ title : 'Load test: 2GB of 100B records',
+ itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
+ runner : CommonTestProperties.Runner.DATAFLOW,
+ jobProperties: [
+ project : 'apache-beam-testing',
+ appName :
"load_tests_Java_Dataflow_${jobType}_GBK_2",
+ tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
+ publishToBigQuery : true,
+ bigQueryDataset : 'load_test',
+ bigQueryTable :
"java_dataflow_${jobType}_GBK_2",
+ sourceOptions : """
+ {
+ "numRecords": 20000000,
+ "keySizeBytes": 10,
+ "valueSizeBytes": 90
+ }
+ """.trim().replaceAll("\\s", ""),
+ fanout : 1,
+ iterations : 1,
+ maxNumWorkers : 5,
+ numWorkers : 5,
+ autoscalingAlgorithm: "NONE",
+ streaming : isStreaming
+ ]
+ ],
+ [
- title : 'Load test: 2GB of 100kB records',
- itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
- runner : CommonTestProperties.Runner.DATAFLOW,
- jobProperties: [
- project : 'apache-beam-testing',
- appName :
'load_tests_Java_Dataflow_Batch_GBK_3',
- tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
- publishToBigQuery : true,
- bigQueryDataset : 'load_test',
- bigQueryTable : 'java_dataflow_batch_GBK_3',
- sourceOptions : """
- {
- "numRecords": 2000,
- "keySizeBytes": 100000,
- "valueSizeBytes": 900000
- }
- """.trim().replaceAll("\\s", ""),
- fanout : 1,
- iterations : 1,
- maxNumWorkers : 5,
- numWorkers : 5,
- autoscalingAlgorithm: "NONE"
- ]
+ title : 'Load test: 2GB of 100kB records',
+ itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
+ runner : CommonTestProperties.Runner.DATAFLOW,
+ jobProperties: [
+ project : 'apache-beam-testing',
+ appName :
"load_tests_Java_Dataflow_${jobType}_GBK_3",
+ tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
+ publishToBigQuery : true,
+ bigQueryDataset : 'load_test',
+ bigQueryTable :
"java_dataflow_${jobType}_GBK_3",
+ sourceOptions : """
+ {
+ "numRecords": 2000,
+ "keySizeBytes": 100000,
+ "valueSizeBytes": 900000
+ }
+ """.trim().replaceAll("\\s", ""),
+ fanout : 1,
+ iterations : 1,
+ maxNumWorkers : 5,
+ numWorkers : 5,
+ autoscalingAlgorithm: "NONE",
+ streaming : isStreaming
+ ]
- ],
- [
- title : 'Load test: fanout 4 times with 2GB 10-byte
records total',
- itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
- runner : CommonTestProperties.Runner.DATAFLOW,
- jobProperties: [
- project : 'apache-beam-testing',
- appName :
'load_tests_Java_Dataflow_Batch_GBK_4',
- tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
- publishToBigQuery : true,
- bigQueryDataset : 'load_test',
- bigQueryTable : 'java_dataflow_batch_GBK_4',
- sourceOptions : """
- {
- "numRecords": 5000000,
- "keySizeBytes": 10,
- "valueSizeBytes": 90
- }
- """.trim().replaceAll("\\s", ""),
- fanout : 4,
- iterations : 1,
- maxNumWorkers : 16,
- numWorkers : 16,
- autoscalingAlgorithm: "NONE"
- ]
- ],
- [
- title : 'Load test: fanout 8 times with 2GB 10-byte
records total',
- itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
- runner : CommonTestProperties.Runner.DATAFLOW,
- jobProperties: [
- project : 'apache-beam-testing',
- appName :
'load_tests_Java_Dataflow_Batch_GBK_5',
- tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
- publishToBigQuery : true,
- bigQueryDataset : 'load_test',
- bigQueryTable : 'java_dataflow_batch_GBK_5',
- sourceOptions : """
- {
- "numRecords": 2500000,
- "keySizeBytes": 10,
- "valueSizeBytes": 90
- }
- """.trim().replaceAll("\\s", ""),
- fanout : 8,
- iterations : 1,
- maxNumWorkers : 16,
- numWorkers : 16,
- autoscalingAlgorithm: "NONE"
- ]
- ],
- [
- title : 'Load test: reiterate 4 times 10kB values',
- itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
- runner : CommonTestProperties.Runner.DATAFLOW,
- jobProperties: [
- project : 'apache-beam-testing',
- appName :
'load_tests_Java_Dataflow_Batch_GBK_6',
- tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
- publishToBigQuery : true,
- bigQueryDataset : 'load_test',
- bigQueryTable : 'java_dataflow_batch_GBK_6',
- sourceOptions : """
- {
- "numRecords": 20000000,
- "keySizeBytes": 10,
- "valueSizeBytes": 90,
- "numHotKeys": 200,
- "hotKeyFraction": 1
- }
- """.trim().replaceAll("\\s", ""),
- fanout : 1,
- iterations : 4,
- maxNumWorkers : 5,
- numWorkers : 5,
- autoscalingAlgorithm: "NONE"
- ]
- ],
- [
- title : 'Load test: reiterate 4 times 2MB values',
- itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
- runner : CommonTestProperties.Runner.DATAFLOW,
- jobProperties: [
- project : 'apache-beam-testing',
- appName :
'load_tests_Java_Dataflow_Batch_GBK_7',
- tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
- publishToBigQuery : true,
- bigQueryDataset : 'load_test',
- bigQueryTable : 'java_dataflow_batch_GBK_7',
- sourceOptions : """
- {
- "numRecords": 20000000,
- "keySizeBytes": 10,
- "valueSizeBytes": 90,
- "numHotKeys": 10,
- "hotKeyFraction": 1
- }
- """.trim().replaceAll("\\s", ""),
- fanout : 1,
- iterations : 4,
- maxNumWorkers : 5,
- numWorkers : 5,
- autoscalingAlgorithm: "NONE"
- ]
+ ],
+ [
+ title : 'Load test: fanout 4 times with 2GB 10-byte
records total',
+ itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
+ runner : CommonTestProperties.Runner.DATAFLOW,
+ jobProperties: [
+ project : 'apache-beam-testing',
+ appName :
"load_tests_Java_Dataflow_${jobType}_GBK_4",
+ tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
+ publishToBigQuery : true,
+ bigQueryDataset : 'load_test',
+ bigQueryTable :
"java_dataflow_${jobType}_GBK_4",
+ sourceOptions : """
+ {
+ "numRecords": 5000000,
+ "keySizeBytes": 10,
+ "valueSizeBytes": 90
+ }
+ """.trim().replaceAll("\\s", ""),
+ fanout : 4,
+ iterations : 1,
+ maxNumWorkers : 16,
+ numWorkers : 16,
+ autoscalingAlgorithm: "NONE",
+ streaming : isStreaming
+ ]
+ ],
+ [
+ title : 'Load test: fanout 8 times with 2GB 10-byte
records total',
+ itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
+ runner : CommonTestProperties.Runner.DATAFLOW,
+ jobProperties: [
+ project : 'apache-beam-testing',
+ appName :
"load_tests_Java_Dataflow_${jobType}_GBK_5",
+ tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
+ publishToBigQuery : true,
+ bigQueryDataset : 'load_test',
+ bigQueryTable :
"java_dataflow_${jobType}_GBK_5",
+ sourceOptions : """
+ {
+ "numRecords": 2500000,
+ "keySizeBytes": 10,
+ "valueSizeBytes": 90
+ }
+ """.trim().replaceAll("\\s", ""),
+ fanout : 8,
+ iterations : 1,
+ maxNumWorkers : 16,
+ numWorkers : 16,
+ autoscalingAlgorithm: "NONE",
+ streaming : isStreaming
+ ]
+ ],
+ [
+ title : 'Load test: reiterate 4 times 10kB values',
+ itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
+ runner : CommonTestProperties.Runner.DATAFLOW,
+ jobProperties: [
+ project : 'apache-beam-testing',
+ appName :
"load_tests_Java_Dataflow_${jobType}_GBK_6",
+ tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
+ publishToBigQuery : true,
+ bigQueryDataset : 'load_test',
+ bigQueryTable :
"java_dataflow_${jobType}_GBK_6",
+ sourceOptions : """
+ {
+ "numRecords": 20000000,
+ "keySizeBytes": 10,
+ "valueSizeBytes": 90,
+ "numHotKeys": 200,
+ "hotKeyFraction": 1
+ }
+ """.trim().replaceAll("\\s", ""),
+ fanout : 1,
+ iterations : 4,
+ maxNumWorkers : 5,
+ numWorkers : 5,
+ autoscalingAlgorithm: "NONE",
+ streaming : isStreaming
+ ]
+ ],
+ [
+ title : 'Load test: reiterate 4 times 2MB values',
+ itClass :
'org.apache.beam.sdk.loadtests.GroupByKeyLoadTest',
+ runner : CommonTestProperties.Runner.DATAFLOW,
+ jobProperties: [
+ project : 'apache-beam-testing',
+ appName :
"load_tests_Java_Dataflow_${jobType}_GBK_7",
+ tempLocation :
'gs://temp-storage-for-perf-tests/loadtests',
+ publishToBigQuery : true,
+ bigQueryDataset : 'load_test',
+ bigQueryTable :
"java_dataflow_${jobType}_GBK_7",
+ sourceOptions : """
+ {
+ "numRecords": 20000000,
+ "keySizeBytes": 10,
+ "valueSizeBytes": 90,
+ "numHotKeys": 10,
+ "hotKeyFraction": 1
+ }
+ """.trim().replaceAll("\\s", ""),
+ fanout : 1,
+ iterations : 4,
+ maxNumWorkers : 5,
+ numWorkers : 5,
+ autoscalingAlgorithm: "NONE",
+ streaming : isStreaming
+ ]
+ ]
]
-]
+ }
+
def loadTestJob = { scope, triggeringContext ->
Review comment:
Can we make `loadTestJob` more specific like `batchLoadTestJob` given we
have `streamingLoadTestJob`?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 226171)
Time Spent: 3.5h (was: 3h 20m)
> Create GroupByKey streaming load test job for Java SDK
> ------------------------------------------------------
>
> Key: BEAM-7005
> URL: https://issues.apache.org/jira/browse/BEAM-7005
> Project: Beam
> Issue Type: Sub-task
> Components: testing
> Reporter: Michal Walenia
> Assignee: Michal Walenia
> Priority: Minor
> Time Spent: 3.5h
> Remaining Estimate: 0h
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
