Apache
/
druid
mirror of https://github.com/apache/druid.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Simplify ITHttpInputSourceTest to mitigate flakiness (#11751) 

* Increment retry count to add more time for tests to pass

* Re-enable ITHttpInputSourceTest

* Restore original count

* This test is about input source, hash partitioning takes longer and not required thus changing to dynamic

* Further simplify by removing sketches
This commit is contained in:
Agustin Gonzalez 2021-10-12 09:51:27 -07:00 committed by GitHub
parent adb2237628
commit 887cecf29e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 19 additions and 88 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
integration-tests/src/test/java/org/apache/druid/tests/indexer/ITHttpInputSourceTest.java
View File

@ -36,8 +36,6 @@ public class ITHttpInputSourceTest extends AbstractITBatchIndexTest
private static final String INDEX_TASK = "/indexer/wikipedia_http_inputsource_task.json";
private static final String INDEX_QUERIES_RESOURCE = "/indexer/wikipedia_http_inputsource_queries.json";
// Ignore while we debug...
@Test(enabled = false)
public void doTest() throws IOException
{
final String indexDatasource = "wikipedia_http_inputsource_test_" + UUID.randomUUID();

85
integration-tests/src/test/resources/indexer/wikipedia_http_inputsource_queries.json
View File

@ -16,82 +16,31 @@
]
},
{
"description": "timeseries, datasketch aggs, all",
"description": "simple aggr",
"query":{
"queryType" : "timeseries",
"dataSource": "%%DATASOURCE%%",
"granularity":"day",
"intervals":[
"2016-06-27/P1D"
],
"filter":null,
"aggregations":[
"queryType" : "topN",
"dataSource" : "%%DATASOURCE%%",
"intervals" : ["2016-06-27/2016-06-28"],
"granularity" : "all",
"dimension" : "page",
"metric" : "count",
"threshold" : 3,
"aggregations" : [
{
"type": "HLLSketchMerge",
"name": "approxCountHLL",
"fieldName": "HLLSketchBuild",
"lgK": 12,
"tgtHllType": "HLL_4",
"round": true
},
{
"type":"thetaSketch",
"name":"approxCountTheta",
"fieldName":"thetaSketch",
"size":16384,
"shouldFinalize":true,
"isInputThetaSketch":false,
"errorBoundsStdDev":null
},
{
"type":"quantilesDoublesSketch",
"name":"quantilesSketch",
"fieldName":"quantilesDoublesSketch",
"k":128
"type" : "count",
"name" : "count"
}
]
},
"expectedResults":[
{
"timestamp" : "2016-06-27T00:00:00.000Z",
"result" : {
"quantilesSketch":48866,
"approxCountTheta":7862.0,
"approxCountHLL":7961
}
}
"timestamp" : "2016-06-27T00:00:11.000Z",
"result" :
[
{"count":58,"page":"Copa América Centenario"},
{"count":32,"page":"User:Cyde/List of candidates for speedy deletion/Subpage"},
{"count":32,"page":"Wikipedia:Administrators' noticeboard/Incidents"}
]
},
{
"description": "timeseries, stringFirst/stringLast aggs, all",
"query":{
"queryType" : "timeseries",
"dataSource": "%%DATASOURCE%%",
"granularity":"day",
"intervals":[
"2016-06-27/P1D"
],
"filter":null,
"aggregations":[
{
"type": "stringFirst",
"name": "first_user",
"fieldName": "user"
},
{
"type":"stringLast",
"name":"last_user",
"fieldName":"user"
}
]
},
"expectedResults":[
{
"timestamp" : "2016-06-27T00:00:00.000Z",
"result" : {
"first_user":"Lsjbot",
"last_user":"EmausBot"
}
}
]
}

18
integration-tests/src/test/resources/indexer/wikipedia_http_inputsource_task.json
View File

@ -41,21 +41,6 @@
"type": "doubleSum",
"name": "delta",
"fieldName": "delta"
},
{
"name": "thetaSketch",
"type": "thetaSketch",
"fieldName": "user"
},
{
"name": "quantilesDoublesSketch",
"type": "quantilesDoublesSketch",
"fieldName": "delta"
},
{
"name": "HLLSketchBuild",
"type": "HLLSketchBuild",
"fieldName": "user"
}
],
"granularitySpec": {
@ -78,9 +63,8 @@
"type": "index_parallel",
"maxNumConcurrentSubTasks": 10,
"partitionsSpec": {
"type": "hashed"
"type": "dynamic"
},
"forceGuaranteedRollup": true,
"splitHintSpec": {
"type": "maxSize",
"maxNumFiles": 1