[
https://issues.apache.org/jira/browse/HUDI-4156?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17545663#comment-17545663
]
sivabalan narayanan commented on HUDI-4156:
-------------------------------------------
local fix to unblock myself for now
{code:java}
diff --git
a/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java
b/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java
index f5a96fb676..1e67020810 100644
---
a/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java
+++
b/hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java
@@ -955,7 +955,6 @@ public abstract class HoodieBackedTableMetadataWriter
implements HoodieTableMeta
HoodieTableFileSystemView fsView =
HoodieTableMetadataUtil.getFileSystemView(metadataMetaClient);
for (Map.Entry<MetadataPartitionType, HoodieData<HoodieRecord>> entry :
partitionRecordsMap.entrySet()) {
final String partitionName = entry.getKey().getPartitionPath();
- final int fileGroupCount = entry.getKey().getFileGroupCount();
HoodieData<HoodieRecord> records = entry.getValue();
List<FileSlice> fileSlices =
@@ -965,9 +964,10 @@ public abstract class HoodieBackedTableMetadataWriter
implements HoodieTableMeta
// so if there are no committed file slices, look for inflight slices
fileSlices =
HoodieTableMetadataUtil.getPartitionLatestFileSlicesIncludingInflight(metadataMetaClient,
Option.ofNullable(fsView), partitionName);
}
- ValidationUtils.checkArgument(fileSlices.size() == fileGroupCount,
+ final int fileGroupCount = fileSlices.size();
+ /*ValidationUtils.checkArgument(fileSlices.size() == fileGroupCount,
String.format("Invalid number of file groups for partition:%s,
found=%d, required=%d",
- partitionName, fileSlices.size(), fileGroupCount));
+ partitionName, fileSlices.size(), fileGroupCount));*/
List<FileSlice> finalFileSlices = fileSlices;
HoodieData<HoodieRecord> rddSinglePartitionRecords = records.map(r -> {
{code}
> AsyncIndexer fails for column stats partition
> ----------------------------------------------
>
> Key: HUDI-4156
> URL: https://issues.apache.org/jira/browse/HUDI-4156
> Project: Apache Hudi
> Issue Type: Bug
> Components: metadata
> Reporter: sivabalan narayanan
> Assignee: Sagar Sumit
> Priority: Major
> Fix For: 0.11.1
>
>
> Tried to build col stats for a hudi table w/ async indexer and ran into below
> exception
>
> Configs I had set are
> {code:java}
> hoodie.metadata.enable=true
> hoodie.metadata.index.async=true
> hoodie.metadata.index.column.stats.enable=true
> hoodie.write.concurrency.mode=optimistic_concurrency_control
> hoodie.write.lock.provider=org.apache.hudi.client.transaction.lock.InProcessLockProvider
> {code}
> command
> {code:java}
> ./bin/spark-submit --class org.apache.hudi.utilities.HoodieIndexer
> /home/hadoop/hudi-utilities-bundle_2.12-0.12.0-SNAPSHOT.jar --props
> file:///home/hadoop/indexer.properties --mode scheduleandexecute --base-path
> TBL_PATH --table-name call_center --index-types COLUMN_STATS --parallelism 1
> --spark-memory 10g {code}
>
>
> {code:java}
> 2022-05-26 00:14:27,936 INFO util.ClusteringUtils: Found 0 files in pending
> clustering operations
> 2022-05-26 00:14:27,937 INFO client.BaseHoodieClient: Stopping Timeline
> service !!
> 2022-05-26 00:14:27,937 INFO embedded.EmbeddedTimelineService: Closing
> Timeline server
> 2022-05-26 00:14:27,937 INFO service.TimelineService: Closing Timeline Service
> 2022-05-26 00:14:27,937 INFO javalin.Javalin: Stopping Javalin ...
> 2022-05-26 00:14:27,945 INFO javalin.Javalin: Javalin has stopped
> 2022-05-26 00:14:27,945 INFO service.TimelineService: Closed Timeline Service
> 2022-05-26 00:14:27,945 INFO embedded.EmbeddedTimelineService: Closed
> Timeline server
> 2022-05-26 00:14:27,945 INFO transaction.TransactionManager: Transaction
> manager closed
> 2022-05-26 00:14:27,946 ERROR utilities.UtilHelpers: Indexer failed
> java.lang.IllegalArgumentException: Invalid number of file groups for
> partition:column_stats, found=2, required=1
> at
> org.apache.hudi.common.util.ValidationUtils.checkArgument(ValidationUtils.java:40)
> at
> org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.prepRecords(HoodieBackedTableMetadataWriter.java:968)
> at
> org.apache.hudi.metadata.SparkHoodieBackedTableMetadataWriter.commit(SparkHoodieBackedTableMetadataWriter.java:132)
> at
> org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.initialCommit(HoodieBackedTableMetadataWriter.java:1087)
> at
> org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.buildMetadataPartitions(HoodieBackedTableMetadataWriter.java:858)
> at
> org.apache.hudi.table.action.index.RunIndexActionExecutor.execute(RunIndexActionExecutor.java:140)
> at
> org.apache.hudi.table.HoodieSparkCopyOnWriteTable.index(HoodieSparkCopyOnWriteTable.java:291)
> at
> org.apache.hudi.client.BaseHoodieWriteClient.index(BaseHoodieWriteClient.java:1027)
> at
> org.apache.hudi.utilities.HoodieIndexer.scheduleAndRunIndexing(HoodieIndexer.java:278)
> at
> org.apache.hudi.utilities.HoodieIndexer.lambda$start$1(HoodieIndexer.java:198)
> at org.apache.hudi.utilities.UtilHelpers.retry(UtilHelpers.java:541)
> at org.apache.hudi.utilities.HoodieIndexer.start(HoodieIndexer.java:185)
> at org.apache.hudi.utilities.HoodieIndexer.main(HoodieIndexer.java:154)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at
> org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
> at
> org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:955)
> at
> org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
> at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
> at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
> at
> org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1043)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1052)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> 2022-05-26 00:14:27,947 ERROR utilities.HoodieIndexer: Indexing with
> basePath:
> s3a://sagars-testlake/TPC-DS/1TB/hudi_hand_tuned_may20_1/call_center,
> tableName: call_center, runningMode: scheduleandexecute failed
> 2022-05-26 00:14:27,954 INFO server.AbstractConnector: Stopped
> Spark@450794b4{HTTP/1.1, (http/1.1)}{0.0.0.0:8090}
> 2022-05-26 00:14:27,954 INFO ui.SparkUI: Stopped Spark web UI at
> http://ip-172-31-39-68.us-east-2.compute.internal:8090
> 2022-05-26 00:14:27,964 INFO spark.MapOutputTrackerMasterEndpoint:
> MapOutputTrackerMasterEndpoint stopped! {code}
>
>
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
