You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by "ASF GitHub Bot (Jira)" <ji...@apache.org> on 2023/01/30 22:23:00 UTC

[jira] [Updated] (HUDI-5654) Metadata commits/read fails when data table has rollbacks with empty completed file

     [ https://issues.apache.org/jira/browse/HUDI-5654?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

ASF GitHub Bot updated HUDI-5654:
---------------------------------
    Labels: pull-request-available  (was: )

> Metadata commits/read fails when data table has rollbacks with empty completed file
> -----------------------------------------------------------------------------------
>
>                 Key: HUDI-5654
>                 URL: https://issues.apache.org/jira/browse/HUDI-5654
>             Project: Apache Hudi
>          Issue Type: Bug
>          Components: writer-core
>            Reporter: sivabalan narayanan
>            Priority: Major
>              Labels: pull-request-available
>
> instant.rollback (completed rollback file) in timeline is expected to be non-empty. 
> So, in such cases, metadata commits /read fail since we could not parse rollback commits. 
>  
> {code:java}
> org.apache.hudi.exception.HoodieException: Unable to do hoodie metadata table validation in file:///Users/ljain/codebase/onehouse/local_test/tbl_cow_4_2/hoodie_table
>         at org.apache.hudi.utilities.HoodieMetadataTableValidator.run(HoodieMetadataTableValidator.java:369)
>         at org.apache.hudi.utilities.HoodieMetadataTableValidator.main(HoodieMetadataTableValidator.java:350)
>         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)
> Caused by: org.apache.hudi.exception.HoodieException: Error fetching partition paths from metadata table
>         at org.apache.hudi.common.fs.FSUtils.getAllPartitionPaths(FSUtils.java:308)
>         at org.apache.hudi.utilities.HoodieMetadataTableValidator.validatePartitions(HoodieMetadataTableValidator.java:529)
>         at org.apache.hudi.utilities.HoodieMetadataTableValidator.doMetadataTableValidation(HoodieMetadataTableValidator.java:437)
>         at org.apache.hudi.utilities.HoodieMetadataTableValidator.doHoodieMetadataTableValidationOnce(HoodieMetadataTableValidator.java:380)
>         at org.apache.hudi.utilities.HoodieMetadataTableValidator.run(HoodieMetadataTableValidator.java:366)
>         ... 13 more        at org.apache.hudi.utilities.HoodieMetadataTableValidator.doHoodieMetadataTableValidationOnce(HoodieMetadataTableValidator.java:380)
>         at org.apache.hudi.utilities.HoodieMetadataTableValidator.run(HoodieMetadataTableValidator.java:366)
>         ... 13 more
> Caused by: org.apache.hudi.exception.HoodieMetadataException: Failed to retrieve list of partition from metadata
>         at org.apache.hudi.metadata.BaseTableMetadata.getAllPartitionPaths(BaseTableMetadata.java:123)
>         at org.apache.hudi.common.fs.FSUtils.getAllPartitionPaths(FSUtils.java:306)
>         ... 17 more
> Caused by: org.apache.hudi.exception.HoodieMetadataException: Error retrieving rollback commits for instant [20230119223110895__rollback__COMPLETED]
>         at org.apache.hudi.metadata.HoodieBackedTableMetadata.getRollbackedCommits(HoodieBackedTableMetadata.java:576)
>         at org.apache.hudi.metadata.HoodieBackedTableMetadata.lambda$getValidInstantTimestamps$15(HoodieBackedTableMetadata.java:484)
>         at java.util.stream.ForEachOps$ForEachOp$OfRef.accept(ForEachOps.java:183)
>         at java.util.stream.ReferencePipeline$2$1.accept(ReferencePipeline.java:175)
>         at java.util.ArrayList$ArrayListSpliterator.forEachRemaining(ArrayList.java:1384)
>         at java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:482)
>         at java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:472)
>         at java.util.stream.ForEachOps$ForEachOp.evaluateSequential(ForEachOps.java:150)
>         at java.util.stream.ForEachOps$ForEachOp$OfRef.evaluateSequential(ForEachOps.java:173)
>         at java.util.stream.AbstractPipeline.evaluate(AbstractPipeline.java:234)
>         at java.util.stream.ReferencePipeline.forEach(ReferencePipeline.java:485)
>         at org.apache.hudi.metadata.HoodieBackedTableMetadata.getValidInstantTimestamps(HoodieBackedTableMetadata.java:483)
>         at org.apache.hudi.metadata.HoodieBackedTableMetadata.getLogRecordScanner(HoodieBackedTableMetadata.java:503)
>         at org.apache.hudi.metadata.HoodieBackedTableMetadata.openReaders(HoodieBackedTableMetadata.java:438)
>         at org.apache.hudi.metadata.HoodieBackedTableMetadata.getOrCreateReaders(HoodieBackedTableMetadata.java:423)
>         at org.apache.hudi.metadata.HoodieBackedTableMetadata.lambda$getRecordsByKeys$2(HoodieBackedTableMetadata.java:227)        at java.util.HashMap.forEach(HashMap.java:1290)
>         at org.apache.hudi.metadata.HoodieBackedTableMetadata.getRecordsByKeys(HoodieBackedTableMetadata.java:225)
>         at org.apache.hudi.metadata.HoodieBackedTableMetadata.getRecordByKey(HoodieBackedTableMetadata.java:148)
>         at org.apache.hudi.metadata.BaseTableMetadata.fetchAllPartitionPaths(BaseTableMetadata.java:295)
>         at org.apache.hudi.metadata.BaseTableMetadata.getAllPartitionPaths(BaseTableMetadata.java:121)
>         ... 18 more
> Caused by: org.apache.avro.InvalidAvroMagicException: Not an Avro data file
>         at org.apache.avro.file.DataFileReader.openReader(DataFileReader.java:57)
>         at org.apache.hudi.common.table.timeline.TimelineMetadataUtils.deserializeAvroMetadata(TimelineMetadataUtils.java:207)
>         at org.apache.hudi.common.table.timeline.TimelineMetadataUtils.deserializeHoodieRollbackMetadata(TimelineMetadataUtils.java:177)
>         at org.apache.hudi.metadata.HoodieBackedTableMetadata.getRollbackedCommits(HoodieBackedTableMetadata.java:560)
>         ... 38 more{code}
>  
> {code:java}
>  {code}



--
This message was sent by Atlassian Jira
(v8.20.10#820010)