You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by "Vinoth Chandar (Jira)" <ji...@apache.org> on 2019/12/25 22:54:00 UTC
[jira] [Closed] (HUDI-468) Not an avro data file - error while
archiving post rename() change
[ https://issues.apache.org/jira/browse/HUDI-468?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Vinoth Chandar closed HUDI-468.
-------------------------------
Resolution: Duplicate
dupe of HUDI-453
> Not an avro data file - error while archiving post rename() change
> ------------------------------------------------------------------
>
> Key: HUDI-468
> URL: https://issues.apache.org/jira/browse/HUDI-468
> Project: Apache Hudi (incubating)
> Issue Type: Bug
> Components: Write Client
> Reporter: Vinoth Chandar
> Assignee: Balaji Varadarajan
> Priority: Major
> Fix For: 0.5.1
>
>
> Here are reproduce steps.
> 1, Build from latest source
> mvn clean package -DskipTests -DskipITs -Dcheckstyle.skip=true -Drat.skip=true
> 2, Write Data
> export SPARK_HOME=/work/BigData/install/spark/spark-2.3.3-bin-hadoop2.6
> ${SPARK_HOME}/bin/spark-shell --jars `ls packaging/hudi-spark-bundle/target/hudi-spark-bundle-*.*.*-SNAPSHOT.jar` --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer'
> import org.apache.spark.sql.SaveMode._
> var datas = List("\{ \"name\": \"kenken\", \"ts\": 1574297893836, \"age\": 12, \"location\": \"latitude\"}")
> val df = spark.read.json(spark.sparkContext.parallelize(datas, 2))
> df.write.format("org.apache.hudi").
> option("hoodie.insert.shuffle.parallelism", "10").
> option("hoodie.upsert.shuffle.parallelism", "10").
> option("hoodie.delete.shuffle.parallelism", "10").
> option("hoodie.bulkinsert.shuffle.parallelism", "10").
> option("hoodie.datasource.write.recordkey.field", "name").
> option("hoodie.datasource.write.partitionpath.field", "location").
> option("hoodie.datasource.write.precombine.field", "ts").
> option("[hoodie.table.name|http://hoodie.table.name/]", "hudi_mor_table").
> mode(Overwrite).
> save("file:///tmp/hudi_mor_table")
> 3, Append Data
> df.write.format("org.apache.hudi").
> option("hoodie.insert.shuffle.parallelism", "10").
> option("hoodie.upsert.shuffle.parallelism", "10").
> option("hoodie.delete.shuffle.parallelism", "10").
> option("hoodie.bulkinsert.shuffle.parallelism", "10").
> option("hoodie.datasource.write.recordkey.field", "name").
> option("hoodie.datasource.write.partitionpath.field", "location").
> option("hoodie.datasource.write.precombine.field", "ts").
> option("hoodie.keep.max.commits", "5").
> option("hoodie.keep.min.commits", "4").
> option("hoodie.cleaner.commits.retained", "3").
> option("[hoodie.table.name|http://hoodie.table.name/]", "hudi_mor_table").
> mode(Append).
> save("file:///tmp/hudi_mor_table")
> 4, Repeat about six times Append Data operation(above), will get the stackstrace
> 19/12/24 13:34:09 ERROR HoodieCommitArchiveLog: Failed to archive commits, .commit file: 20191224132942.clean.requested
> java.io.IOException: Not an Avro data file
> at org.apache.avro.file.DataFileReader.openReader(DataFileReader.java:50)
> at org.apache.hudi.common.util.AvroUtils.deserializeAvroMetadata(AvroUtils.java:147)
> at org.apache.hudi.common.util.CleanerUtils.getCleanerPlan(CleanerUtils.java:88)
> at [org.apache.hudi.io|http://org.apache.hudi.io/].HoodieCommitArchiveLog.convertToAvroRecord(HoodieCommitArchiveLog.java:294)
> at [org.apache.hudi.io|http://org.apache.hudi.io/].HoodieCommitArchiveLog.archive(HoodieCommitArchiveLog.java:253)
> at [org.apache.hudi.io|http://org.apache.hudi.io/].HoodieCommitArchiveLog.archiveIfRequired(HoodieCommitArchiveLog.java:122)
> at org.apache.hudi.HoodieWriteClient.commit(HoodieWriteClient.java:562)
> at org.apache.hudi.HoodieWriteClient.commit(HoodieWriteClient.java:523)
> at org.apache.hudi.HoodieWriteClient.commit(HoodieWriteClient.java:514)
> at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:159)
> at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:91)
> at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45)
> at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
> at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
> at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
--
This message was sent by Atlassian Jira
(v8.3.4#803005)