putaozhi123 opened a new issue #4466:
URL: https://github.com/apache/hudi/issues/4466
**Environment Description**
Hudi version : 0.8.0
Spark version : 2.4.7
Storage (HDFS/S3/GCS..) : HDFS
Running on Docker? (yes/no) : no
**Additional context**
the hudi program restart fails when I restart sparksubmit , the exception
is as follows:
**Stacktrace**
21/12/29 05:57:06 ERROR table.HoodieTimelineArchiveLog: Failed to archive
commits, .commit file: 20210916102118.rollback.inflight
java.io.IOException: Not an Avro data file
at
org.apache.avro.file.DataFileReader.openReader(DataFileReader.java:50)
at
org.apache.hudi.common.table.timeline.TimelineMetadataUtils.deserializeAvroMetadata(TimelineMetadataUtils.java:175)
at
org.apache.hudi.client.utils.MetadataConversionUtils.createMetaWrapper(MetadataConversionUtils.java:84)
at
org.apache.hudi.table.HoodieTimelineArchiveLog.convertToAvroRecord(HoodieTimelineArchiveLog.java:370)
at
org.apache.hudi.table.HoodieTimelineArchiveLog.archive(HoodieTimelineArchiveLog.java:311)
at
org.apache.hudi.table.HoodieTimelineArchiveLog.archiveIfRequired(HoodieTimelineArchiveLog.java:128)
at
org.apache.hudi.client.AbstractHoodieWriteClient.postCommit(AbstractHoodieWriteClient.java:430)
at
org.apache.hudi.client.AbstractHoodieWriteClient.commitStats(AbstractHoodieWriteClient.java:186)
at
org.apache.hudi.client.SparkRDDWriteClient.commit(SparkRDDWriteClient.java:121)
at
org.apache.hudi.HoodieSparkSqlWriter$.commitAndPerformPostOperations(HoodieSparkSqlWriter.scala:476)
at
org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:222)
at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:145)
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$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:83)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:81)
at
org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:696)
at
org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:696)
at
org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:80)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75)
at
org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:696)
at
org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:305)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:291)
at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:249)
at hudi.WriteHudi$$anonfun$1.apply(WriteHudi.scala:148)
at hudi.WriteHudi$$anonfun$1.apply(WriteHudi.scala:136)
at
org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:35)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$5$$anonfun$apply$17.apply(MicroBatchExecution.scala:537)
at
org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:80)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$5.apply(MicroBatchExecution.scala:535)
at
org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:351)
at
org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution.org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch(MicroBatchExecution.scala:534)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply$mcV$sp(MicroBatchExecution.scala:198)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:166)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:166)
at
org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:351)
at
org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1.apply$mcZ$sp(MicroBatchExecution.scala:166)
at
org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56)
at
org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:160)
at
org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:281)
at
org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:193)
Caused by: java.io.IOException: Not an Avro data file
at
org.apache.avro.file.DataFileReader.openReader(DataFileReader.java:50)
at
org.apache.hudi.common.table.timeline.TimelineMetadataUtils.deserializeAvroMetadata(TimelineMetadataUtils.java:175)
at
org.apache.hudi.client.utils.MetadataConversionUtils.createMetaWrapper(MetadataConversionUtils.java:84)
at
org.apache.hudi.table.HoodieTimelineArchiveLog.convertToAvroRecord(HoodieTimelineArchiveLog.java:370)
at
org.apache.hudi.table.HoodieTimelineArchiveLog.archive(HoodieTimelineArchiveLog.java:311)
... 49 more
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
