KarlManong commented on issue #1378:
URL: https://github.com/apache/iceberg/issues/1378#issuecomment-977549837
I got the same issue when using version 0.12.1 on spark 3.1.2 executed by
kyuubi.
```
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2258)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2207)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2206)
at
scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at
scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2206)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1079)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1079)
at scala.Option.foreach(Option.scala:407)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1079)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2445)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2387)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2376)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:868)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2196)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2217)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2236)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2261)
at org.apache.spark.rdd.RDD.$anonfun$collect$1(RDD.scala:1030)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
at org.apache.spark.rdd.RDD.collect(RDD.scala:1029)
at
org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:390)
at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:3697)
at
org.apache.spark.sql.Dataset.$anonfun$collect$1(Dataset.scala:2966)
at
org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3688)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3686)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:2966)
at
org.apache.kyuubi.engine.spark.operation.ExecuteStatement.$anonfun$executeStatement$1(ExecuteStatement.scala:88)
at
scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at
org.apache.kyuubi.engine.spark.operation.ExecuteStatement.withLocalProperties(ExecuteStatement.scala:134)
at
org.apache.kyuubi.engine.spark.operation.ExecuteStatement.org$apache$kyuubi$engine$spark$operation$ExecuteStatement$$executeStatement(ExecuteStatement.scala:80)
at
org.apache.kyuubi.engine.spark.operation.ExecuteStatement$$anon$1.run(ExecuteStatement.scala:103)
at
java.base/java.util.concurrent.Executors$RunnableAdapter.call(Unknown Source)
at java.base/java.util.concurrent.FutureTask.run(Unknown Source)
at
java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at
java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: java.lang.IllegalArgumentException: Missing required field:
data_file
at
org.apache.iceberg.relocated.com.google.common.base.Preconditions.checkArgument(Preconditions.java:217)
at
org.apache.iceberg.avro.BuildAvroProjection.record(BuildAvroProjection.java:99)
at
org.apache.iceberg.avro.BuildAvroProjection.record(BuildAvroProjection.java:43)
at
org.apache.iceberg.avro.AvroCustomOrderSchemaVisitor.visit(AvroCustomOrderSchemaVisitor.java:51)
at
org.apache.iceberg.avro.AvroSchemaUtil.buildAvroProjection(AvroSchemaUtil.java:105)
at
org.apache.iceberg.avro.ProjectionDatumReader.setSchema(ProjectionDatumReader.java:68)
at
org.apache.iceberg.shaded.org.apache.avro.file.DataFileStream.initialize(DataFileStream.java:133)
at
org.apache.iceberg.shaded.org.apache.avro.file.DataFileReader.<init>(DataFileReader.java:130)
at
org.apache.iceberg.shaded.org.apache.avro.file.DataFileReader.<init>(DataFileReader.java:122)
at
org.apache.iceberg.shaded.org.apache.avro.file.DataFileReader.openReader(DataFileReader.java:66)
at
org.apache.iceberg.avro.AvroIterable.newFileReader(AvroIterable.java:100)
at
org.apache.iceberg.avro.AvroIterable.iterator(AvroIterable.java:77)
at
org.apache.iceberg.io.CloseableIterable$4$1.<init>(CloseableIterable.java:99)
at
org.apache.iceberg.io.CloseableIterable$4.iterator(CloseableIterable.java:98)
at
org.apache.iceberg.io.CloseableIterable.lambda$filter$0(CloseableIterable.java:79)
at
org.apache.iceberg.io.CloseableIterable$2.iterator(CloseableIterable.java:73)
at
org.apache.iceberg.io.CloseableIterable$4$1.<init>(CloseableIterable.java:99)
at
org.apache.iceberg.io.CloseableIterable$4.iterator(CloseableIterable.java:98)
at
org.apache.iceberg.ManifestReader.iterator(ManifestReader.java:233)
at
org.apache.iceberg.io.CloseableIterable$4$1.<init>(CloseableIterable.java:99)
at
org.apache.iceberg.io.CloseableIterable$4.iterator(CloseableIterable.java:98)
at
org.apache.iceberg.io.CloseableIterable$4$1.<init>(CloseableIterable.java:99)
at
org.apache.iceberg.io.CloseableIterable$4.iterator(CloseableIterable.java:98)
at
org.apache.iceberg.io.CloseableIterable$4.iterator(CloseableIterable.java:90)
at org.apache.iceberg.util.Filter.lambda$filter$0(Filter.java:35)
at
org.apache.iceberg.io.CloseableIterable$2.iterator(CloseableIterable.java:73)
at
org.apache.iceberg.spark.source.RowDataReader.open(RowDataReader.java:78)
at
org.apache.iceberg.spark.source.BaseDataReader.next(BaseDataReader.java:93)
at
org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:79)
at
org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:112)
at
org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:458)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.agg_doAggregateWithoutKey_1$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.agg_doAggregateWithoutKey_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:345)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
at
org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:498)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:501)
... 3 more (state=,code=0)
```
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
