jiantao-vungle commented on issue #10103:
URL: https://github.com/apache/iceberg/issues/10103#issuecomment-2056319114
and yesterday we encountered a similar problem again:
```
Py4JJavaError: An error occurred while calling o140.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 2
in stage 5.0 failed 4 times, most recent failure: Lost task 2.3 in stage 5.0
(TID 15) (172.26.33.207 executor 1):
org.apache.parquet.io.ParquetDecodingException: Failed to read from input stream
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readNextGroup(VectorizedRleValuesReader.java:942)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readIntegers(VectorizedRleValuesReader.java:696)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetVectorUpdaterFactory$IntegerUpdater.readValues(ParquetVectorUpdaterFactory.java:256)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readBatchInternal(VectorizedRleValuesReader.java:244)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readIntegers(VectorizedRleValuesReader.java:193)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.readBatch(VectorizedColumnReader.java:204)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:316)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:212)
at
org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:39)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:116)
at
org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:554)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.hashAgg_doAggregateWithKeys_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$$anon$1.hasNext(WholeStageCodegenExec.scala:760)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at
org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:140)
at
org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
at org.apache.spark.scheduler.Task.run(Task.scala:136)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:548)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1504)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:551)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.EOFException
at
org.apache.parquet.bytes.SingleBufferInputStream.slice(SingleBufferInputStream.java:116)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readNextGroup(VectorizedRleValuesReader.java:933)
... 27 more
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2672)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2608)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2607)
at
scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at
scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2607)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1182)
at
org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1182)
at scala.Option.foreach(Option.scala:407)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1182)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2860)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2802)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2791)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
Caused by: org.apache.parquet.io.ParquetDecodingException: Failed to read
from input stream
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readNextGroup(VectorizedRleValuesReader.java:942)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readIntegers(VectorizedRleValuesReader.java:696)
at
org.apache.spark.sql.execution.datasources.parquet.ParquetVectorUpdaterFactory$IntegerUpdater.readValues(ParquetVectorUpdaterFactory.java:256)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readBatchInternal(VectorizedRleValuesReader.java:244)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readIntegers(VectorizedRleValuesReader.java:193)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.readBatch(VectorizedColumnReader.java:204)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:316)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:212)
at
org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:39)
at
org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:116)
at
org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:554)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.hashAgg_doAggregateWithKeys_0$(Unknown
Source)
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown
Source)
at
org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at
org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:760)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at
org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:140)
at
org.apache.spark.shuffle.ShuffleWriteProcessor.write(ShuffleWriteProcessor.scala:59)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:52)
at org.apache.spark.scheduler.Task.run(Task.scala:136)
at
org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:548)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1504)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:551)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.EOFException
at
org.apache.parquet.bytes.SingleBufferInputStream.slice(SingleBufferInputStream.java:116)
at
org.apache.spark.sql.execution.datasources.parquet.VectorizedRleValuesReader.readNextGroup(VectorizedRleValuesReader.java:933)
... 27 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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
