[
https://issues.apache.org/jira/browse/HIVE-14171?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16356325#comment-16356325
]
KaiXu edited comment on HIVE-14171 at 2/8/18 1:16 AM:
------------------------------------------------------
Found similar issue with hive.vectorized.use.row.serde.deserialize=true on
TPC-DS query12, parquet file format:
Hive2.2.0 with patch HIVE-14029
Spark2.0.2
Hadoop2.7.3
Job aborted due to stage failure: Task 76 in stage 1.0 failed 4 times, most
recent failure: Lost task 76.3 in stage 1.0 (TID 35, skl-slave2):
java.io.IOException: java.io.IOException: java.lang.NullPointerException
at
org.apache.hadoop.hive.io.HiveIOExceptionHandlerChain.handleRecordReaderNextException(HiveIOExceptionHandlerChain.java:121)
at
org.apache.hadoop.hive.io.HiveIOExceptionHandlerUtil.handleRecordReaderNextException(HiveIOExceptionHandlerUtil.java:77)
at
org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileRecordReader.doNextWithExceptionHandler(HadoopShimsSecure.java:231)
at
org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileRecordReader.next(HadoopShimsSecure.java:141)
at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:254)
at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:208)
at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
at
org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at
scala.collection.convert.Wrappers$IteratorWrapper.hasNext(Wrappers.scala:30)
at
org.apache.hadoop.hive.ql.exec.spark.HiveBaseFunctionResultList.hasNext(HiveBaseFunctionResultList.java:83)
at
scala.collection.convert.Wrappers$JIteratorWrapper.hasNext(Wrappers.scala:42)
at
org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:200)
at
org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:63)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:79)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:47)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.IOException: java.lang.NullPointerException
at
org.apache.hadoop.hive.io.HiveIOExceptionHandlerChain.handleRecordReaderNextException(HiveIOExceptionHandlerChain.java:121)
at
org.apache.hadoop.hive.io.HiveIOExceptionHandlerUtil.handleRecordReaderNextException(HiveIOExceptionHandlerUtil.java:77)
at
org.apache.hadoop.hive.ql.io.HiveContextAwareRecordReader.doNext(HiveContextAwareRecordReader.java:355)
at
org.apache.hadoop.hive.ql.io.CombineHiveRecordReader.doNext(CombineHiveRecordReader.java:157)
at
org.apache.hadoop.hive.ql.io.CombineHiveRecordReader.doNext(CombineHiveRecordReader.java:51)
at
org.apache.hadoop.hive.ql.io.HiveContextAwareRecordReader.next(HiveContextAwareRecordReader.java:116)
at
org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileRecordReader.doNextWithExceptionHandler(HadoopShimsSecure.java:228)
... 17 more
Caused by: java.lang.NullPointerException
at
org.apache.hadoop.hive.ql.io.parquet.read.ParquetRecordReaderWrapper.next(ParquetRecordReaderWrapper.java:206)
at
org.apache.hadoop.hive.ql.io.parquet.VectorizedParquetInputFormat$VectorizedParquetRecordReader.next(VectorizedParquetInputFormat.java:118)
at
org.apache.hadoop.hive.ql.io.parquet.VectorizedParquetInputFormat$VectorizedParquetRecordReader.next(VectorizedParquetInputFormat.java:51)
at
org.apache.hadoop.hive.ql.io.HiveContextAwareRecordReader.doNext(HiveContextAwareRecordReader.java:350)
... 21 more
was (Author: kaixu):
Found similar issue with hive.vectorized.use.row.serde.deserialize=true on
TPC-DS query12, parquet file format:
Job aborted due to stage failure: Task 76 in stage 1.0 failed 4 times, most
recent failure: Lost task 76.3 in stage 1.0 (TID 35, skl-slave2):
java.io.IOException: java.io.IOException: java.lang.NullPointerException
at
org.apache.hadoop.hive.io.HiveIOExceptionHandlerChain.handleRecordReaderNextException(HiveIOExceptionHandlerChain.java:121)
at
org.apache.hadoop.hive.io.HiveIOExceptionHandlerUtil.handleRecordReaderNextException(HiveIOExceptionHandlerUtil.java:77)
at
org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileRecordReader.doNextWithExceptionHandler(HadoopShimsSecure.java:231)
at
org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileRecordReader.next(HadoopShimsSecure.java:141)
at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:254)
at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:208)
at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
at
org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at
scala.collection.convert.Wrappers$IteratorWrapper.hasNext(Wrappers.scala:30)
at
org.apache.hadoop.hive.ql.exec.spark.HiveBaseFunctionResultList.hasNext(HiveBaseFunctionResultList.java:83)
at
scala.collection.convert.Wrappers$JIteratorWrapper.hasNext(Wrappers.scala:42)
at
org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:200)
at
org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:63)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:79)
at
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:47)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.IOException: java.lang.NullPointerException
at
org.apache.hadoop.hive.io.HiveIOExceptionHandlerChain.handleRecordReaderNextException(HiveIOExceptionHandlerChain.java:121)
at
org.apache.hadoop.hive.io.HiveIOExceptionHandlerUtil.handleRecordReaderNextException(HiveIOExceptionHandlerUtil.java:77)
at
org.apache.hadoop.hive.ql.io.HiveContextAwareRecordReader.doNext(HiveContextAwareRecordReader.java:355)
at
org.apache.hadoop.hive.ql.io.CombineHiveRecordReader.doNext(CombineHiveRecordReader.java:157)
at
org.apache.hadoop.hive.ql.io.CombineHiveRecordReader.doNext(CombineHiveRecordReader.java:51)
at
org.apache.hadoop.hive.ql.io.HiveContextAwareRecordReader.next(HiveContextAwareRecordReader.java:116)
at
org.apache.hadoop.hive.shims.HadoopShimsSecure$CombineFileRecordReader.doNextWithExceptionHandler(HadoopShimsSecure.java:228)
... 17 more
Caused by: java.lang.NullPointerException
at
org.apache.hadoop.hive.ql.io.parquet.read.ParquetRecordReaderWrapper.next(ParquetRecordReaderWrapper.java:206)
at
org.apache.hadoop.hive.ql.io.parquet.VectorizedParquetInputFormat$VectorizedParquetRecordReader.next(VectorizedParquetInputFormat.java:118)
at
org.apache.hadoop.hive.ql.io.parquet.VectorizedParquetInputFormat$VectorizedParquetRecordReader.next(VectorizedParquetInputFormat.java:51)
at
org.apache.hadoop.hive.ql.io.HiveContextAwareRecordReader.doNext(HiveContextAwareRecordReader.java:350)
... 21 more
> Parquet: Simple vectorization throws NPEs
> -----------------------------------------
>
> Key: HIVE-14171
> URL: https://issues.apache.org/jira/browse/HIVE-14171
> Project: Hive
> Issue Type: Bug
> Components: File Formats, Vectorization
> Affects Versions: 2.2.0
> Reporter: Gopal V
> Priority: Major
> Labels: Parquet
>
> {code}
> create temporary table cd_parquet stored as parquet as select * from
> customer_demographics;
> select count(1) from cd_parquet where cd_gender = 'F';
> {code}
> {code}
> Caused by: java.lang.NullPointerException
> at
> org.apache.hadoop.hive.ql.io.parquet.read.ParquetRecordReaderWrapper.next(ParquetRecordReaderWrapper.java:206)
> at
> org.apache.hadoop.hive.ql.io.parquet.VectorizedParquetInputFormat$VectorizedParquetRecordReader.next(VectorizedParquetInputFormat.java:118)
> at
> org.apache.hadoop.hive.ql.io.parquet.VectorizedParquetInputFormat$VectorizedParquetRecordReader.next(VectorizedParquetInputFormat.java:51)
> at
> org.apache.hadoop.hive.ql.io.HiveContextAwareRecordReader.doNext(HiveContextAwareRecordReader.java:350)
> ... 17 more
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
