You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Weizhong (JIRA)" <ji...@apache.org> on 2015/07/03 10:17:05 UTC
[jira] [Updated] (SPARK-8811) Read array struct data from parquet
error
[ https://issues.apache.org/jira/browse/SPARK-8811?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Weizhong updated SPARK-8811:
----------------------------
Description:
Now we have a table which have some array<struct<...>> fields, we save the table data as parquet.
But we can not read it.
The details are:
{noformat}
15/07/03 15:51:41 ERROR CliDriver: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 6.0 failed 1 times, most recent failure: Lost task 0.0 in stage 6.0 (TID 6, localhost): org.apache.parquet.io.ParquetDecodingException: Can not read value at 0 in block -1 in file hdfs://vm117:9000/user/hive/warehouse/cdr_voice_call/hour=10/last_msisdn=0/part-00000
at org.apache.parquet.hadoop.InternalParquetRecordReader.nextKeyValue(InternalParquetRecordReader.java:228)
at org.apache.parquet.hadoop.ParquetRecordReader.nextKeyValue(ParquetRecordReader.java:201)
at org.apache.spark.sql.sources.SqlNewHadoopRDD$$anon$1.hasNext(SqlNewHadoopRDD.scala:163)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:144)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:144)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1774)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1774)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
at org.apache.spark.scheduler.Task.run(Task.scala:70)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ArrayIndexOutOfBoundsException
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1294)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1285)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1284)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1284)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:751)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:751)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:751)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1505)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1466)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
{noformat}
was:
Now we have a external table which have some array<struct<...>> fields, we save the table data as parquet.
But we can not read it.
The details are:
{noformat}
15/07/03 15:51:41 ERROR CliDriver: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 6.0 failed 1 times, most recent failure: Lost task 0.0 in stage 6.0 (TID 6, localhost): org.apache.parquet.io.ParquetDecodingException: Can not read value at 0 in block -1 in file hdfs://vm117:9000/user/hive/warehouse/cdr_voice_call/hour=10/last_msisdn=0/part-00000
at org.apache.parquet.hadoop.InternalParquetRecordReader.nextKeyValue(InternalParquetRecordReader.java:228)
at org.apache.parquet.hadoop.ParquetRecordReader.nextKeyValue(ParquetRecordReader.java:201)
at org.apache.spark.sql.sources.SqlNewHadoopRDD$$anon$1.hasNext(SqlNewHadoopRDD.scala:163)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:144)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:144)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1774)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1774)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
at org.apache.spark.scheduler.Task.run(Task.scala:70)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ArrayIndexOutOfBoundsException
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1294)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1285)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1284)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1284)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:751)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:751)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:751)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1505)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1466)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
{noformat}
> Read array struct data from parquet error
> -----------------------------------------
>
> Key: SPARK-8811
> URL: https://issues.apache.org/jira/browse/SPARK-8811
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Reporter: Weizhong
>
> Now we have a table which have some array<struct<...>> fields, we save the table data as parquet.
> But we can not read it.
> The details are:
> {noformat}
> 15/07/03 15:51:41 ERROR CliDriver: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 6.0 failed 1 times, most recent failure: Lost task 0.0 in stage 6.0 (TID 6, localhost): org.apache.parquet.io.ParquetDecodingException: Can not read value at 0 in block -1 in file hdfs://vm117:9000/user/hive/warehouse/cdr_voice_call/hour=10/last_msisdn=0/part-00000
> at org.apache.parquet.hadoop.InternalParquetRecordReader.nextKeyValue(InternalParquetRecordReader.java:228)
> at org.apache.parquet.hadoop.ParquetRecordReader.nextKeyValue(ParquetRecordReader.java:201)
> at org.apache.spark.sql.sources.SqlNewHadoopRDD$$anon$1.hasNext(SqlNewHadoopRDD.scala:163)
> at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:308)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:144)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$3.apply(SparkPlan.scala:144)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1774)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1774)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
> at org.apache.spark.scheduler.Task.run(Task.scala:70)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.ArrayIndexOutOfBoundsException
> Driver stacktrace:
> at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1294)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1285)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1284)
> at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1284)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:751)
> at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:751)
> at scala.Option.foreach(Option.scala:236)
> at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:751)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1505)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1466)
> at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org