You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Cheng Lian (JIRA)" <ji...@apache.org> on 2015/08/16 13:29:46 UTC
[jira] [Updated] (SPARK-10005) Parquet reader doesn't handle schema
merging properly for nested structs
[ https://issues.apache.org/jira/browse/SPARK-10005?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Cheng Lian updated SPARK-10005:
-------------------------------
Description:
Spark shell snippet to reproduce this issue (note that both {{DataFrame}} written below contain a single struct column with multiple fields):
{code}
import sqlContext.implicits._
val path = "file:///tmp/foo"
(0 until 3).map(i => Tuple1((s"a_$i", s"b_$i"))).toDF().coalesce(1).write.mode("overwrite").parquet(path)
(0 until 3).map(i => Tuple1((s"a_$i", s"b_$i", s"c_$i"))).toDF().coalesce(1).write.mode("append").parquet(path)
sqlContext.read.option("schemaMerging", "true").parquet(path).show()
{code}
Exception:
{noformat}
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 39.0 failed 1 times, most recent failure: Lost task 0.0 in stage 39.0 (TID 122, localhost): org.apache.parquet.io.ParquetDecodingException: Can not read value at 0 in block -1 in file file:/tmp/foo/part-r-00000-ba9dc7cf-3210-4006-9cf7-02c3d57483cd.gz.parquet
at org.apache.parquet.hadoop.InternalParquetRecordReader.nextKeyValue(InternalParquetRecordReader.java:228)
at org.apache.parquet.hadoop.ParquetRecordReader.nextKeyValue(ParquetRecordReader.java:201)
at org.apache.spark.rdd.SqlNewHadoopRDD$$anon$1.hasNext(SqlNewHadoopRDD.scala:168)
at scala.collection.Iterator$$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$5.apply(SparkPlan.scala:215)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1826)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1826)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 2
at org.apache.spark.sql.execution.datasources.parquet.CatalystRowConverter.getConverter(CatalystRowConverter.scala:136)
at org.apache.parquet.io.RecordReaderImplementation.<init>(RecordReaderImplementation.java:269)
at org.apache.parquet.io.MessageColumnIO$1.visit(MessageColumnIO.java:134)
at org.apache.parquet.io.MessageColumnIO$1.visit(MessageColumnIO.java:99)
at org.apache.parquet.filter2.compat.FilterCompat$NoOpFilter.accept(FilterCompat.java:154)
at org.apache.parquet.io.MessageColumnIO.getRecordReader(MessageColumnIO.java:99)
at org.apache.parquet.hadoop.InternalParquetRecordReader.checkRead(InternalParquetRecordReader.java:137)
at org.apache.parquet.hadoop.InternalParquetRecordReader.nextKeyValue(InternalParquetRecordReader.java:208)
... 25 more
{noformat}
was:
Spark shell snippet to reproduce this issue:
{code}
import sqlContext.implicits._
val path = "file:///tmp/foo"
(0 until 3).map(i => Tuple1((s"a_$i", s"b_$i"))).toDF().coalesce(1).write.mode("overwrite").parquet(path)
(0 until 3).map(i => Tuple1((s"a_$i", s"b_$i", s"c_$i"))).toDF().coalesce(1).write.mode("append").parquet(path)
sqlContext.read.option("schemaMerging", "true").parquet(path).show()
{code}
Exception:
{noformat}
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 39.0 failed 1 times, most recent failure: Lost task 0.0 in stage 39.0 (TID 122, localhost): org.apache.parquet.io.ParquetDecodingException: Can not read value at 0 in block -1 in file file:/tmp/foo/part-r-00000-ba9dc7cf-3210-4006-9cf7-02c3d57483cd.gz.parquet
at org.apache.parquet.hadoop.InternalParquetRecordReader.nextKeyValue(InternalParquetRecordReader.java:228)
at org.apache.parquet.hadoop.ParquetRecordReader.nextKeyValue(ParquetRecordReader.java:201)
at org.apache.spark.rdd.SqlNewHadoopRDD$$anon$1.hasNext(SqlNewHadoopRDD.scala:168)
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$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1826)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1826)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 2
at org.apache.spark.sql.execution.datasources.parquet.CatalystRowConverter.getConverter(CatalystRowConverter.scala:136)
at org.apache.parquet.io.RecordReaderImplementation.<init>(RecordReaderImplementation.java:269)
at org.apache.parquet.io.MessageColumnIO$1.visit(MessageColumnIO.java:134)
at org.apache.parquet.io.MessageColumnIO$1.visit(MessageColumnIO.java:99)
at org.apache.parquet.filter2.compat.FilterCompat$NoOpFilter.accept(FilterCompat.java:154)
at org.apache.parquet.io.MessageColumnIO.getRecordReader(MessageColumnIO.java:99)
at org.apache.parquet.hadoop.InternalParquetRecordReader.checkRead(InternalParquetRecordReader.java:137)
at org.apache.parquet.hadoop.InternalParquetRecordReader.nextKeyValue(InternalParquetRecordReader.java:208)
... 25 more
{noformat}
> Parquet reader doesn't handle schema merging properly for nested structs
> ------------------------------------------------------------------------
>
> Key: SPARK-10005
> URL: https://issues.apache.org/jira/browse/SPARK-10005
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.5.0
> Reporter: Cheng Lian
> Assignee: Cheng Lian
> Priority: Blocker
>
> Spark shell snippet to reproduce this issue (note that both {{DataFrame}} written below contain a single struct column with multiple fields):
> {code}
> import sqlContext.implicits._
> val path = "file:///tmp/foo"
> (0 until 3).map(i => Tuple1((s"a_$i", s"b_$i"))).toDF().coalesce(1).write.mode("overwrite").parquet(path)
> (0 until 3).map(i => Tuple1((s"a_$i", s"b_$i", s"c_$i"))).toDF().coalesce(1).write.mode("append").parquet(path)
> sqlContext.read.option("schemaMerging", "true").parquet(path).show()
> {code}
> Exception:
> {noformat}
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 39.0 failed 1 times, most recent failure: Lost task 0.0 in stage 39.0 (TID 122, localhost): org.apache.parquet.io.ParquetDecodingException: Can not read value at 0 in block -1 in file file:/tmp/foo/part-r-00000-ba9dc7cf-3210-4006-9cf7-02c3d57483cd.gz.parquet
> at org.apache.parquet.hadoop.InternalParquetRecordReader.nextKeyValue(InternalParquetRecordReader.java:228)
> at org.apache.parquet.hadoop.ParquetRecordReader.nextKeyValue(ParquetRecordReader.java:201)
> at org.apache.spark.rdd.SqlNewHadoopRDD$$anon$1.hasNext(SqlNewHadoopRDD.scala:168)
> at scala.collection.Iterator$$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$5.apply(SparkPlan.scala:215)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1826)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1826)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.ArrayIndexOutOfBoundsException: 2
> at org.apache.spark.sql.execution.datasources.parquet.CatalystRowConverter.getConverter(CatalystRowConverter.scala:136)
> at org.apache.parquet.io.RecordReaderImplementation.<init>(RecordReaderImplementation.java:269)
> at org.apache.parquet.io.MessageColumnIO$1.visit(MessageColumnIO.java:134)
> at org.apache.parquet.io.MessageColumnIO$1.visit(MessageColumnIO.java:99)
> at org.apache.parquet.filter2.compat.FilterCompat$NoOpFilter.accept(FilterCompat.java:154)
> at org.apache.parquet.io.MessageColumnIO.getRecordReader(MessageColumnIO.java:99)
> at org.apache.parquet.hadoop.InternalParquetRecordReader.checkRead(InternalParquetRecordReader.java:137)
> at org.apache.parquet.hadoop.InternalParquetRecordReader.nextKeyValue(InternalParquetRecordReader.java:208)
> ... 25 more
> {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