[
https://issues.apache.org/jira/browse/SPARK-6360?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Cheng Lian updated SPARK-6360:
------------------------------
Description:
Spark shell session for reproduction (use {{:paste}}):
{noformat}
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.catalyst.types.decimal._
import org.apache.spark.sql.catalyst.types._
import org.apache.hadoop.fs._
val sqlContext = new SQLContext(sc)
val fs = FileSystem.get(sc.hadoopConfiguration)
fs.delete(new Path("a.parquet"))
fs.delete(new Path("b.parquet"))
import sc._
import sqlContext._
val r1 = parallelize(1 to 10)
.map(i => Tuple1(Decimal(i, 10, 0)))
.select('_1 cast DecimalType(10, 0))
// OK
r1.saveAsParquetFile("a.parquet")
val r2 = parallelize(1 to 10)
.map(i => Tuple1(Decimal(i, 10, 0)))
.select('_1 cast DecimalType(10, 0))
val r3 = r2.coalesce(1)
// Error
r3.saveAsParquetFile("b.parquet")
{noformat}
Exception thrown:
{noformat}
java.lang.ClassCastException: scala.math.BigDecimal cannot be cast to
org.apache.spark.sql.catalyst.types.decimal.Decimal
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.consumeType(ParquetTableSupport.scala:359)
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:328)
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:314)
at
parquet.hadoop.InternalParquetRecordWriter.write(InternalParquetRecordWriter.java:120)
at parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:81)
at parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:37)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable.org$apache$spark$sql$parquet$InsertIntoParquetTable$$writeShard$1(ParquetTableOperations.scala:308)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
15/03/17 00:04:13 WARN TaskSetManager: Lost task 0.0 in stage 2.0 (TID 2,
localhost): java.lang.ClassCastException: scala.math.BigDecimal cannot be cast
to org.apache.spark.sql.catalyst.types.decimal.Decimal
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.consumeType(ParquetTableSupport.scala:359)
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:328)
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:314)
at
parquet.hadoop.InternalParquetRecordWriter.write(InternalParquetRecordWriter.java:120)
at parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:81)
at parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:37)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable.org$apache$spark$sql$parquet$InsertIntoParquetTable$$writeShard$1(ParquetTableOperations.scala:308)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
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)
{noformat}
The query plan of {{r1}} is:
{noformat}
== Parsed Logical Plan ==
'Project [CAST('_1, DecimalType(10,0)) AS c0#60]
LogicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
ExistingRDD.scala:36
== Analyzed Logical Plan ==
Project [CAST(_1#59, DecimalType(10,0)) AS c0#60]
LogicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
ExistingRDD.scala:36
== Optimized Logical Plan ==
Project [CAST(_1#59, DecimalType(10,0)) AS c0#60]
LogicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
ExistingRDD.scala:36
== Physical Plan ==
Project [CAST(_1#59, DecimalType(10,0)) AS c0#60]
PhysicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
ExistingRDD.scala:36
Code Generation: false
== RDD ==
{noformat}
while {{r3}}'s query plan is:
{noformat}
== Parsed Logical Plan ==
LogicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
== Analyzed Logical Plan ==
LogicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
== Optimized Logical Plan ==
LogicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
== Physical Plan ==
PhysicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
Code Generation: false
== RDD ==
{noformat}
The key difference here is that, {{r3}} wraps an existing {{SchemaRDD}}
({{r2}}, beneath the {{CoalescedRDD}}). While evaluating {{r3}}, {{r2.compute}}
is called, which calls {{ScalaReflection.convertRowToScala}}. Here, Catalyst
{{Decimal}} values are converted into Java {{BigDecimal}}s, and finally causes
the exception.
Note that {{DataFrame}} in Spark 1.3 doesn't suffer this issue.
was:
Spark shell session for reproduction (use {{:paste}}):
{noformat}
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.catalyst.types.decimal._
import org.apache.spark.sql.catalyst.types._
import org.apache.hadoop.fs._
val sqlContext = new SQLContext(sc)
val fs = FileSystem.get(sc.hadoopConfiguration)
fs.delete(new Path("a.parquet"))
fs.delete(new Path("b.parquet"))
import sc._
import sqlContext._
val r1 = parallelize(1 to 10)
.map(i => Tuple1(Decimal(i, 10, 0)))
.select('_1 cast DecimalType(10, 0))
// OK
r1.saveAsParquetFile("a.parquet")
val r2 = parallelize(1 to 10)
.map(i => Tuple1(Decimal(i, 10, 0)))
.select('_1 cast DecimalType(10, 0))
val r3 = r2.coalesce(1)
// Error
r3.saveAsParquetFile("b.parquet")
{noformat}
Exception thrown:
{noformat}
java.lang.ClassCastException: scala.math.BigDecimal cannot be cast to
org.apache.spark.sql.catalyst.types.decimal.Decimal
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.consumeType(ParquetTableSupport.scala:359)
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:328)
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:314)
at
parquet.hadoop.InternalParquetRecordWriter.write(InternalParquetRecordWriter.java:120)
at parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:81)
at parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:37)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable.org$apache$spark$sql$parquet$InsertIntoParquetTable$$writeShard$1(ParquetTableOperations.scala:308)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
15/03/17 00:04:13 WARN TaskSetManager: Lost task 0.0 in stage 2.0 (TID 2,
localhost): java.lang.ClassCastException: scala.math.BigDecimal cannot be cast
to org.apache.spark.sql.catalyst.types.decimal.Decimal
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.consumeType(ParquetTableSupport.scala:359)
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:328)
at
org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:314)
at
parquet.hadoop.InternalParquetRecordWriter.write(InternalParquetRecordWriter.java:120)
at parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:81)
at parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:37)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable.org$apache$spark$sql$parquet$InsertIntoParquetTable$$writeShard$1(ParquetTableOperations.scala:308)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
at
org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
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)
{noformat}
The query plan of {{r1}} is:
{noformat}
== Parsed Logical Plan ==
'Project [CAST('_1, DecimalType(10,0)) AS c0#60]
LogicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
ExistingRDD.scala:36
== Analyzed Logical Plan ==
Project [CAST(_1#59, DecimalType(10,0)) AS c0#60]
LogicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
ExistingRDD.scala:36
== Optimized Logical Plan ==
Project [CAST(_1#59, DecimalType(10,0)) AS c0#60]
LogicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
ExistingRDD.scala:36
== Physical Plan ==
Project [CAST(_1#59, DecimalType(10,0)) AS c0#60]
PhysicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
ExistingRDD.scala:36
Code Generation: false
== RDD ==
{noformat}
while {{r3}}'s query plan is:
{noformat}
== Parsed Logical Plan ==
LogicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
== Analyzed Logical Plan ==
LogicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
== Optimized Logical Plan ==
LogicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
== Physical Plan ==
PhysicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
Code Generation: false
== RDD ==
{noformat}
The key difference here is that, {{r3}} wraps an existing {{SchemaRDD}}
({{r2}}, beneath the {{CoalescedRDD}}). While evaluating {{r3}}, {{r2.compute}}
is called, which calls {{ScalaReflection.convertRowToScala}}. Here, Catalyst
{{Decimal}} values are converted into Java {{BigDecimals}}, and finally causes
the exception.
Note that {{DataFrame}} in Spark 1.3 doesn't suffer this issue.
> For Spark 1.2, after any RDD transformations, calling saveAsParquetFile over
> a SchemaRDD with decimal or UDT column throws
> --------------------------------------------------------------------------------------------------------------------------
>
> Key: SPARK-6360
> URL: https://issues.apache.org/jira/browse/SPARK-6360
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.1.0, 1.2.0
> Reporter: Cheng Lian
>
> Spark shell session for reproduction (use {{:paste}}):
> {noformat}
> import org.apache.spark.sql.SQLContext
> import org.apache.spark.sql.catalyst.types.decimal._
> import org.apache.spark.sql.catalyst.types._
> import org.apache.hadoop.fs._
> val sqlContext = new SQLContext(sc)
> val fs = FileSystem.get(sc.hadoopConfiguration)
> fs.delete(new Path("a.parquet"))
> fs.delete(new Path("b.parquet"))
> import sc._
> import sqlContext._
> val r1 = parallelize(1 to 10)
> .map(i => Tuple1(Decimal(i, 10, 0)))
> .select('_1 cast DecimalType(10, 0))
> // OK
> r1.saveAsParquetFile("a.parquet")
> val r2 = parallelize(1 to 10)
> .map(i => Tuple1(Decimal(i, 10, 0)))
> .select('_1 cast DecimalType(10, 0))
> val r3 = r2.coalesce(1)
> // Error
> r3.saveAsParquetFile("b.parquet")
> {noformat}
> Exception thrown:
> {noformat}
> java.lang.ClassCastException: scala.math.BigDecimal cannot be cast to
> org.apache.spark.sql.catalyst.types.decimal.Decimal
> at
> org.apache.spark.sql.parquet.MutableRowWriteSupport.consumeType(ParquetTableSupport.scala:359)
> at
> org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:328)
> at
> org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:314)
> at
> parquet.hadoop.InternalParquetRecordWriter.write(InternalParquetRecordWriter.java:120)
> at
> parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:81)
> at
> parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:37)
> at
> org.apache.spark.sql.parquet.InsertIntoParquetTable.org$apache$spark$sql$parquet$InsertIntoParquetTable$$writeShard$1(ParquetTableOperations.scala:308)
> at
> org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
> at
> org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> 15/03/17 00:04:13 WARN TaskSetManager: Lost task 0.0 in stage 2.0 (TID 2,
> localhost): java.lang.ClassCastException: scala.math.BigDecimal cannot be
> cast to org.apache.spark.sql.catalyst.types.decimal.Decimal
> at
> org.apache.spark.sql.parquet.MutableRowWriteSupport.consumeType(ParquetTableSupport.scala:359)
> at
> org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:328)
> at
> org.apache.spark.sql.parquet.MutableRowWriteSupport.write(ParquetTableSupport.scala:314)
> at
> parquet.hadoop.InternalParquetRecordWriter.write(InternalParquetRecordWriter.java:120)
> at
> parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:81)
> at
> parquet.hadoop.ParquetRecordWriter.write(ParquetRecordWriter.java:37)
> at
> org.apache.spark.sql.parquet.InsertIntoParquetTable.org$apache$spark$sql$parquet$InsertIntoParquetTable$$writeShard$1(ParquetTableOperations.scala:308)
> at
> org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
> at
> org.apache.spark.sql.parquet.InsertIntoParquetTable$$anonfun$saveAsHadoopFile$1.apply(ParquetTableOperations.scala:325)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:56)
> at
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
> 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)
> {noformat}
> The query plan of {{r1}} is:
> {noformat}
> == Parsed Logical Plan ==
> 'Project [CAST('_1, DecimalType(10,0)) AS c0#60]
> LogicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
> ExistingRDD.scala:36
> == Analyzed Logical Plan ==
> Project [CAST(_1#59, DecimalType(10,0)) AS c0#60]
> LogicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
> ExistingRDD.scala:36
> == Optimized Logical Plan ==
> Project [CAST(_1#59, DecimalType(10,0)) AS c0#60]
> LogicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
> ExistingRDD.scala:36
> == Physical Plan ==
> Project [CAST(_1#59, DecimalType(10,0)) AS c0#60]
> PhysicalRDD [_1#59], MapPartitionsRDD[71] at mapPartitions at
> ExistingRDD.scala:36
> Code Generation: false
> == RDD ==
> {noformat}
> while {{r3}}'s query plan is:
> {noformat}
> == Parsed Logical Plan ==
> LogicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
> == Analyzed Logical Plan ==
> LogicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
> == Optimized Logical Plan ==
> LogicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
> == Physical Plan ==
> PhysicalRDD [c0#61], CoalescedRDD[74] at coalesce at SchemaRDD.scala:456
> Code Generation: false
> == RDD ==
> {noformat}
> The key difference here is that, {{r3}} wraps an existing {{SchemaRDD}}
> ({{r2}}, beneath the {{CoalescedRDD}}). While evaluating {{r3}},
> {{r2.compute}} is called, which calls {{ScalaReflection.convertRowToScala}}.
> Here, Catalyst {{Decimal}} values are converted into Java {{BigDecimal}}s,
> and finally causes the exception.
> Note that {{DataFrame}} in Spark 1.3 doesn't suffer this issue.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
