[ https://issues.apache.org/jira/browse/SPARK-33502?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Arwin S Tio updated SPARK-33502: -------------------------------- Description: On Spark 2.4.7 Standalone Mode on my laptop (Macbook Pro 2015), I ran the following: {code:java} public class TestSparkStackOverflow { public static void main(String [] args) { SparkSession spark = SparkSession .builder() .config("spark.master", "local[8]") .appName(TestSparkStackOverflow.class.getSimpleName()) .getOrCreate(); StructType inputSchema = new StructType(); inputSchema = inputSchema.add("foo", DataTypes.StringType); Dataset<Row> inputDf = spark.createDataFrame( Arrays.asList( RowFactory.create("1"), RowFactory.create("2"), RowFactory.create("3") ), inputSchema ); List<Column> lotsOfColumns = new ArrayList<>(); for (int i = 0; i < 3000; i++) { lotsOfColumns.add(lit("").as("field" + i).cast(DataTypes.StringType)); } lotsOfColumns.add(new Column("foo")); inputDf .select(JavaConverters.collectionAsScalaIterableConverter(lotsOfColumns).asScala().toSeq()) .write() .format("csv") .mode(SaveMode.Append) .save("file:///tmp/testoutput"); } } {code} And I get a StackOverflowError: {code:java} Exception in thread "main" org.apache.spark.SparkException: Job aborted.Exception in thread "main" org.apache.spark.SparkException: Job aborted. at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:198) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:159) at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104) at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102) at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:83) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:81) at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:696) at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:696) at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:80) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75) at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:696) at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:305) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:291) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:249) at udp.task.TestSparkStackOverflow.main(TestSparkStackOverflow.java:52)Caused by: java.lang.StackOverflowError at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1522) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) ... redacted {code} The StackOverflowError goes away at around 500 columns. When running it through the debugger, I found that it happens when trying to serialize the "[executeTask|https://github.com/apache/spark/blob/14211a19f53bd0f413396582c8970e3e0a74281d/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala#L169-L177[]|https://github.com/apache/spark/blob/14211a19f53bd0f413396582c8970e3e0a74281d/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala#L169-L177]" func in "[ClosureCleaner|https://github.com/apache/spark/blob/14211a19f53bd0f413396582c8970e3e0a74281d/core/src/main/scala/org/apache/spark/util/ClosureCleaner.scala#L405-L407]" was: On Spark 2.4.7 Standalone Mode on my laptop (Macbook Pro 2015), I ran the following: {code:java} public class TestSparkStackOverflow { public static void main(String [] args) { SparkSession spark = SparkSession .builder() .config("spark.master", "local[8]") .appName(TestSparkStackOverflow.class.getSimpleName()) .getOrCreate(); StructType inputSchema = new StructType(); inputSchema = inputSchema.add("foo", DataTypes.StringType); Dataset<Row> inputDf = spark.createDataFrame( Arrays.asList( RowFactory.create("1"), RowFactory.create("2"), RowFactory.create("3") ), inputSchema ); List<Column> lotsOfColumns = new ArrayList<>(); for (int i = 0; i < 3000; i++) { lotsOfColumns.add(lit("").as("field" + i).cast(DataTypes.StringType)); } lotsOfColumns.add(new Column("foo")); inputDf .select(JavaConverters.collectionAsScalaIterableConverter(lotsOfColumns).asScala().toSeq()) .write() .format("csv") .mode(SaveMode.Append) .save("file:///tmp/testoutput"); } } {code} And I get a StackOverflowError: {code:java} Exception in thread "main" org.apache.spark.SparkException: Job aborted.Exception in thread "main" org.apache.spark.SparkException: Job aborted. at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:198) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:159) at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104) at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102) at org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:83) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:81) at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:696) at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:696) at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:80) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75) at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:696) at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:305) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:291) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:249) at udp.task.TestSparkStackOverflow.main(TestSparkStackOverflow.java:52)Caused by: java.lang.StackOverflowError at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1522) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) ... redacted {code} The StackOverflowError goes away at around 500 columns > Large number of SELECT columns causes StackOverflowError > -------------------------------------------------------- > > Key: SPARK-33502 > URL: https://issues.apache.org/jira/browse/SPARK-33502 > Project: Spark > Issue Type: Bug > Components: SQL > Affects Versions: 2.4.7 > Reporter: Arwin S Tio > Priority: Minor > > On Spark 2.4.7 Standalone Mode on my laptop (Macbook Pro 2015), I ran the > following: > {code:java} > public class TestSparkStackOverflow { > public static void main(String [] args) { > SparkSession spark = SparkSession > .builder() > .config("spark.master", "local[8]") > .appName(TestSparkStackOverflow.class.getSimpleName()) > .getOrCreate(); StructType inputSchema = new StructType(); > inputSchema = inputSchema.add("foo", DataTypes.StringType); > Dataset<Row> inputDf = spark.createDataFrame( > Arrays.asList( > RowFactory.create("1"), > RowFactory.create("2"), > RowFactory.create("3") > ), > inputSchema > ); > > List<Column> lotsOfColumns = new ArrayList<>(); > for (int i = 0; i < 3000; i++) { > lotsOfColumns.add(lit("").as("field" + i).cast(DataTypes.StringType)); > } > lotsOfColumns.add(new Column("foo")); inputDf > > .select(JavaConverters.collectionAsScalaIterableConverter(lotsOfColumns).asScala().toSeq()) > .write() > .format("csv") > .mode(SaveMode.Append) > .save("file:///tmp/testoutput"); > } > } > {code} > > And I get a StackOverflowError: > {code:java} > Exception in thread "main" org.apache.spark.SparkException: Job > aborted.Exception in thread "main" org.apache.spark.SparkException: Job > aborted. at > org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:198) > at > org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand.run(InsertIntoHadoopFsRelationCommand.scala:159) > at > org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104) > at > org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102) > at > org.apache.spark.sql.execution.command.DataWritingCommandExec.doExecute(commands.scala:122) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) > at > org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152) at > org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127) at > org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:83) > at > org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:81) > at > org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:696) > at > org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:696) > at > org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:80) > at > org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:127) > at > org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:75) > at > org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:696) at > org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:305) > at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:291) at > org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:249) at > udp.task.TestSparkStackOverflow.main(TestSparkStackOverflow.java:52)Caused > by: java.lang.StackOverflowError at > java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1522) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at > java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at > java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) at > java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) > ... redacted {code} > > The StackOverflowError goes away at around 500 columns. > > When running it through the debugger, I found that it happens when trying to > serialize the > "[executeTask|https://github.com/apache/spark/blob/14211a19f53bd0f413396582c8970e3e0a74281d/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala#L169-L177[]|https://github.com/apache/spark/blob/14211a19f53bd0f413396582c8970e3e0a74281d/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala#L169-L177]" > func in > "[ClosureCleaner|https://github.com/apache/spark/blob/14211a19f53bd0f413396582c8970e3e0a74281d/core/src/main/scala/org/apache/spark/util/ClosureCleaner.scala#L405-L407]" -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org