[
https://issues.apache.org/jira/browse/SPARK-25987?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ivan Tsukanov updated SPARK-25987:
----------------------------------
Description:
When I execute
{code:java}
val columnsCount = 100
val columns = (1 to columnsCount).map(i => s"col$i")
val initialData = (1 to columnsCount).map(i => s"val$i")
val df = sparkSession.createDataFrame(
rowRDD = sparkSession.sparkContext.makeRDD(Seq(Row.fromSeq(initialData))),
schema = StructType(columns.map(StructField(_, StringType, true)))
)
val addSuffixUDF = udf(
(str: String) => str + "_added"
)
implicit class DFOps(df: DataFrame) {
def addSuffix() = {
df.select(columns.map(col =>
addSuffixUDF(df(col)).as(col)
): _*)
}
}
df
.addSuffix()
.addSuffix()
.addSuffix()
.show()
{code}
I get
{code:java}
An exception or error caused a run to abort.
java.lang.StackOverflowError
at org.codehaus.janino.CodeContext.flowAnalysis(CodeContext.java:385)
at org.codehaus.janino.CodeContext.flowAnalysis(CodeContext.java:553)
...
{code}
If I reduce columns number (to 10 for example) or do `addSuffix` only once - it
works fine.
was:
When I execute
{code:java}
val columnsCount = 100
val columns = (1 to columnsCount).map(i => s"col$i")
val initialData = (1 to columnsCount).map(i => s"val$i")
val df = sparkSession.createDataFrame(
rowRDD = sparkSession.sparkContext.makeRDD(Seq(Row.fromSeq(initialData))),
schema = StructType(columns.map(StructField(_, StringType, true)))
)
val addSuffixUDF = udf(
(str: String) => str + "_added"
)
implicit class DFOps(df: DataFrame) {
def addSuffix() = {
df.select(columns.map(col =>
addSuffixUDF(df(col)).as(col)
): _*)
}
}
df
.addSuffix()
.addSuffix()
.addSuffix()
.show()
{code}
I get
{code:java}
An exception or error caused a run to abort.
java.lang.StackOverflowError
at org.codehaus.janino.CodeContext.flowAnalysis(CodeContext.java:385)
at org.codehaus.janino.CodeContext.flowAnalysis(CodeContext.java:553)
...
{code}
If I reduce columns number (to 10 for example) or do `addSuffix` only once - it
works fine.
> StackOverflowError when executing many operations on a table with many columns
> ------------------------------------------------------------------------------
>
> Key: SPARK-25987
> URL: https://issues.apache.org/jira/browse/SPARK-25987
> Project: Spark
> Issue Type: Bug
> Components: Spark Core
> Affects Versions: 2.2.1, 2.2.2, 2.3.0, 2.3.2
> Environment: Ubuntu 18.04.1 LTS, openjdk "1.8.0_181"
> Reporter: Ivan Tsukanov
> Priority: Major
>
> When I execute
> {code:java}
> val columnsCount = 100
> val columns = (1 to columnsCount).map(i => s"col$i")
> val initialData = (1 to columnsCount).map(i => s"val$i")
> val df = sparkSession.createDataFrame(
> rowRDD = sparkSession.sparkContext.makeRDD(Seq(Row.fromSeq(initialData))),
> schema = StructType(columns.map(StructField(_, StringType, true)))
> )
> val addSuffixUDF = udf(
> (str: String) => str + "_added"
> )
> implicit class DFOps(df: DataFrame) {
> def addSuffix() = {
> df.select(columns.map(col =>
> addSuffixUDF(df(col)).as(col)
> ): _*)
> }
> }
> df
> .addSuffix()
> .addSuffix()
> .addSuffix()
> .show()
> {code}
> I get
> {code:java}
> An exception or error caused a run to abort.
> java.lang.StackOverflowError
> at org.codehaus.janino.CodeContext.flowAnalysis(CodeContext.java:385)
> at org.codehaus.janino.CodeContext.flowAnalysis(CodeContext.java:553)
> ...
> {code}
> If I reduce columns number (to 10 for example) or do `addSuffix` only once -
> it works fine.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
