LuciferYang commented on code in PR #38064:
URL: https://github.com/apache/spark/pull/38064#discussion_r1025953966
##########
sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala:
##########
@@ -2228,6 +2231,31 @@ class DatasetSuite extends QueryTest
}
}
+class DatasetLargeResultCollectingSuite extends QueryTest
+ with SharedSparkSession {
+
+ override protected def sparkConf: SparkConf =
super.sparkConf.set(MAX_RESULT_SIZE.key, "4g")
+ test("collect data with single partition larger than 2GB bytes array limit")
{
+ // This test requires large memory and leads to OOM in Github Action so we
skip it. Developer
+ // should verify it in local build.
+ assume(!sys.env.contains("GITHUB_ACTIONS"))
Review Comment:
hmm... I test this suite with **Java 8/11/17** on Linux/MacOS On Apple
Silicon with following commands:
- Maven:
```
build/mvn clean install -DskipTests -pl sql/core -am
build/mvn clean test -pl sql/core -Dtest=none
-DwildcardSuites=org.apache.spark.sql.DatasetLargeResultCollectingSuite
```
and
```
dev/change-scala-version.sh 2.13
build/mvn clean install -DskipTests -pl sql/core -am -Pscala-2.13
build/mvn clean test -pl sql/core -Pscala-2.13 -Dtest=none
-DwildcardSuites=org.apache.spark.sql.DatasetLargeResultCollectingSuite
```
- SBT:
```
build/sbt clean "sql/testOnly
org.apache.spark.sql.DatasetLargeResultCollectingSuite"
```
```
dev/change-scala-version.sh 2.13
build/sbt clean "sql/testOnly
org.apache.spark.sql.DatasetLargeResultCollectingSuite" -Pscala-2.13
```
All test failed with `java.lang.OutOfMemoryError: Java heap space` as
follows:
```
10:19:56.910 ERROR org.apache.spark.executor.Executor: Exception in task 0.0
in stage 0.0 (TID 0)
java.lang.OutOfMemoryError: Java heap space
at java.nio.HeapByteBuffer.<init>(HeapByteBuffer.java:57)
at java.nio.ByteBuffer.allocate(ByteBuffer.java:335)
at
org.apache.spark.serializer.SerializerHelper$.$anonfun$serializeToChunkedBuffer$1(SerializerHelper.scala:40)
at
org.apache.spark.serializer.SerializerHelper$.$anonfun$serializeToChunkedBuffer$1$adapted(SerializerHelper.scala:40)
at
org.apache.spark.serializer.SerializerHelper$$$Lambda$2321/1995130077.apply(Unknown
Source)
at
org.apache.spark.util.io.ChunkedByteBufferOutputStream.allocateNewChunkIfNeeded(ChunkedByteBufferOutputStream.scala:87)
at
org.apache.spark.util.io.ChunkedByteBufferOutputStream.write(ChunkedByteBufferOutputStream.scala:75)
at
java.io.ObjectOutputStream$BlockDataOutputStream.write(ObjectOutputStream.java:1853)
at java.io.ObjectOutputStream.write(ObjectOutputStream.java:709)
at
org.apache.spark.util.Utils$.$anonfun$writeByteBuffer$1(Utils.scala:271)
at
org.apache.spark.util.Utils$.$anonfun$writeByteBuffer$1$adapted(Utils.scala:271)
at org.apache.spark.util.Utils$$$Lambda$2324/69671223.apply(Unknown
Source)
at org.apache.spark.util.Utils$.writeByteBufferImpl(Utils.scala:249)
at org.apache.spark.util.Utils$.writeByteBuffer(Utils.scala:271)
at
org.apache.spark.util.io.ChunkedByteBuffer.$anonfun$writeExternal$2(ChunkedByteBuffer.scala:103)
at
org.apache.spark.util.io.ChunkedByteBuffer.$anonfun$writeExternal$2$adapted(ChunkedByteBuffer.scala:103)
at
org.apache.spark.util.io.ChunkedByteBuffer$$Lambda$2323/1073743200.apply(Unknown
Source)
at scala.collection.ArrayOps$.foreach$extension(ArrayOps.scala:1328)
at
org.apache.spark.util.io.ChunkedByteBuffer.writeExternal(ChunkedByteBuffer.scala:103)
at
java.io.ObjectOutputStream.writeExternalData(ObjectOutputStream.java:1459)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1430)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1378)
at
java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174)
at
java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at
org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:46)
at
org.apache.spark.serializer.SerializerHelper$.serializeToChunkedBuffer(SerializerHelper.scala:42)
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:599)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
