Skip to content

[SPARK-58408][CORE] Register TimestampNanosVal in KryoSerializer #57607

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
viirya wants to merge 1 commit into from
+12 −1
Closed

[SPARK-58408][CORE] Register TimestampNanosVal in KryoSerializer #57607

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion core/src/main/scala/org/apache/spark/serializer/KryoSerializer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ import org.apache.spark.internal.io.FileCommitProtocol._
import org.apache.spark.network.util.ByteUnit
import org.apache.spark.scheduler.{CompressedMapStatus, HighlyCompressedMapStatus}
import org.apache.spark.storage._
import org.apache.spark.unsafe.types.UTF8String
import org.apache.spark.unsafe.types.{TimestampNanosVal, UTF8String}
import org.apache.spark.util.{BoundedPriorityQueue, ByteBufferInputStream, NextIterator, SerializableConfiguration, SerializableJobConf, Utils}
import org.apache.spark.util.collection.{BitSet, CompactBuffer}
import org.apache.spark.util.io.ChunkedByteBuffer
Expand Down Expand Up @@ -236,6 +236,9 @@ class KryoSerializer(conf: SparkConf)
kryo.register(classOf[ArrayBuffer[Any]])
kryo.register(classOf[Array[Array[Byte]]])
kryo.register(classOf[UTF8String])
// Nanosecond-timestamp min/max bounds inside cached-batch statistics rows
// (TimestampNanosColumnStats and the Arrow cache's vector-side stats).
kryo.register(classOf[TimestampNanosVal])

// We can't load those class directly in order to avoid unnecessary jar dependencies.
// We load them safely, ignore it if the class not found.
Expand Down
8 changes: 8 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/CacheTableInKryoSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,14 @@ class CacheTableInKryoSuite extends SharedSparkSession {
}
}

test("SPARK-58408: TimestampNanosVal stats should be registered in KryoSerializer") {
// Cached-batch statistics rows carry TimestampNanosVal min/max bounds for
// nanosecond-timestamp columns (TimestampNanosColumnStats), so persisting such a cache
// through Kryo with registrationRequired must find the class registered.
val df = sql("SELECT CAST('2025-01-06 12:30:45.123456789' AS TIMESTAMP_NTZ(9)) AS ts")
assert(df.persist(StorageLevel.DISK_ONLY).count() === 1)
}

test("SPARK-51813 DefaultCachedBatchKryoSerializer do not propagate nulls") {
val ks = new KryoSerializer(this.sparkConf)
val kryo = ks.newKryo()
Expand Down