Skip to content

[HUDI-5868] Make hudi-spark compatible against Spark 3.3.2 #8082

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

Merged
danny0405 merged 2 commits into from
May 11, 2023
Merged

[HUDI-5868] Make hudi-spark compatible against Spark 3.3.2 #8082

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3dca5eb
[HUDI-5868] Make hudi-spark compatible against Spark 3.3.2
Mar 1, 2023
36f9bb2
remove test
May 10, 2023
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
2 changes: 2 additions & 0 deletions ...i-spark-client/src/main/java/org/apache/hudi/io/storage/HoodieSparkFileReaderFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,8 @@ protected HoodieFileReader newParquetFileReader(Configuration conf, Path path) {
conf.setIfUnset(SQLConf.PARQUET_BINARY_AS_STRING().key(), SQLConf.PARQUET_BINARY_AS_STRING().defaultValueString());
conf.setIfUnset(SQLConf.PARQUET_INT96_AS_TIMESTAMP().key(), SQLConf.PARQUET_INT96_AS_TIMESTAMP().defaultValueString());
conf.setIfUnset(SQLConf.CASE_SENSITIVE().key(), SQLConf.CASE_SENSITIVE().defaultValueString());
// Using string value of this conf to preserve compatibility across spark versions.
conf.setIfUnset("spark.sql.legacy.parquet.nanosAsLong", "false");
return new HoodieSparkParquetReader(conf, path);
}

Expand Down
1 change: 1 addition & 0 deletions hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/HoodieSparkUtils.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,7 @@ private[hudi] trait SparkVersionsSupport {
def gteqSpark3_2_1: Boolean = getSparkVersion >= "3.2.1"
def gteqSpark3_2_2: Boolean = getSparkVersion >= "3.2.2"
def gteqSpark3_3: Boolean = getSparkVersion >= "3.3"
def gteqSpark3_3_2: Boolean = getSparkVersion >= "3.3.2"
Copy link
Contributor

@yihua yihua May 8, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this based on compile-time Spark version or runtime Spark version?

Copy link
Contributor

@danny0405 danny0405 May 9, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should be runtime, I think.

}

object HoodieSparkUtils extends SparkAdapterSupport with SparkVersionsSupport with Logging {
Expand Down
5 changes: 4 additions & 1 deletion ...rk-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/BaseFileOnlyRelation.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,10 @@ case class BaseFileOnlyRelation(override val sqlContext: SQLContext,

override def imbueConfigs(sqlContext: SQLContext): Unit = {
super.imbueConfigs(sqlContext)
sqlContext.sparkSession.sessionState.conf.setConfString("spark.sql.parquet.enableVectorizedReader", "true")
// TODO Issue with setting this to true in spark 332
if (!HoodieSparkUtils.gteqSpark3_3_2) {
sqlContext.sparkSession.sessionState.conf.setConfString("spark.sql.parquet.enableVectorizedReader", "true")
}
}

protected override def composeRDD(fileSplits: Seq[HoodieBaseFileSplit],
Expand Down
6 changes: 5 additions & 1 deletion ...g/apache/spark/sql/execution/datasources/parquet/Spark32PlusHoodieParquetFileFormat.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,11 @@ class Spark32PlusHoodieParquetFileFormat(private val shouldAppendPartitionValues
hadoopConf.setBoolean(
SQLConf.PARQUET_INT96_AS_TIMESTAMP.key,
sparkSession.sessionState.conf.isParquetINT96AsTimestamp)

// Using string value of this conf to preserve compatibility across spark versions.
hadoopConf.setBoolean(
"spark.sql.legacy.parquet.nanosAsLong",
sparkSession.sessionState.conf.getConfString("spark.sql.legacy.parquet.nanosAsLong", "false").toBoolean
)
val internalSchemaStr = hadoopConf.get(SparkInternalSchemaConverter.HOODIE_QUERY_SCHEMA)
// For Spark DataSource v1, there's no Physical Plan projection/schema pruning w/in Spark itself,
// therefore it's safe to do schema projection here
Expand Down
2 changes: 2 additions & 0 deletions pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2213,6 +2213,7 @@
<spark3.version>${spark33.version}</spark3.version>
<spark.version>${spark3.version}</spark.version>
<sparkbundle.version>3</sparkbundle.version>
<scala12.version>2.12.15</scala12.version>
<scala.version>${scala12.version}</scala.version>
<scala.binary.version>2.12</scala.binary.version>
<hudi.spark.module>hudi-spark3.3.x</hudi.spark.module>
Expand Down Expand Up @@ -2337,6 +2338,7 @@
<spark3.version>${spark33.version}</spark3.version>
<spark.version>${spark3.version}</spark.version>
<sparkbundle.version>3.3</sparkbundle.version>
<scala12.version>2.12.15</scala12.version>
<scala.version>${scala12.version}</scala.version>
<scala.binary.version>2.12</scala.binary.version>
<hudi.spark.module>hudi-spark3.3.x</hudi.spark.module>
Expand Down