lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-4348] fix merge into sql data quality in concurrent scene (#6020)

Browse Source
This commit is contained in:
KnightChess
2022-07-24 21:29:47 +08:00
committed by GitHub
parent 1a5a9f7f03
commit a54c963543
1 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/hudi/command/payload/SqlTypedRecord.scala
View File

@@ -17,7 +17,7 @@
package org.apache.spark.sql.hudi.command.payload
import com.google.common.cache.CacheBuilder
import com.google.common.cache.{Cache, CacheBuilder}
import org.apache.avro.Schema
import org.apache.avro.generic.IndexedRecord
import org.apache.hudi.HoodieSparkUtils.sparkAdapter
@@ -51,7 +51,10 @@ object SqlTypedRecord {
private val sqlTypeCache = CacheBuilder.newBuilder().build[Schema, StructType]()
private val avroDeserializerCache = CacheBuilder.newBuilder().build[Schema, HoodieAvroDeserializer]()
private val avroDeserializerCacheLocal = new ThreadLocal[Cache[Schema, HoodieAvroDeserializer]] {
override def initialValue(): Cache[Schema, HoodieAvroDeserializer] =
CacheBuilder.newBuilder().build[Schema, HoodieAvroDeserializer]()
}
def getSqlType(schema: Schema): StructType = {
sqlTypeCache.get(schema, new Callable[StructType] {
@@ -64,10 +67,10 @@ object SqlTypedRecord {
}
def getAvroDeserializer(schema: Schema): HoodieAvroDeserializer= {
avroDeserializerCache.get(schema, new Callable[HoodieAvroDeserializer] {
avroDeserializerCacheLocal.get().get(schema, new Callable[HoodieAvroDeserializer] {
override def call(): HoodieAvroDeserializer = {
val deserializer = sparkAdapter.createAvroDeserializer(schema, getSqlType(schema))
avroDeserializerCache.put(schema, deserializer)
avroDeserializerCacheLocal.get().put(schema, deserializer)
deserializer
}
})