JkSelf commented on code in PR #8931:
URL: https://github.com/apache/incubator-gluten/pull/8931#discussion_r2536675240
##########
backends-velox/src/main/scala/org/apache/spark/sql/execution/ColumnarBuildSideRelation.scala:
##########
@@ -133,6 +148,85 @@ case class ColumnarBuildSideRelation(
override def asReadOnlyCopy(): ColumnarBuildSideRelation = this
+ private var hashTableData: Long = 0L
+
+ def buildHashTable(
+ broadCastContext: BroadcastHashJoinContext): (Long,
ColumnarBuildSideRelation) =
+ synchronized {
+ if (hashTableData == 0) {
+ val runtime = Runtimes.contextInstance(
+ BackendsApiManager.getBackendName,
+ "ColumnarBuildSideRelation#buildHashTable")
+ val jniWrapper = ColumnarBatchSerializerJniWrapper.create(runtime)
+ val serializeHandle: Long = {
+ val allocator = ArrowBufferAllocators.contextInstance()
+ val cSchema = ArrowSchema.allocateNew(allocator)
+ val arrowSchema = SparkArrowUtil.toArrowSchema(
+ SparkShimLoader.getSparkShims.structFromAttributes(output),
+ SQLConf.get.sessionLocalTimeZone)
+ ArrowAbiUtil.exportSchema(allocator, arrowSchema, cSchema)
+ val handle = jniWrapper
+ .init(cSchema.memoryAddress())
+ cSchema.close()
+ handle
+ }
+
+ val batchArray = new ArrayBuffer[Long]
+
+ var batchId = 0
+ while (batchId < batches.size) {
+ batchArray.append(jniWrapper.deserialize(serializeHandle,
batches(batchId)))
+ batchId += 1
+ }
+
+ logDebug(
+ s"BHJ value size: " +
+ s"${broadCastContext.buildHashTableId} = ${batches.length}")
+
+ val (keys, newOutput) = if (newBuildKeys.isEmpty) {
+ (
+ broadCastContext.buildSideJoinKeys.asJava,
+ broadCastContext.buildSideStructure.asJava
+ )
+ } else {
+ (
+ newBuildKeys.asJava,
+ output.asJava
+ )
+ }
+
+ val joinKey = keys.asScala
+ .map {
+ key =>
+ val attr = ConverterUtils.getAttrFromExpr(key)
+ ConverterUtils.genColumnNameWithExprId(attr)
+ }
+ .mkString(",")
+
+ // Build the hash table
+ hashTableData = HashJoinBuilder
+ .nativeBuild(
+ broadCastContext.buildHashTableId,
+ batchArray.toArray,
+ joinKey,
+ broadCastContext.substraitJoinType.ordinal(),
+ broadCastContext.hasMixedFiltCondition,
+ broadCastContext.isExistenceJoin,
+ SubstraitUtil.toNameStruct(newOutput).toByteArray,
+ broadCastContext.isNullAwareAntiJoin
+ )
+
+ jniWrapper.close(serializeHandle)
+ (hashTableData, this)
+ } else {
+ (HashJoinBuilder.cloneHashTable(hashTableData), null)
+ }
+ }
+
+ def reset(): Unit = synchronized {
+ hashTableData = 0
Review Comment:
We will release the real data by calling
https://github.com/apache/incubator-gluten/pull/8931/files#diff-1c998fbcdc31d781f6bbe45f4b6fdd3e29925b6c9187849bb3ab2f7867148199R109
--
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]
