viirya commented on a change in pull request #29104:
URL: https://github.com/apache/spark/pull/29104#discussion_r458444651
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala
##########
@@ -71,6 +71,18 @@ private[execution] sealed trait HashedRelation extends
KnownSizeEstimation {
*/
def keyIsUnique: Boolean
+ /**
+ * Note that, the hashed relation can be empty despite the
Iterator[InternalRow] being not empty,
+ * since the hashed relation skips over null keys.
+ */
Review comment:
Reading this doc, sounds like `inputEmpty` returns true if there are
null keys. But I saw
```
def inputEmpty: Boolean = numKeys == 0 && !anyNullKeyExists
```
Can you rephase this doc to clearly state when `inputEmpty` returns true?
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNullAwareHashJoinExec.scala
##########
@@ -0,0 +1,205 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.joins
+
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext,
ExprCode, GenerateUnsafeProjection}
+import org.apache.spark.sql.catalyst.optimizer.{BuildRight, BuildSide}
+import org.apache.spark.sql.catalyst.plans._
+import org.apache.spark.sql.catalyst.plans.physical._
+import org.apache.spark.sql.execution.{CodegenSupport, ExplainUtils, SparkPlan}
+import org.apache.spark.sql.execution.metric.SQLMetrics
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.types.LongType
+
+case class BroadcastNullAwareHashJoinExec(
+ leftKeys: Seq[Expression],
+ rightKeys: Seq[Expression],
+ left: SparkPlan,
+ right: SparkPlan,
+ buildSide: BuildSide,
+ joinType: JoinType,
+ condition: Option[Expression]) extends BaseJoinExec with CodegenSupport {
+
+ // TODO support multi column NULL-aware anti join in future.
+ // See. http://www.vldb.org/pvldb/vol2/vldb09-423.pdf Section 6
+ // multi-column null aware anti join is much more complicated than single
column ones.
+ require(leftKeys.length == 1, "leftKeys length should be 1")
+ require(rightKeys.length == 1, "rightKeys length should be 1")
+ require(right.output.length == 1, "null aware anti join only supports single
column.")
+ require(joinType == LeftAnti, "joinType must be LeftAnti.")
+ require(buildSide == BuildRight, "buildSide must be BuildRight.")
+ require(SQLConf.get.nullAwareAntiJoinOptimizeEnabled,
+ "nullAwareAntiJoinOptimizeEnabled must be on for null aware anti join
optimize.")
+
+ override lazy val metrics = Map(
+ "numOutputRows" -> SQLMetrics.createMetric(sparkContext, "number of output
rows"))
+
+ private val (streamed, broadcast) = (left, right)
+
+ override def simpleStringWithNodeId(): String = {
+ val opId = ExplainUtils.getOpId(this)
+ s"$nodeName $joinType ${buildSide} ($opId)".trim
+ }
+
+ override def requiredChildDistribution: Seq[Distribution] = {
+ UnspecifiedDistribution :: BroadcastDistribution(IdentityBroadcastMode) ::
Nil
+ }
+
+ private[this] def genResultProjection: UnsafeProjection = {
+ UnsafeProjection.create(output, output)
+ }
+
+ override def output: Seq[Attribute] = {
+ left.output
+ }
+
+ private def prepareBroadcastHashedRelation = {
+ val buildSideRows = broadcast.executeBroadcast[Array[InternalRow]]().value
+ HashedRelation(buildSideRows.iterator,
+ BindReferences.bindReferences[Expression](
+ Seq(right.output.head), AttributeSeq(right.output)),
+ buildSideRows.length)
+ }
Review comment:
why don't just call `buildPlan.executeBroadcast[HashedRelation]()` like
BroadcastHashJoinExec?
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNullAwareHashJoinExec.scala
##########
@@ -0,0 +1,205 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.joins
+
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext,
ExprCode, GenerateUnsafeProjection}
+import org.apache.spark.sql.catalyst.optimizer.{BuildRight, BuildSide}
+import org.apache.spark.sql.catalyst.plans._
+import org.apache.spark.sql.catalyst.plans.physical._
+import org.apache.spark.sql.execution.{CodegenSupport, ExplainUtils, SparkPlan}
+import org.apache.spark.sql.execution.metric.SQLMetrics
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.types.LongType
+
+case class BroadcastNullAwareHashJoinExec(
+ leftKeys: Seq[Expression],
+ rightKeys: Seq[Expression],
+ left: SparkPlan,
+ right: SparkPlan,
+ buildSide: BuildSide,
+ joinType: JoinType,
+ condition: Option[Expression]) extends BaseJoinExec with CodegenSupport {
+
+ // TODO support multi column NULL-aware anti join in future.
+ // See. http://www.vldb.org/pvldb/vol2/vldb09-423.pdf Section 6
+ // multi-column null aware anti join is much more complicated than single
column ones.
+ require(leftKeys.length == 1, "leftKeys length should be 1")
+ require(rightKeys.length == 1, "rightKeys length should be 1")
+ require(right.output.length == 1, "null aware anti join only supports single
column.")
Review comment:
I think single-key column optimization just requires one column involved
in the NAAJ condition. Why we also require right.output.length == 1?
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNullAwareHashJoinExec.scala
##########
@@ -0,0 +1,205 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.joins
+
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext,
ExprCode, GenerateUnsafeProjection}
+import org.apache.spark.sql.catalyst.optimizer.{BuildRight, BuildSide}
+import org.apache.spark.sql.catalyst.plans._
+import org.apache.spark.sql.catalyst.plans.physical._
+import org.apache.spark.sql.execution.{CodegenSupport, ExplainUtils, SparkPlan}
+import org.apache.spark.sql.execution.metric.SQLMetrics
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.types.LongType
+
+case class BroadcastNullAwareHashJoinExec(
+ leftKeys: Seq[Expression],
+ rightKeys: Seq[Expression],
+ left: SparkPlan,
+ right: SparkPlan,
+ buildSide: BuildSide,
+ joinType: JoinType,
+ condition: Option[Expression]) extends BaseJoinExec with CodegenSupport {
+
+ // TODO support multi column NULL-aware anti join in future.
+ // See. http://www.vldb.org/pvldb/vol2/vldb09-423.pdf Section 6
+ // multi-column null aware anti join is much more complicated than single
column ones.
+ require(leftKeys.length == 1, "leftKeys length should be 1")
+ require(rightKeys.length == 1, "rightKeys length should be 1")
+ require(right.output.length == 1, "null aware anti join only supports single
column.")
+ require(joinType == LeftAnti, "joinType must be LeftAnti.")
Review comment:
If this is only for LeftAnti, maybe just name it as
BroadcastNullAwareLeftAntiHashJoinExec?
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala
##########
@@ -300,8 +318,12 @@ private[joins] class UnsafeHashedRelation(
}
override def read(kryo: Kryo, in: Input): Unit = Utils.tryOrIOException {
- read(() => in.readInt(), () => in.readLong(), in.readBytes)
+ read(() => in.readBoolean(), () => in.readInt(), () => in.readLong(),
in.readBytes)
}
+
+ override def inputEmpty: Boolean = binaryMap.inputEmpty
Review comment:
Don't need `!anyNullKeyExists` here?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
