Github user marmbrus commented on a diff in the pull request:
https://github.com/apache/spark/pull/7162#discussion_r33883033
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastHashOuterJoin.scala
---
@@ -0,0 +1,120 @@
+/*
+ * 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.annotation.DeveloperApi
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.plans.physical.{Distribution,
UnspecifiedDistribution}
+import org.apache.spark.sql.catalyst.plans.{JoinType, LeftOuter,
RightOuter}
+import org.apache.spark.sql.execution.{BinaryNode, SparkPlan}
+import org.apache.spark.util.ThreadUtils
+
+import scala.concurrent._
+import scala.concurrent.duration._
+
+/**
+ * :: DeveloperApi ::
+ * Performs a outer hash join for two child relations. When the output
RDD of this operator is
+ * being constructed, a Spark job is asynchronously started to calculate
the values for the
+ * broadcasted relation. This data is then placed in a Spark broadcast
variable. The streamed
+ * relation is not shuffled.
+ */
+@DeveloperApi
+case class BroadcastHashOuterJoin(
+ leftKeys: Seq[Expression],
+ rightKeys: Seq[Expression],
+ joinType: JoinType,
+ condition: Option[Expression],
+ left: SparkPlan,
+ right: SparkPlan) extends BinaryNode with HashOuterJoin {
+
+ val timeout = {
+ val timeoutValue = sqlContext.conf.broadcastTimeout
+ if (timeoutValue < 0) {
+ Duration.Inf
+ } else {
+ timeoutValue.seconds
+ }
+ }
+
+ override def requiredChildDistribution: Seq[Distribution] =
+ UnspecifiedDistribution :: UnspecifiedDistribution :: Nil
+
+ private[this] lazy val (buildPlan, streamedPlan) = joinType match {
+ case RightOuter => (left, right)
+ case LeftOuter => (right, left)
+ case x =>
+ throw new IllegalArgumentException(
+ s"BroadcastHashOuterJoin should not take $x as the JoinType")
+ }
+
+ private[this] lazy val (buildKeys, streamedKeys) = joinType match {
+ case RightOuter => (leftKeys, rightKeys)
+ case LeftOuter => (rightKeys, leftKeys)
+ case x =>
+ throw new IllegalArgumentException(
+ s"BroadcastHashOuterJoin should not take $x as the JoinType")
+ }
+
+ @transient
+ private val broadcastFuture = future {
+ // Note that we use .execute().collect() because we don't want to
convert data to Scala types
+ val input: Array[InternalRow] =
buildPlan.execute().map(_.copy()).collect()
+ // buildHashTable uses code-generated rows as keys, which are not
serializable
+ val hashed = new GeneralHashedRelation(
+ buildHashTable(input.iterator, newProjection(buildKeys,
buildPlan.output)))
--- End diff --
This still fails for me when I run it on a real cluster. I'd just change
this to `buildHashTable(input.iterator, new InterpretedProjection(buildKeys,
buildPlan.output))) or we might even just change `newProjection` to always use
`InterpretedProjection`.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
