viirya commented on a change in pull request #32875:
URL: https://github.com/apache/spark/pull/32875#discussion_r774351199
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala
##########
@@ -352,3 +350,151 @@ case class BroadcastPartitioning(mode: BroadcastMode)
extends Partitioning {
case _ => false
}
}
+
+/**
+ * This is used in the scenario where an operator has multiple children (e.g.,
join) and one or more
+ * of which have their own requirement regarding whether its data can be
considered as
+ * co-partitioned from others. This offers APIs for:
+ *
+ * - Comparing with specs from other children of the operator and check if
they are compatible.
+ * When two specs are compatible, we can say their data are
co-partitioned, and Spark will
+ * potentially be able to eliminate shuffle if necessary.
+ * - Creating a partitioning that can be used to re-partition another child,
so that to make it
+ * having a compatible partitioning as this node.
+ */
+trait ShuffleSpec {
+ /**
+ * Returns the number of partitions of this shuffle spec
+ */
+ def numPartitions: Int
+
+ /**
+ * Returns true iff this spec is compatible with the provided shuffle spec.
+ *
+ * A true return value means that the data partitioning from this spec can
be seen as
+ * co-partitioned with the `other`, and therefore no shuffle is required
when joining the two
+ * sides.
+ */
+ def isCompatibleWith(other: ShuffleSpec): Boolean
+
+ /**
+ * Whether this shuffle spec can be used to create partitionings for the
other children.
+ */
+ def canCreatePartitioning: Boolean = false
+
+ /**
+ * Creates a partitioning that can be used to re-partition the other side
with the given
+ * clustering expressions.
+ *
+ * This will only be called when:
+ * - [[canCreatePartitioning]] returns true.
+ * - [[isCompatibleWith]] returns false on the side where the `clustering`
is from.
+ */
+ def createPartitioning(clustering: Seq[Expression]): Partitioning =
+ throw new UnsupportedOperationException("Operation unsupported for " +
+ s"${getClass.getCanonicalName}")
+}
+
+case object SinglePartitionShuffleSpec extends ShuffleSpec {
+ override def isCompatibleWith(other: ShuffleSpec): Boolean = {
+ other.numPartitions == 1
+ }
+
+ override def canCreatePartitioning: Boolean = true
+
+ override def createPartitioning(clustering: Seq[Expression]): Partitioning =
+ SinglePartition
+
+ override def numPartitions: Int = 1
+}
+
+case class RangeShuffleSpec(
+ numPartitions: Int,
+ distribution: ClusteredDistribution) extends ShuffleSpec {
+
+ override def isCompatibleWith(other: ShuffleSpec): Boolean = other match {
+ case SinglePartitionShuffleSpec => numPartitions == 1
+ case ShuffleSpecCollection(specs) => specs.exists(isCompatibleWith)
+ // `RangePartitioning` is not compatible with any other partitioning since
it can't guarantee
+ // data are co-partitioned for all the children, as range boundaries are
randomly sampled.
+ case _ => false
Review comment:
ya, as range shuffle spec can have only one partition too.
--
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]
