Github user zsxwing commented on a diff in the pull request: https://github.com/apache/spark/pull/16758#discussion_r99243402 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/statefulOperators.scala --- @@ -235,3 +234,79 @@ case class StateStoreSaveExec( override def outputPartitioning: Partitioning = child.outputPartitioning } + + +/** Physical operator for executing streaming mapGroupsWithState. */ +case class MapGroupsWithStateExec( + func: (Any, Iterator[Any], LogicalKeyedState[Any]) => Iterator[Any], + keyDeserializer: Expression, + valueDeserializer: Expression, + groupingAttributes: Seq[Attribute], + dataAttributes: Seq[Attribute], + outputObjAttr: Attribute, + stateId: Option[OperatorStateId], + stateDeserializer: Expression, + stateSerializer: Seq[NamedExpression], + child: SparkPlan) extends UnaryExecNode with ObjectProducerExec with StateStoreWriter { + + override def outputPartitioning: Partitioning = child.outputPartitioning + + /** Distribute by grouping attributes */ + override def requiredChildDistribution: Seq[Distribution] = + ClusteredDistribution(groupingAttributes) :: Nil + + /** Ordering needed for using GroupingIterator */ + override def requiredChildOrdering: Seq[Seq[SortOrder]] = + Seq(groupingAttributes.map(SortOrder(_, Ascending))) + + override protected def doExecute(): RDD[InternalRow] = { + child.execute().mapPartitionsWithStateStore[InternalRow]( + getStateId.checkpointLocation, + operatorId = getStateId.operatorId, + storeVersion = getStateId.batchId, + groupingAttributes.toStructType, + child.output.toStructType, + sqlContext.sessionState, + Some(sqlContext.streams.stateStoreCoordinator)) { (store, iter) => + val numTotalStateRows = longMetric("numTotalStateRows") + val numUpdatedStateRows = longMetric("numUpdatedStateRows") + val numOutputRows = longMetric("numOutputRows") + + val groupedIter = GroupedIterator(iter, groupingAttributes, child.output) + + val getKeyObj = ObjectOperator.deserializeRowToObject(keyDeserializer, groupingAttributes) + val getKey = GenerateUnsafeProjection.generate(groupingAttributes, child.output) --- End diff -- nit: not used
--- 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