HyukjinKwon commented on code in PR #38468:
URL: https://github.com/apache/spark/pull/38468#discussion_r1018681767
##########
connector/connect/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectStreamHandler.scala:
##########
@@ -114,10 +123,97 @@ class SparkConnectStreamHandler(responseObserver:
StreamObserver[Response]) exte
responseObserver.onNext(response.build())
}
- responseObserver.onNext(sendMetricsToResponse(clientId, rows))
+ responseObserver.onNext(sendMetricsToResponse(clientId, dataframe))
responseObserver.onCompleted()
}
+ def processRowsAsArrowBatches(clientId: String, dataframe: DataFrame): Unit
= {
+ val spark = dataframe.sparkSession
+ val schema = dataframe.schema
+ // TODO: control the batch size instead of max records
+ val maxRecordsPerBatch = spark.sessionState.conf.arrowMaxRecordsPerBatch
+ val timeZoneId = spark.sessionState.conf.sessionLocalTimeZone
+
+ SQLExecution.withNewExecutionId(dataframe.queryExecution,
Some("collectArrow")) {
+ val rows = dataframe.queryExecution.executedPlan.execute()
+ val numPartitions = rows.getNumPartitions
+ var numSent = 0
+
+ if (numPartitions > 0) {
+ type Batch = (Array[Byte], Long, Long)
+
+ val batches = rows.mapPartitionsInternal { iter =>
+ ArrowConverters
+ .toArrowBatchIterator(iter, schema, maxRecordsPerBatch, timeZoneId)
+ }
+
+ val signal = new Object
+ val partitions = Array.fill[Array[Batch]](numPartitions)(null)
+
+ val processPartition = (iter: Iterator[Batch]) => iter.toArray
+
+ val resultHandler = (partitionId: Int, partition: Array[Batch]) => {
+ signal.synchronized {
+ partitions(partitionId) = partition
+ signal.notify()
+ }
+ val i = 0 // Unit
+ }
+
+ spark.sparkContext.runJob(batches, processPartition, resultHandler)
+
+ var currentPartitionId = 0
+ while (currentPartitionId < numPartitions) {
+ val partition = signal.synchronized {
+ while (partitions(currentPartitionId) == null) {
+ signal.wait()
Review Comment:
Is it to wait the partitions to be fetched in order? I think we can just
fetch all and send the first if that arrives. To optimize this, I think we
should eventually do the reordering in some way to match with PySpark's
implementation. Even we should deduplicate the codes ideally.
--
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]
