HyukjinKwon commented on code in PR #38468:
URL: https://github.com/apache/spark/pull/38468#discussion_r1019820867
##########
connector/connect/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectStreamHandler.scala:
##########
@@ -114,10 +120,93 @@ class SparkConnectStreamHandler(responseObserver:
StreamObserver[Response]) exte
responseObserver.onNext(response.build())
}
- responseObserver.onNext(sendMetricsToResponse(clientId, rows))
+ responseObserver.onNext(sendMetricsToResponse(clientId, dataframe))
responseObserver.onCompleted()
}
+ def processAsArrowBatches(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)
+
+ val batches = rows.mapPartitionsInternal { iter =>
+ ArrowConverters
+ .toArrowBatchIterator(iter, schema, maxRecordsPerBatch, timeZoneId)
+ }
+
+ val signal = new Object
+ val partitions = collection.mutable.Map.empty[Int, Array[Batch]]
+
+ val processPartition = (iter: Iterator[Batch]) => iter.toArray
+
+ // This callback is executed by the DAGScheduler thread.
+ // After fetching a partition, it inserts the partition into the Map,
and then
+ // wakes up the main thread.
+ val resultHandler = (partitionId: Int, partition: Array[Batch]) => {
+ signal.synchronized {
+ partitions(partitionId) = partition
+ signal.notify()
+ }
+ ()
+ }
+
+ spark.sparkContext.runJob(batches, processPartition, resultHandler)
Review Comment:
Seems like it had to be (async) `submitJob` instead of (sync) `runJob`
(https://github.com/apache/spark/pull/38468#discussion_r1013184548). In fact, I
figured out a simpler way to avoid synchronization. PTAL
https://github.com/apache/spark/pull/38613
--
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]
