You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2022/11/04 01:33:00 UTC
[GitHub] [spark] HyukjinKwon commented on a diff in pull request #38468: [SPARK-41005][CONNECT][PYTHON] Arrow-based collect
HyukjinKwon commented on code in PR #38468:
URL: https://github.com/apache/spark/pull/38468#discussion_r1013528536
##########
connector/connect/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectStreamHandler.scala:
##########
@@ -117,7 +131,36 @@ 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 schema = dataframe.schema
+ val maxRecordsPerBatch = dataframe.sparkSession.sessionState.conf.arrowMaxRecordsPerBatch
+ val timeZoneId = dataframe.sparkSession.sessionState.conf.sessionLocalTimeZone
+
+ val batches = dataframe.queryExecution.executedPlan
+ .execute()
+ .mapPartitionsInternal { iter =>
+ ArrowConverters
+ .toArrowBatchIterator(iter, schema, maxRecordsPerBatch, timeZoneId, TaskContext.get)
+ }
+
+ batches.toLocalIterator.foreach { case (bytes, count, size) =>
Review Comment:
Yeah we should avoid `toLocalIterator`
--
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: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org