hvanhovell commented on code in PR #38468: URL: https://github.com/apache/spark/pull/38468#discussion_r1013186031
########## 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) Review Comment: Can you file a follow-up to limit the size of the batch? GRPC does not really like it when we send large messages ( > 4 MB). -- 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-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org