zhengruifeng commented on code in PR #38468: URL: https://github.com/apache/spark/pull/38468#discussion_r1012441577
########## connector/connect/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectStreamHandler.scala: ########## @@ -117,7 +121,38 @@ 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 = { + import org.apache.arrow.vector.ipc.message.{IpcOption, MessageSerializer} + + val schema = dataframe.schema + val maxRecordsPerBatch = dataframe.sparkSession.sessionState.conf.arrowMaxRecordsPerBatch + val timeZoneId = dataframe.sparkSession.sessionState.conf.sessionLocalTimeZone + val arrowSchema = ArrowUtils.toArrowSchema(schema, timeZoneId) + val schemaBuffer = MessageSerializer.serializeMetadata(arrowSchema, IpcOption.DEFAULT) + + val rows = dataframe.queryExecution.executedPlan.execute().map(_.copy()).collect() Review Comment: 1, agree, will update 2, i think we can use `toLocalIterator`, but it may trigger multi jobs https://github.com/apache/spark/pull/38300#discussion_r1001301224 -- 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