hvanhovell commented on code in PR #38468: URL: https://github.com/apache/spark/pull/38468#discussion_r1015644446
########## connector/connect/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectStreamHandler.scala: ########## @@ -117,10 +129,91 @@ 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 pool = ThreadUtils.newDaemonSingleThreadExecutor("connect-collect-arrow") Review Comment: You can also use 2 fields in the proto: `partition_id` & `batch_id` -- 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