Github user ueshin commented on a diff in the pull request: https://github.com/apache/spark/pull/18732#discussion_r141788690 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowEvalPythonExec.scala --- @@ -44,14 +44,17 @@ case class ArrowEvalPythonExec(udfs: Seq[PythonUDF], output: Seq[Attribute], chi val schemaOut = StructType.fromAttributes(output.drop(child.output.length).zipWithIndex .map { case (attr, i) => attr.withName(s"_$i") }) + val batchedIter: Iterator[Iterator[InternalRow]] = + iter.grouped(conf.arrowMaxRecordsPerBatch).map(_.iterator) --- End diff -- What if `conf.arrowMaxRecordsPerBatch <= 0`?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org