yabola commented on code in PR #39950: URL: https://github.com/apache/spark/pull/39950#discussion_r1143531801
########## sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/parquet/ParquetPartitionReaderFactory.scala: ########## @@ -88,12 +88,18 @@ case class ParquetPartitionReaderFactory( private def getFooter(file: PartitionedFile): ParquetMetadata = { val conf = broadcastedConf.value.value val filePath = file.toPath + val split = new FileSplit(file.toPath, file.start, file.length, Array.empty[String]) - if (aggregation.isEmpty) { - ParquetFooterReader.readFooter(conf, filePath, SKIP_ROW_GROUPS) - } else { + if (aggregation.isDefined) { // For aggregate push down, we will get max/min/count from footer statistics. ParquetFooterReader.readFooter(conf, filePath, NO_FILTER) + } else if (enableVectorizedReader) { + // This can avoid reading the footer twice(currently only optimize for vectorized read). + // Read all the row groups in advance and filter the row groups later if there are + // filters that need push down. + ParquetFooterReader.readFooter(conf, split, ParquetFooterReader.WITH_ROW_GROUPS) + } else { Review Comment: I think we can use ```java if (aggregation.isDefined || enableVectorizedReader) { ParquetFooterReader.readFooter(conf, split, ParquetFooterReader.WITH_ROW_GROUPS) } ``` -- 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