Github user felixcheung commented on a diff in the pull request: https://github.com/apache/spark/pull/20619#discussion_r168714722 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFileFormat.scala --- @@ -395,16 +395,19 @@ class ParquetFileFormat ParquetInputFormat.setFilterPredicate(hadoopAttemptContext.getConfiguration, pushed.get) } val taskContext = Option(TaskContext.get()) - val parquetReader = if (enableVectorizedReader) { + val iter = if (enableVectorizedReader) { val vectorizedReader = new VectorizedParquetRecordReader( convertTz.orNull, enableOffHeapColumnVector && taskContext.isDefined, capacity) + val recordReaderIterator = new RecordReaderIterator(vectorizedReader) + // Register a task completion lister before `initalization`. --- End diff -- ok
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org