westonpace commented on a change in pull request #10103: URL: https://github.com/apache/arrow/pull/10103#discussion_r619576450
########## File path: cpp/src/arrow/dataset/file_csv.cc ########## @@ -242,5 +240,15 @@ Result<ScanTaskIterator> CsvFileFormat::ScanFile( return MakeVectorIterator<std::shared_ptr<ScanTask>>({std::move(task)}); } +Result<RecordBatchGenerator> CsvFileFormat::ScanBatchesAsync( + const std::shared_ptr<ScanOptions>& scan_options, + const std::shared_ptr<FileFragment>& file) const { + auto this_ = checked_pointer_cast<const CsvFileFormat>(shared_from_this()); + auto source = file->source(); + auto reader_fut = + OpenReaderAsync(source, *this, scan_options, internal::GetCpuThreadPool()); + return GeneratorFromReader(std::move(reader_fut)); Review comment: Adding serial readahead here did not have any effect on performance. -- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org