westonpace commented on a change in pull request #10061:
URL: https://github.com/apache/arrow/pull/10061#discussion_r616025836
##########
File path: cpp/src/arrow/dataset/file_csv.cc
##########
@@ -154,9 +180,26 @@ class CsvScanTask : public ScanTask {
source_(fragment->source()) {}
Result<RecordBatchIterator> Execute() override {
- ARROW_ASSIGN_OR_RAISE(auto reader,
- OpenReader(source_, *format_, options(),
options()->pool));
- return IteratorFromReader(std::move(reader));
+ auto reader_fut = OpenReaderAsync(source_, *format_, options(),
+ internal::GetCpuThreadPool(),
options()->pool);
+ auto reader_gen = GeneratorFromReader(std::move(reader_fut));
+ return MakeSimpleGeneratorIterator(std::move(reader_gen));
+ }
+
+ Future<RecordBatchVector> SafeExecute(internal::Executor* executor) override
{
+ auto reader_fut =
+ OpenReaderAsync(source_, *format_, options(), executor,
options()->pool);
Review comment:
`SerialExecutor` assumes the current thread which may be from the CPU
thread pool. So, for example, `SyncScanner::ToTable` will continue to run
`SafeExecute` on the CPU thread pool.
--
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:
[email protected]
