VictorPlusC commented on a change in pull request #16601:
URL: https://github.com/apache/beam/pull/16601#discussion_r794114089
##########
File path:
sdks/python/apache_beam/runners/interactive/interactive_environment.py
##########
@@ -373,11 +376,24 @@ def get_cache_manager(self, pipeline,
create_if_absent=False):
'/'.join(cache_root_path.parts[1:]), id(pipeline))
else:
cache_dir = tempfile.mkdtemp(dir=cache_root)
+ if not isinstance(pipeline_runner, direct_runner.DirectRunner):
+ _LOGGER.warning(
+ 'A local cache directory has been specified while '
+ 'not using DirectRunner. It is recommended to cache into a '
+ 'GCS bucket instead.')
else:
- cache_dir = tempfile.mkdtemp(
- suffix=str(id(pipeline)),
- prefix='it-',
- dir=os.environ.get('TEST_TMPDIR', None))
+ temp_location = pipeline.options.get_all_options()['temp_location']
+ if isinstance(pipeline_runner, DataflowRunner()) and temp_location:
+ cache_dir = temp_location
Review comment:
I've abstracted the code into 'get_gcs_cache_dir'. Thanks!
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
