shunping commented on code in PR #39161:
URL: https://github.com/apache/beam/pull/39161#discussion_r3651421203
##########
sdks/python/apache_beam/runners/interactive/recording_manager.py:
##########
@@ -891,23 +910,32 @@ def record(
'Cannot record because a dependency failed to compute'
' asynchronously.')
- self._clear()
-
- merged_options = pipeline_options.PipelineOptions(
- **{
- **self.user_pipeline.options.get_all_options(
- drop_default=True, retain_unknown_options=True),
- **options.get_all_options(
- drop_default=True, retain_unknown_options=True)
- }) if options else self.user_pipeline.options
-
- cache_path = ie.current_env().options.cache_root
- is_remote_run = cache_path and ie.current_env(
- ).options.cache_root.startswith('gs://')
- pf.PipelineFragment(
- list(uncomputed_pcolls), merged_options,
- runner=runner).run(blocking=is_remote_run)
- result = ie.current_env().pipeline_result(self.user_pipeline)
+ # Recalculate uncomputed PCollections because some may have finished
computing during the wait
+ computed_pcolls = set(
+ pcoll for pcoll in pcolls
+ if pcoll in ie.current_env().computed_pcollections)
+ uncomputed_pcolls = set(pcolls).difference(computed_pcolls)
Review Comment:
If we have the previous helper function `_get_uncomputed_pcolls`, we can
call it here.
--
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]
