Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

BeamRunPythonPipelineOperator: push_xcom dataflow_job_id right before starting pipeline #34707

Closed
wants to merge 1 commit into from
Closed

BeamRunPythonPipelineOperator: push_xcom dataflow_job_id right before starting pipeline #34707

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 21 additions & 21 deletions airflow/providers/apache/beam/operators/beam.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -320,6 +320,13 @@ def execute_sync(self, context: Context):
self.snake_case_pipeline_options["requirements_file"] = tmp_req_file.name

if self.is_dataflow and self.dataflow_hook:
DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
with self.dataflow_hook.provide_authorized_gcloud():
self.beam_hook.start_python_pipeline(
variables=self.snake_case_pipeline_options,
Expand All @@ -330,13 +337,6 @@ def execute_sync(self, context: Context):
py_system_site_packages=self.py_system_site_packages,
process_line_callback=self.process_line_callback,
)
DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
return {"dataflow_job_id": self.dataflow_job_id}
else:
self.beam_hook.start_python_pipeline(
Expand Down Expand Up @@ -507,6 +507,13 @@ def execute(self, context: Context):
self.jar = tmp_gcs_file.name

if is_dataflow and self.dataflow_hook:
DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
is_running = False
if self.dataflow_config.check_if_running != CheckJobRunning.IgnoreJob:
is_running = (
Expand Down Expand Up @@ -542,13 +549,6 @@ def execute(self, context: Context):
)
if dataflow_job_name and self.dataflow_config.location:
multiple_jobs = self.dataflow_config.multiple_jobs or False
DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
self.dataflow_hook.wait_for_done(
job_name=dataflow_job_name,
location=self.dataflow_config.location,
Expand Down Expand Up @@ -686,20 +686,20 @@ def execute(self, context: Context):
go_artifact.download_from_gcs(gcs_hook=gcs_hook, tmp_dir=tmp_dir)

if is_dataflow and self.dataflow_hook:
with self.dataflow_hook.provide_authorized_gcloud():
go_artifact.start_pipeline(
beam_hook=self.beam_hook,
variables=snake_case_pipeline_options,
process_line_callback=process_line_callback,
)

DataflowJobLink.persist(
self,
context,
self.dataflow_config.project_id,
self.dataflow_config.location,
self.dataflow_job_id,
)
with self.dataflow_hook.provide_authorized_gcloud():
go_artifact.start_pipeline(
beam_hook=self.beam_hook,
variables=snake_case_pipeline_options,
process_line_callback=process_line_callback,
)

if dataflow_job_name and self.dataflow_config.location:
self.dataflow_hook.wait_for_done(
job_name=dataflow_job_name,
Expand Down
Loading