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

Update dataflow python to use external containers #26383

Merged
merged 6 commits into from
Apr 24, 2023
Merged

Update dataflow python to use external containers #26383

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
f94a239
Update dataflow python to use external containers
damccorm Apr 21, 2023
075270f
Lint
damccorm Apr 21, 2023
3bee1d9
Update tests to new container format
damccorm Apr 22, 2023
a5ae1fe
Merge branch 'master' of https://github.com/damccorm/beam into users/…
damccorm Apr 22, 2023
83a2914
Lint
damccorm Apr 24, 2023
37c7d58
remove version_suffix
damccorm Apr 24, 2023
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
22 changes: 12 additions & 10 deletions sdks/python/apache_beam/runners/dataflow/internal/apiclient.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1207,19 +1207,21 @@ def get_container_image_from_options(pipeline_options):
if worker_options.sdk_container_image:
return worker_options.sdk_container_image

# TODO(tvalentyn): Use enumerated type instead of strings for job types.
if _is_runner_v2(pipeline_options):
fnapi_suffix = '-fnapi'
else:
fnapi_suffix = ''
is_runner_v2 = _is_runner_v2(pipeline_options)

# Legacy and runner v2 exist in different repositories.
# Set to legacy format, override if runner v2
version_suffix = '%s%s' % (sys.version_info[0:2])
image_name = '{repository}/python{version_suffix}{fnapi_suffix}'.format(
repository=names.DATAFLOW_CONTAINER_IMAGE_REPOSITORY,
version_suffix=version_suffix,
fnapi_suffix=fnapi_suffix)
container_repo = names.DATAFLOW_CONTAINER_IMAGE_REPOSITORY
image_name = '{repository}/python{version_suffix}'.format(
repository=container_repo, version_suffix=version_suffix)

if is_runner_v2:
version_suffix = '%s.%s' % (sys.version_info[0:2])
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: extra line

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We actually need this, it inserts a . while the last one does not.

With that said, I don't think this is helpful (the difference is too subtle), so I removed version_suffix entirely and replaced it with major/minor

image_name = '{repository}/beam_python{version_suffix}_sdk'.format(
repository=container_repo, version_suffix=version_suffix)

image_tag = _get_required_container_version(_is_runner_v2(pipeline_options))
image_tag = _get_required_container_version(is_runner_v2)
return image_name + ':' + image_tag


Expand Down
8 changes: 4 additions & 4 deletions sdks/python/apache_beam/runners/dataflow/internal/apiclient_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -631,8 +631,8 @@ def test_pinned_worker_harness_image_tag_used_in_dev_sdk(self):
self.assertEqual(
env.proto.workerPools[0].workerHarnessContainerImage,
(
names.DATAFLOW_CONTAINER_IMAGE_REPOSITORY + '/python%d%d-fnapi:%s' %
(
names.DATAFLOW_CONTAINER_IMAGE_REPOSITORY +
'/beam_python%d.%d_sdk:%s' % (
sys.version_info[0],
sys.version_info[1],
names.BEAM_FNAPI_CONTAINER_VERSION)))
Expand Down Expand Up @@ -670,7 +670,7 @@ def test_worker_harness_image_tag_matches_released_sdk_version(self):
env.proto.workerPools[0].workerHarnessContainerImage,
(
names.DATAFLOW_CONTAINER_IMAGE_REPOSITORY +
'/python%d%d-fnapi:2.2.0' %
'/beam_python%d.%d_sdk:2.2.0' %
(sys.version_info[0], sys.version_info[1])))

# batch, legacy pipeline.
Expand Down Expand Up @@ -704,7 +704,7 @@ def test_worker_harness_image_tag_matches_base_sdk_version_of_an_rc(self):
env.proto.workerPools[0].workerHarnessContainerImage,
(
names.DATAFLOW_CONTAINER_IMAGE_REPOSITORY +
'/python%d%d-fnapi:2.2.0' %
'/beam_python%d.%d_sdk:2.2.0' %
(sys.version_info[0], sys.version_info[1])))

# batch, legacy pipeline.
Expand Down
2 changes: 1 addition & 1 deletion sdks/python/apache_beam/runners/dataflow/internal/names.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@
BEAM_CONTAINER_VERSION = 'beam-master-20230412'
# Update this version to the next version whenever there is a change that
# requires changes to SDK harness container or SDK harness launcher.
BEAM_FNAPI_CONTAINER_VERSION = 'beam-master-20230412'
BEAM_FNAPI_CONTAINER_VERSION = 'beam-master-20230422'

DATAFLOW_CONTAINER_IMAGE_REPOSITORY = 'gcr.io/cloud-dataflow/v1beta3'

Expand Down