Skip to content

Fix interactive environment clean up failure at atexit. #38526

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

Merged
shunping merged 3 commits into from
May 18, 2026
Merged

Fix interactive environment clean up failure at atexit. #38526

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
932d459
Fix interactive environment clean up failure at atexit.
shunping May 18, 2026
fbe67fb
Fix failed tests.
shunping May 18, 2026
bd8fa41
Formatting.
shunping May 18, 2026
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: 15 additions & 7 deletions sdks/python/apache_beam/runners/interactive/cache_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@

import base64
import collections
import logging
import os
import tempfile
from urllib.parse import quote
Expand All @@ -29,9 +30,12 @@
from apache_beam.io import filesystems
from apache_beam.io import textio
from apache_beam.io import tfrecordio
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.testing import test_stream
from apache_beam.transforms import combiners

_LOGGER = logging.getLogger(__name__)


class CacheManager(object):
"""Abstract class for caching PCollections.
Expand Down Expand Up @@ -286,13 +290,17 @@ def raw_source(self, *labels):
return self._reader_class(self._glob_path(*labels))

def cleanup(self):
if self._cache_dir.startswith('gs://'):
from apache_beam.io.gcp import gcsfilesystem
from apache_beam.options.pipeline_options import PipelineOptions
fs = gcsfilesystem.GCSFileSystem(PipelineOptions())
fs.delete([self._cache_dir + '/full/'])
elif filesystems.FileSystems.exists(self._cache_dir):
filesystems.FileSystems.delete([self._cache_dir])
try:
if self._cache_dir.startswith('gs://'):
# Import GCP dependencies only when needed.
from apache_beam.io.gcp import gcsfilesystem
fs = gcsfilesystem.GCSFileSystem(PipelineOptions())
Comment thread
shunping marked this conversation as resolved.
fs.delete([self._cache_dir + '/full/'])
elif filesystems.FileSystems.exists(self._cache_dir):
filesystems.FileSystems.delete([self._cache_dir])
except Exception as e:
_LOGGER.warning(
'Failed to clean up cache directory %s: %s', self._cache_dir, e)
self._saved_pcoders = {}

def _glob_path(self, *labels):
Expand Down
Loading