deadlock_pipeline.py

import logging

import apache_beam as beam
from apache_beam.options.pipeline_options import PipelineOptions, SetupOptions

_log = logging.getLogger(__name__)


def main(argv=None):
    logging.basicConfig(level=logging.INFO)

    pipeline_options = PipelineOptions(argv)

    setup_options = pipeline_options.view_as(SetupOptions)  # type: SetupOptions
    setup_options.save_main_session = True

    _log.info("Running pipeline")

    with beam.Pipeline(runner="DirectRunner", options=pipeline_options) as p:
        p | beam.Create(["hello", "world"]) | beam.Map(lambda x: print(x))

    print("""
    Call to _log.info will now deadlock, since the logging handler's
    threading.RLock() has been passed through dill.
    
    When you press Ctrl-C, the traceback should confirm that the process is 
    stuck at:
    
      File "/usr/lib/python3.5/logging/__init__.py", line 810, in acquire
        self.lock.acquire()
    """)
    _log.info("Pipeline done")
    print("Launching nukes")


if __name__ == '__main__':
    main()