[ 
https://issues.apache.org/jira/browse/BEAM-11790?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Nir Gazit updated BEAM-11790:
-----------------------------
    Status: Resolved  (was: Resolved)

> Error when trying to read from S3 with Python SDK and external runners
> ----------------------------------------------------------------------
>
>                 Key: BEAM-11790
>                 URL: https://issues.apache.org/jira/browse/BEAM-11790
>             Project: Beam
>          Issue Type: Bug
>          Components: io-py-aws
>    Affects Versions: 2.27.0
>            Reporter: Nir Gazit
>            Priority: P2
>             Fix For: 2.28.0
>
>          Time Spent: 3h 10m
>  Remaining Estimate: 0h
>
> Using external environment with Python SDK on Flink and File IO that reads 
> from S3 causes the following error to be thrown:
> {code:java}
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py",
>  line 289, in _execute'
> INFO:apache_beam.utils.subprocess_server:b'    response = task()'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py",
>  line 362, in <lambda>'
> INFO:apache_beam.utils.subprocess_server:b'    lambda: 
> self.create_worker().do_instruction(request), request)'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py",
>  line 606, in do_instruction'
> INFO:apache_beam.utils.subprocess_server:b'    return getattr(self, 
> request_type)('
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py",
>  line 644, in process_bundle'
> INFO:apache_beam.utils.subprocess_server:b'    
> bundle_processor.process_bundle(instruction_id))'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py",
>  line 999, in process_bundle'
> INFO:apache_beam.utils.subprocess_server:b'    
> input_op_by_transform_id[element.transform_id].process_encoded('
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py",
>  line 228, in process_encoded'
> INFO:apache_beam.utils.subprocess_server:b'    self.output(decoded_value)'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "apache_beam/runners/worker/operations.py", line 357, in 
> apache_beam.runners.worker.operations.Operation.output'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "apache_beam/runners/worker/operations.py", line 359, in 
> apache_beam.runners.worker.operations.Operation.output'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "apache_beam/runners/worker/operations.py", line 221, in 
> apache_beam.runners.worker.operations.SingletonConsumerSet.receive'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "apache_beam/runners/worker/operations.py", line 718, in 
> apache_beam.runners.worker.operations.DoOperation.process'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "apache_beam/runners/worker/operations.py", line 719, in 
> apache_beam.runners.worker.operations.DoOperation.process'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "apache_beam/runners/common.py", line 1241, in 
> apache_beam.runners.common.DoFnRunner.process'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "apache_beam/runners/common.py", line 1321, in 
> apache_beam.runners.common.DoFnRunner._reraise_augmented'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/future/utils/__init__.py", line 446, 
> in raise_with_traceback'
> INFO:apache_beam.utils.subprocess_server:b'    raise 
> exc.with_traceback(traceback)'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "apache_beam/runners/common.py", line 1239, in 
> apache_beam.runners.common.DoFnRunner.process'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "apache_beam/runners/common.py", line 768, in 
> apache_beam.runners.common.PerWindowInvoker.invoke_process'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "apache_beam/runners/common.py", line 893, in 
> apache_beam.runners.common.PerWindowInvoker._invoke_process_per_window'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1131, 
> in process'
> INFO:apache_beam.utils.subprocess_server:b'    self.writer = 
> self.sink.open_writer(init_result, str(uuid.uuid4()))'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py",
>  line 200, in _f'
> INFO:apache_beam.utils.subprocess_server:b'    return fnc(self, *args, 
> **kwargs)'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsink.py", 
> line 196, in open_writer'
> INFO:apache_beam.utils.subprocess_server:b'    return 
> FileBasedSinkWriter(self, writer_path)'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsink.py", 
> line 417, in __init__'
> INFO:apache_beam.utils.subprocess_server:b'    self.temp_handle = 
> self.sink.open(temp_shard_path)'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/io/textio.py", line 405, 
> in open'
> INFO:apache_beam.utils.subprocess_server:b'    file_handle = super(_TextSink, 
> self).open(temp_path)'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py",
>  line 200, in _f'
> INFO:apache_beam.utils.subprocess_server:b'    return fnc(self, *args, 
> **kwargs)'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsink.py", 
> line 138, in open'
> INFO:apache_beam.utils.subprocess_server:b'    return 
> FileSystems.create(temp_path, self.mime_type, self.compression_type)'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 
> 229, in create'
> INFO:apache_beam.utils.subprocess_server:b'    return filesystem.create(path, 
> mime_type, compression_type)'
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/io/aws/s3filesystem.py", 
> line 171, in create'
> INFO:apache_beam.utils.subprocess_server:b"    return self._path_open(path, 
> 'wb', mime_type, compression_type)"
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/io/aws/s3filesystem.py", 
> line 151, in _path_open'
> INFO:apache_beam.utils.subprocess_server:b'    raw_file = 
> s3io.S3IO(options=self._options).open('
> INFO:apache_beam.utils.subprocess_server:b'  File 
> "/usr/local/lib/python3.8/site-packages/apache_beam/io/aws/s3io.py", line 63, 
> in __init__'
> INFO:apache_beam.utils.subprocess_server:b"    raise ValueError('Must provide 
> one of client or options')"
> INFO:apache_beam.utils.subprocess_server:b"ValueError: Must provide one of 
> client or options [while running 'Write/Write/WriteImpl/WriteBundles']"
> {code}
> I assume this is somehow related to a recent 
> [PR|https://github.com/apache/beam/pull/13180/files#diff-baf773ac5ea3ea041d61c2d1d76c1716428899d8906e40bb0e08bf80355da7e0]
>  that added this assertion that is now failing.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

Reply via email to