-
-
Save ferryvg/d6be9f5b1ca739bc378d7743cb1b8e07 to your computer and use it in GitHub Desktop.
Apache Beam "Must provide one of client or options" (Flink, external env)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
beam-worker | Starting worker with command ['/opt/apache/beam/boot', '--id=1-1', '--logging_endpoint=localhost:45389', '--artifact_endpoint=localhost:34731', '--provision_endpoint=localhost:43605', '--control_endpoint=localhost:41783'] | |
beam-worker | 2021/02/11 08:27:51 Provision info: | |
beam-worker | pipeline_options:{fields:{key:"beam:option:app_name:v1" value:{null_value:NULL_VALUE}} fields:{key:"beam:option:artifact_port:v1" value:{string_value:"0"}} fields:{key:"beam:option:beam_services:v1" value:{struct_value:{}}} fields:{key:"beam:option:dataflow_endpoint:v1" value:{string_value:"https://dataflow.googleapis.com"}} fields:{key:"beam:option:direct_num_workers:v1" value:{string_value:"1"}} fields:{key:"beam:option:direct_runner_bundle_repeat:v1" value:{string_value:"0"}} fields:{key:"beam:option:direct_runner_use_stacked_bundle:v1" value:{bool_value:true}} fields:{key:"beam:option:direct_running_mode:v1" value:{string_value:"in_memory"}} fields:{key:"beam:option:dry_run:v1" value:{bool_value:false}} fields:{key:"beam:option:enable_streaming_engine:v1" value:{bool_value:false}} fields:{key:"beam:option:environment_cache_millis:v1" value:{string_value:"0"}} fields:{key:"beam:option:environment_config:v1" value:{string_value:"127.0.0.1:50000"}} fields:{key:"beam:option:environment_type:v1" value:{string_value:"EXTERNAL"}} fields:{key:"beam:option:expansion_port:v1" value:{string_value:"0"}} fields:{key:"beam:option:experiments:v1" value:{list_value:{values:{string_value:"beam_fn_api"}}}} fields:{key:"beam:option:extra_packages:v1" value:{list_value:{values:{string_value:"/tmp/tmpvy0mx3pm/build/tfx/dist/tfx_ephemeral-0.27.0.tar.gz"}}}} fields:{key:"beam:option:flink_master:v1" value:{string_value:"[auto]"}} fields:{key:"beam:option:flink_submit_uber_jar:v1" value:{bool_value:true}} fields:{key:"beam:option:flink_version:v1" value:{string_value:"1.10"}} fields:{key:"beam:option:hdfs_full_urls:v1" value:{bool_value:false}} fields:{key:"beam:option:job_name:v1" value:{string_value:"BeamApp-orbitadserving-0211082747-ebedf113"}} fields:{key:"beam:option:job_port:v1" value:{string_value:"0"}} fields:{key:"beam:option:job_server_java_launcher:v1" value:{string_value:"java"}} fields:{key:"beam:option:job_server_timeout:v1" value:{string_value:"60"}} fields:{key:"beam:option:labels:v1" value:{list_value:{values:{string_value:"tfx_executor=tfx-components-example_gen-import_example_gen-executor-executor"} values:{string_value:"tfx_py_version=3-8"} values:{string_value:"tfx_runner=local"} values:{string_value:"tfx_version=0-27-0"}}}} fields:{key:"beam:option:no_auth:v1" value:{bool_value:false}} fields:{key:"beam:option:options_id:v1" value:{number_value:1}} fields:{key:"beam:option:performance_runtime_type_check:v1" value:{bool_value:false}} fields:{key:"beam:option:pipeline_type_check:v1" value:{bool_value:true}} fields:{key:"beam:option:profile_cpu:v1" value:{bool_value:false}} fields:{key:"beam:option:profile_memory:v1" value:{bool_value:false}} fields:{key:"beam:option:profile_sample_rate:v1" value:{number_value:1}} fields:{key:"beam:option:runtime_type_check:v1" value:{bool_value:false}} fields:{key:"beam:option:s3_access_key_id:v1" value:{string_value:"valid-access-key"}} fields:{key:"beam:option:s3_disable_ssl:v1" value:{bool_value:false}} fields:{key:"beam:option:s3_endpoint_url:v1" value:{string_value:"http://192.168.0.117:49000"}} fields:{key:"beam:option:s3_region_name:v1" value:{string_value:"us-east-1"}} fields:{key:"beam:option:s3_secret_access_key:v1" value:{string_value:"valid-secret-key"}} fields:{key:"beam:option:s3_verify:v1" value:{string_value:"false"}} fields:{key:"beam:option:save_main_session:v1" value:{bool_value:false}} fields:{key:"beam:option:sdk_location:v1" value:{string_value:"container"}} fields:{key:"beam:option:sdk_worker_parallelism:v1" value:{string_value:"1"}} fields:{key:"beam:option:spark_master_url:v1" value:{string_value:"local[4]"}} fields:{key:"beam:option:spark_submit_uber_jar:v1" value:{bool_value:false}} fields:{key:"beam:option:streaming:v1" value:{bool_value:false}} fields:{key:"beam:option:type_check_additional:v1" value:{string_value:""}} fields:{key:"beam:option:type_check_strictness:v1" value:{string_value:"DEFAULT_TO_ANY"}} fields:{key:"beam:option:update:v1" value:{bool_value:false}}} retrieval_token:"__no_artifacts_staged__" logging_endpoint:{url:"localhost:45389"} artifact_endpoint:{url:"localhost:34731"} control_endpoint:{url:"localhost:41783"} dependencies:{type_urn:"beam:artifact:type:file:v1" type_payload:"\n\xb2\x01classpath://BEAM-PIPELINE/pipeline/artifacts/job-43df62c0-1fc5-4803-9fd1-f79edae75dbb/e8fb0840cad8d39c94306ae72f60eaef875fa8494e831c359990191c82ee2fa3-tfx_ephemeral-0.27.0.tar.gz" role_urn:"beam:artifact:role:staging_to:v1" role_payload:"\n\x1btfx_ephemeral-0.27.0.tar.gz"} dependencies:{type_urn:"beam:artifact:type:file:v1" type_payload:"\n\xa9\x01classpath://BEAM-PIPELINE/pipeline/artifacts/job-43df62c0-1fc5-4803-9fd1-f79edae75dbb/9d0ea0019a043f9037a05efac4457cb449632fec335676550dbbc67e7e3bf83f-extra_packages.txt" role_urn:"beam:artifact:role:staging_to:v1" role_payload:"\n\x12extra_packages.txt"} | |
beam-worker | 2021/02/11 08:27:51 Initializing python harness: /opt/apache/beam/boot --id=1-1 --logging_endpoint=localhost:45389 --artifact_endpoint=localhost:34731 --provision_endpoint=localhost:43605 --control_endpoint=localhost:41783 | |
beam-worker | 2021/02/11 08:27:51 Found artifact: tfx_ephemeral-0.27.0.tar.gz | |
beam-worker | 2021/02/11 08:27:51 Found artifact: extra_packages.txt | |
beam-worker | 2021/02/11 08:27:51 Installing setup packages ... | |
beam-worker | 2021/02/11 08:27:51 Installing extra package: tfx_ephemeral-0.27.0.tar.gz | |
beam-worker | WARNING: You are using pip version 20.3.3; however, version 21.0.1 is available. | |
beam-worker | You should consider upgrading via the '/usr/local/bin/python -m pip install --upgrade pip' command. | |
beam-worker | DEPRECATION: Source distribution is being reinstalled despite an installed package having the same name and version as the installed package. pip 21.1 will remove support for this functionality. A possible replacement is use --force-reinstall. You can find discussion regarding this at https://github.com/pypa/pip/issues/8711. | |
beam-worker | WARNING: You are using pip version 20.3.3; however, version 21.0.1 is available. | |
beam-worker | You should consider upgrading via the '/usr/local/bin/python -m pip install --upgrade pip' command. | |
beam-worker | 2021/02/11 08:30:01 Executing: python -m apache_beam.runners.worker.sdk_worker_main | |
beam-worker | Traceback (most recent call last): | |
beam-worker | File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
beam-worker | File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
beam-worker | File "apache_beam/runners/common.py", line 1374, in apache_beam.runners.common._OutputProcessor.process_outputs | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1425, in process | |
beam-worker | initial_restriction = self.restriction_provider.initial_restriction( | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1545, in initial_restriction | |
beam-worker | range_tracker = element_source.get_range_tracker(None, None) | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 210, in get_range_tracker | |
beam-worker | return self._get_concat_source().get_range_tracker( | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py", line 200, in _f | |
beam-worker | return fnc(self, *args, **kwargs) | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 145, in _get_concat_source | |
beam-worker | match_result = FileSystems.match([pattern])[0] | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 209, in match | |
beam-worker | return filesystem.match(patterns, limits) | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystem.py", line 765, in match | |
beam-worker | raise BeamIOError("Match operation failed", exceptions) | |
beam-worker | apache_beam.io.filesystem.BeamIOError: Match operation failed with exceptions {'s3://bucket_name/data_path/*': BeamIOError("List operation failed with exceptions {'s3://bucket_name/data_path/': ValueError('Must provide one of client or options')}")} | |
beam-worker | | |
beam-worker | During handling of the above exception, another exception occurred: | |
beam-worker | | |
beam-worker | Traceback (most recent call last): | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 289, in _execute | |
beam-worker | response = task() | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 362, in <lambda> | |
beam-worker | lambda: self.create_worker().do_instruction(request), request) | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 606, in do_instruction | |
beam-worker | return getattr(self, request_type)( | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 644, in process_bundle | |
beam-worker | bundle_processor.process_bundle(instruction_id)) | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 999, in process_bundle | |
beam-worker | input_op_by_transform_id[element.transform_id].process_encoded( | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 228, in process_encoded | |
beam-worker | self.output(decoded_value) | |
beam-worker | File "apache_beam/runners/worker/operations.py", line 357, in apache_beam.runners.worker.operations.Operation.output | |
beam-worker | File "apache_beam/runners/worker/operations.py", line 359, in apache_beam.runners.worker.operations.Operation.output | |
beam-worker | File "apache_beam/runners/worker/operations.py", line 221, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive | |
beam-worker | File "apache_beam/runners/worker/operations.py", line 718, in apache_beam.runners.worker.operations.DoOperation.process | |
beam-worker | File "apache_beam/runners/worker/operations.py", line 719, in apache_beam.runners.worker.operations.DoOperation.process | |
beam-worker | File "apache_beam/runners/common.py", line 1241, in apache_beam.runners.common.DoFnRunner.process | |
beam-worker | File "apache_beam/runners/common.py", line 1306, in apache_beam.runners.common.DoFnRunner._reraise_augmented | |
beam-worker | File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
beam-worker | File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
beam-worker | File "apache_beam/runners/common.py", line 1401, in apache_beam.runners.common._OutputProcessor.process_outputs | |
beam-worker | File "apache_beam/runners/worker/operations.py", line 221, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive | |
beam-worker | File "apache_beam/runners/worker/operations.py", line 718, in apache_beam.runners.worker.operations.DoOperation.process | |
beam-worker | File "apache_beam/runners/worker/operations.py", line 719, in apache_beam.runners.worker.operations.DoOperation.process | |
beam-worker | File "apache_beam/runners/common.py", line 1241, in apache_beam.runners.common.DoFnRunner.process | |
beam-worker | File "apache_beam/runners/common.py", line 1321, in apache_beam.runners.common.DoFnRunner._reraise_augmented | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/future/utils/__init__.py", line 446, in raise_with_traceback | |
beam-worker | raise exc.with_traceback(traceback) | |
beam-worker | File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
beam-worker | File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
beam-worker | File "apache_beam/runners/common.py", line 1374, in apache_beam.runners.common._OutputProcessor.process_outputs | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1425, in process | |
beam-worker | initial_restriction = self.restriction_provider.initial_restriction( | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1545, in initial_restriction | |
beam-worker | range_tracker = element_source.get_range_tracker(None, None) | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 210, in get_range_tracker | |
beam-worker | return self._get_concat_source().get_range_tracker( | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py", line 200, in _f | |
beam-worker | return fnc(self, *args, **kwargs) | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 145, in _get_concat_source | |
beam-worker | match_result = FileSystems.match([pattern])[0] | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 209, in match | |
beam-worker | return filesystem.match(patterns, limits) | |
beam-worker | File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystem.py", line 765, in match | |
beam-worker | raise BeamIOError("Match operation failed", exceptions) | |
beam-worker | apache_beam.io.filesystem.BeamIOError: Match operation failed with exceptions {'s3://bucket_name/data_path/*': BeamIOError("List operation failed with exceptions {'s3://bucket_name/data_path/': ValueError('Must provide one of client or options')}")} [while running 'InputToRecord/_ImportSerializedRecord({'input_base': 's3://bucket_name/data_path', 'input_config': '{\n "splits": [\n {\n "name": "single_split",\n "pattern": "*"\n }\n ]\n}', 'output_config': '{\n "split_config": {\n "splits": [\n {\n "hash_buckets": 2,\n "name": "train"\n },\n {\n "hash_buckets": 1,\n "name": "eval"\n }\n ]\n }\n}', 'output_data_format': 6, 'custom_config': None, 'range_config': None, 'span': 0, 'version': None, 'input_fingerprint': 'split:single_split,num_files:1,total_bytes:24321563,xor_checksum:1612792982,sum_checksum:1612792982', '_beam_pipeline_args': ['--runner=FlinkRunner', '--flink_master=stand7:8081', '--environment_type=EXTERNAL', '--environment_config=127.0.0.1:50000', '--flink_version=1.10', '--flink_submit_uber_jar', '--s3_access_key=valid-access-key', '--s3_secret_access_key=valid-secret-key', '--s3_endpoint_url=http://192.168.0.117:49000', '--s3_region_name=us-east-1', '--s3_verify=false', '--extra_package=/tmp/tmpvy0mx3pm/build/tfx/dist/tfx_ephemeral-0.27.0.tar.gz', '--labels', 'tfx_executor=tfx-components-example_gen-import_example_gen-executor-executor', '--labels', 'tfx_py_version=3-8', '--labels', 'tfx_runner=local', '--labels', 'tfx_version=0-27-0']})/ReadFromTFRecord/Read/SDFBoundedSourceReader/ParDo(SDFBoundedSourceDoFn)/PairWithRestriction0'] with exceptions None |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
DEBUG:absl:Processing input s3://bucket_name/data_path. | |
INFO:absl:select span and version = (0, None) | |
INFO:absl:latest span and version = (0, None) | |
DEBUG:absl:Resolved input artifacts are: {} | |
DEBUG:absl:Run context pipe-name already exists. | |
DEBUG:absl:ID of run context pipe-name is 1. | |
DEBUG:absl:Pipeline context [pipe-name : 1] | |
DEBUG:absl:ID of run context pipe-name.2021-02-11T11:27:15.999211 is 575. | |
DEBUG:absl:Pipeline run context [pipe-name.2021-02-11T11:27:15.999211 : 575] | |
DEBUG:absl:Prepared EXECUTION: | |
type_id: 3 | |
last_known_state: RUNNING | |
properties { | |
key: "component_id" | |
value { | |
string_value: "ImportExampleGen" | |
} | |
} | |
properties { | |
key: "custom_config" | |
value { | |
string_value: "None" | |
} | |
} | |
properties { | |
key: "input_base" | |
value { | |
string_value: "s3://bucket_name/data_path" | |
} | |
} | |
properties { | |
key: "input_config" | |
value { | |
string_value: "{\n \"splits\": [\n {\n \"name\": \"single_split\",\n \"pattern\": \"*\"\n }\n ]\n}" | |
} | |
} | |
properties { | |
key: "input_fingerprint" | |
value { | |
string_value: "split:single_split,num_files:1,total_bytes:24321563,xor_checksum:1612792982,sum_checksum:1612792982" | |
} | |
} | |
properties { | |
key: "output_config" | |
value { | |
string_value: "{\n \"split_config\": {\n \"splits\": [\n {\n \"hash_buckets\": 2,\n \"name\": \"train\"\n },\n {\n \"hash_buckets\": 1,\n \"name\": \"eval\"\n }\n ]\n }\n}" | |
} | |
} | |
properties { | |
key: "output_data_format" | |
value { | |
string_value: "6" | |
} | |
} | |
properties { | |
key: "pipeline_name" | |
value { | |
string_value: "pipe-name" | |
} | |
} | |
properties { | |
key: "pipeline_root" | |
value { | |
string_value: "s3://bucket_name/pipeline_output/pipe-name" | |
} | |
} | |
properties { | |
key: "range_config" | |
value { | |
string_value: "None" | |
} | |
} | |
properties { | |
key: "run_id" | |
value { | |
string_value: "2021-02-11T11:27:15.999211" | |
} | |
} | |
properties { | |
key: "span" | |
value { | |
string_value: "0" | |
} | |
} | |
properties { | |
key: "state" | |
value { | |
string_value: "new" | |
} | |
} | |
properties { | |
key: "version" | |
value { | |
string_value: "None" | |
} | |
} | |
DEBUG:absl:Cached results not found, move on to new execution | |
DEBUG:absl:Creating output artifact uri s3://bucket_name/pipeline_output/pipe-name/ImportExampleGen/examples/192 as directory | |
DEBUG:absl:Output artifacts skeleton for the upcoming execution are: {'examples': [Artifact(artifact: uri: "s3://bucket_name/pipeline_output/pipe-name/ImportExampleGen/examples/192" | |
custom_properties { | |
key: "input_fingerprint" | |
value { | |
string_value: "split:single_split,num_files:1,total_bytes:24321563,xor_checksum:1612792982,sum_checksum:1612792982" | |
} | |
} | |
custom_properties { | |
key: "span" | |
value { | |
string_value: "0" | |
} | |
} | |
, artifact_type: name: "Examples" | |
properties { | |
key: "span" | |
value: INT | |
} | |
properties { | |
key: "split_names" | |
value: STRING | |
} | |
properties { | |
key: "version" | |
value: INT | |
} | |
)]} | |
DEBUG:absl:Execution properties for the upcoming execution are: {'input_base': 's3://bucket_name/data_path', 'input_config': '{\n "splits": [\n {\n "name": "single_split",\n "pattern": "*"\n }\n ]\n}', 'output_config': '{\n "split_config": {\n "splits": [\n {\n "hash_buckets": 2,\n "name": "train"\n },\n {\n "hash_buckets": 1,\n "name": "eval"\n }\n ]\n }\n}', 'output_data_format': 6, 'custom_config': None, 'range_config': None, 'span': 0, 'version': None, 'input_fingerprint': 'split:single_split,num_files:1,total_bytes:24321563,xor_checksum:1612792982,sum_checksum:1612792982'} | |
INFO:absl:Running executor for ImportExampleGen | |
INFO:absl:Attempting to infer TFX Python dependency for beam | |
INFO:absl:Copying all content from install dir /home/local/projects/py/project_name/venv/lib/python3.8/site-packages/tfx to temp dir /tmp/tmpvy0mx3pm/build/tfx | |
INFO:absl:Generating a temp setup file at /tmp/tmpvy0mx3pm/build/tfx/setup.py | |
INFO:absl:Creating temporary sdist package, logs available at /tmp/tmpvy0mx3pm/build/tfx/setup.log | |
INFO:absl:Added --extra_package=/tmp/tmpvy0mx3pm/build/tfx/dist/tfx_ephemeral-0.27.0.tar.gz to beam args | |
DEBUG:absl:Starting Executor execution. | |
DEBUG:absl:Inputs for Executor are: {} | |
DEBUG:absl:Outputs for Executor are: {"examples": [{"artifact": {"id": "233", "type_id": "5", "uri": "s3://bucket_name/pipeline_output/pipe-name/ImportExampleGen/examples/192", "custom_properties": {"span": {"string_value": "0"}, "input_fingerprint": {"string_value": "split:single_split,num_files:1,total_bytes:24321563,xor_checksum:1612792982,sum_checksum:1612792982"}}}, "artifact_type": {"id": "5", "name": "Examples", "properties": {"version": "INT", "split_names": "STRING", "span": "INT"}}, "__artifact_class_module__": "tfx.types.standard_artifacts", "__artifact_class_name__": "Examples"}]} | |
DEBUG:absl:Execution properties for Executor are: {"input_base": "s3://bucket_name/data_path", "input_config": "{\n \"splits\": [\n {\n \"name\": \"single_split\",\n \"pattern\": \"*\"\n }\n ]\n}", "output_config": "{\n \"split_config\": {\n \"splits\": [\n {\n \"hash_buckets\": 2,\n \"name\": \"train\"\n },\n {\n \"hash_buckets\": 1,\n \"name\": \"eval\"\n }\n ]\n }\n}", "output_data_format": 6, "custom_config": null, "range_config": null, "span": 0, "version": null, "input_fingerprint": "split:single_split,num_files:1,total_bytes:24321563,xor_checksum:1612792982,sum_checksum:1612792982"} | |
INFO:absl:Generating examples. | |
INFO:absl:Reading input TFRecord data s3://bucket_name/data_path/*. | |
WARNING:root:Make sure that locally built Python SDK docker image has Python 3.8 interpreter. | |
ERROR:root:java.util.concurrent.ExecutionException: java.lang.RuntimeException: Error received from SDK harness for instruction 7: Traceback (most recent call last): | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1374, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1425, in process | |
initial_restriction = self.restriction_provider.initial_restriction( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1545, in initial_restriction | |
range_tracker = element_source.get_range_tracker(None, None) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 210, in get_range_tracker | |
return self._get_concat_source().get_range_tracker( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py", line 200, in _f | |
return fnc(self, *args, **kwargs) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 145, in _get_concat_source | |
match_result = FileSystems.match([pattern])[0] | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 209, in match | |
return filesystem.match(patterns, limits) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystem.py", line 765, in match | |
raise BeamIOError("Match operation failed", exceptions) | |
apache_beam.io.filesystem.BeamIOError: Match operation failed with exceptions {'s3://bucket_name/data_path/*': BeamIOError("List operation failed with exceptions {'s3://bucket_name/data_path/': ValueError('Must provide one of client or options')}")} | |
During handling of the above exception, another exception occurred: | |
Traceback (most recent call last): | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 289, in _execute | |
response = task() | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 362, in <lambda> | |
lambda: self.create_worker().do_instruction(request), request) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 606, in do_instruction | |
return getattr(self, request_type)( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 644, in process_bundle | |
bundle_processor.process_bundle(instruction_id)) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 999, in process_bundle | |
input_op_by_transform_id[element.transform_id].process_encoded( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 228, in process_encoded | |
self.output(decoded_value) | |
File "apache_beam/runners/worker/operations.py", line 357, in apache_beam.runners.worker.operations.Operation.output | |
File "apache_beam/runners/worker/operations.py", line 359, in apache_beam.runners.worker.operations.Operation.output | |
File "apache_beam/runners/worker/operations.py", line 221, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive | |
File "apache_beam/runners/worker/operations.py", line 718, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/worker/operations.py", line 719, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/common.py", line 1241, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 1306, in apache_beam.runners.common.DoFnRunner._reraise_augmented | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1401, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "apache_beam/runners/worker/operations.py", line 221, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive | |
File "apache_beam/runners/worker/operations.py", line 718, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/worker/operations.py", line 719, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/common.py", line 1241, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 1321, in apache_beam.runners.common.DoFnRunner._reraise_augmented | |
File "/usr/local/lib/python3.8/site-packages/future/utils/__init__.py", line 446, in raise_with_traceback | |
raise exc.with_traceback(traceback) | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1374, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1425, in process | |
initial_restriction = self.restriction_provider.initial_restriction( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1545, in initial_restriction | |
range_tracker = element_source.get_range_tracker(None, None) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 210, in get_range_tracker | |
return self._get_concat_source().get_range_tracker( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py", line 200, in _f | |
return fnc(self, *args, **kwargs) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 145, in _get_concat_source | |
match_result = FileSystems.match([pattern])[0] | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 209, in match | |
return filesystem.match(patterns, limits) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystem.py", line 765, in match | |
raise BeamIOError("Match operation failed", exceptions) | |
apache_beam.io.filesystem.BeamIOError: Match operation failed with exceptions {'s3://bucket_name/data_path/*': BeamIOError("List operation failed with exceptions {'s3://bucket_name/data_path/': ValueError('Must provide one of client or options')}")} [while running 'InputToRecord/_ImportSerializedRecord({'input_base': 's3://bucket_name/data_path', 'input_config': '{\n "splits": [\n {\n "name": "single_split",\n "pattern": "*"\n }\n ]\n}', 'output_config': '{\n "split_config": {\n "splits": [\n {\n "hash_buckets": 2,\n "name": "train"\n },\n {\n "hash_buckets": 1,\n "name": "eval"\n }\n ]\n }\n}', 'output_data_format': 6, 'custom_config': None, 'range_config': None, 'span': 0, 'version': None, 'input_fingerprint': 'split:single_split,num_files:1,total_bytes:24321563,xor_checksum:1612792982,sum_checksum:1612792982', '_beam_pipeline_args': ['--runner=FlinkRunner', '--flink_master=flink-cluster:8081', '--environment_type=EXTERNAL', '--environment_config=127.0.0.1:50000', '--flink_version=1.10', '--flink_submit_uber_jar', '--s3_access_key=valid-access-key', '--s3_secret_access_key=valid-secret-key', '--s3_endpoint_url=http://192.168.0.117:49000', '--s3_region_name=us-east-1', '--s3_verify=false', '--extra_package=/tmp/tmpvy0mx3pm/build/tfx/dist/tfx_ephemeral-0.27.0.tar.gz', '--labels', 'tfx_executor=tfx-components-example_gen-import_example_gen-executor-executor', '--labels', 'tfx_py_version=3-8', '--labels', 'tfx_runner=local', '--labels', 'tfx_version=0-27-0']})/ReadFromTFRecord/Read/SDFBoundedSourceReader/ParDo(SDFBoundedSourceDoFn)/PairWithRestriction0'] with exceptions None | |
at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:357) | |
at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:1895) | |
at org.apache.beam.sdk.util.MoreFutures.get(MoreFutures.java:60) | |
at org.apache.beam.runners.fnexecution.control.SdkHarnessClient$BundleProcessor$ActiveBundle.close(SdkHarnessClient.java:504) | |
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory$SimpleStageBundleFactory$1.close(DefaultJobBundleFactory.java:555) | |
at org.apache.beam.runners.flink.translation.functions.FlinkExecutableStageFunction.$closeResource(FlinkExecutableStageFunction.java:268) | |
at org.apache.beam.runners.flink.translation.functions.FlinkExecutableStageFunction.mapPartition(FlinkExecutableStageFunction.java:268) | |
at org.apache.flink.runtime.operators.MapPartitionDriver.run(MapPartitionDriver.java:103) | |
at org.apache.flink.runtime.operators.BatchTask.run(BatchTask.java:504) | |
at org.apache.flink.runtime.operators.BatchTask.invoke(BatchTask.java:369) | |
at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:708) | |
at org.apache.flink.runtime.taskmanager.Task.run(Task.java:533) | |
at java.lang.Thread.run(Thread.java:745) | |
Caused by: java.lang.RuntimeException: Error received from SDK harness for instruction 7: Traceback (most recent call last): | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1374, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1425, in process | |
initial_restriction = self.restriction_provider.initial_restriction( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1545, in initial_restriction | |
range_tracker = element_source.get_range_tracker(None, None) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 210, in get_range_tracker | |
return self._get_concat_source().get_range_tracker( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py", line 200, in _f | |
return fnc(self, *args, **kwargs) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 145, in _get_concat_source | |
match_result = FileSystems.match([pattern])[0] | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 209, in match | |
return filesystem.match(patterns, limits) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystem.py", line 765, in match | |
raise BeamIOError("Match operation failed", exceptions) | |
apache_beam.io.filesystem.BeamIOError: Match operation failed with exceptions {'s3://bucket_name/data_path/*': BeamIOError("List operation failed with exceptions {'s3://bucket_name/data_path/': ValueError('Must provide one of client or options')}")} | |
During handling of the above exception, another exception occurred: | |
Traceback (most recent call last): | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 289, in _execute | |
response = task() | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 362, in <lambda> | |
lambda: self.create_worker().do_instruction(request), request) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 606, in do_instruction | |
return getattr(self, request_type)( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 644, in process_bundle | |
bundle_processor.process_bundle(instruction_id)) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 999, in process_bundle | |
input_op_by_transform_id[element.transform_id].process_encoded( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 228, in process_encoded | |
self.output(decoded_value) | |
File "apache_beam/runners/worker/operations.py", line 357, in apache_beam.runners.worker.operations.Operation.output | |
File "apache_beam/runners/worker/operations.py", line 359, in apache_beam.runners.worker.operations.Operation.output | |
File "apache_beam/runners/worker/operations.py", line 221, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive | |
File "apache_beam/runners/worker/operations.py", line 718, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/worker/operations.py", line 719, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/common.py", line 1241, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 1306, in apache_beam.runners.common.DoFnRunner._reraise_augmented | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1401, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "apache_beam/runners/worker/operations.py", line 221, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive | |
File "apache_beam/runners/worker/operations.py", line 718, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/worker/operations.py", line 719, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/common.py", line 1241, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 1321, in apache_beam.runners.common.DoFnRunner._reraise_augmented | |
File "/usr/local/lib/python3.8/site-packages/future/utils/__init__.py", line 446, in raise_with_traceback | |
raise exc.with_traceback(traceback) | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1374, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1425, in process | |
initial_restriction = self.restriction_provider.initial_restriction( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1545, in initial_restriction | |
range_tracker = element_source.get_range_tracker(None, None) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 210, in get_range_tracker | |
return self._get_concat_source().get_range_tracker( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py", line 200, in _f | |
return fnc(self, *args, **kwargs) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 145, in _get_concat_source | |
match_result = FileSystems.match([pattern])[0] | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 209, in match | |
return filesystem.match(patterns, limits) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystem.py", line 765, in match | |
raise BeamIOError("Match operation failed", exceptions) | |
apache_beam.io.filesystem.BeamIOError: Match operation failed with exceptions {'s3://bucket_name/data_path/*': BeamIOError("List operation failed with exceptions {'s3://bucket_name/data_path/': ValueError('Must provide one of client or options')}")} [while running 'InputToRecord/_ImportSerializedRecord({'input_base': 's3://bucket_name/data_path', 'input_config': '{\n "splits": [\n {\n "name": "single_split",\n "pattern": "*"\n }\n ]\n}', 'output_config': '{\n "split_config": {\n "splits": [\n {\n "hash_buckets": 2,\n "name": "train"\n },\n {\n "hash_buckets": 1,\n "name": "eval"\n }\n ]\n }\n}', 'output_data_format': 6, 'custom_config': None, 'range_config': None, 'span': 0, 'version': None, 'input_fingerprint': 'split:single_split,num_files:1,total_bytes:24321563,xor_checksum:1612792982,sum_checksum:1612792982', '_beam_pipeline_args': ['--runner=FlinkRunner', '--flink_master=flink-cluster:8081', '--environment_type=EXTERNAL', '--environment_config=127.0.0.1:50000', '--flink_version=1.10', '--flink_submit_uber_jar', '--s3_access_key=valid-access-key', '--s3_secret_access_key=valid-secret-key', '--s3_endpoint_url=http://192.168.0.117:49000', '--s3_region_name=us-east-1', '--s3_verify=false', '--extra_package=/tmp/tmpvy0mx3pm/build/tfx/dist/tfx_ephemeral-0.27.0.tar.gz', '--labels', 'tfx_executor=tfx-components-example_gen-import_example_gen-executor-executor', '--labels', 'tfx_py_version=3-8', '--labels', 'tfx_runner=local', '--labels', 'tfx_version=0-27-0']})/ReadFromTFRecord/Read/SDFBoundedSourceReader/ParDo(SDFBoundedSourceDoFn)/PairWithRestriction0'] with exceptions None | |
at org.apache.beam.runners.fnexecution.control.FnApiControlClient$ResponseStreamObserver.onNext(FnApiControlClient.java:180) | |
at org.apache.beam.runners.fnexecution.control.FnApiControlClient$ResponseStreamObserver.onNext(FnApiControlClient.java:160) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.stub.ServerCalls$StreamingServerCallHandler$StreamingServerCallListener.onMessage(ServerCalls.java:251) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.ForwardingServerCallListener.onMessage(ForwardingServerCallListener.java:33) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.Contexts$ContextualizedServerCallListener.onMessage(Contexts.java:76) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.internal.ServerCallImpl$ServerStreamListenerImpl.messagesAvailableInternal(ServerCallImpl.java:309) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.internal.ServerCallImpl$ServerStreamListenerImpl.messagesAvailable(ServerCallImpl.java:292) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.internal.ServerImpl$JumpToApplicationThreadServerStreamListener$1MessagesAvailable.runInContext(ServerImpl.java:782) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.internal.ContextRunnable.run(ContextRunnable.java:37) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.internal.SerializingExecutor.run(SerializingExecutor.java:123) | |
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) | |
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) | |
... 1 more | |
Traceback (most recent call last): | |
File "/usr/lib/python3.8/contextlib.py", line 131, in __exit__ | |
self.gen.throw(type, value, traceback) | |
File "/home/local/projects/py/project_name/venv/lib/python3.8/site-packages/tfx/utils/telemetry_utils.py", line 51, in scoped_labels | |
yield | |
File "/home/local/projects/py/project_name/venv/lib/python3.8/site-packages/tfx/orchestration/local/local_dag_runner.py", line 92, in run | |
component_launcher.launch() | |
File "/home/local/projects/py/project_name/venv/lib/python3.8/site-packages/tfx/orchestration/launcher/base_component_launcher.py", line 206, in launch | |
self._run_executor(execution_decision.execution_id, | |
File "/home/local/projects/py/project_name/venv/lib/python3.8/site-packages/tfx/orchestration/launcher/in_process_component_launcher.py", line 71, in _run_executor | |
executor.Do( | |
File "/home/local/projects/py/project_name/venv/lib/python3.8/site-packages/tfx/components/example_gen/base_example_gen_executor.py", line 300, in Do | |
(example_split | |
File "/home/local/projects/py/project_name/venv/lib/python3.8/site-packages/apache_beam/pipeline.py", line 583, in __exit__ | |
self.result.wait_until_finish() | |
File "/home/local/projects/py/project_name/venv/lib/python3.8/site-packages/apache_beam/runners/portability/portable_runner.py", line 581, in wait_until_finish | |
raise self._runtime_exception | |
RuntimeError: Pipeline job-43df62c0-1fc5-4803-9fd1-f79edae75dbb failed in state FAILED: java.util.concurrent.ExecutionException: java.lang.RuntimeException: Error received from SDK harness for instruction 7: Traceback (most recent call last): | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1374, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1425, in process | |
initial_restriction = self.restriction_provider.initial_restriction( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1545, in initial_restriction | |
range_tracker = element_source.get_range_tracker(None, None) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 210, in get_range_tracker | |
return self._get_concat_source().get_range_tracker( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py", line 200, in _f | |
return fnc(self, *args, **kwargs) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 145, in _get_concat_source | |
match_result = FileSystems.match([pattern])[0] | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 209, in match | |
return filesystem.match(patterns, limits) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystem.py", line 765, in match | |
raise BeamIOError("Match operation failed", exceptions) | |
apache_beam.io.filesystem.BeamIOError: Match operation failed with exceptions {'s3://bucket_name/data_path/*': BeamIOError("List operation failed with exceptions {'s3://bucket_name/data_path/': ValueError('Must provide one of client or options')}")} | |
During handling of the above exception, another exception occurred: | |
Traceback (most recent call last): | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 289, in _execute | |
response = task() | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 362, in <lambda> | |
lambda: self.create_worker().do_instruction(request), request) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 606, in do_instruction | |
return getattr(self, request_type)( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 644, in process_bundle | |
bundle_processor.process_bundle(instruction_id)) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 999, in process_bundle | |
input_op_by_transform_id[element.transform_id].process_encoded( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 228, in process_encoded | |
self.output(decoded_value) | |
File "apache_beam/runners/worker/operations.py", line 357, in apache_beam.runners.worker.operations.Operation.output | |
File "apache_beam/runners/worker/operations.py", line 359, in apache_beam.runners.worker.operations.Operation.output | |
File "apache_beam/runners/worker/operations.py", line 221, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive | |
File "apache_beam/runners/worker/operations.py", line 718, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/worker/operations.py", line 719, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/common.py", line 1241, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 1306, in apache_beam.runners.common.DoFnRunner._reraise_augmented | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1401, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "apache_beam/runners/worker/operations.py", line 221, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive | |
File "apache_beam/runners/worker/operations.py", line 718, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/worker/operations.py", line 719, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/common.py", line 1241, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 1321, in apache_beam.runners.common.DoFnRunner._reraise_augmented | |
File "/usr/local/lib/python3.8/site-packages/future/utils/__init__.py", line 446, in raise_with_traceback | |
raise exc.with_traceback(traceback) | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1374, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1425, in process | |
initial_restriction = self.restriction_provider.initial_restriction( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1545, in initial_restriction | |
range_tracker = element_source.get_range_tracker(None, None) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 210, in get_range_tracker | |
return self._get_concat_source().get_range_tracker( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py", line 200, in _f | |
return fnc(self, *args, **kwargs) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 145, in _get_concat_source | |
match_result = FileSystems.match([pattern])[0] | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 209, in match | |
return filesystem.match(patterns, limits) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystem.py", line 765, in match | |
raise BeamIOError("Match operation failed", exceptions) | |
apache_beam.io.filesystem.BeamIOError: Match operation failed with exceptions {'s3://bucket_name/data_path/*': BeamIOError("List operation failed with exceptions {'s3://bucket_name/data_path/': ValueError('Must provide one of client or options')}")} [while running 'InputToRecord/_ImportSerializedRecord({'input_base': 's3://bucket_name/data_path', 'input_config': '{\n "splits": [\n {\n "name": "single_split",\n "pattern": "*"\n }\n ]\n}', 'output_config': '{\n "split_config": {\n "splits": [\n {\n "hash_buckets": 2,\n "name": "train"\n },\n {\n "hash_buckets": 1,\n "name": "eval"\n }\n ]\n }\n}', 'output_data_format': 6, 'custom_config': None, 'range_config': None, 'span': 0, 'version': None, 'input_fingerprint': 'split:single_split,num_files:1,total_bytes:24321563,xor_checksum:1612792982,sum_checksum:1612792982', '_beam_pipeline_args': ['--runner=FlinkRunner', '--flink_master=flink-cluster:8081', '--environment_type=EXTERNAL', '--environment_config=127.0.0.1:50000', '--flink_version=1.10', '--flink_submit_uber_jar', '--s3_access_key=valid-access-key', '--s3_secret_access_key=valid-secret-key', '--s3_endpoint_url=http://192.168.0.117:49000', '--s3_region_name=us-east-1', '--s3_verify=false', '--extra_package=/tmp/tmpvy0mx3pm/build/tfx/dist/tfx_ephemeral-0.27.0.tar.gz', '--labels', 'tfx_executor=tfx-components-example_gen-import_example_gen-executor-executor', '--labels', 'tfx_py_version=3-8', '--labels', 'tfx_runner=local', '--labels', 'tfx_version=0-27-0']})/ReadFromTFRecord/Read/SDFBoundedSourceReader/ParDo(SDFBoundedSourceDoFn)/PairWithRestriction0'] with exceptions None | |
at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:357) | |
at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:1895) | |
at org.apache.beam.sdk.util.MoreFutures.get(MoreFutures.java:60) | |
at org.apache.beam.runners.fnexecution.control.SdkHarnessClient$BundleProcessor$ActiveBundle.close(SdkHarnessClient.java:504) | |
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory$SimpleStageBundleFactory$1.close(DefaultJobBundleFactory.java:555) | |
at org.apache.beam.runners.flink.translation.functions.FlinkExecutableStageFunction.$closeResource(FlinkExecutableStageFunction.java:268) | |
at org.apache.beam.runners.flink.translation.functions.FlinkExecutableStageFunction.mapPartition(FlinkExecutableStageFunction.java:268) | |
at org.apache.flink.runtime.operators.MapPartitionDriver.run(MapPartitionDriver.java:103) | |
at org.apache.flink.runtime.operators.BatchTask.run(BatchTask.java:504) | |
at org.apache.flink.runtime.operators.BatchTask.invoke(BatchTask.java:369) | |
at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:708) | |
at org.apache.flink.runtime.taskmanager.Task.run(Task.java:533) | |
at java.lang.Thread.run(Thread.java:745) | |
Caused by: java.lang.RuntimeException: Error received from SDK harness for instruction 7: Traceback (most recent call last): | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1374, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1425, in process | |
initial_restriction = self.restriction_provider.initial_restriction( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1545, in initial_restriction | |
range_tracker = element_source.get_range_tracker(None, None) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 210, in get_range_tracker | |
return self._get_concat_source().get_range_tracker( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py", line 200, in _f | |
return fnc(self, *args, **kwargs) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 145, in _get_concat_source | |
match_result = FileSystems.match([pattern])[0] | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 209, in match | |
return filesystem.match(patterns, limits) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystem.py", line 765, in match | |
raise BeamIOError("Match operation failed", exceptions) | |
apache_beam.io.filesystem.BeamIOError: Match operation failed with exceptions {'s3://bucket_name/data_path/*': BeamIOError("List operation failed with exceptions {'s3://bucket_name/data_path/': ValueError('Must provide one of client or options')}")} | |
During handling of the above exception, another exception occurred: | |
Traceback (most recent call last): | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 289, in _execute | |
response = task() | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 362, in <lambda> | |
lambda: self.create_worker().do_instruction(request), request) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 606, in do_instruction | |
return getattr(self, request_type)( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/sdk_worker.py", line 644, in process_bundle | |
bundle_processor.process_bundle(instruction_id)) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 999, in process_bundle | |
input_op_by_transform_id[element.transform_id].process_encoded( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 228, in process_encoded | |
self.output(decoded_value) | |
File "apache_beam/runners/worker/operations.py", line 357, in apache_beam.runners.worker.operations.Operation.output | |
File "apache_beam/runners/worker/operations.py", line 359, in apache_beam.runners.worker.operations.Operation.output | |
File "apache_beam/runners/worker/operations.py", line 221, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive | |
File "apache_beam/runners/worker/operations.py", line 718, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/worker/operations.py", line 719, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/common.py", line 1241, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 1306, in apache_beam.runners.common.DoFnRunner._reraise_augmented | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1401, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "apache_beam/runners/worker/operations.py", line 221, in apache_beam.runners.worker.operations.SingletonConsumerSet.receive | |
File "apache_beam/runners/worker/operations.py", line 718, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/worker/operations.py", line 719, in apache_beam.runners.worker.operations.DoOperation.process | |
File "apache_beam/runners/common.py", line 1241, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 1321, in apache_beam.runners.common.DoFnRunner._reraise_augmented | |
File "/usr/local/lib/python3.8/site-packages/future/utils/__init__.py", line 446, in raise_with_traceback | |
raise exc.with_traceback(traceback) | |
File "apache_beam/runners/common.py", line 1239, in apache_beam.runners.common.DoFnRunner.process | |
File "apache_beam/runners/common.py", line 587, in apache_beam.runners.common.SimpleInvoker.invoke_process | |
File "apache_beam/runners/common.py", line 1374, in apache_beam.runners.common._OutputProcessor.process_outputs | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/runners/worker/bundle_processor.py", line 1425, in process | |
initial_restriction = self.restriction_provider.initial_restriction( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/iobase.py", line 1545, in initial_restriction | |
range_tracker = element_source.get_range_tracker(None, None) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 210, in get_range_tracker | |
return self._get_concat_source().get_range_tracker( | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/options/value_provider.py", line 200, in _f | |
return fnc(self, *args, **kwargs) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filebasedsource.py", line 145, in _get_concat_source | |
match_result = FileSystems.match([pattern])[0] | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystems.py", line 209, in match | |
return filesystem.match(patterns, limits) | |
File "/usr/local/lib/python3.8/site-packages/apache_beam/io/filesystem.py", line 765, in match | |
raise BeamIOError("Match operation failed", exceptions) | |
apache_beam.io.filesystem.BeamIOError: Match operation failed with exceptions {'s3://bucket_name/data_path/*': BeamIOError("List operation failed with exceptions {'s3://bucket_name/data_path/': ValueError('Must provide one of client or options')}")} [while running 'InputToRecord/_ImportSerializedRecord({'input_base': 's3://bucket_name/data_path', 'input_config': '{\n "splits": [\n {\n "name": "single_split",\n "pattern": "*"\n }\n ]\n}', 'output_config': '{\n "split_config": {\n "splits": [\n {\n "hash_buckets": 2,\n "name": "train"\n },\n {\n "hash_buckets": 1,\n "name": "eval"\n }\n ]\n }\n}', 'output_data_format': 6, 'custom_config': None, 'range_config': None, 'span': 0, 'version': None, 'input_fingerprint': 'split:single_split,num_files:1,total_bytes:24321563,xor_checksum:1612792982,sum_checksum:1612792982', '_beam_pipeline_args': ['--runner=FlinkRunner', '--flink_master=flink-cluster:8081', '--environment_type=EXTERNAL', '--environment_config=127.0.0.1:50000', '--flink_version=1.10', '--flink_submit_uber_jar', '--s3_access_key=valid-access-key', '--s3_secret_access_key=valid-secret-key', '--s3_endpoint_url=http://192.168.0.117:49000', '--s3_region_name=us-east-1', '--s3_verify=false', '--extra_package=/tmp/tmpvy0mx3pm/build/tfx/dist/tfx_ephemeral-0.27.0.tar.gz', '--labels', 'tfx_executor=tfx-components-example_gen-import_example_gen-executor-executor', '--labels', 'tfx_py_version=3-8', '--labels', 'tfx_runner=local', '--labels', 'tfx_version=0-27-0']})/ReadFromTFRecord/Read/SDFBoundedSourceReader/ParDo(SDFBoundedSourceDoFn)/PairWithRestriction0'] with exceptions None | |
at org.apache.beam.runners.fnexecution.control.FnApiControlClient$ResponseStreamObserver.onNext(FnApiControlClient.java:180) | |
at org.apache.beam.runners.fnexecution.control.FnApiControlClient$ResponseStreamObserver.onNext(FnApiControlClient.java:160) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.stub.ServerCalls$StreamingServerCallHandler$StreamingServerCallListener.onMessage(ServerCalls.java:251) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.ForwardingServerCallListener.onMessage(ForwardingServerCallListener.java:33) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.Contexts$ContextualizedServerCallListener.onMessage(Contexts.java:76) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.internal.ServerCallImpl$ServerStreamListenerImpl.messagesAvailableInternal(ServerCallImpl.java:309) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.internal.ServerCallImpl$ServerStreamListenerImpl.messagesAvailable(ServerCallImpl.java:292) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.internal.ServerImpl$JumpToApplicationThreadServerStreamListener$1MessagesAvailable.runInContext(ServerImpl.java:782) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.internal.ContextRunnable.run(ContextRunnable.java:37) | |
at org.apache.beam.vendor.grpc.v1p26p0.io.grpc.internal.SerializingExecutor.run(SerializingExecutor.java:123) | |
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) | |
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) | |
... 1 more | |
python-BaseException | |
Process finished with exit code 130 (interrupted by signal 2: SIGINT) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
--runner=FlinkRunner | |
--flink_master=flink-cluster:8081 | |
--environment_type=EXTERNAL | |
--environment_config=127.0.0.1:50000 # at least one beam worker pool on each flink taskmanager | |
--flink_version=1.10 | |
--flink_submit_uber_jar | |
--s3_access_key=valid-access-key | |
--s3_secret_access_key=valid-secret-key | |
--s3_endpoint_url=http://192.168.0.117:49000 | |
--s3_region_name=us-east-1 | |
--s3_verify=false |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment