Mark Liu created BEAM-1577:
------------------------------
Summary: Python BigqueryTornadoes Example Failed
Key: BEAM-1577
URL: https://issues.apache.org/jira/browse/BEAM-1577
Project: Beam
Issue Type: Bug
Components: sdk-py
Affects Versions: 0.6.0
Reporter: Mark Liu
Assignee: Ahmet Altay
Running bigquery_tornadoes on DataflowRunner failed with following commands:
python -m apache_beam.examples.cookbook.bigquery_tornadoes \
--project google.com:clouddfe \
--runner DataflowRunner \
--staging_location gs://.../tmp/python/staging \
--temp_location gs://.../tmp/python/temp \
--output BigQueryTornadoesIT.monthly_tornadoes_0001 \
--sdk_location dist/apache-beam-0.6.0.dev0.tar.gz
JobName: beamapp-markliu-0301012437-463604
Job Link:
https://pantheon.corp.google.com/dataflow/job/2017-02-28_17_24_39-6087587560567828169?project=google.com:clouddfe&organizationId=433637338589
Full stack trace:
{code}
Traceback (most recent call last):
File "/usr/local/lib/python2.7/dist-packages/dataflow_worker/batchworker.py",
line 544, in do_work
work_executor.execute()
File "dataflow_worker/executor.py", line 971, in
dataflow_worker.executor.MapTaskExecutor.execute
(dataflow_worker/executor.c:30533)
with op.scoped_metrics_container:
File "dataflow_worker/executor.py", line 972, in
dataflow_worker.executor.MapTaskExecutor.execute
(dataflow_worker/executor.c:30481)
op.start()
File "dataflow_worker/executor.py", line 207, in
dataflow_worker.executor.ReadOperation.start (dataflow_worker/executor.c:8758)
def start(self):
File "dataflow_worker/executor.py", line 208, in
dataflow_worker.executor.ReadOperation.start (dataflow_worker/executor.c:8663)
with self.scoped_start_state:
File "dataflow_worker/executor.py", line 213, in
dataflow_worker.executor.ReadOperation.start (dataflow_worker/executor.c:8579)
with self.spec.source.reader() as reader:
File "dataflow_worker/executor.py", line 223, in
dataflow_worker.executor.ReadOperation.start (dataflow_worker/executor.c:8524)
self.output(windowed_value)
File "dataflow_worker/executor.py", line 151, in
dataflow_worker.executor.Operation.output (dataflow_worker/executor.c:6317)
cython.cast(Receiver, self.receivers[output_index]).receive(windowed_value)
File "dataflow_worker/executor.py", line 84, in
dataflow_worker.executor.ConsumerSet.receive (dataflow_worker/executor.c:4021)
cython.cast(Operation, consumer).process(windowed_value)
File "dataflow_worker/executor.py", line 544, in
dataflow_worker.executor.DoOperation.process (dataflow_worker/executor.c:18474)
with self.scoped_process_state:
File "dataflow_worker/executor.py", line 545, in
dataflow_worker.executor.DoOperation.process (dataflow_worker/executor.c:18428)
self.dofn_receiver.receive(o)
File "apache_beam/runners/common.py", line 195, in
apache_beam.runners.common.DoFnRunner.receive
(apache_beam/runners/common.c:5142)
self.process(windowed_value)
File "apache_beam/runners/common.py", line 267, in
apache_beam.runners.common.DoFnRunner.process
(apache_beam/runners/common.c:7201)
self.reraise_augmented(exn)
File "apache_beam/runners/common.py", line 279, in
apache_beam.runners.common.DoFnRunner.reraise_augmented
(apache_beam/runners/common.c:7590)
raise type(exn), args, sys.exc_info()[2]
File "apache_beam/runners/common.py", line 263, in
apache_beam.runners.common.DoFnRunner.process
(apache_beam/runners/common.c:7090)
self._dofn_simple_invoker(element)
File "apache_beam/runners/common.py", line 198, in
apache_beam.runners.common.DoFnRunner._dofn_simple_invoker
(apache_beam/runners/common.c:5288)
self._process_outputs(element, self.dofn_process(element.value))
File "apache_beam/runners/common.py", line 326, in
apache_beam.runners.common.DoFnRunner._process_outputs
(apache_beam/runners/common.c:8563)
self.main_receivers.receive(windowed_value)
File "dataflow_worker/executor.py", line 82, in
dataflow_worker.executor.ConsumerSet.receive (dataflow_worker/executor.c:3987)
self.update_counters_start(windowed_value)
File "dataflow_worker/executor.py", line 88, in
dataflow_worker.executor.ConsumerSet.update_counters_start
(dataflow_worker/executor.c:4207)
self.opcounter.update_from(windowed_value)
File "dataflow_worker/opcounters.py", line 57, in
dataflow_worker.opcounters.OperationCounters.update_from
(dataflow_worker/opcounters.c:2396)
self.do_sample(windowed_value)
File "dataflow_worker/opcounters.py", line 75, in
dataflow_worker.opcounters.OperationCounters.do_sample
(dataflow_worker/opcounters.c:3017)
self.coder_impl.get_estimated_size_and_observables(windowed_value))
File "apache_beam/coders/coder_impl.py", line 695, in
apache_beam.coders.coder_impl.WindowedValueCoderImpl.get_estimated_size_and_observables
(apache_beam/coders/coder_impl.c:22894)
def get_estimated_size_and_observables(self, value, nested=False):
File "apache_beam/coders/coder_impl.py", line 704, in
apache_beam.coders.coder_impl.WindowedValueCoderImpl.get_estimated_size_and_observables
(apache_beam/coders/coder_impl.c:22613)
self._value_coder.get_estimated_size_and_observables(
File "apache_beam/coders/coder_impl.py", line 494, in
apache_beam.coders.coder_impl.AbstractComponentCoderImpl.get_estimated_size_and_observables
(apache_beam/coders/coder_impl.c:18402)
c.get_estimated_size_and_observables(
File "apache_beam/coders/coder_impl.py", line 247, in
apache_beam.coders.coder_impl.FastPrimitivesCoderImpl.get_estimated_size_and_observables
(apache_beam/coders/coder_impl.c:9564)
out = ByteCountingOutputStream()
File "apache_beam/coders/stream.pyx", line 28, in
apache_beam.coders.stream.OutputStream.__cinit__
(apache_beam/coders/stream.c:1241)
self.buffer_size = 1024
AttributeError: 'apache_beam.coders.stream.ByteCountingOutputStream' object has
no attribute 'buffer_size' [while running 'months with tornatoes']
{code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
