def run_pipeline(self, pipeline):
portable_options = pipeline.options.view_as(PortableOptions)
job_endpoint = portable_options.job_endpoint
# TODO: https://issues.apache.org/jira/browse/BEAM-5525
# portable runner specific default
if pipeline.options.view_as(SetupOptions).sdk_location == 'default':
pipeline.options.view_as(SetupOptions).sdk_location = 'container'
if not job_endpoint:
docker = DockerizedJobServer()
job_endpoint = docker.start()
proto_context = pipeline_context.PipelineContext(
default_environment=PortableRunner._create_environment(
portable_options))
proto_pipeline = pipeline.to_runner_api(context=proto_context)
# Some runners won't detect the GroupByKey transform unless it has no
# subtransforms. Remove all sub-transforms until BEAM-4605 is resolved.
for _, transform_proto in list(
proto_pipeline.components.transforms.items()):
if transform_proto.spec.urn == common_urns.primitives.GROUP_BY_KEY.urn:
for sub_transform in transform_proto.subtransforms:
del proto_pipeline.components.transforms[sub_transform]
del transform_proto.subtransforms[:]
# TODO: Define URNs for options.
# convert int values: https://issues.apache.org/jira/browse/BEAM-5509
options = {'beam:option:' + k + ':v1': (str(v) if type(v) == int else v)
for k, v in pipeline._options.get_all_options().items()
if v is not None}
channel = grpc.insecure_channel(job_endpoint)
grpc.channel_ready_future(channel).result()
job_service = beam_job_api_pb2_grpc.JobServiceStub(channel)
# Sends the PrepareRequest but retries in case the channel is not ready
def send_prepare_request(max_retries=5):
num_retries = 0
while True:
try:
# This reports channel is READY but connections may fail
# Seems to be only an issue on Mac with port forwardings
grpc.channel_ready_future(channel).result()
return job_service.Prepare(
beam_job_api_pb2.PrepareJobRequest(
job_name='job', pipeline=proto_pipeline,
pipeline_options=job_utils.dict_to_struct(options)))
except grpc._channel._Rendezvous as e:
num_retries += 1
if num_retries > max_retries:
raise e
prepare_response = send_prepare_request()
if prepare_response.artifact_staging_endpoint.url:
stager = portable_stager.PortableStager(
grpc.insecure_channel(prepare_response.artifact_staging_endpoint.url),
prepare_response.staging_session_token)
retrieval_token, _ = stager.stage_job_resources(
pipeline._options,
staging_location='')
else:
retrieval_token = None
run_response = job_service.Run(
beam_job_api_pb2.RunJobRequest(
preparation_id=prepare_response.preparation_id,
retrieval_token=retrieval_token))
return PipelineResult(job_service, run_response.job_id)
def run_pipeline(self, pipeline):
portable_options = pipeline.options.view_as(PortableOptions)
job_endpoint = portable_options.job_endpoint
# TODO: https://issues.apache.org/jira/browse/BEAM-5525
# portable runner specific default
if pipeline.options.view_as(SetupOptions).sdk_location == 'default':
pipeline.options.view_as(SetupOptions).sdk_location = 'container'
if not job_endpoint:
docker = DockerizedJobServer()
job_endpoint = docker.start()
proto_context = pipeline_context.PipelineContext(
default_environment=PortableRunner._create_environment(
portable_options))
proto_pipeline = pipeline.to_runner_api(context=proto_context)
if not self.is_embedded_fnapi_runner:
# Java has different expectations about coders
# (windowed in Fn API, but *un*windowed in runner API), whereas the
# embedded FnApiRunner treats them consistently, so we must guard this
# for now, until FnApiRunner is fixed.
# See also BEAM-2717.
for pcoll in proto_pipeline.components.pcollections.values():
if pcoll.coder_id not in proto_context.coders:
# This is not really a coder id, but a pickled coder.
coder = coders.registry.get_coder(pickler.loads(pcoll.coder_id))
pcoll.coder_id = proto_context.coders.get_id(coder)
proto_context.coders.populate_map(proto_pipeline.components.coders)
# Some runners won't detect the GroupByKey transform unless it has no
# subtransforms. Remove all sub-transforms until BEAM-4605 is resolved.
for _, transform_proto in list(
proto_pipeline.components.transforms.items()):
if transform_proto.spec.urn == common_urns.primitives.GROUP_BY_KEY.urn:
for sub_transform in transform_proto.subtransforms:
del proto_pipeline.components.transforms[sub_transform]
del transform_proto.subtransforms[:]
# TODO: Define URNs for options.
# convert int values: https://issues.apache.org/jira/browse/BEAM-5509
options = {'beam:option:' + k + ':v1': (str(v) if type(v) == int else v)
for k, v in pipeline._options.get_all_options().items()
if v is not None}
channel = grpc.insecure_channel(job_endpoint)
grpc.channel_ready_future(channel).result()
job_service = beam_job_api_pb2_grpc.JobServiceStub(channel)
# Sends the PrepareRequest but retries in case the channel is not ready
def send_prepare_request(max_retries=5):
num_retries = 0
while True:
try:
# This reports channel is READY but connections may fail
# Seems to be only an issue on Mac with port forwardings
grpc.channel_ready_future(channel).result()
return job_service.Prepare(
beam_job_api_pb2.PrepareJobRequest(
job_name='job', pipeline=proto_pipeline,
pipeline_options=job_utils.dict_to_struct(options)))
except grpc._channel._Rendezvous as e:
num_retries += 1
if num_retries > max_retries:
raise e
prepare_response = send_prepare_request()
if prepare_response.artifact_staging_endpoint.url:
stager = portable_stager.PortableStager(
grpc.insecure_channel(prepare_response.artifact_staging_endpoint.url),
prepare_response.staging_session_token)
retrieval_token, _ = stager.stage_job_resources(
pipeline._options,
staging_location='')
else:
retrieval_token = None
run_response = job_service.Run(
beam_job_api_pb2.RunJobRequest(
preparation_id=prepare_response.preparation_id,
retrieval_token=retrieval_token))
return PipelineResult(job_service, run_response.job_id)
def run_pipeline(self, pipeline, options):
portable_options = options.view_as(PortableOptions)
job_endpoint = portable_options.job_endpoint
# TODO: https://issues.apache.org/jira/browse/BEAM-5525
# portable runner specific default
if options.view_as(SetupOptions).sdk_location == 'default':
options.view_as(SetupOptions).sdk_location = 'container'
if not job_endpoint:
# TODO Provide a way to specify a container Docker URL
# https://issues.apache.org/jira/browse/BEAM-6328
docker = DockerizedJobServer()
job_endpoint = docker.start()
# This is needed as we start a worker server if one is requested
# but none is provided.
if portable_options.environment_type == 'LOOPBACK':
portable_options.environment_config, server = (
BeamFnExternalWorkerPoolServicer.start(
sdk_worker_main._get_worker_count(options)))
cleanup_callbacks = [functools.partial(server.stop, 1)]
else:
cleanup_callbacks = []
proto_pipeline = pipeline.to_runner_api(
default_environment=PortableRunner._create_environment(
portable_options))
# Some runners won't detect the GroupByKey transform unless it has no
# subtransforms. Remove all sub-transforms until BEAM-4605 is resolved.
for _, transform_proto in list(
proto_pipeline.components.transforms.items()):
if transform_proto.spec.urn == common_urns.primitives.GROUP_BY_KEY.urn:
for sub_transform in transform_proto.subtransforms:
del proto_pipeline.components.transforms[sub_transform]
del transform_proto.subtransforms[:]
# Preemptively apply combiner lifting, until all runners support it.
# This optimization is idempotent.
if not options.view_as(StandardOptions).streaming:
stages = list(
fn_api_runner_transforms.leaf_transform_stages(
proto_pipeline.root_transform_ids,
proto_pipeline.components))
stages = fn_api_runner_transforms.lift_combiners(
stages,
fn_api_runner_transforms.TransformContext(
proto_pipeline.components))
proto_pipeline = fn_api_runner_transforms.with_stages(
proto_pipeline, stages)
# TODO: Define URNs for options.
# convert int values: https://issues.apache.org/jira/browse/BEAM-5509
p_options = {
'beam:option:' + k + ':v1': (str(v) if type(v) == int else v)
for k, v in options.get_all_options().items() if v is not None
}
channel = grpc.insecure_channel(job_endpoint)
grpc.channel_ready_future(channel).result()
job_service = beam_job_api_pb2_grpc.JobServiceStub(channel)
# Sends the PrepareRequest but retries in case the channel is not ready
def send_prepare_request(max_retries=5):
num_retries = 0
while True:
try:
# This reports channel is READY but connections may fail
# Seems to be only an issue on Mac with port forwardings
grpc.channel_ready_future(channel).result()
return job_service.Prepare(
beam_job_api_pb2.PrepareJobRequest(
job_name='job',
pipeline=proto_pipeline,
pipeline_options=job_utils.dict_to_struct(
p_options)))
except grpc._channel._Rendezvous as e:
num_retries += 1
if num_retries > max_retries:
raise e
prepare_response = send_prepare_request()
if prepare_response.artifact_staging_endpoint.url:
stager = portable_stager.PortableStager(
grpc.insecure_channel(
prepare_response.artifact_staging_endpoint.url),
prepare_response.staging_session_token)
retrieval_token, _ = stager.stage_job_resources(
options, staging_location='')
else:
retrieval_token = None
try:
state_stream = job_service.GetStateStream(
beam_job_api_pb2.GetJobStateRequest(
job_id=prepare_response.preparation_id))
# If there's an error, we don't always get it until we try to read.
# Fortunately, there's always an immediate current state published.
state_stream = itertools.chain([next(state_stream)], state_stream)
message_stream = job_service.GetMessageStream(
beam_job_api_pb2.JobMessagesRequest(
job_id=prepare_response.preparation_id))
except Exception:
# TODO(BEAM-6442): Unify preparation_id and job_id for all runners.
state_stream = message_stream = None
# Run the job and wait for a result.
run_response = job_service.Run(
beam_job_api_pb2.RunJobRequest(
preparation_id=prepare_response.preparation_id,
retrieval_token=retrieval_token))
if state_stream is None:
state_stream = job_service.GetStateStream(
beam_job_api_pb2.GetJobStateRequest(
job_id=run_response.job_id))
message_stream = job_service.GetMessageStream(
beam_job_api_pb2.JobMessagesRequest(
job_id=run_response.job_id))
return PipelineResult(job_service, run_response.job_id, message_stream,
state_stream, cleanup_callbacks)
def run_pipeline(self, pipeline, options):
portable_options = options.view_as(PortableOptions)
job_endpoint = portable_options.job_endpoint
# TODO: https://issues.apache.org/jira/browse/BEAM-5525
# portable runner specific default
if options.view_as(SetupOptions).sdk_location == 'default':
options.view_as(SetupOptions).sdk_location = 'container'
if not job_endpoint:
# TODO Provide a way to specify a container Docker URL
# https://issues.apache.org/jira/browse/BEAM-6328
docker = DockerizedJobServer()
job_endpoint = docker.start()
job_service = None
elif job_endpoint == 'embed':
job_service = local_job_service.LocalJobServicer()
else:
job_service = None
# This is needed as we start a worker server if one is requested
# but none is provided.
if portable_options.environment_type == 'LOOPBACK':
portable_options.environment_config, server = (
BeamFnExternalWorkerPoolServicer.start(
sdk_worker_main._get_worker_count(options)))
globals()['x'] = server
cleanup_callbacks = [functools.partial(server.stop, 1)]
else:
cleanup_callbacks = []
proto_pipeline = pipeline.to_runner_api(
default_environment=PortableRunner._create_environment(
portable_options))
# Some runners won't detect the GroupByKey transform unless it has no
# subtransforms. Remove all sub-transforms until BEAM-4605 is resolved.
for _, transform_proto in list(
proto_pipeline.components.transforms.items()):
if transform_proto.spec.urn == common_urns.primitives.GROUP_BY_KEY.urn:
for sub_transform in transform_proto.subtransforms:
del proto_pipeline.components.transforms[sub_transform]
del transform_proto.subtransforms[:]
# Preemptively apply combiner lifting, until all runners support it.
# This optimization is idempotent.
pre_optimize = options.view_as(DebugOptions).lookup_experiment(
'pre_optimize', 'combine').lower()
if not options.view_as(StandardOptions).streaming:
flink_known_urns = frozenset([
common_urns.composites.RESHUFFLE.urn,
common_urns.primitives.IMPULSE.urn,
common_urns.primitives.FLATTEN.urn,
common_urns.primitives.GROUP_BY_KEY.urn])
if pre_optimize == 'combine':
proto_pipeline = fn_api_runner_transforms.optimize_pipeline(
proto_pipeline,
phases=[fn_api_runner_transforms.lift_combiners],
known_runner_urns=flink_known_urns,
partial=True)
elif pre_optimize == 'all':
proto_pipeline = fn_api_runner_transforms.optimize_pipeline(
proto_pipeline,
phases=[fn_api_runner_transforms.annotate_downstream_side_inputs,
fn_api_runner_transforms.annotate_stateful_dofns_as_roots,
fn_api_runner_transforms.fix_side_input_pcoll_coders,
fn_api_runner_transforms.lift_combiners,
fn_api_runner_transforms.fix_flatten_coders,
# fn_api_runner_transforms.sink_flattens,
fn_api_runner_transforms.greedily_fuse,
fn_api_runner_transforms.read_to_impulse,
fn_api_runner_transforms.extract_impulse_stages,
fn_api_runner_transforms.remove_data_plane_ops,
fn_api_runner_transforms.sort_stages],
known_runner_urns=flink_known_urns)
elif pre_optimize == 'none':
pass
else:
raise ValueError('Unknown value for pre_optimize: %s' % pre_optimize)
if not job_service:
channel = grpc.insecure_channel(job_endpoint)
grpc.channel_ready_future(channel).result()
job_service = beam_job_api_pb2_grpc.JobServiceStub(channel)
else:
channel = None
# fetch runner options from job service
# retries in case the channel is not ready
def send_options_request(max_retries=5):
num_retries = 0
while True:
try:
# This reports channel is READY but connections may fail
# Seems to be only an issue on Mac with port forwardings
if channel:
grpc.channel_ready_future(channel).result()
return job_service.DescribePipelineOptions(
beam_job_api_pb2.DescribePipelineOptionsRequest())
except grpc._channel._Rendezvous as e:
num_retries += 1
if num_retries > max_retries:
raise e
time.sleep(1)
options_response = send_options_request()
def add_runner_options(parser):
for option in options_response.options:
try:
# no default values - we don't want runner options
# added unless they were specified by the user
add_arg_args = {'action' : 'store', 'help' : option.description}
if option.type == beam_job_api_pb2.PipelineOptionType.BOOLEAN:
add_arg_args['action'] = 'store_true'\
if option.default_value != 'true' else 'store_false'
elif option.type == beam_job_api_pb2.PipelineOptionType.INTEGER:
add_arg_args['type'] = int
elif option.type == beam_job_api_pb2.PipelineOptionType.ARRAY:
add_arg_args['action'] = 'append'
parser.add_argument("--%s" % option.name, **add_arg_args)
except Exception as e:
# ignore runner options that are already present
# only in this case is duplicate not treated as error
if 'conflicting option string' not in str(e):
raise
logging.debug("Runner option '%s' was already added" % option.name)
all_options = options.get_all_options(add_extra_args_fn=add_runner_options)
# TODO: Define URNs for options.
# convert int values: https://issues.apache.org/jira/browse/BEAM-5509
p_options = {'beam:option:' + k + ':v1': (str(v) if type(v) == int else v)
for k, v in all_options.items()
if v is not None}
prepare_response = job_service.Prepare(
beam_job_api_pb2.PrepareJobRequest(
job_name='job', pipeline=proto_pipeline,
pipeline_options=job_utils.dict_to_struct(p_options)))
if prepare_response.artifact_staging_endpoint.url:
stager = portable_stager.PortableStager(
grpc.insecure_channel(prepare_response.artifact_staging_endpoint.url),
prepare_response.staging_session_token)
retrieval_token, _ = stager.stage_job_resources(
options,
staging_location='')
else:
retrieval_token = None
try:
state_stream = job_service.GetStateStream(
beam_job_api_pb2.GetJobStateRequest(
job_id=prepare_response.preparation_id))
# If there's an error, we don't always get it until we try to read.
# Fortunately, there's always an immediate current state published.
state_stream = itertools.chain(
[next(state_stream)],
state_stream)
message_stream = job_service.GetMessageStream(
beam_job_api_pb2.JobMessagesRequest(
job_id=prepare_response.preparation_id))
except Exception:
# TODO(BEAM-6442): Unify preparation_id and job_id for all runners.
state_stream = message_stream = None
# Run the job and wait for a result.
run_response = job_service.Run(
beam_job_api_pb2.RunJobRequest(
preparation_id=prepare_response.preparation_id,
retrieval_token=retrieval_token))
if state_stream is None:
state_stream = job_service.GetStateStream(
beam_job_api_pb2.GetJobStateRequest(
job_id=run_response.job_id))
message_stream = job_service.GetMessageStream(
beam_job_api_pb2.JobMessagesRequest(
job_id=run_response.job_id))
return PipelineResult(job_service, run_response.job_id, message_stream,
state_stream, cleanup_callbacks)
def run_pipeline(self, pipeline):
portable_options = pipeline.options.view_as(PortableOptions)
job_endpoint = portable_options.job_endpoint
if not job_endpoint:
docker = DockerizedJobServer()
job_endpoint = docker.start()
proto_context = pipeline_context.PipelineContext(
default_environment=PortableRunner._create_environment(
portable_options))
proto_pipeline = pipeline.to_runner_api(context=proto_context)
if not self.is_embedded_fnapi_runner:
# Java has different expectations about coders
# (windowed in Fn API, but *un*windowed in runner API), whereas the
# embedded FnApiRunner treats them consistently, so we must guard this
# for now, until FnApiRunner is fixed.
# See also BEAM-2717.
for pcoll in proto_pipeline.components.pcollections.values():
if pcoll.coder_id not in proto_context.coders:
# This is not really a coder id, but a pickled coder.
coder = coders.registry.get_coder(
pickler.loads(pcoll.coder_id))
pcoll.coder_id = proto_context.coders.get_id(coder)
proto_context.coders.populate_map(proto_pipeline.components.coders)
# Some runners won't detect the GroupByKey transform unless it has no
# subtransforms. Remove all sub-transforms until BEAM-4605 is resolved.
for _, transform_proto in list(
proto_pipeline.components.transforms.items()):
if transform_proto.spec.urn == common_urns.primitives.GROUP_BY_KEY.urn:
for sub_transform in transform_proto.subtransforms:
del proto_pipeline.components.transforms[sub_transform]
del transform_proto.subtransforms[:]
# TODO: Define URNs for options.
# convert int values: https://issues.apache.org/jira/browse/BEAM-5509
options = {
'beam:option:' + k + ':v1': (str(v) if type(v) == int else v)
for k, v in pipeline._options.get_all_options().items()
if v is not None
}
channel = grpc.insecure_channel(job_endpoint)
grpc.channel_ready_future(channel).result()
job_service = beam_job_api_pb2_grpc.JobServiceStub(channel)
# Sends the PrepareRequest but retries in case the channel is not ready
def send_prepare_request(max_retries=5):
num_retries = 0
while True:
try:
# This reports channel is READY but connections may fail
# Seems to be only an issue on Mac with port forwardings
grpc.channel_ready_future(channel).result()
return job_service.Prepare(
beam_job_api_pb2.PrepareJobRequest(
job_name='job',
pipeline=proto_pipeline,
pipeline_options=job_utils.dict_to_struct(
options)))
except grpc._channel._Rendezvous as e:
num_retries += 1
if num_retries > max_retries:
raise e
prepare_response = send_prepare_request()
if prepare_response.artifact_staging_endpoint.url:
stager = portable_stager.PortableStager(
grpc.insecure_channel(
prepare_response.artifact_staging_endpoint.url),
prepare_response.staging_session_token)
retrieval_token, _ = stager.stage_job_resources(
pipeline._options, staging_location='')
else:
retrieval_token = None
run_response = job_service.Run(
beam_job_api_pb2.RunJobRequest(
preparation_id=prepare_response.preparation_id,
retrieval_token=retrieval_token))
return PipelineResult(job_service, run_response.job_id)
def run_pipeline(self, pipeline, options):
portable_options = options.view_as(PortableOptions)
job_endpoint = portable_options.job_endpoint
# TODO: https://issues.apache.org/jira/browse/BEAM-5525
# portable runner specific default
if options.view_as(SetupOptions).sdk_location == 'default':
options.view_as(SetupOptions).sdk_location = 'container'
if not job_endpoint:
# TODO Provide a way to specify a container Docker URL
# https://issues.apache.org/jira/browse/BEAM-6328
docker = DockerizedJobServer()
job_endpoint = docker.start()
job_service = None
elif job_endpoint == 'embed':
job_service = local_job_service.LocalJobServicer()
else:
job_service = None
# This is needed as we start a worker server if one is requested
# but none is provided.
if portable_options.environment_type == 'LOOPBACK':
portable_options.environment_config, server = (
BeamFnExternalWorkerPoolServicer.start(
sdk_worker_main._get_worker_count(options)))
globals()['x'] = server
cleanup_callbacks = [functools.partial(server.stop, 1)]
else:
cleanup_callbacks = []
proto_pipeline = pipeline.to_runner_api(
default_environment=PortableRunner._create_environment(
portable_options))
# Some runners won't detect the GroupByKey transform unless it has no
# subtransforms. Remove all sub-transforms until BEAM-4605 is resolved.
for _, transform_proto in list(
proto_pipeline.components.transforms.items()):
if transform_proto.spec.urn == common_urns.primitives.GROUP_BY_KEY.urn:
for sub_transform in transform_proto.subtransforms:
del proto_pipeline.components.transforms[sub_transform]
del transform_proto.subtransforms[:]
# Preemptively apply combiner lifting, until all runners support it.
# This optimization is idempotent.
pre_optimize = options.view_as(DebugOptions).lookup_experiment(
'pre_optimize', 'combine').lower()
if not options.view_as(StandardOptions).streaming:
flink_known_urns = frozenset([
common_urns.composites.RESHUFFLE.urn,
common_urns.primitives.IMPULSE.urn,
common_urns.primitives.FLATTEN.urn,
common_urns.primitives.GROUP_BY_KEY.urn])
if pre_optimize == 'combine':
proto_pipeline = fn_api_runner_transforms.optimize_pipeline(
proto_pipeline,
phases=[fn_api_runner_transforms.lift_combiners],
known_runner_urns=flink_known_urns,
partial=True)
elif pre_optimize == 'all':
proto_pipeline = fn_api_runner_transforms.optimize_pipeline(
proto_pipeline,
phases=[fn_api_runner_transforms.annotate_downstream_side_inputs,
fn_api_runner_transforms.annotate_stateful_dofns_as_roots,
fn_api_runner_transforms.fix_side_input_pcoll_coders,
fn_api_runner_transforms.lift_combiners,
fn_api_runner_transforms.fix_flatten_coders,
# fn_api_runner_transforms.sink_flattens,
fn_api_runner_transforms.greedily_fuse,
fn_api_runner_transforms.read_to_impulse,
fn_api_runner_transforms.extract_impulse_stages,
fn_api_runner_transforms.remove_data_plane_ops,
fn_api_runner_transforms.sort_stages],
known_runner_urns=flink_known_urns)
elif pre_optimize == 'none':
pass
else:
raise ValueError('Unknown value for pre_optimize: %s' % pre_optimize)
if not job_service:
channel = grpc.insecure_channel(job_endpoint)
grpc.channel_ready_future(channel).result()
job_service = beam_job_api_pb2_grpc.JobServiceStub(channel)
else:
channel = None
# fetch runner options from job service
# retries in case the channel is not ready
def send_options_request(max_retries=5):
num_retries = 0
while True:
try:
# This reports channel is READY but connections may fail
# Seems to be only an issue on Mac with port forwardings
if channel:
grpc.channel_ready_future(channel).result()
return job_service.DescribePipelineOptions(
beam_job_api_pb2.DescribePipelineOptionsRequest())
except grpc._channel._Rendezvous as e:
num_retries += 1
if num_retries > max_retries:
raise e
options_response = send_options_request()
def add_runner_options(parser):
for option in options_response.options:
try:
# no default values - we don't want runner options
# added unless they were specified by the user
add_arg_args = {'action' : 'store', 'help' : option.description}
if option.type == beam_job_api_pb2.PipelineOptionType.BOOLEAN:
add_arg_args['action'] = 'store_true'\
if option.default_value != 'true' else 'store_false'
elif option.type == beam_job_api_pb2.PipelineOptionType.INTEGER:
add_arg_args['type'] = int
elif option.type == beam_job_api_pb2.PipelineOptionType.ARRAY:
add_arg_args['action'] = 'append'
parser.add_argument("--%s" % option.name, **add_arg_args)
except Exception as e:
# ignore runner options that are already present
# only in this case is duplicate not treated as error
if 'conflicting option string' not in str(e):
raise
logging.debug("Runner option '%s' was already added" % option.name)
all_options = options.get_all_options(add_extra_args_fn=add_runner_options)
# TODO: Define URNs for options.
# convert int values: https://issues.apache.org/jira/browse/BEAM-5509
p_options = {'beam:option:' + k + ':v1': (str(v) if type(v) == int else v)
for k, v in all_options.items()
if v is not None}
prepare_response = job_service.Prepare(
beam_job_api_pb2.PrepareJobRequest(
job_name='job', pipeline=proto_pipeline,
pipeline_options=job_utils.dict_to_struct(p_options)))
if prepare_response.artifact_staging_endpoint.url:
stager = portable_stager.PortableStager(
grpc.insecure_channel(prepare_response.artifact_staging_endpoint.url),
prepare_response.staging_session_token)
retrieval_token, _ = stager.stage_job_resources(
options,
staging_location='')
else:
retrieval_token = None
try:
state_stream = job_service.GetStateStream(
beam_job_api_pb2.GetJobStateRequest(
job_id=prepare_response.preparation_id))
# If there's an error, we don't always get it until we try to read.
# Fortunately, there's always an immediate current state published.
state_stream = itertools.chain(
[next(state_stream)],
state_stream)
message_stream = job_service.GetMessageStream(
beam_job_api_pb2.JobMessagesRequest(
job_id=prepare_response.preparation_id))
except Exception:
# TODO(BEAM-6442): Unify preparation_id and job_id for all runners.
state_stream = message_stream = None
# Run the job and wait for a result.
run_response = job_service.Run(
beam_job_api_pb2.RunJobRequest(
preparation_id=prepare_response.preparation_id,
retrieval_token=retrieval_token))
if state_stream is None:
state_stream = job_service.GetStateStream(
beam_job_api_pb2.GetJobStateRequest(
job_id=run_response.job_id))
message_stream = job_service.GetMessageStream(
beam_job_api_pb2.JobMessagesRequest(
job_id=run_response.job_id))
return PipelineResult(job_service, run_response.job_id, message_stream,
state_stream, cleanup_callbacks)
def run_pipeline(self, pipeline):
portable_options = pipeline.options.view_as(PortableOptions)
job_endpoint = portable_options.job_endpoint
# TODO: https://issues.apache.org/jira/browse/BEAM-5525
# portable runner specific default
if pipeline.options.view_as(SetupOptions).sdk_location == 'default':
pipeline.options.view_as(SetupOptions).sdk_location = 'container'
if not job_endpoint:
docker = DockerizedJobServer()
job_endpoint = docker.start()
proto_pipeline = pipeline.to_runner_api()
# Some runners won't detect the GroupByKey transform unless it has no
# subtransforms. Remove all sub-transforms until BEAM-4605 is resolved.
for _, transform_proto in list(
proto_pipeline.components.transforms.items()):
if transform_proto.spec.urn == common_urns.primitives.GROUP_BY_KEY.urn:
for sub_transform in transform_proto.subtransforms:
del proto_pipeline.components.transforms[sub_transform]
del transform_proto.subtransforms[:]
# TODO: Define URNs for options.
# convert int values: https://issues.apache.org/jira/browse/BEAM-5509
options = {'beam:option:' + k + ':v1': (str(v) if type(v) == int else v)
for k, v in pipeline._options.get_all_options().items()
if v is not None}
channel = grpc.insecure_channel(job_endpoint)
grpc.channel_ready_future(channel).result()
job_service = beam_job_api_pb2_grpc.JobServiceStub(channel)
# Sends the PrepareRequest but retries in case the channel is not ready
def send_prepare_request(max_retries=5):
num_retries = 0
while True:
try:
# This reports channel is READY but connections may fail
# Seems to be only an issue on Mac with port forwardings
grpc.channel_ready_future(channel).result()
return job_service.Prepare(
beam_job_api_pb2.PrepareJobRequest(
job_name='job', pipeline=proto_pipeline,
pipeline_options=job_utils.dict_to_struct(options)))
except grpc._channel._Rendezvous as e:
num_retries += 1
if num_retries > max_retries:
raise e
prepare_response = send_prepare_request()
if prepare_response.artifact_staging_endpoint.url:
stager = portable_stager.PortableStager(
grpc.insecure_channel(prepare_response.artifact_staging_endpoint.url),
prepare_response.staging_session_token)
retrieval_token, _ = stager.stage_job_resources(
pipeline._options,
staging_location='')
else:
retrieval_token = None
run_response = job_service.Run(
beam_job_api_pb2.RunJobRequest(
preparation_id=prepare_response.preparation_id,
retrieval_token=retrieval_token))
return PipelineResult(job_service, run_response.job_id)
def init_dockerized_job_server(self): # TODO Provide a way to specify a container Docker URL # https://issues.apache.org/jira/browse/BEAM-6328 docker = DockerizedJobServer() self._job_endpoint = docker.start()
def init_dockerized_job_server(self): # TODO Provide a way to specify a container Docker URL # https://issues.apache.org/jira/browse/BEAM-6328 docker = DockerizedJobServer() self._job_endpoint = docker.start()