def rerun_job(job_id, role, party_id):
DAGScheduler.set_job_rerun(
job_id=job_id,
initiator_role=role,
initiator_party_id=party_id,
component_name=request.json.get("component_name"),
force=request.json.get("force", False),
auto=False)
#todo: 判断状态
return get_json_result(retcode=0, retmsg='success')
def submit_job():
submit_result = DAGScheduler.submit(JobConfigurationBase(**request.json))
return get_json_result(retcode=submit_result["code"],
retmsg=submit_result["message"],
job_id=submit_result["job_id"],
data=submit_result if submit_result["code"]
== RetCode.SUCCESS else None)
def download_upload(access_module):
job_id = job_utils.generate_job_id()
if access_module == "upload" and UPLOAD_DATA_FROM_CLIENT and not (request.json and request.json.get("use_local_data") == 0):
file = request.files['file']
filename = os.path.join(job_utils.get_job_directory(job_id), 'fate_upload_tmp', file.filename)
os.makedirs(os.path.dirname(filename), exist_ok=True)
try:
file.save(filename)
except Exception as e:
shutil.rmtree(os.path.join(job_utils.get_job_directory(job_id), 'fate_upload_tmp'))
raise e
job_config = request.args.to_dict()
if "namespace" in job_config and "table_name" in job_config:
pass
else:
# higher than version 1.5.1, support eggroll run parameters
job_config = json_loads(list(job_config.keys())[0])
job_config['file'] = filename
else:
job_config = request.json
required_arguments = ['work_mode', 'namespace', 'table_name']
if access_module == 'upload':
required_arguments.extend(['file', 'head', 'partition'])
elif access_module == 'download':
required_arguments.extend(['output_path'])
else:
raise Exception('can not support this operating: {}'.format(access_module))
detect_utils.check_config(job_config, required_arguments=required_arguments)
data = {}
# compatibility
if "table_name" in job_config:
job_config["name"] = job_config["table_name"]
if "backend" not in job_config:
job_config["backend"] = 0
for _ in ["work_mode", "backend", "head", "partition", "drop"]:
if _ in job_config:
job_config[_] = int(job_config[_])
if access_module == "upload":
if job_config.get('drop', 0) == 1:
job_config["destroy"] = True
else:
job_config["destroy"] = False
data['table_name'] = job_config["table_name"]
data['namespace'] = job_config["namespace"]
data_table_meta = storage.StorageTableMeta(name=job_config["table_name"], namespace=job_config["namespace"])
if data_table_meta and not job_config["destroy"]:
return get_json_result(retcode=100,
retmsg='The data table already exists.'
'If you still want to continue uploading, please add the parameter -drop.'
' 0 means not to delete and continue uploading, '
'1 means to upload again after deleting the table')
job_dsl, job_runtime_conf = gen_data_access_job_config(job_config, access_module)
submit_result = DAGScheduler.submit({'job_dsl': job_dsl, 'job_runtime_conf': job_runtime_conf}, job_id=job_id)
data.update(submit_result)
return get_json_result(job_id=job_id, data=data)
def submit_job():
work_mode = JobRuntimeConfigAdapter(
request.json.get('job_runtime_conf', {})).get_job_work_mode()
detect_utils.check_config({'work_mode': work_mode},
required_arguments=[('work_mode',
(WorkMode.CLUSTER,
WorkMode.STANDALONE))])
submit_result = DAGScheduler.submit(request.json)
return get_json_result(retcode=0,
retmsg='success',
job_id=submit_result.get("job_id"),
data=submit_result)
def update_parameters():
job_info = request.json
component_parameters = job_info.pop("component_parameters", None)
job_parameters = job_info.pop("job_parameters", None)
job_info["is_initiator"] = True
jobs = JobSaver.query_job(**job_info)
if not jobs:
return get_json_result(
retcode=RetCode.DATA_ERROR,
retmsg=log_utils.failed_log(f"query job by {job_info}"))
else:
retcode, retdata = DAGScheduler.update_parameters(
jobs[0], job_parameters, component_parameters)
return get_json_result(retcode=retcode, data=retdata)
def operate_model(model_operation):
request_config = request.json or request.form.to_dict()
job_id = job_utils.generate_job_id()
if model_operation not in [
ModelOperation.STORE, ModelOperation.RESTORE,
ModelOperation.EXPORT, ModelOperation.IMPORT
]:
raise Exception(
'Can not support this operating now: {}'.format(model_operation))
required_arguments = ["model_id", "model_version", "role", "party_id"]
check_config(request_config, required_arguments=required_arguments)
request_config["model_id"] = gen_party_model_id(
model_id=request_config["model_id"],
role=request_config["role"],
party_id=request_config["party_id"])
if model_operation in [ModelOperation.EXPORT, ModelOperation.IMPORT]:
if model_operation == ModelOperation.IMPORT:
try:
file = request.files.get('file')
file_path = os.path.join(TEMP_DIRECTORY, file.filename)
# if not os.path.exists(file_path):
# raise Exception('The file is obtained from the fate flow client machine, but it does not exist, '
# 'please check the path: {}'.format(file_path))
try:
os.makedirs(os.path.dirname(file_path), exist_ok=True)
file.save(file_path)
except Exception as e:
shutil.rmtree(file_path)
raise e
request_config['file'] = file_path
model = pipelined_model.PipelinedModel(
model_id=request_config["model_id"],
model_version=request_config["model_version"])
model.unpack_model(file_path)
pipeline = model.read_component_model('pipeline',
'pipeline')['Pipeline']
train_runtime_conf = json_loads(pipeline.train_runtime_conf)
permitted_party_id = []
for key, value in train_runtime_conf.get('role', {}).items():
for v in value:
permitted_party_id.extend([v, str(v)])
if request_config["party_id"] not in permitted_party_id:
shutil.rmtree(model.model_path)
raise Exception(
"party id {} is not in model roles, please check if the party id is valid."
)
try:
adapter = JobRuntimeConfigAdapter(train_runtime_conf)
job_parameters = adapter.get_common_parameters().to_dict()
with DB.connection_context():
db_model = MLModel.get_or_none(
MLModel.f_job_id == job_parameters.get(
"model_version"),
MLModel.f_role == request_config["role"])
if not db_model:
model_info = model_utils.gather_model_info_data(model)
model_info['imported'] = 1
model_info['job_id'] = model_info['f_model_version']
model_info['size'] = model.calculate_model_file_size()
model_info['role'] = request_config["model_id"].split(
'#')[0]
model_info['party_id'] = request_config[
"model_id"].split('#')[1]
if model_utils.compare_version(
model_info['f_fate_version'], '1.5.1') == 'lt':
model_info['roles'] = model_info.get(
'f_train_runtime_conf', {}).get('role', {})
model_info['initiator_role'] = model_info.get(
'f_train_runtime_conf',
{}).get('initiator', {}).get('role')
model_info['initiator_party_id'] = model_info.get(
'f_train_runtime_conf',
{}).get('initiator', {}).get('party_id')
model_info[
'work_mode'] = adapter.get_job_work_mode()
model_info['parent'] = False if model_info.get(
'f_inference_dsl') else True
model_utils.save_model_info(model_info)
else:
stat_logger.info(
f'job id: {job_parameters.get("model_version")}, '
f'role: {request_config["role"]} model info already existed in database.'
)
except peewee.IntegrityError as e:
stat_logger.exception(e)
operation_record(request_config, "import", "success")
return get_json_result()
except Exception:
operation_record(request_config, "import", "failed")
raise
else:
try:
model = pipelined_model.PipelinedModel(
model_id=request_config["model_id"],
model_version=request_config["model_version"])
if model.exists():
archive_file_path = model.packaging_model()
operation_record(request_config, "export", "success")
return send_file(archive_file_path,
attachment_filename=os.path.basename(
archive_file_path),
as_attachment=True)
else:
operation_record(request_config, "export", "failed")
res = error_response(
response_code=210,
retmsg="Model {} {} is not exist.".format(
request_config.get("model_id"),
request_config.get("model_version")))
return res
except Exception as e:
operation_record(request_config, "export", "failed")
stat_logger.exception(e)
return error_response(response_code=210, retmsg=str(e))
else:
data = {}
job_dsl, job_runtime_conf = gen_model_operation_job_config(
request_config, model_operation)
submit_result = DAGScheduler.submit(
{
'job_dsl': job_dsl,
'job_runtime_conf': job_runtime_conf
},
job_id=job_id)
data.update(submit_result)
operation_record(data=job_runtime_conf,
oper_type=model_operation,
oper_status='')
return get_json_result(job_id=job_id, data=data)
def stop_job(job_id, role, party_id, stop_status):
retcode, retmsg = DAGScheduler.stop_job(job_id=job_id,
role=role,
party_id=party_id,
stop_status=stop_status)
return get_json_result(retcode=retcode, retmsg=retmsg)
def rerun_job(job_id, role, party_id):
DAGScheduler.rerun_job(job_id=job_id, initiator_role=role, initiator_party_id=party_id,
component_name=request.json.get("component_name"))
return get_json_result(retcode=0, retmsg='success')
init_arch_db()
# init runtime config
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--standalone_node',
default=False,
help="if standalone node mode or not ",
action='store_true')
args = parser.parse_args()
RuntimeConfig.init_env()
RuntimeConfig.set_process_role(ProcessRole.DRIVER)
PrivilegeAuth.init()
ServiceUtils.register()
ResourceManager.initialize()
Detector(interval=5 * 1000).start()
DAGScheduler(interval=2 * 1000).start()
thread_pool_executor = ThreadPoolExecutor(
max_workers=GRPC_SERVER_MAX_WORKERS)
stat_logger.info(
f"start grpc server thread pool by {thread_pool_executor._max_workers} max workers"
)
server = grpc.server(
thread_pool=thread_pool_executor,
options=[(cygrpc.ChannelArgKey.max_send_message_length, -1),
(cygrpc.ChannelArgKey.max_receive_message_length, -1)])
proxy_pb2_grpc.add_DataTransferServiceServicer_to_server(
UnaryService(), server)
server.add_insecure_port("{}:{}".format(IP, GRPC_PORT))
server.start()
stat_logger.info("FATE Flow grpc server start successfully")