def get_job_parameters_dict(self, job_parameters: RunParameters = None):
if job_parameters:
if int(self.job_runtime_conf.get('dsl_version', 1)) == 2:
self.job_runtime_conf['job_parameters']['common'] = job_parameters.to_dict()
else:
self.job_runtime_conf['job_parameters'] = job_parameters.to_dict()
return self.job_runtime_conf['job_parameters']
def update_common_parameters(self, common_parameters: RunParameters):
if int(self.job_runtime_conf.get("dsl_version", 1)) == 2:
if "common" not in self.job_runtime_conf["job_parameters"]:
raise RuntimeError("the configuration format for v2 version must be job_parameters:common")
self.job_runtime_conf["job_parameters"]["common"] = common_parameters.to_dict()
else:
self.job_runtime_conf["job_parameters"] = common_parameters.to_dict()
return self.job_runtime_conf
def get_common_parameters(self):
if int(self.job_runtime_conf.get('dsl_version', 1)) == 2:
if "common" not in self.job_runtime_conf["job_parameters"]:
raise RuntimeError("the configuration format for v2 version must be job_parameters:common")
job_parameters = RunParameters(**self.job_runtime_conf['job_parameters']['common'])
self.job_runtime_conf['job_parameters']['common'] = job_parameters.to_dict()
else:
if "processors_per_node" in self.job_runtime_conf['job_parameters']:
self.job_runtime_conf['job_parameters']["eggroll_run"] = \
{"eggroll.session.processors.per.node": self.job_runtime_conf['job_parameters']["processors_per_node"]}
job_parameters = RunParameters(**self.job_runtime_conf['job_parameters'])
self.job_runtime_conf['job_parameters'] = job_parameters.to_dict()
return job_parameters
def create_job(cls, job_id, role, party_id, job_info):
# parse job configuration
dsl = job_info['dsl']
runtime_conf = job_info['runtime_conf']
train_runtime_conf = job_info['train_runtime_conf']
if USE_AUTHENTICATION:
authentication_check(src_role=job_info.get('src_role', None),
src_party_id=job_info.get(
'src_party_id', None),
dsl=dsl,
runtime_conf=runtime_conf,
role=role,
party_id=party_id)
job_parameters = RunParameters(**runtime_conf['job_parameters'])
job_initiator = runtime_conf['initiator']
dsl_parser = schedule_utils.get_job_dsl_parser(
dsl=dsl,
runtime_conf=runtime_conf,
train_runtime_conf=train_runtime_conf)
# save new job into db
if role == job_initiator['role'] and party_id == job_initiator[
'party_id']:
is_initiator = True
else:
is_initiator = False
job_info["status"] = JobStatus.WAITING
roles = job_info['roles']
# this party configuration
job_info["role"] = role
job_info["party_id"] = party_id
job_info["is_initiator"] = is_initiator
job_info["progress"] = 0
engines_info = cls.get_job_engines_address(
job_parameters=job_parameters)
cls.special_role_parameters(role=role, job_parameters=job_parameters)
cls.check_parameters(job_parameters=job_parameters,
engines_info=engines_info)
runtime_conf["job_parameters"] = job_parameters.to_dict()
JobSaver.create_job(job_info=job_info)
job_utils.save_job_conf(job_id=job_id,
job_dsl=dsl,
job_runtime_conf=runtime_conf,
train_runtime_conf=train_runtime_conf,
pipeline_dsl=None)
cls.initialize_tasks(job_id, role, party_id, True, job_initiator,
job_parameters, dsl_parser)
cls.initialize_job_tracker(job_id=job_id,
role=role,
party_id=party_id,
job_info=job_info,
is_initiator=is_initiator,
dsl_parser=dsl_parser)
def create_job(cls, job_id, role, party_id, job_info):
# parse job configuration
dsl = job_info['dsl']
runtime_conf = job_info['runtime_conf']
train_runtime_conf = job_info['train_runtime_conf']
if USE_AUTHENTICATION:
authentication_check(src_role=job_info.get('src_role', None), src_party_id=job_info.get('src_party_id', None),
dsl=dsl, runtime_conf=runtime_conf, role=role, party_id=party_id)
dsl_parser = schedule_utils.get_job_dsl_parser(dsl=dsl,
runtime_conf=runtime_conf,
train_runtime_conf=train_runtime_conf)
job_parameters = dsl_parser.get_job_parameters().get(role, {}).get(party_id, {})
schedule_logger(job_id).info('job parameters:{}'.format(job_parameters))
job_parameters = RunParameters(**job_parameters)
# save new job into db
if role == job_info["initiator_role"] and party_id == job_info["initiator_party_id"]:
is_initiator = True
else:
is_initiator = False
job_info["status"] = JobStatus.WAITING
# this party configuration
job_info["role"] = role
job_info["party_id"] = party_id
job_info["is_initiator"] = is_initiator
job_info["progress"] = 0
cls.adapt_job_parameters(role=role, job_parameters=job_parameters)
engines_info = cls.get_job_engines_address(job_parameters=job_parameters)
cls.check_parameters(job_parameters=job_parameters, role=role, party_id=party_id, engines_info=engines_info)
job_info["runtime_conf_on_party"]["job_parameters"] = job_parameters.to_dict()
job_utils.save_job_conf(job_id=job_id,
role=role,
job_dsl=dsl,
job_runtime_conf=runtime_conf,
job_runtime_conf_on_party=job_info["runtime_conf_on_party"],
train_runtime_conf=train_runtime_conf,
pipeline_dsl=None)
cls.initialize_tasks(job_id=job_id, role=role, party_id=party_id, run_on_this_party=True, initiator_role=job_info["initiator_role"], initiator_party_id=job_info["initiator_party_id"], job_parameters=job_parameters, dsl_parser=dsl_parser)
job_parameters = job_info['runtime_conf_on_party']['job_parameters']
roles = job_info['roles']
cls.initialize_job_tracker(job_id=job_id, role=role, party_id=party_id, job_parameters=job_parameters, roles=roles, is_initiator=is_initiator, dsl_parser=dsl_parser)
JobSaver.create_job(job_info=job_info)
def create_job(cls, job_id, role, party_id, job_info):
# parse job configuration
dsl = job_info['dsl']
runtime_conf = job_info['runtime_conf']
train_runtime_conf = job_info['train_runtime_conf']
if USE_AUTHENTICATION:
authentication_check(src_role=job_info.get('src_role', None),
src_party_id=job_info.get(
'src_party_id', None),
dsl=dsl,
runtime_conf=runtime_conf,
role=role,
party_id=party_id)
dsl_parser = schedule_utils.get_job_dsl_parser(
dsl=dsl,
runtime_conf=runtime_conf,
train_runtime_conf=train_runtime_conf)
job_parameters = dsl_parser.get_job_parameters().get(role, {}).get(
party_id, {})
schedule_logger(job_id).info(
'job parameters:{}'.format(job_parameters))
dest_user = dsl_parser.get_job_parameters().get(role, {}).get(
party_id, {}).get("user", '')
user = {}
src_party_id = int(job_info.get('src_party_id')) if job_info.get(
'src_party_id') else 0
src_user = dsl_parser.get_job_parameters().get(
job_info.get('src_role'), {}).get(src_party_id,
{}).get("user", '')
for _role, party_id_item in dsl_parser.get_job_parameters().items():
user[_role] = {}
for _party_id, _parameters in party_id_item.items():
user[_role][_party_id] = _parameters.get("user", "")
schedule_logger(job_id).info('job user:{}'.format(user))
if USE_DATA_AUTHENTICATION:
job_args = dsl_parser.get_args_input()
schedule_logger(job_id).info('job args:{}'.format(job_args))
dataset_dict = cls.get_dataset(False, role, party_id,
runtime_conf.get("role"), job_args)
dataset_list = []
if dataset_dict.get(role, {}).get(party_id):
for k, v in dataset_dict[role][party_id].items():
dataset_list.append({
"namespace": v.split('.')[0],
"table_name": v.split('.')[1]
})
data_authentication_check(
src_role=job_info.get('src_role'),
src_party_id=job_info.get('src_party_id'),
src_user=src_user,
dest_user=dest_user,
dataset_list=dataset_list)
job_parameters = RunParameters(**job_parameters)
# save new job into db
if role == job_info["initiator_role"] and party_id == job_info[
"initiator_party_id"]:
is_initiator = True
else:
is_initiator = False
job_info["status"] = JobStatus.WAITING
job_info["user_id"] = dest_user
job_info["src_user"] = src_user
job_info["user"] = user
# this party configuration
job_info["role"] = role
job_info["party_id"] = party_id
job_info["is_initiator"] = is_initiator
job_info["progress"] = 0
cls.adapt_job_parameters(role=role, job_parameters=job_parameters)
engines_info = cls.get_job_engines_address(
job_parameters=job_parameters)
cls.check_parameters(job_parameters=job_parameters,
role=role,
party_id=party_id,
engines_info=engines_info)
job_info["runtime_conf_on_party"][
"job_parameters"] = job_parameters.to_dict()
job_utils.save_job_conf(
job_id=job_id,
role=role,
job_dsl=dsl,
job_runtime_conf=runtime_conf,
job_runtime_conf_on_party=job_info["runtime_conf_on_party"],
train_runtime_conf=train_runtime_conf,
pipeline_dsl=None)
cls.initialize_tasks(job_id=job_id,
role=role,
party_id=party_id,
run_on_this_party=True,
initiator_role=job_info["initiator_role"],
initiator_party_id=job_info["initiator_party_id"],
job_parameters=job_parameters,
dsl_parser=dsl_parser)
job_parameters = job_info['runtime_conf_on_party']['job_parameters']
roles = job_info['roles']
cls.initialize_job_tracker(job_id=job_id,
role=role,
party_id=party_id,
job_parameters=job_parameters,
roles=roles,
is_initiator=is_initiator,
dsl_parser=dsl_parser)
JobSaver.create_job(job_info=job_info)
def submit(cls, job_data, job_id=None):
if not job_id:
job_id = job_utils.generate_job_id()
schedule_logger(job_id).info('submit job, job_id {}, body {}'.format(job_id, job_data))
job_dsl = job_data.get('job_dsl', {})
job_runtime_conf = job_data.get('job_runtime_conf', {})
job_initiator = job_runtime_conf['initiator']
job_parameters = RunParameters(**job_runtime_conf['job_parameters'])
cls.backend_compatibility(job_parameters=job_parameters)
job_utils.check_job_runtime_conf(job_runtime_conf)
if job_parameters.job_type != 'predict':
# generate job model info
job_parameters.model_id = model_utils.gen_model_id(job_runtime_conf['role'])
job_parameters.model_version = job_id
train_runtime_conf = {}
else:
detect_utils.check_config(job_parameters.to_dict(), ['model_id', 'model_version'])
# get inference dsl from pipeline model as job dsl
tracker = Tracker(job_id=job_id, role=job_initiator['role'], party_id=job_initiator['party_id'],
model_id=job_parameters.model_id, model_version=job_parameters.model_version)
pipeline_model = tracker.get_output_model('pipeline')
if not job_dsl:
job_dsl = json_loads(pipeline_model['Pipeline'].inference_dsl)
train_runtime_conf = json_loads(pipeline_model['Pipeline'].train_runtime_conf)
path_dict = job_utils.save_job_conf(job_id=job_id,
job_dsl=job_dsl,
job_runtime_conf=job_runtime_conf,
train_runtime_conf=train_runtime_conf,
pipeline_dsl=None)
job = Job()
job.f_job_id = job_id
job.f_dsl = job_dsl
job_runtime_conf["job_parameters"] = job_parameters.to_dict()
job.f_runtime_conf = job_runtime_conf
job.f_train_runtime_conf = train_runtime_conf
job.f_roles = job_runtime_conf['role']
job.f_work_mode = job_parameters.work_mode
job.f_initiator_role = job_initiator['role']
job.f_initiator_party_id = job_initiator['party_id']
initiator_role = job_initiator['role']
initiator_party_id = job_initiator['party_id']
if initiator_party_id not in job_runtime_conf['role'][initiator_role]:
schedule_logger(job_id).info("initiator party id error:{}".format(initiator_party_id))
raise Exception("initiator party id error {}".format(initiator_party_id))
dsl_parser = schedule_utils.get_job_dsl_parser(dsl=job_dsl,
runtime_conf=job_runtime_conf,
train_runtime_conf=train_runtime_conf)
cls.adapt_job_parameters(job_parameters=job_parameters)
# update runtime conf
job_runtime_conf["job_parameters"] = job_parameters.to_dict()
job.f_runtime_conf = job_runtime_conf
status_code, response = FederatedScheduler.create_job(job=job)
if status_code != FederatedSchedulingStatusCode.SUCCESS:
raise Exception("create job failed: {}".format(response))
if job_parameters.work_mode == WorkMode.CLUSTER:
# Save the status information of all participants in the initiator for scheduling
for role, party_ids in job_runtime_conf["role"].items():
for party_id in party_ids:
if role == job_initiator['role'] and party_id == job_initiator['party_id']:
continue
JobController.initialize_tasks(job_id, role, party_id, False, job_initiator, job_parameters, dsl_parser)
# push into queue
try:
JobQueue.create_event(job_id=job_id, initiator_role=initiator_role, initiator_party_id=initiator_party_id)
except Exception as e:
raise Exception(f'push job into queue failed:\n{e}')
schedule_logger(job_id).info(
'submit job successfully, job id is {}, model id is {}'.format(job.f_job_id, job_parameters.model_id))
board_url = "http://{}:{}{}".format(
ServiceUtils.get_item("fateboard", "host"),
ServiceUtils.get_item("fateboard", "port"),
FATE_BOARD_DASHBOARD_ENDPOINT).format(job_id, job_initiator['role'], job_initiator['party_id'])
logs_directory = job_utils.get_job_log_directory(job_id)
return job_id, path_dict['job_dsl_path'], path_dict['job_runtime_conf_path'], logs_directory, \
{'model_id': job_parameters.model_id, 'model_version': job_parameters.model_version}, board_url