def submit_job(job_data):
job_id = generate_job_id()
schedule_logger.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_utils.check_pipeline_job_runtime_conf(job_runtime_conf)
job_parameters = job_runtime_conf['job_parameters']
job_initiator = job_runtime_conf['initiator']
job_type = job_parameters.get('job_type', '')
if job_type != 'predict':
# generate job model info
job_parameters['model_id'] = '#'.join([dtable_utils.all_party_key(job_runtime_conf['role']), 'model'])
job_parameters['model_version'] = job_id
train_runtime_conf = {}
else:
detect_utils.check_config(job_parameters, ['model_id', 'model_version'])
# get inference dsl from pipeline model as job dsl
job_tracker = Tracking(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 = job_tracker.get_output_model('pipeline')
job_dsl = json_loads(pipeline_model['Pipeline'].inference_dsl)
train_runtime_conf = json_loads(pipeline_model['Pipeline'].train_runtime_conf)
job_dsl_path, job_runtime_conf_path = save_job_conf(job_id=job_id,
job_dsl=job_dsl,
job_runtime_conf=job_runtime_conf)
job = Job()
job.f_job_id = job_id
job.f_roles = json_dumps(job_runtime_conf['role'])
job.f_work_mode = job_parameters['work_mode']
job.f_initiator_party_id = job_initiator['party_id']
job.f_dsl = json_dumps(job_dsl)
job.f_runtime_conf = json_dumps(job_runtime_conf)
job.f_train_runtime_conf = json_dumps(train_runtime_conf)
job.f_run_ip = ''
job.f_status = JobStatus.WAITING
job.f_progress = 0
job.f_create_time = current_timestamp()
# save job info
TaskScheduler.distribute_job(job=job, roles=job_runtime_conf['role'], job_initiator=job_initiator)
# push into queue
RuntimeConfig.JOB_QUEUE.put_event({
'job_id': job_id,
"initiator_role": job_initiator['role'],
"initiator_party_id": job_initiator['party_id']
}
)
schedule_logger.info(
'submit job successfully, job id is {}, model id is {}'.format(job.f_job_id, job_parameters['model_id']))
board_url = BOARD_DASHBOARD_URL.format(job_id, job_initiator['role'], job_initiator['party_id'])
return job_id, job_dsl_path, job_runtime_conf_path, {'model_id': job_parameters['model_id'],
'model_version': job_parameters[
'model_version']}, board_url
def update_job_progress(job_id, dag, current_task_id):
component_count = len(dag.get_dependency()['component_list'])
success_count = success_task_count(job_id=job_id)
job = Job()
job.f_progress = float(success_count) / component_count * 100
job.f_update_time = current_timestamp()
job.f_current_tasks = json_dumps([current_task_id])
return job
def save_pipeline(job_id, role, party_id, model_id, model_version):
job_dsl, job_runtime_conf, train_runtime_conf = job_utils.get_job_configuration(job_id=job_id, role=role,
party_id=party_id)
job_parameters = job_runtime_conf.get('job_parameters', {})
job_type = job_parameters.get('job_type', '')
if job_type == 'predict':
return
dag = job_utils.get_job_dsl_parser(dsl=job_dsl,
runtime_conf=job_runtime_conf,
train_runtime_conf=train_runtime_conf)
predict_dsl = dag.get_predict_dsl(role=role)
pipeline = pipeline_pb2.Pipeline()
pipeline.inference_dsl = json_dumps(predict_dsl, byte=True)
pipeline.train_dsl = json_dumps(job_dsl, byte=True)
pipeline.train_runtime_conf = json_dumps(job_runtime_conf, byte=True)
job_tracker = Tracking(job_id=job_id, role=role, party_id=party_id, model_id=model_id,
model_version=model_version)
job_tracker.save_output_model({'Pipeline': pipeline}, 'pipeline')
def save_commit_tmp(commit_id, data_table_namespace, tag, branch):
version_tmp_table = get_commit_tmp_table(
data_table_namespace=data_table_namespace)
version_tmp_table.put(commit_id,
json_dumps({
"tag": tag,
"branch": branch
}),
use_serialize=False)
def save_version_info(version_table, branch, commit_id, parent,
data_table_info):
version_info = dict()
version_info["commitId"] = commit_id
if parent != commit_id:
version_info["parent"] = parent
else:
version_info.update(
get_version_info(version_table=version_table, commit_id=parent))
version_info["repeatCommit"] = True
version_info.update(data_table_info)
version_table.put(commit_id, json_dumps(version_info), use_serialize=False)
# todo: should be use a lock
version_table.put(branch, commit_id, use_serialize=False)
def save_data_table_meta(kv, data_table_name, data_table_namespace):
"""
save data table meta information
:param kv: v should be serialized by JSON
:param data_table_name: table name of this data table
:param data_table_namespace: table name of this data table
:return:
"""
data_meta_table = eggroll.table(name="%s.meta" % data_table_name,
namespace=data_table_namespace,
partition=1,
create_if_missing=True, error_if_exist=False)
for k, v in kv.items():
data_meta_table.put(k, json_dumps(v), use_serialize=False)
def save_feature_header(features,
labels,
commit_log="",
commit_id=None,
tag=None,
branch="master"):
version_table, data_table_info, scene_key, parent, commit_id = save_version(
"feature_header_version", commit_id=commit_id, tag=tag, branch=branch)
data_table_info = gen_data_table_info("feature_header",
scene_key=scene_key,
commit_id=commit_id)
data_table = get_data_table(data_table_info=data_table_info,
create_if_missing=True)
data_table.put("features", json_dumps(features), use_serialize=False)
data_table.put("labels", json_dumps(labels), use_serialize=False)
# save version info
data_table_info["commitLog"] = commit_log
save_version_info(version_table=version_table,
branch=branch,
commit_id=commit_id,
parent=parent,
data_table_info=data_table_info)
return commit_id
def save_version_info(commit_id, data_table_namespace, version_log, tag, branch):
version_table = get_version_table(data_table_namespace=data_table_namespace)
parent = get_branch_current_commit(version_table=version_table, branch_name=branch)
version_info = dict()
version_info["commitId"] = commit_id
if parent != commit_id:
version_info["parent"] = parent
else:
version_info.update(get_version_info(version_table=version_table, commit_id=parent))
version_info["repeatCommit"] = True
version_info["name"] = commit_id
version_info["namespace"] = data_table_namespace
version_info["log"] = version_log
version_info["tag"] = tag
version_table.put(commit_id, json_dumps(version_info), use_serialize=False)
# todo: should be use a lock
version_table.put(branch, commit_id, use_serialize=False)
def save_data_table_meta(kv, data_table_name, data_table_namespace):
"""
save data table meta information
:param kv: v should be serialized by JSON
:param data_table_name: table name of this data table
:param data_table_namespace: table name of this data table
:return:
"""
from arch.api.utils.core import json_dumps
data_meta_table = FateSession.get_instance().table(
name="%s.meta" % data_table_name,
namespace=data_table_namespace,
partition=1,
create_if_missing=True,
error_if_exist=False,
persistent=True,
in_place_computing=False)
for k, v in kv.items():
data_meta_table.put(k, json_dumps(v), use_serialize=False)
def save_feature_meta(kv_meta,
commit_log="",
commit_id=None,
tag="",
branch="master"):
version_table, data_table_info, scene_key, parent, commit_id = save_version(
"feature_version", commit_id=commit_id, tag=tag, branch=branch)
data_table_info = gen_data_table_info("feature_meta",
scene_key=scene_key,
commit_id=commit_id)
data_table = get_data_table(data_table_info=data_table_info,
create_if_missing=True)
for k, v in kv_meta.items():
data_table.put(k, json_dumps(v), use_serialize=False)
# save version info
data_table_info["commitLog"] = commit_log
save_version_info(version_table=version_table,
branch=branch,
commit_id=commit_id,
parent=parent,
data_table_info=data_table_info)
return commit_id
def submit_job(job_data):
job_id = 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_utils.check_pipeline_job_runtime_conf(job_runtime_conf)
job_parameters = job_runtime_conf['job_parameters']
job_initiator = job_runtime_conf['initiator']
job_type = job_parameters.get('job_type', '')
if job_type != 'predict':
# generate job model info
job_parameters['model_id'] = '#'.join([dtable_utils.all_party_key(job_runtime_conf['role']), 'model'])
job_parameters['model_version'] = job_id
train_runtime_conf = {}
else:
detect_utils.check_config(job_parameters, ['model_id', 'model_version'])
# get inference dsl from pipeline model as job dsl
job_tracker = Tracking(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 = job_tracker.get_output_model('pipeline')
job_dsl = json_loads(pipeline_model['Pipeline'].inference_dsl)
train_runtime_conf = json_loads(pipeline_model['Pipeline'].train_runtime_conf)
path_dict = 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_roles = json_dumps(job_runtime_conf['role'])
job.f_work_mode = job_parameters['work_mode']
job.f_initiator_party_id = job_initiator['party_id']
job.f_dsl = json_dumps(job_dsl)
job.f_runtime_conf = json_dumps(job_runtime_conf)
job.f_train_runtime_conf = json_dumps(train_runtime_conf)
job.f_run_ip = ''
job.f_status = JobStatus.WAITING
job.f_progress = 0
job.f_create_time = current_timestamp()
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))
get_job_dsl_parser(dsl=job_dsl,
runtime_conf=job_runtime_conf,
train_runtime_conf=train_runtime_conf)
TaskScheduler.distribute_job(job=job, roles=job_runtime_conf['role'], job_initiator=job_initiator)
# push into queue
job_event = job_utils.job_event(job_id, initiator_role, initiator_party_id)
try:
RuntimeConfig.JOB_QUEUE.put_event(job_event)
except Exception as e:
raise Exception('push job into queue failed')
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 = BOARD_DASHBOARD_URL.format(job_id, job_initiator['role'], job_initiator['party_id'])
logs_directory = 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
