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 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 schedule_running_job(cls, job: Job, force_sync_status=False):
schedule_logger(job.f_job_id).info(f"scheduling running job")
dsl_parser = schedule_utils.get_job_dsl_parser(
dsl=job.f_dsl,
runtime_conf=job.f_runtime_conf_on_party,
train_runtime_conf=job.f_train_runtime_conf)
task_scheduling_status_code, auto_rerun_tasks, tasks = TaskScheduler.schedule(
job=job, dsl_parser=dsl_parser, canceled=job.f_cancel_signal)
tasks_status = dict([(task.f_component_name, task.f_status)
for task in tasks])
new_job_status = cls.calculate_job_status(
task_scheduling_status_code=task_scheduling_status_code,
tasks_status=tasks_status.values())
if new_job_status == JobStatus.WAITING and job.f_cancel_signal:
new_job_status = JobStatus.CANCELED
total, finished_count = cls.calculate_job_progress(
tasks_status=tasks_status)
new_progress = float(finished_count) / total * 100
schedule_logger(job.f_job_id).info(
f"job status is {new_job_status}, calculate by task status list: {tasks_status}"
)
if new_job_status != job.f_status or new_progress != job.f_progress:
# Make sure to update separately, because these two fields update with anti-weight logic
if int(new_progress) - job.f_progress > 0:
job.f_progress = new_progress
FederatedScheduler.sync_job(job=job,
update_fields=["progress"])
cls.update_job_on_initiator(initiator_job=job,
update_fields=["progress"])
if new_job_status != job.f_status:
job.f_status = new_job_status
if EndStatus.contains(job.f_status):
FederatedScheduler.save_pipelined_model(job=job)
FederatedScheduler.sync_job_status(job=job)
cls.update_job_on_initiator(initiator_job=job,
update_fields=["status"])
if EndStatus.contains(job.f_status):
cls.finish(job=job, end_status=job.f_status)
if auto_rerun_tasks:
schedule_logger(job.f_job_id).info("job have auto rerun tasks")
cls.set_job_rerun(job_id=job.f_job_id,
initiator_role=job.f_initiator_role,
initiator_party_id=job.f_initiator_party_id,
tasks=auto_rerun_tasks,
auto=True)
if force_sync_status:
FederatedScheduler.sync_job_status(job=job)
schedule_logger(job.f_job_id).info("finish scheduling running job")
def run_job(job_id, initiator_role, initiator_party_id):
job_dsl, job_runtime_conf, train_runtime_conf = job_utils.get_job_configuration(
job_id=job_id, role=initiator_role, party_id=initiator_party_id)
job_parameters = job_runtime_conf.get('job_parameters', {})
job_initiator = job_runtime_conf.get('initiator', {})
dag = get_job_dsl_parser(dsl=job_dsl,
runtime_conf=job_runtime_conf,
train_runtime_conf=train_runtime_conf)
job_args = dag.get_args_input()
if not job_initiator:
return False
storage.init_storage(job_id=job_id, work_mode=RuntimeConfig.WORK_MODE)
job = Job()
job.f_job_id = job_id
job.f_start_time = current_timestamp()
job.f_status = JobStatus.RUNNING
job.f_update_time = current_timestamp()
TaskScheduler.sync_job_status(
job_id=job_id,
roles=job_runtime_conf['role'],
work_mode=job_parameters['work_mode'],
initiator_party_id=job_initiator['party_id'],
job_info=job.to_json())
top_level_task_status = set()
components = dag.get_next_components(None)
schedule_logger.info('job {} root components is {}'.format(
job.f_job_id, [component.get_name() for component in components],
None))
for component in components:
try:
# run a component as task
run_status = TaskScheduler.run_component(
job_id, job_runtime_conf, job_parameters, job_initiator,
job_args, dag, component)
except Exception as e:
schedule_logger.info(e)
run_status = False
top_level_task_status.add(run_status)
if not run_status:
break
if len(top_level_task_status) == 2:
job.f_status = JobStatus.PARTIAL
elif True in top_level_task_status:
job.f_status = JobStatus.SUCCESS
else:
job.f_status = JobStatus.FAILED
job.f_end_time = current_timestamp()
job.f_elapsed = job.f_end_time - job.f_start_time
if job.f_status == JobStatus.SUCCESS:
job.f_progress = 100
job.f_update_time = current_timestamp()
TaskScheduler.sync_job_status(
job_id=job_id,
roles=job_runtime_conf['role'],
work_mode=job_parameters['work_mode'],
initiator_party_id=job_initiator['party_id'],
job_info=job.to_json())
TaskScheduler.finish_job(job_id=job_id,
job_runtime_conf=job_runtime_conf)
schedule_logger.info('job {} finished, status is {}'.format(
job.f_job_id, job.f_status))
def run_job(job_id, initiator_role, initiator_party_id):
job_dsl, job_runtime_conf, train_runtime_conf = job_utils.get_job_configuration(job_id=job_id,
role=initiator_role,
party_id=initiator_party_id)
job_parameters = job_runtime_conf.get('job_parameters', {})
job_initiator = job_runtime_conf.get('initiator', {})
dag = get_job_dsl_parser(dsl=job_dsl,
runtime_conf=job_runtime_conf,
train_runtime_conf=train_runtime_conf)
job_args = dag.get_args_input()
if not job_initiator:
return False
timeout = job_utils.get_timeout(job_id, job_parameters.get("timeout", None), job_runtime_conf, job_dsl)
t = Timer(timeout, TaskScheduler.job_handler, [job_id])
t.start()
job = Job()
job.f_job_id = job_id
job.f_start_time = current_timestamp()
job.f_status = JobStatus.RUNNING
job.f_update_time = current_timestamp()
TaskScheduler.sync_job_status(job_id=job_id, roles=job_runtime_conf['role'],
work_mode=job_parameters['work_mode'],
initiator_party_id=job_initiator['party_id'],
initiator_role=job_initiator['role'],
job_info=job.to_json())
top_level_task_status = set()
components = dag.get_next_components(None)
schedule_logger(job_id).info(
'job {} root components is {}'.format(job.f_job_id, [component.get_name() for component in components],
None))
for component in components:
try:
# run a component as task
run_status = TaskScheduler.run_component(job_id, job_runtime_conf, job_parameters, job_initiator,
job_args, dag,
component)
except Exception as e:
schedule_logger(job_id).exception(e)
run_status = False
top_level_task_status.add(run_status)
if not run_status:
break
if len(top_level_task_status) == 2:
job.f_status = JobStatus.FAILED
elif True in top_level_task_status:
job.f_status = JobStatus.COMPLETE
else:
job.f_status = JobStatus.FAILED
job.f_end_time = current_timestamp()
job.f_elapsed = job.f_end_time - job.f_start_time
if job.f_status == JobStatus.COMPLETE:
job.f_progress = 100
job.f_update_time = current_timestamp()
try:
TaskScheduler.finish_job(job_id=job_id, job_runtime_conf=job_runtime_conf)
except Exception as e:
schedule_logger(job_id).exception(e)
job.f_status = JobStatus.FAILED
if job.f_status == JobStatus.FAILED:
TaskScheduler.stop(job_id=job_id, end_status=JobStatus.FAILED)
try:
TaskScheduler.sync_job_status(job_id=job_id, roles=job_runtime_conf['role'],
work_mode=job_parameters['work_mode'],
initiator_party_id=job_initiator['party_id'],
initiator_role=job_initiator['role'],
job_info=job.to_json())
except Exception as e:
schedule_logger(job_id).exception(e)
schedule_logger(job_id).warning('job {} sync status failed'.format(job.f_job_id))
schedule_logger(job_id).info('job {} finished, status is {}'.format(job.f_job_id, job.f_status))
t.cancel()
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
