def clean_queue():
schedule_logger().info('get clean queue command')
jobs = job_utils.query_job(is_initiator=1, status=JobStatus.WAITING)
if jobs:
for job in jobs:
schedule_logger(job.f_job_id).info(
'start send {} job {} command success'.format(JobStatus.CANCELED, job.f_job_id))
job_info = {'f_job_id': job.f_job_id, 'f_status': JobStatus.CANCELED}
roles = json_loads(job.f_roles)
job_work_mode = job.f_work_mode
initiator_party_id = job.f_party_id
TaskScheduler.sync_job_status(job_id=job.f_job_id, roles=roles, initiator_party_id=initiator_party_id,
initiator_role=job.f_role,
work_mode=job_work_mode,
job_info=job_info)
job_runtime_conf = json_loads(job.f_runtime_conf)
event = job_utils.job_event(job.f_job_id,
job_runtime_conf['initiator']['role'],
job_runtime_conf['initiator']['party_id'])
try:
RuntimeConfig.JOB_QUEUE.del_event(event)
schedule_logger(job.f_job_id).info(
'send {} job {} command success'.format(JobStatus.CANCELED, job.f_job_id))
except Exception as e:
schedule_logger(job.f_job_id).error(e)
else:
raise Exception('There are no jobs in the queue')
def cancel_job(job_id, role, party_id, job_initiator):
schedule_logger(job_id).info(
'{} {} get cancel waiting job {} command'.format(
role, party_id, job_id))
jobs = job_utils.query_job(job_id=job_id, is_initiator=1)
if jobs:
job = jobs[0]
job_runtime_conf = json_loads(job.f_runtime_conf)
event = job_utils.job_event(
job.f_job_id, job_runtime_conf['initiator']['role'],
job_runtime_conf['initiator']['party_id'])
try:
RuntimeConfig.JOB_QUEUE.del_event(event)
except:
return False
schedule_logger(job_id).info(
'cancel waiting job successfully, job id is {}'.format(
job.f_job_id))
return True
else:
jobs = job_utils.query_job(job_id=job_id)
if jobs:
raise Exception(
'role {} party id {} cancel waiting job {} failed, not is initiator'
.format(role, party_id, job_id))
raise Exception(
'role {} party id {} cancel waiting job failed, no find jod {}'
.format(role, party_id, job_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