def check_task_status(job_id, component, interval=1):
task_id = job_utils.generate_task_id(
job_id=job_id, component_name=component.get_name())
while True:
try:
status_collect = set()
parameters = component.get_role_parameters()
for _role, _partys_parameters in parameters.items():
for _party_parameters in _partys_parameters:
_party_id = _party_parameters.get('local',
{}).get('party_id')
tasks = query_task(job_id=job_id,
task_id=task_id,
role=_role,
party_id=_party_id)
if tasks:
task_status = tasks[0].f_status
else:
task_status = 'notRunning'
schedule_logger.info(
'job {} component {} run on {} {} status is {}'.
format(job_id, component.get_name(), _role,
_party_id, task_status))
status_collect.add(task_status)
if 'failed' in status_collect:
return False
elif len(status_collect) == 1 and 'success' in status_collect:
return True
else:
time.sleep(interval)
except Exception as e:
schedule_logger.exception(e)
return False
def start_task(job_id, component_name, task_id, role, party_id,
task_config):
schedule_logger.info('job {} {} {} {} task subprocess is ready'.format(
job_id, component_name, role, party_id, task_config))
task_process_start_status = False
try:
task_dir = os.path.join(job_utils.get_job_directory(job_id=job_id),
role, party_id, component_name)
os.makedirs(task_dir, exist_ok=True)
task_config_path = os.path.join(task_dir, 'task_config.json')
with open(task_config_path, 'w') as fw:
json.dump(task_config, fw)
process_cmd = [
'python3', sys.modules[TaskExecutor.__module__].__file__, '-j',
job_id, '-n', component_name, '-t', task_id, '-r', role, '-p',
party_id, '-c', task_config_path
]
task_log_dir = os.path.join(
job_utils.get_job_log_directory(job_id=job_id), role, party_id,
component_name)
schedule_logger.info(
'job {} {} {} {} task subprocess start'.format(
job_id, component_name, role, party_id, task_config))
p = job_utils.run_subprocess(config_dir=task_dir,
process_cmd=process_cmd,
log_dir=task_log_dir)
if p:
task_process_start_status = True
except Exception as e:
schedule_logger.exception(e)
finally:
schedule_logger.info(
'job {} component {} on {} {} start task subprocess {}'.format(
job_id, component_name, role, party_id,
'success' if task_process_start_status else 'failed'))
def clean_job(job_id, role, party_id):
schedule_logger.info('job {} on {} {} start to clean'.format(job_id, role, party_id))
tasks = job_utils.query_task(job_id=job_id, role=role, party_id=party_id)
for task in tasks:
try:
Tracking(job_id=job_id, role=role, party_id=party_id, task_id=task.f_task_id).clean_task()
schedule_logger.info(
'job {} component {} on {} {} clean done'.format(job_id, task.f_component_name, role, party_id))
except Exception as e:
schedule_logger.info(
'job {} component {} on {} {} clean failed'.format(job_id, task.f_component_name, role, party_id))
schedule_logger.exception(e)
schedule_logger.info('job {} on {} {} clean done'.format(job_id, role, party_id))
def run(self):
if not self.queue.is_ready():
schedule_logger.error('queue is not ready')
return False
all_jobs = []
while True:
try:
if len(all_jobs) == self.concurrent_num:
for future in as_completed(all_jobs):
all_jobs.remove(future)
break
job_event = self.queue.get_event()
schedule_logger.info('schedule job {}'.format(job_event))
future = self.job_executor_pool.submit(DAGScheduler.handle_event, job_event)
future.add_done_callback(DAGScheduler.get_result)
all_jobs.append(future)
except Exception as e:
schedule_logger.exception(e)
def kill_job(job_id, role, party_id, job_initiator):
schedule_logger.info('{} {} get kill job {} command'.format(role, party_id, job_id))
tasks = job_utils.query_task(job_id=job_id, role=role, party_id=party_id)
for task in tasks:
kill_status = False
try:
kill_status = job_utils.kill_process(int(task.f_run_pid))
except Exception as e:
schedule_logger.exception(e)
finally:
schedule_logger.info(
'job {} component {} on {} {} process {} kill {}'.format(job_id, task.f_component_name, task.f_role,
task.f_party_id, task.f_run_pid,
'success' if kill_status else 'failed'))
if task.f_status != TaskStatus.SUCCESS:
task.f_status = TaskStatus.FAILED
TaskExecutor.sync_task_status(job_id=job_id, component_name=task.f_component_name, task_id=task.f_task_id,
role=role,
party_id=party_id, initiator_party_id=job_initiator.get('party_id', None),
task_info=task.to_json())
def run_task():
task = Task()
task.f_create_time = current_timestamp()
try:
parser = argparse.ArgumentParser()
parser.add_argument('-j',
'--job_id',
required=True,
type=str,
help="job id")
parser.add_argument('-n',
'--component_name',
required=True,
type=str,
help="component name")
parser.add_argument('-t',
'--task_id',
required=True,
type=str,
help="task id")
parser.add_argument('-r',
'--role',
required=True,
type=str,
help="role")
parser.add_argument('-p',
'--party_id',
required=True,
type=str,
help="party id")
parser.add_argument('-c',
'--config',
required=True,
type=str,
help="task config")
parser.add_argument('--job_server', help="job server", type=str)
args = parser.parse_args()
schedule_logger.info('enter task process')
schedule_logger.info(args)
# init function args
if args.job_server:
RuntimeConfig.init_config(
HTTP_PORT=args.job_server.split(':')[1])
job_id = args.job_id
component_name = args.component_name
task_id = args.task_id
role = args.role
party_id = int(args.party_id)
task_config = file_utils.load_json_conf(args.config)
job_parameters = task_config['job_parameters']
job_initiator = task_config['job_initiator']
job_args = task_config['job_args']
task_input_dsl = task_config['input']
task_output_dsl = task_config['output']
parameters = task_config['parameters']
module_name = task_config['module_name']
except Exception as e:
schedule_logger.exception(e)
task.f_status = TaskStatus.FAILED
return
try:
# init environment, process is shared globally
RuntimeConfig.init_config(WORK_MODE=job_parameters['work_mode'])
storage.init_storage(job_id=task_id,
work_mode=RuntimeConfig.WORK_MODE)
federation.init(job_id=task_id, runtime_conf=parameters)
job_log_dir = os.path.join(
job_utils.get_job_log_directory(job_id=job_id), role,
str(party_id))
task_log_dir = os.path.join(job_log_dir, component_name)
log_utils.LoggerFactory.set_directory(directory=task_log_dir,
parent_log_dir=job_log_dir,
append_to_parent_log=True,
force=True)
task.f_job_id = job_id
task.f_component_name = component_name
task.f_task_id = task_id
task.f_role = role
task.f_party_id = party_id
task.f_operator = 'python_operator'
tracker = Tracking(job_id=job_id,
role=role,
party_id=party_id,
component_name=component_name,
task_id=task_id,
model_id=job_parameters['model_id'],
model_version=job_parameters['model_version'],
module_name=module_name)
task.f_start_time = current_timestamp()
task.f_run_ip = get_lan_ip()
task.f_run_pid = os.getpid()
run_class_paths = parameters.get('CodePath').split('/')
run_class_package = '.'.join(
run_class_paths[:-2]) + '.' + run_class_paths[-2].replace(
'.py', '')
run_class_name = run_class_paths[-1]
task_run_args = TaskExecutor.get_task_run_args(
job_id=job_id,
role=role,
party_id=party_id,
job_parameters=job_parameters,
job_args=job_args,
input_dsl=task_input_dsl)
run_object = getattr(importlib.import_module(run_class_package),
run_class_name)()
run_object.set_tracker(tracker=tracker)
run_object.set_taskid(taskid=task_id)
task.f_status = TaskStatus.RUNNING
TaskExecutor.sync_task_status(job_id=job_id,
component_name=component_name,
task_id=task_id,
role=role,
party_id=party_id,
initiator_party_id=job_initiator.get(
'party_id', None),
task_info=task.to_json())
schedule_logger.info('run {} {} {} {} {} task'.format(
job_id, component_name, task_id, role, party_id))
schedule_logger.info(parameters)
schedule_logger.info(task_input_dsl)
run_object.run(parameters, task_run_args)
if task_output_dsl:
if task_output_dsl.get('data', []):
output_data = run_object.save_data()
tracker.save_output_data_table(
output_data,
task_output_dsl.get('data')[0])
if task_output_dsl.get('model', []):
output_model = run_object.export_model()
# There is only one model output at the current dsl version.
tracker.save_output_model(output_model,
task_output_dsl['model'][0])
task.f_status = TaskStatus.SUCCESS
except Exception as e:
schedule_logger.exception(e)
task.f_status = TaskStatus.FAILED
finally:
try:
task.f_end_time = current_timestamp()
task.f_elapsed = task.f_end_time - task.f_start_time
task.f_update_time = current_timestamp()
TaskExecutor.sync_task_status(
job_id=job_id,
component_name=component_name,
task_id=task_id,
role=role,
party_id=party_id,
initiator_party_id=job_initiator.get('party_id', None),
task_info=task.to_json())
except Exception as e:
schedule_logger.exception(e)
schedule_logger.info('finish {} {} {} {} {} {} task'.format(
job_id, component_name, task_id, role, party_id, task.f_status))
print('finish {} {} {} {} {} {} task'.format(job_id, component_name,
task_id, role, party_id,
task.f_status))
def handle_event(job_event):
try:
return TaskScheduler.run_job(**job_event)
except Exception as e:
schedule_logger.exception(e)
return False
