nopaque/daemon/tasks/check_jobs.py

from datetime import datetime
from logger.logger import init_logger
from tasks import Session, docker_client, NOPAQUE_STORAGE
from tasks.Models import Job, NotificationData, NotificationEmailData, JobResult
import docker
import json
import os


def check_jobs():
    # logger = init_logger()
    cj_session = Session()
    jobs = cj_session.query(Job).all()
    for job in filter(lambda job: job.status == 'submitted', jobs):
        __create_job_service(job)
    for job in filter(lambda job: (job.status == 'queued'), jobs):
        __checkout_job_service(job, cj_session)
        __add_notification_data(job, 'queued', cj_session)
    for job in filter(lambda job: (job.status == 'running'), jobs):
        __checkout_job_service(job, cj_session)
        __add_notification_data(job, 'running', cj_session)
    for job in filter(lambda job: job.status == 'complete', jobs):
        __add_notification_data(job, 'complete', cj_session)
    for job in filter(lambda job: job.status == 'failed', jobs):
        __add_notification_data(job, 'failed', cj_session)
    for job in filter(lambda job: job.status == 'canceling', jobs):
        __remove_job_service(job)
    cj_session.commit()
    Session.remove()


def __add_notification_data(job, notified_on_status, scoped_session):
    logger = init_logger()
    # checks if user wants any notifications at all
    if (job.user.setting_job_status_mail_notifications == 'none'):
        # logger.warning('User does not want any notifications!')
        return
    # checks if user wants only notification on completed jobs
    elif (job.user.setting_job_status_mail_notifications == 'end'
          and notified_on_status != 'complete'):
        # logger.warning('User only wants notifications on job completed!')
        return
    else:
        # check if a job already has associated NotificationData
        notification_exists = len(job.notification_data)
        # create notification_data for current job if there is none
        if (notification_exists == 0):
            notification_data = NotificationData(job_id=job.id)
            scoped_session.add(notification_data)
            scoped_session.commit()
            # If no commit job will have no NotificationData
            # logger.warning('Created NotificationData for current Job.'))
        else:
            pass
            # logger.warning('Job already had notification: {}'.format(notification_exists))
        if (job.notification_data[0].notified_on != notified_on_status):
            notification_email_data = NotificationEmailData(job_id=job.id)
            notification_email_data.notify_status = notified_on_status
            notification_email_data.creation_date = datetime.utcnow()
            job.notification_data[0].notified_on = notified_on_status
            scoped_session.add(notification_email_data)
            logger.warning('Created NotificationEmailData for current Job.')
        else:
            # logger.warning('NotificationEmailData has already been created for current Job!')
            pass


def __create_job_service(job):
    job_dir = os.path.join(NOPAQUE_STORAGE, str(job.user_id), 'jobs',
                           str(job.id))
    service_args = {'command': ('{} /files /files/output'.format(job.service)
                                + ' {}'.format(job.secure_filename
                                               if job.service == 'file-setup'
                                               else '')
                                + ' --log-dir /files'
                                + ' --zip [{}]_{}'.format(job.service,
                                                          job.secure_filename)
                                + ' ' + ' '.join(json.loads(job.service_args))
                                ),
                    'constraints': ['node.role==worker'],
                    'labels': {'origin': 'nopaque',
                               'type': 'service.{}'.format(job.service),
                               'job_id': str(job.id)},
                    'mounts': [job_dir + ':/files:rw'],
                    'name': 'job_{}'.format(job.id),
                    'resources': docker.types.Resources(
                        cpu_reservation=job.n_cores * (10 ** 9),
                        mem_reservation=job.mem_mb * (10 ** 6)),
                    'restart_policy': docker.types.RestartPolicy()}
    service_image = ('gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/'
                     + job.service + ':' + job.service_version)
    try:
        service = docker_client.services.get(service_args['name'])
    except docker.errors.NotFound:
        pass
    except docker.errors.DockerException:
        return
    else:
        service.remove()
    try:
        docker_client.services.create(service_image, **service_args)
    except docker.errors.DockerException:
        job.status = 'failed'
    else:
        job.status = 'queued'


def __checkout_job_service(job, scoped_session):
    logger = init_logger()
    service_name = 'job_{}'.format(job.id)
    try:
        service = docker_client.services.get(service_name)
    except docker.errors.NotFound:
        logger.error('__checkout_job_service({}):'.format(job.id)
                     + ' The service does not exist.'
                     + ' (stauts: {} -> failed)'.format(job.status))
        job.status = 'failed'
        return
    except docker.errors.DockerException:
        return
    service_tasks = service.tasks()
    if not service_tasks:
        return
    task_state = service_tasks[0].get('Status').get('State')
    if job.status == 'queued' and task_state != 'pending':
        job.status = 'running'
    elif (job.status == 'running'
          and (task_state == 'complete' or task_state == 'failed')):
        service.remove()
        job.end_date = datetime.utcnow()
        job.status = task_state
        if task_state == 'complete':
            results_dir = os.path.join(NOPAQUE_STORAGE, str(job.user_id),
                                       'jobs', str(job.id), 'output')
            results = filter(lambda x: x.endswith('.zip'),
                             os.listdir(results_dir))
            for result in results:
                job_result = JobResult(dir=results_dir, filename=result,
                                       job_id=job.id)
                scoped_session.add(job_result)


def __remove_job_service(job):
    service_name = 'job_{}'.format(job.id)
    try:
        service = docker_client.services.get(service_name)
    except docker.errors.NotFound:
        job.status = 'canceled'
    except docker.errors.DockerException:
        return
    else:
        service.update(mounts=None)
        service.remove()