Simplify daemon logic

This commit is contained in:
Patrick Jentsch
2020-11-09 16:14:19 +01:00
parent 0f30e518af
commit cb9da5c7dd
21 changed files with 308 additions and 555 deletions

35
web/app/tasks/__init__.py Normal file
View File

@ -0,0 +1,35 @@
from .. import db
from ..models import Corpus, Job
import docker
docker_client = docker.from_env()
from . import corpus_utils, job_utils # noqa
def check_corpora():
corpora = Corpus.query.all()
for corpus in filter(lambda corpus: corpus.status == 'submitted', corpora):
corpus_utils.create_build_corpus_service(corpus)
for corpus in filter(lambda corpus: (corpus.status == 'queued'
or corpus.status == 'running'),
corpora):
corpus_utils.checkout_build_corpus_service(corpus)
for corpus in filter(lambda corpus: corpus.status == 'start analysis',
corpora):
corpus_utils.create_cqpserver_container(corpus)
for corpus in filter(lambda corpus: corpus.status == 'stop analysis',
corpora):
corpus_utils.remove_cqpserver_container(corpus)
db.session.commit()
def check_jobs():
jobs = Job.query.all()
for job in filter(lambda job: job.status == 'submitted', jobs):
job_utils.create_job_service(job)
for job in filter(lambda job: job.status == 'queued', jobs):
job_utils.checkout_job_service(job)
for job in filter(lambda job: job.status == 'running', jobs):
job_utils.checkout_job_service(job)
db.session.commit()

View File

@ -0,0 +1,120 @@
from flask import current_app
from . import docker_client
import docker
import logging
import os
import shutil
def create_build_corpus_service(corpus):
corpus_dir = os.path.join(current_app.config['DATA_DIR'],
str(corpus.user_id),
'corpora',
str(corpus.id))
corpus_data_dir = os.path.join(corpus_dir, 'data')
corpus_file = os.path.join(corpus_dir, 'merged', 'corpus.vrt')
corpus_registry_dir = os.path.join(corpus_dir, 'registry')
if os.path.exists(corpus_data_dir):
shutil.rmtree(corpus_data_dir)
if os.path.exists(corpus_registry_dir):
shutil.rmtree(corpus_registry_dir)
os.mkdir(corpus_data_dir)
os.mkdir(corpus_registry_dir)
service_args = {
'command': 'docker-entrypoint.sh build-corpus',
'constraints': ['node.role==worker'],
'labels': {'origin': 'nopaque',
'type': 'corpus.prepare',
'corpus_id': str(corpus.id)},
'mounts': [corpus_file + ':/root/files/corpus.vrt:ro',
corpus_data_dir + ':/corpora/data:rw',
corpus_registry_dir + ':/usr/local/share/cwb/registry:rw'],
'name': 'build-corpus_{}'.format(corpus.id),
'restart_policy': docker.types.RestartPolicy()
}
service_image = \
'gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/cqpserver:latest'
try:
docker_client.services.create(service_image, **service_args)
except docker.errors.APIError as e:
logging.error('create_build_corpus_service({}): '.format(corpus.id)
+ '{} (status: {} -> failed)'.format(e, corpus.status))
corpus.status = 'failed'
else:
corpus.status = 'queued'
finally:
# TODO: send email
pass
def checkout_build_corpus_service(corpus):
service_name = 'build-corpus_{}'.format(corpus.id)
try:
service = docker_client.services.get(service_name)
except docker.errors.NotFound as e:
logging.error('checkout_build_corpus_service({}):'.format(corpus.id)
+ ' {} (stauts: {} -> failed)'.format(e, corpus.status))
corpus.status = 'failed'
# TODO: handle docker.errors.APIError and docker.errors.InvalidVersion
else:
service_tasks = service.tasks()
if not service_tasks:
return
task_state = service_tasks[0].get('Status').get('State')
if corpus.status == 'queued' and task_state != 'pending':
corpus.status = 'running'
elif corpus.status == 'running' and task_state == 'complete':
service.remove()
corpus.status = 'prepared'
elif corpus.status == 'running' and task_state == 'failed':
service.remove()
corpus.status = task_state
finally:
# TODO: send email
pass
def create_cqpserver_container(corpus):
corpus_dir = os.path.join(current_app.config['DATA_DIR'],
str(corpus.user_id),
'corpora',
str(corpus.id))
corpus_data_dir = os.path.join(corpus_dir, 'data')
corpus_registry_dir = os.path.join(corpus_dir, 'registry')
container_args = {
'command': 'cqpserver',
'detach': True,
'volumes': [corpus_data_dir + ':/corpora/data:rw',
corpus_registry_dir + ':/usr/local/share/cwb/registry:rw'],
'name': 'cqpserver_{}'.format(corpus.id),
'network': 'nopaque_default'
}
container_image = \
'gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/cqpserver:latest'
try:
container = docker_client.containers.get(container_args['name'])
except docker.errors.NotFound:
pass
except docker.errors.DockerException:
return
else:
container.remove(force=True)
try:
docker_client.containers.run(container_image, **container_args)
except docker.errors.DockerException:
return
else:
corpus.status = 'analysing'
def remove_cqpserver_container(corpus):
container_name = 'cqpserver_{}'.format(corpus.id)
try:
container = docker_client.containers.get(container_name)
except docker.errors.NotFound:
pass
except docker.errors.DockerException:
return
else:
container.remove(force=True)
corpus.status = 'prepared'

101
web/app/tasks/job_utils.py Normal file
View File

@ -0,0 +1,101 @@
from datetime import datetime
from flask import current_app
from . import docker_client
from .. import db
from ..models import JobResult
import docker
import logging
import json
import os
def create_job_service(job):
job_dir = os.path.join(current_app.config['DATA_DIR'],
str(job.user_id),
'jobs',
str(job.id))
cmd = '{} -i /files -o /files/output'.format(job.service)
if job.service == 'file-setup':
cmd += ' -f {}'.format(job.secure_filename)
cmd += ' --log-dir /files'
cmd += ' --zip [{}]_{}'.format(job.service, job.secure_filename)
cmd += ' ' + ' '.join(json.loads(job.service_args))
service_args = {'command': cmd,
'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:
docker_client.services.create(service_image, **service_args)
except docker.errors.APIError as e:
logging.error('create_job_service({}): {} '.format(job.id, e)
+ '(status: {} -> failed)'.format(job.status))
job.status = 'failed'
else:
job.status = 'queued'
finally:
# TODO: send email
pass
def checkout_job_service(job):
service_name = 'job_{}'.format(job.id)
try:
service = docker_client.services.get(service_name)
except docker.errors.NotFound as e:
logging.error('checkout_job_service({}): {} '.format(job.id, e)
+ '(status: {} -> submitted)'.format(job.status))
job.status = 'submitted'
# TODO: handle docker.errors.APIError and docker.errors.InvalidVersion
else:
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 == 'queued' and task_state == 'complete':
service.remove()
job.end_date = datetime.utcnow()
job.status = task_state
if task_state == 'complete':
results_dir = os.path.join(current_app.config['DATA_DIR'],
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)
db.session.add(job_result)
elif job.status == 'running' and task_state == 'failed':
service.remove()
job.end_date = datetime.utcnow()
job.status = task_state
finally:
# TODO: send email
pass
def remove_job_service(job):
service_name = 'job_{}'.format(job.id)
try:
service = docker_client.services.get(service_name)
except docker.errors.NotFound:
# TODO: send email
job.status = 'canceled'
# TODO: handle docker.errors.APIError and docker.errors.InvalidVersion
else:
service.update(mounts=None)
service.remove()