Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Cancel or delete stale pending and failed exports #1086

Merged
merged 5 commits into from
Aug 11, 2017
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ build
*~
*orig
celerybeat-schedule
celerybeat.pid
*.swp
.venv
*.ropeproject
Expand Down Expand Up @@ -72,4 +73,4 @@ bob

# visual studio code
.vscode/
tags
tags
35 changes: 35 additions & 0 deletions onadata/apps/viewer/tasks.py
Original file line number Diff line number Diff line change
@@ -1,8 +1,11 @@
import sys
from datetime import timedelta

from celery import task
from celery.task.schedules import crontab
from django.conf import settings
from django.shortcuts import get_object_or_404
from django.utils import timezone
from requests import ConnectionError

from onadata.apps.viewer.models.export import Export
Expand Down Expand Up @@ -349,3 +352,35 @@ def delete_export(export_id):
export.delete()
return True
return False


@task.periodic_task(
run_every=(crontab(hour='*/7')),
ignore_result=True
)
def mark_expired_pending_exports_as_failed():
"""
Exports that have not completed within a set time should be marked as
failed
"""
# import pdb; pdb.set_trace()
task_lifespan = settings.EXPORT_TASK_LIFESPAN
time_threshold = timezone.now() - timedelta(hours=task_lifespan)
exports = Export.objects.filter(internal_status=Export.PENDING,
created_on__lt=time_threshold)
exports.update(internal_status=Export.FAILED)


@task.periodic_task(
run_every=(crontab(hour='*/7')),
ignore_result=True
)
def delete_expired_failed_exports():
"""
Delete old failed exports
"""
task_lifespan = settings.EXPORT_TASK_LIFESPAN
time_threshold = timezone.now() - timedelta(hours=task_lifespan)
exports = Export.objects.filter(internal_status=Export.FAILED,
created_on__lt=time_threshold)
exports.delete()
34 changes: 33 additions & 1 deletion onadata/apps/viewer/tests/test_tasks.py
Original file line number Diff line number Diff line change
@@ -1,9 +1,14 @@
from datetime import timedelta

from celery import current_app
from django.conf import settings
from django.utils import timezone

from onadata.apps.main.tests.test_base import TestBase
from onadata.apps.viewer.models.export import Export
from onadata.apps.viewer.tasks import create_async_export
from onadata.apps.viewer.tasks import mark_expired_pending_exports_as_failed
from onadata.apps.viewer.tasks import delete_expired_failed_exports


class TestExportTasks(TestBase):
Expand Down Expand Up @@ -33,8 +38,35 @@ def test_create_async(self):
for export_type, extra_options in export_types:
result = create_async_export(
self.xform, export_type, None, False, options)

export = result[0]
self.assertTrue(export.id)
self.assertIn("username", options)
self.assertEquals(options.get("id_string"), self.xform.id_string)

def test_mark_expired_pending_exports_as_failed(self):
self._publish_transportation_form_and_submit_instance()
over_threshold = settings.EXPORT_TASK_LIFESPAN + 2
export = Export.objects.create(xform=self.xform,
export_type=Export.CSV_EXPORT,
internal_status=Export.PENDING,
filename="")
# we set created_on here because Export.objects.create() overrides it
export.created_on = timezone.now() - timedelta(hours=over_threshold)
export.save()
mark_expired_pending_exports_as_failed()
export = Export.objects.filter(pk=export.pk).first()
self.assertEquals(export.internal_status, Export.FAILED)

def test_delete_expired_failed_exports(self):
self._publish_transportation_form_and_submit_instance()
over_threshold = settings.EXPORT_TASK_LIFESPAN + 2
export = Export.objects.create(xform=self.xform,
export_type=Export.CSV_EXPORT,
internal_status=Export.FAILED,
filename="")
# we set created_on here because Export.objects.create() overrides it
export.created_on = timezone.now() - timedelta(hours=over_threshold)
export.save()
pk = export.pk
delete_expired_failed_exports()
self.assertEquals(Export.objects.filter(pk=pk).first(), None)
1 change: 1 addition & 0 deletions onadata/settings/common.py
Original file line number Diff line number Diff line change
Expand Up @@ -435,6 +435,7 @@ def configure_logging(logger, **kwargs):

# number of records on export or CSV import before a progress update
EXPORT_TASK_PROGRESS_UPDATE_BATCH = 1000
EXPORT_TASK_LIFESPAN = 6 # six hours

# default content length for submission requests
DEFAULT_CONTENT_LENGTH = 10000000
Expand Down