def delete_project(object_id, transaction_id=None, **kwargs):
from sentry import deletions
from sentry.models import Project, ProjectStatus
try:
instance = Project.objects.get(id=object_id)
except Project.DoesNotExist:
return
if instance.status == ProjectStatus.VISIBLE:
raise DeleteAborted
task = deletions.get(
model=Project,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
delete_project.apply_async(
kwargs={'object_id': object_id,
'transaction_id': transaction_id},
countdown=15,
)
def delete_groups(object_ids, transaction_id=None, eventstream_state=None, **kwargs):
from sentry import deletions, eventstream
from sentry.models import Group
transaction_id = transaction_id or uuid4().hex
max_batch_size = 100
current_batch, rest = object_ids[:max_batch_size], object_ids[max_batch_size:]
task = deletions.get(
model=Group,
query={
'id__in': current_batch,
},
transaction_id=transaction_id,
)
has_more = task.chunk()
if has_more or rest:
delete_groups.apply_async(
kwargs={'object_ids': object_ids if has_more else rest,
'transaction_id': transaction_id,
'eventstream_state': eventstream_state},
countdown=15,
)
else:
# all groups have been deleted
if eventstream_state:
eventstream.end_delete_groups(eventstream_state)
def delete_api_application(object_id, transaction_id=None, **kwargs):
from sentry import deletions
from sentry.models import ApiApplication, ApiApplicationStatus
try:
instance = ApiApplication.objects.get(id=object_id)
except ApiApplication.DoesNotExist:
return
if instance.status == ApiApplicationStatus.active:
raise DeleteAborted
task = deletions.get(
model=ApiApplication,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
delete_api_application.apply_async(
kwargs={'object_id': object_id,
'transaction_id': transaction_id},
countdown=15,
)
def generic_delete(app_label, model_name, object_id, transaction_id=None, actor_id=None, **kwargs):
from sentry import deletions
model = get_model(app_label, model_name)
try:
instance = model.objects.get(id=object_id)
except model.DoesNotExist:
return
if instance.status == ObjectStatus.VISIBLE:
raise DeleteAborted
task = deletions.get(
model=model,
actor_id=actor_id,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
generic_delete.apply_async(
kwargs={
'app_label': app_label,
'model_name': model_name,
'object_id': object_id,
'transaction_id': transaction_id,
'actor_id': actor_id,
},
countdown=15,
)
def delete_organization(object_id, transaction_id=None, actor_id=None, **kwargs):
from sentry import deletions
from sentry.models import Organization, OrganizationStatus
try:
instance = Organization.objects.get(id=object_id)
except Organization.DoesNotExist:
return
if instance.status == OrganizationStatus.VISIBLE:
raise DeleteAborted
# compat: can be removed after we switch to scheduled deletions
if instance.status != OrganizationStatus.DELETION_IN_PROGRESS:
pending_delete.send(
sender=type(instance),
instance=instance,
)
task = deletions.get(
model=Organization,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
actor_id=actor_id,
)
has_more = task.chunk()
if has_more:
delete_organization.apply_async(
kwargs={'object_id': object_id,
'transaction_id': transaction_id,
'actor_id': actor_id},
countdown=15,
)
def create_deletion_task(days, project_id, model, dtfield, order_by):
from sentry import models
from sentry import deletions
from sentry import similarity
query = {
'{}__lte'.format(dtfield): (timezone.now() - timedelta(days=days)),
}
if project_id:
if 'project' in model._meta.get_all_field_names():
query['project'] = project_id
else:
query['project_id'] = project_id
skip_models = [
# Handled by other parts of cleanup
models.Event,
models.EventMapping,
models.Group,
models.GroupEmailThread,
models.GroupRuleStatus,
# Handled by TTL
similarity.features,
] + [b[0] for b in EXTRA_BULK_QUERY_DELETES]
task = deletions.get(
model=model,
query=query,
order_by=order_by,
skip_models=skip_models,
transaction_id=uuid4().hex,
)
return task
def multiprocess_worker(task_queue):
# Configure within each Process
import logging
from sentry.utils.imports import import_string
logger = logging.getLogger('sentry.cleanup')
configured = False
while True:
j = task_queue.get()
if j == _STOP_WORKER:
task_queue.task_done()
return
# On first task, configure Sentry environment
if not configured:
from sentry.runner import configure
configure()
from sentry import models
from sentry import deletions
from sentry import similarity
skip_models = [
# Handled by other parts of cleanup
models.Event,
models.EventMapping,
models.EventAttachment,
models.UserReport,
models.Group,
models.GroupEmailThread,
models.GroupRuleStatus,
models.GroupHashTombstone,
# Handled by TTL
similarity.features,
] + [b[0] for b in EXTRA_BULK_QUERY_DELETES]
configured = True
model, chunk = j
model = import_string(model)
try:
task = deletions.get(
model=model,
query={'id__in': chunk},
skip_models=skip_models,
transaction_id=uuid4().hex,
)
while True:
if not task.chunk():
break
except Exception as e:
logger.exception(e)
finally:
task_queue.task_done()
def delete_tag_key(object_id, transaction_id=None, **kwargs):
from sentry import deletions
from sentry.models import TagKey
task = deletions.get(
model=TagKey,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
delete_tag_key.apply_async(
kwargs={'object_id': object_id, 'transaction_id': transaction_id},
countdown=15,
)
def generic_delete(app_label, model_name, object_id, transaction_id=None, actor_id=None, **kwargs):
from sentry import deletions
from sentry.models import User
model = get_model(app_label, model_name)
try:
instance = model.objects.get(id=object_id)
except model.DoesNotExist:
return
if instance.status != ObjectStatus.DELETION_IN_PROGRESS:
pending_delete.send(
sender=type(instance),
instance=instance,
actor=User.objects.get(id=actor_id) if actor_id else None,
)
if instance.status == ObjectStatus.VISIBLE:
raise DeleteAborted
task = deletions.get(
model=model,
actor_id=actor_id,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
generic_delete.apply_async(
kwargs={
'app_label': app_label,
'model_name': model_name,
'object_id': object_id,
'transaction_id': transaction_id,
'actor_id': actor_id,
},
countdown=15,
)
def run_deletion(deletion_id):
from sentry import deletions
from sentry.models import ScheduledDeletion
try:
deletion = ScheduledDeletion.objects.get(
id=deletion_id,
)
except ScheduledDeletion.DoesNotExist:
return
if deletion.aborted:
raise DeleteAborted
if not deletion.in_progress:
actor = deletion.get_actor()
instance = deletion.get_instance()
with transaction.atomic():
deletion.update(in_progress=True)
pending_delete.send(
sender=type(instance),
instance=instance,
actor=actor,
)
task = deletions.get(
model=deletion.get_model(),
query={
'id': deletion.object_id,
},
transaction_id=deletion.guid,
actor_id=deletion.actor_id,
)
has_more = task.chunk()
if has_more:
run_deletion.apply_async(
kwargs={'deletion_id': deletion_id},
countdown=15,
)
deletion.delete()
def delete_alert_rule(alert_rule_id, transaction_id=None, **kwargs):
from sentry.incidents.models import AlertRule
try:
instance = AlertRule.objects_with_deleted.get(id=alert_rule_id)
except AlertRule.DoesNotExist:
return
if instance.status not in (
AlertRuleStatus.DELETION_IN_PROGRESS.value,
AlertRuleStatus.PENDING_DELETION.value,
):
raise DeleteAborted
task = deletions.get(
model=AlertRule, query={"id": alert_rule_id}, transaction_id=transaction_id or uuid4().hex
)
has_more = task.chunk()
if has_more:
delete_alert_rule.apply_async(
kwargs={"alert_rule_id": alert_rule_id, "transaction_id": transaction_id}, countdown=15
)
def delete_organization_integration(object_id,
transaction_id=None,
actor_id=None,
**kwargs):
from sentry import deletions
from sentry.models import OrganizationIntegration, Repository
try:
instance = OrganizationIntegration.objects.get(id=object_id)
except OrganizationIntegration.DoesNotExist:
return
if instance.status == ObjectStatus.VISIBLE:
raise DeleteAborted
# dissociate repos from that integration
Repository.objects.filter(
organization_id=instance.organization_id,
integration_id=instance.integration_id,
).update(integration_id=None, )
task = deletions.get(
model=OrganizationIntegration,
actor_id=actor_id,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
delete_organization_integration.apply_async(
kwargs={
'object_id': object_id,
'transaction_id': transaction_id,
'actor_id': actor_id,
},
countdown=15,
)
def delete_api_application(object_id, transaction_id=None, **kwargs):
from sentry import deletions
from sentry.models import ApiApplication, ApiApplicationStatus
try:
instance = ApiApplication.objects.get(id=object_id)
except ApiApplication.DoesNotExist:
return
if instance.status == ApiApplicationStatus.active:
raise DeleteAborted
task = deletions.get(model=ApiApplication,
query={"id": object_id},
transaction_id=transaction_id or uuid4().hex)
has_more = task.chunk()
if has_more:
delete_api_application.apply_async(kwargs={
"object_id": object_id,
"transaction_id": transaction_id
},
countdown=15)
def delete_project(object_id, transaction_id=None, **kwargs):
from sentry import deletions
from sentry.models import Project, ProjectStatus
try:
instance = Project.objects.get(id=object_id)
except Project.DoesNotExist:
return
if instance.status == ProjectStatus.VISIBLE:
raise DeleteAborted
task = deletions.get(model=Project,
query={"id": object_id},
transaction_id=transaction_id or uuid4().hex)
has_more = task.chunk()
if has_more:
delete_project.apply_async(kwargs={
"object_id": object_id,
"transaction_id": transaction_id
},
countdown=15)
def generic_delete(app_label, model_name, object_id, transaction_id=None, actor_id=None, **kwargs):
from sentry import deletions
from sentry.models import User
model = apps.get_model(app_label, model_name)
try:
instance = model.objects.get(id=object_id)
except model.DoesNotExist:
return
if instance.status != ObjectStatus.DELETION_IN_PROGRESS:
pending_delete.send(
sender=type(instance),
instance=instance,
actor=User.objects.get(id=actor_id) if actor_id else None,
)
if instance.status == ObjectStatus.VISIBLE:
raise DeleteAborted
task = deletions.get(
model=model,
actor_id=actor_id,
query={"id": object_id},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
generic_delete.apply_async(
kwargs={
"app_label": app_label,
"model_name": model_name,
"object_id": object_id,
"transaction_id": transaction_id,
"actor_id": actor_id,
},
countdown=15,
)
def delete_repository(object_id, transaction_id=None, actor_id=None, **kwargs):
# TODO this method is no longer in use and should be removed when jobs are
# no longer being enqueued for it.
from sentry import deletions
from sentry.models import Repository, User
try:
instance = Repository.objects.get(id=object_id)
except Repository.DoesNotExist:
return
if instance.status == ObjectStatus.VISIBLE:
raise DeleteAborted
# compat: can be removed after we switch to scheduled deletions
if instance.status != ObjectStatus.DELETION_IN_PROGRESS:
pending_delete.send(
sender=type(instance),
instance=instance,
actor=User.objects.get(id=actor_id) if actor_id else None,
)
task = deletions.get(
model=Repository,
actor_id=actor_id,
query={"id": object_id},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
delete_repository.apply_async(
kwargs={
"object_id": object_id,
"transaction_id": transaction_id,
"actor_id": actor_id
},
countdown=15,
)
def delete_repository(object_id, transaction_id=None, actor_id=None, **kwargs):
from sentry import deletions
from sentry.models import Repository, User
try:
instance = Repository.objects.get(id=object_id)
except Repository.DoesNotExist:
return
if instance.status == ObjectStatus.VISIBLE:
raise DeleteAborted
# compat: can be removed after we switch to scheduled deletions
if instance.status != ObjectStatus.DELETION_IN_PROGRESS:
pending_delete.send(
sender=type(instance),
instance=instance,
actor=User.objects.get(id=actor_id) if actor_id else None,
)
task = deletions.get(
model=Repository,
actor_id=actor_id,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
delete_repository.apply_async(
kwargs={
'object_id': object_id,
'transaction_id': transaction_id,
'actor_id': actor_id,
},
countdown=15,
)
def generic_delete(app_label,
model_name,
object_id,
transaction_id=None,
actor_id=None,
**kwargs):
from sentry import deletions
model = get_model(app_label, model_name)
try:
instance = model.objects.get(id=object_id)
except model.DoesNotExist:
return
if instance.status == ObjectStatus.VISIBLE:
raise DeleteAborted
task = deletions.get(
model=model,
actor_id=actor_id,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
generic_delete.apply_async(
kwargs={
'app_label': app_label,
'model_name': model_name,
'object_id': object_id,
'transaction_id': transaction_id,
'actor_id': actor_id,
},
countdown=15,
)
def run_deletion(deletion_id):
from sentry import deletions
from sentry.models import ScheduledDeletion
try:
deletion = ScheduledDeletion.objects.get(id=deletion_id, )
except ScheduledDeletion.DoesNotExist:
return
if deletion.aborted:
raise DeleteAborted
if not deletion.in_progress:
actor = deletion.get_actor()
instance = deletion.get_instance()
with transaction.atomic():
deletion.update(in_progress=True)
pending_delete.send(
sender=type(instance),
instance=instance,
actor=actor,
)
task = deletions.get(
model=deletion.get_model(),
query={
'id': deletion.object_id,
},
transaction_id=deletion.guid,
actor_id=deletion.actor_id,
)
has_more = task.chunk()
if has_more:
run_deletion.apply_async(
kwargs={'deletion_id': deletion_id},
countdown=15,
)
deletion.delete()
def delete_organization_integration(object_id, transaction_id=None, actor_id=None, **kwargs):
from sentry import deletions
from sentry.models import OrganizationIntegration, Repository
try:
instance = OrganizationIntegration.objects.get(id=object_id)
except OrganizationIntegration.DoesNotExist:
return
if instance.status == ObjectStatus.VISIBLE:
raise DeleteAborted
# dissociate repos from that integration
Repository.objects.filter(
organization_id=instance.organization_id,
integration_id=instance.integration_id,
).update(
integration_id=None,
)
task = deletions.get(
model=OrganizationIntegration,
actor_id=actor_id,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
delete_organization_integration.apply_async(
kwargs={
'object_id': object_id,
'transaction_id': transaction_id,
'actor_id': actor_id,
},
countdown=15,
)
def delete_tag_key(object_id, model=None, transaction_id=None, **kwargs):
from sentry import deletions
# TODO(brett): remove this (and make model a normal arg) after deploy
if model is None:
# if the model wasn't sent we can assume it's from legacy code
from sentry.tagstore.legacy.models import TagKey as model
task = deletions.get(
model=model,
query={
'id': object_id,
},
transaction_id=transaction_id or uuid4().hex,
)
has_more = task.chunk()
if has_more:
delete_tag_key.apply_async(
kwargs={'object_id': object_id,
'model': model,
'transaction_id': transaction_id},
countdown=15,
)
def delete_team(object_id, transaction_id=None, **kwargs):
from sentry import deletions
from sentry.incidents.models import AlertRule
from sentry.models import Rule, Team, TeamStatus
try:
instance = Team.objects.get(id=object_id)
except Team.DoesNotExist:
return
if instance.status == TeamStatus.VISIBLE:
raise DeleteAborted
task = deletions.get(
model=Team, query={"id": object_id}, transaction_id=transaction_id or uuid4().hex
)
AlertRule.objects.filter(owner_id=instance.actor_id).update(owner=None)
Rule.objects.filter(owner_id=instance.actor_id).update(owner=None)
has_more = task.chunk()
if has_more:
delete_team.apply_async(
kwargs={"object_id": object_id, "transaction_id": transaction_id}, countdown=15
)
def delete_api_application(object_id, transaction_id=None, **kwargs):
# TODO this method is no longer in use and should be removed when jobs are
# no longer being enqueued for it.
from sentry import deletions
from sentry.models import ApiApplication, ApiApplicationStatus
try:
instance = ApiApplication.objects.get(id=object_id)
except ApiApplication.DoesNotExist:
return
if instance.status == ApiApplicationStatus.active:
raise DeleteAborted
task = deletions.get(model=ApiApplication,
query={"id": object_id},
transaction_id=transaction_id or uuid4().hex)
has_more = task.chunk()
if has_more:
delete_api_application.apply_async(kwargs={
"object_id": object_id,
"transaction_id": transaction_id
},
countdown=15)
def delete_organization(object_id,
transaction_id=None,
actor_id=None,
**kwargs):
# TODO(mark) remove this task once all in flight jobs have been processed.
from sentry import deletions
from sentry.models import Organization, OrganizationStatus
try:
instance = Organization.objects.get(id=object_id)
except Organization.DoesNotExist:
return
if instance.status == OrganizationStatus.VISIBLE:
raise DeleteAborted
# compat: can be removed after we switch to scheduled deletions
if instance.status != OrganizationStatus.DELETION_IN_PROGRESS:
pending_delete.send(sender=type(instance), instance=instance)
task = deletions.get(
model=Organization,
query={"id": object_id},
transaction_id=transaction_id or uuid4().hex,
actor_id=actor_id,
)
has_more = task.chunk()
if has_more:
delete_organization.apply_async(
kwargs={
"object_id": object_id,
"transaction_id": transaction_id,
"actor_id": actor_id
},
countdown=15,
)
def cleanup(days, project, concurrency, silent, model, router, timed):
"""Delete a portion of trailing data based on creation date.
All data that is older than `--days` will be deleted. The default for
this is 30 days. In the default setting all projects will be truncated
but if you have a specific project you want to limit this to this can be
done with the `--project` flag which accepts a project ID or a string
with the form `org/project` where both are slugs.
"""
if concurrency < 1:
click.echo('Error: Minimum concurrency is 1', err=True)
raise click.Abort()
from threading import Thread
from django.db import router as db_router
from sentry.app import nodestore
from sentry.db.deletion import BulkDeleteQuery
from sentry import deletions
from sentry import models
if timed:
import time
from sentry.utils import metrics
start_time = time.time()
# list of models which this query is restricted to
model_list = {m.lower() for m in model}
def is_filtered(model):
if router is not None and db_router.db_for_write(model) != router:
return True
if not model_list:
return False
return model.__name__.lower() not in model_list
# Deletions that use `BulkDeleteQuery` (and don't need to worry about child relations)
# (model, datetime_field, order_by)
BULK_QUERY_DELETES = (
(models.GroupEmailThread, 'date', None),
(models.GroupRuleStatus, 'date_added', None),
(models.GroupTagValue, 'last_seen', None),
(models.TagValue, 'last_seen', None),
(models.EventTag, 'date_added', 'date_added'),
)
# Deletions that use the `deletions` code path (which handles their child relations)
# (model, datetime_field, order_by)
DELETES = (
(models.Event, 'datetime', None),
(models.Group, 'last_seen', 'last_seen'),
)
if not silent:
click.echo('Removing expired values for LostPasswordHash')
if is_filtered(models.LostPasswordHash):
if not silent:
click.echo('>> Skipping LostPasswordHash')
else:
models.LostPasswordHash.objects.filter(date_added__lte=timezone.now() -
timedelta(hours=48)).delete()
for model in [models.ApiGrant, models.ApiToken]:
if not silent:
click.echo('Removing expired values for {}'.format(model.__name__))
if is_filtered(model):
if not silent:
click.echo('>> Skipping {}'.format(model.__name__))
else:
model.objects.filter(expires_at__lt=timezone.now()).delete()
project_id = None
if project:
click.echo(
"Bulk NodeStore deletion not available for project selection",
err=True)
project_id = get_project(project)
if project_id is None:
click.echo('Error: Project not found', err=True)
raise click.Abort()
else:
if not silent:
click.echo("Removing old NodeStore values")
else:
cutoff = timezone.now() - timedelta(days=days)
try:
nodestore.cleanup(cutoff)
except NotImplementedError:
click.echo(
"NodeStore backend does not support cleanup operation",
err=True)
for model, dtfield, order_by in BULK_QUERY_DELETES:
if not silent:
click.echo(
"Removing {model} for days={days} project={project}".format(
model=model.__name__,
days=days,
project=project or '*',
))
if is_filtered(model):
if not silent:
click.echo('>> Skipping %s' % model.__name__)
else:
BulkDeleteQuery(
model=model,
dtfield=dtfield,
days=days,
project_id=project_id,
order_by=order_by,
).execute()
for model, dtfield, order_by in DELETES:
if not silent:
click.echo(
"Removing {model} for days={days} project={project}".format(
model=model.__name__,
days=days,
project=project or '*',
))
if is_filtered(model):
if not silent:
click.echo('>> Skipping %s' % model.__name__)
else:
query = {
'{}__lte'.format(dtfield):
(timezone.now() - timedelta(days=days)),
}
if project_id:
if 'project' in model._meta.get_all_field_names():
query['project'] = project_id
else:
query['project_id'] = project_id
task = deletions.get(
model=model,
query=query,
order_by=order_by,
transaction_id=uuid4().hex,
)
def _chunk_until_complete(num_shards=None, shard_id=None):
has_more = True
while has_more:
has_more = task.chunk(num_shards=num_shards,
shard_id=shard_id)
if concurrency > 1:
threads = []
for shard_id in range(concurrency):
t = Thread(target=(
lambda shard_id=shard_id: _chunk_until_complete(
num_shards=concurrency, shard_id=shard_id)))
t.start()
threads.append(t)
for t in threads:
t.join()
else:
_chunk_until_complete()
# EventMapping is fairly expensive and is special cased as it's likely you
# won't need a reference to an event for nearly as long
if not silent:
click.echo("Removing expired values for EventMapping")
if is_filtered(models.EventMapping):
if not silent:
click.echo('>> Skipping EventMapping')
else:
BulkDeleteQuery(model=models.EventMapping,
dtfield='date_added',
days=min(days, 7),
project_id=project_id,
order_by='-date_added').execute()
# Clean up FileBlob instances which are no longer used and aren't super
# recent (as there could be a race between blob creation and reference)
if not silent:
click.echo("Cleaning up unused FileBlob references")
if is_filtered(models.FileBlob):
if not silent:
click.echo('>> Skipping FileBlob')
else:
cleanup_unused_files(silent)
if timed:
duration = int(time.time() - start_time)
metrics.timing('cleanup.duration', duration, instance=router)
click.echo("Clean up took %s second(s)." % duration)
