Skip to content

Yuanzhou/fix put timeout #886

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.

Sign up for GitHub

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

Merged
yuanzhou merged 2 commits into from
Jul 9, 2025
Merged

Yuanzhou/fix put timeout #886

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5cb591a
Neo4j lookup based on entity type when flushing cache
yuanzhou Jul 1, 2025
bf23699
Update comments
yuanzhou Jul 2, 2025
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
61 changes: 39 additions & 22 deletions src/app.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5342,37 +5342,54 @@ def require_json(request):
"""
def delete_cache(id):
if MEMCACHED_MODE:
# First delete the target entity cache
entity_dict = query_target_entity(id, get_internal_token())
entity_uuid = entity_dict['uuid']

# Delete the cache of all the descendants
descendant_uuids = schema_neo4j_queries.get_descendants(neo4j_driver_instance, entity_uuid , 'uuid')

# If the target entity is Collection, delete the cache for each of its associated
# Datasets and Publications (via [:IN_COLLECTION]) as well as just Publications (via [:USES_DATA])
entity_type = entity_dict['entity_type']
descendant_uuids = []
collection_dataset_uuids = []
upload_dataset_uuids = []
collection_uuids = []
dataset_upload_dict = {}
publication_collection_dict = {}

# Determine the associated cache keys based on the entity type
# To reduce unnecessary Neo4j lookups that may cause timeout on the PUT call

# For Donor/Datasets/Sample/Publication, delete the cache of all the descendants
if entity_type in ['Donor', 'Sample', 'Dataset', 'Publication']:
descendant_uuids = schema_neo4j_queries.get_descendants(neo4j_driver_instance, entity_uuid , 'uuid')

# For Collection/Epicollection, delete the cache for each of its associated datasets (via [:IN_COLLECTION])
if schema_manager.entity_type_instanceof(entity_type, 'Collection'):
collection_dataset_uuids = schema_neo4j_queries.get_collection_associated_datasets(neo4j_driver_instance, entity_uuid , 'uuid')

# For Upload, delete the cache for each of its associated Datasets (via [:IN_UPLOAD])
if entity_type == 'Upload':
upload_dataset_uuids = schema_neo4j_queries.get_upload_datasets(neo4j_driver_instance, entity_uuid , 'uuid')

# For Dataset, delete the associated Collections cache and single Upload cache
if entity_type == 'Dataset':
collection_uuids = schema_neo4j_queries.get_dataset_collections(neo4j_driver_instance, entity_uuid , 'uuid')
dataset_upload_dict = schema_neo4j_queries.get_dataset_upload(neo4j_driver_instance, entity_uuid)

# For Publication, delete cache of the associated collection
# NOTE: As of 5/30/2025, the [:USES_DATA] workaround has been deprecated.
# Still keep it in the code until further decision - Zhou
collection_dataset_uuids = schema_neo4j_queries.get_collection_associated_datasets(neo4j_driver_instance, entity_uuid , 'uuid')

# If the target entity is Upload, delete the cache for each of its associated Datasets (via [:IN_UPLOAD] relationship)
upload_dataset_uuids = schema_neo4j_queries.get_upload_datasets(neo4j_driver_instance, entity_uuid , 'uuid')

# If the target entity is Datasets/Publication, delete the associated Collections cache, Upload cache
collection_uuids = schema_neo4j_queries.get_dataset_collections(neo4j_driver_instance, entity_uuid , 'uuid')
collection_dict = schema_neo4j_queries.get_publication_associated_collection(neo4j_driver_instance, entity_uuid)
upload_dict = schema_neo4j_queries.get_dataset_upload(neo4j_driver_instance, entity_uuid)

if entity_type == 'Publication':
publication_collection_dict = schema_neo4j_queries.get_publication_associated_collection(neo4j_driver_instance, entity_uuid)

# We only use uuid in the cache key acorss all the cache types
uuids_list = [entity_uuid] + descendant_uuids + collection_dataset_uuids + upload_dataset_uuids + collection_uuids

# It's possible no linked collection or upload
if collection_dict:
uuids_list.append(collection_dict['uuid'])
# It's possible the target dataset has no linked upload
if dataset_upload_dict:
uuids_list.append(dataset_upload_dict['uuid'])

if upload_dict:
uuids_list.append(upload_dict['uuid'])
# It's possible the target publicaiton has no associated collection
if publication_collection_dict:
uuids_list.append(publication_collection_dict['uuid'])

# Final batch delete
schema_manager.delete_memcached_cache(uuids_list)


Expand Down