feat: implement fast FQN prefix-based bulk deletion to fix race conditions and slow cascade#27108

Open

mohityadav766 wants to merge 30 commits intomainfrom

mohit/35dc-improve-deletion

Commits on Apr 10, 2026

feat: implement fast FQN prefix-based bulk deletion to fix race conditions and slow cascade

mohityadav766
and
claude
committed
fix: backfill entity_relationship FQN hashes for all entity types including top-level (nameHash)

mohityadav766
and
claude
committed
refactor: move entity_relationship FQN hash migrations from v1.14.1 to v1.13.0

mohityadav766
and
claude
committed
fix: replace paginated backfill with direct correlated-subquery UPDATE

mohityadav766
and
claude
committed
test: add unit tests for v1.13.0 FQN hash backfill migration

mohityadav766
and
claude
committed
test: add integration and benchmark tests for FQN prefix deletion

mohityadav766
and
claude
committed
feat: expose prefix hard delete at database and schema hierarchy levels

mohityadav766
and
claude
committed
refactor: move prefix hard delete endpoint to EntityResource base class

mohityadav766
and
claude
committed
fix: await async deletion before asserting in PrefixDeletionIT

mohityadav766
and
claude
committed
fix: initialize LockManagerInitializer on startup so PrefixDeletionService is not null

mohityadav766
and
claude
committed
fix: use unique names in PrefixDeletionIT/BenchmarkIT to avoid 409 conflicts

mohityadav766
and
claude
committed
feat: scale benchmark to 10k entities and measure actual async deletion time

mohityadav766
and
claude
committed
perf: parallelize entity seeding in PrefixDeletionBenchmarkIT

mohityadav766
and
claude
committed
fix: use VARCHAR(36) for UUID columns in entity_deletion_lock on PostgreSQL

mohityadav766
and
claude
committed
Revert "fix: use VARCHAR(36) for UUID columns in entity_deletion_lock on PostgreSQL"
mohityadav766
committed
fix: use VARCHAR(36) for UUID columns in entity_deletion_lock on PostgreSQL

mohityadav766
and
claude
committed
fix: use VARCHAR(36) for UUID columns in entity_deletion_lock on PostgreSQL

mohityadav766
and
claude
committed
fix: batch IN-clause deletes to avoid PostgreSQL 65535 parameter limit

mohityadav766
and
claude
committed
refactor: move prefix hard delete endpoint to DatabaseServiceResource

mohityadav766
and
claude
committed
feat: expose DELETE /prefix/{id} endpoint on all EntityResource subclasses

mohityadav766
and
claude
committed
fix: add missing UUID and Response imports in two resource classes

mohityadav766
and
claude
committed
fix: call super.deletePrefixHardById to prevent StackOverflowError

mohityadav766
and
claude
committed
fix: chunk FeedDAO.findByEntityIds to avoid PostgreSQL 65535 parameter limit

mohityadav766
and
claude
committed
feat: clean up Elasticsearch index during prefix hard deletion

mohityadav766
and
claude
committed
feat: run pre/post delete hooks for all entity types during prefix deletion

mohityadav766
and
claude
committed
feat: run pre/post hooks for all entity types during prefix deletion

mohityadav766
and
claude
committed
fix: use information_schema conditional for ADD COLUMN in MySQL migration

mohityadav766
and
claude
committed

Commits on Apr 11, 2026

Commits on Apr 13, 2026

Merge branch 'main' into mohit/35dc-improve-deletion
mohityadav766
authored

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: implement fast FQN prefix-based bulk deletion to fix race conditions and slow cascade#27108

feat: implement fast FQN prefix-based bulk deletion to fix race conditions and slow cascade#27108
mohityadav766 wants to merge 30 commits intomainfrom
mohit/35dc-improve-deletion

Commits on Apr 10, 2026

feat: implement fast FQN prefix-based bulk deletion to fix race conditions and slow cascade

fix: backfill entity_relationship FQN hashes for all entity types including top-level (nameHash)

refactor: move entity_relationship FQN hash migrations from v1.14.1 to v1.13.0

fix: replace paginated backfill with direct correlated-subquery UPDATE

test: add unit tests for v1.13.0 FQN hash backfill migration

test: add integration and benchmark tests for FQN prefix deletion

feat: expose prefix hard delete at database and schema hierarchy levels

refactor: move prefix hard delete endpoint to EntityResource base class

fix: await async deletion before asserting in PrefixDeletionIT

fix: initialize LockManagerInitializer on startup so PrefixDeletionService is not null

fix: use unique names in PrefixDeletionIT/BenchmarkIT to avoid 409 conflicts

feat: scale benchmark to 10k entities and measure actual async deletion time

perf: parallelize entity seeding in PrefixDeletionBenchmarkIT

fix: use VARCHAR(36) for UUID columns in entity_deletion_lock on PostgreSQL

Revert "fix: use VARCHAR(36) for UUID columns in entity_deletion_lock on PostgreSQL"

fix: use VARCHAR(36) for UUID columns in entity_deletion_lock on PostgreSQL

fix: use VARCHAR(36) for UUID columns in entity_deletion_lock on PostgreSQL

fix: batch IN-clause deletes to avoid PostgreSQL 65535 parameter limit

refactor: move prefix hard delete endpoint to DatabaseServiceResource

feat: expose DELETE /prefix/{id} endpoint on all EntityResource subclasses

fix: add missing UUID and Response imports in two resource classes

fix: call super.deletePrefixHardById to prevent StackOverflowError

fix: chunk FeedDAO.findByEntityIds to avoid PostgreSQL 65535 parameter limit

feat: clean up Elasticsearch index during prefix hard deletion

feat: run pre/post delete hooks for all entity types during prefix deletion

feat: run pre/post hooks for all entity types during prefix deletion

fix: use information_schema conditional for ADD COLUMN in MySQL migration

Commits on Apr 11, 2026

fix: drop IF NOT EXISTS from CREATE INDEX in MySQL migration

fix: simplify MySQL migration to plain ALTER TABLE and CREATE INDEX

Commits on Apr 13, 2026

Merge branch 'main' into mohit/35dc-improve-deletion