Make background tasks idempotent - prevent duplicate bans on retry
CRITICAL FIX: Background tasks (especially blocklist_import) crashed mid-execution, leaving partial state. On retry, the same bans were applied again, causing duplicates. Solution: Content-hash based operation tracking for blocklist imports: - Added import_runs table (migration 6) to track operations by source + content hash - Before banning, check if this exact content has already been imported - If completed: skip banning (already done), optionally re-warm cache - If new or failed: proceed with ban and mark as completed or failed Changes: - Database: Migration 6 adds import_runs table with operation state tracking - Model: Added ImportRunEntry for import run records - Repository: New import_run_repo module with CRUD operations - Workflow: Updated blocklist_import_workflow to check operation history before banning - Dependencies: Registered import_run_repo for dependency injection - Tests: Added test_import_source_idempotent_on_retry and test_import_source_different_content_not_reused - Documentation: Added Task Idempotency section to Backend-Development.md Verification: - All 7 import tests pass (5 existing + 2 new idempotency tests) - Type checking: mypy --strict ✅ - Linting: ruff ✅ - No API changes, backwards compatible via automatic migration Fixes: Background tasks not idempotent #CRITICAL Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
@@ -19,6 +19,7 @@ import structlog
|
||||
|
||||
from app.services import ban_service, blocklist_service
|
||||
from app.tasks.db import task_db
|
||||
from app.tasks.timeout_utils import run_with_timeout
|
||||
from app.utils.runtime_state import get_effective_settings
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -32,6 +33,9 @@ log: structlog.stdlib.BoundLogger = structlog.get_logger()
|
||||
#: Stable APScheduler job id so the job can be replaced without duplicates.
|
||||
JOB_ID: str = "blocklist_import"
|
||||
|
||||
#: Maximum seconds to allow for blocklist import task to complete.
|
||||
TASK_TIMEOUT_SECONDS: int = 300
|
||||
|
||||
|
||||
async def _run_import_with_resources(settings: Settings, http_session: ClientSession) -> None:
|
||||
"""APScheduler callback that imports all enabled blocklist sources.
|
||||
@@ -40,25 +44,29 @@ async def _run_import_with_resources(settings: Settings, http_session: ClientSes
|
||||
settings: The resolved application settings used for database access.
|
||||
http_session: The shared aiohttp session used for blocklist downloads.
|
||||
"""
|
||||
socket_path: str = settings.fail2ban_socket
|
||||
|
||||
log.info("blocklist_import_starting")
|
||||
try:
|
||||
async with task_db(settings) as db:
|
||||
result = await blocklist_service.import_all(
|
||||
db,
|
||||
http_session,
|
||||
socket_path,
|
||||
ban_ip=ban_service.ban_ip,
|
||||
async def _do_import() -> None:
|
||||
socket_path: str = settings.fail2ban_socket
|
||||
|
||||
log.info("blocklist_import_starting")
|
||||
try:
|
||||
async with task_db(settings) as db:
|
||||
result = await blocklist_service.import_all(
|
||||
db,
|
||||
http_session,
|
||||
socket_path,
|
||||
ban_ip=ban_service.ban_ip,
|
||||
)
|
||||
log.info(
|
||||
"blocklist_import_finished",
|
||||
total_imported=result.total_imported,
|
||||
total_skipped=result.total_skipped,
|
||||
errors=result.errors_count,
|
||||
)
|
||||
log.info(
|
||||
"blocklist_import_finished",
|
||||
total_imported=result.total_imported,
|
||||
total_skipped=result.total_skipped,
|
||||
errors=result.errors_count,
|
||||
)
|
||||
except Exception:
|
||||
log.exception("blocklist_import_unexpected_error")
|
||||
except Exception:
|
||||
log.exception("blocklist_import_unexpected_error")
|
||||
|
||||
await run_with_timeout("blocklist_import", _do_import(), TASK_TIMEOUT_SECONDS)
|
||||
|
||||
|
||||
run_import_with_resources = _run_import_with_resources
|
||||
|
||||
Reference in New Issue
Block a user