Lukas
52f237d5d4
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>
99 lines
3.3 KiB
Python
99 lines
3.3 KiB
Python
"""Geo cache cleanup background task.
|
|
|
|
Registers an APScheduler job that periodically removes stale entries from the
|
|
``geo_cache`` table — entries that have not been referenced in the configured
|
|
retention period (default: 90 days). This prevents unbounded growth of the
|
|
database file and maintains query performance on geo lookups.
|
|
|
|
When a stale IP is encountered again after purge, it will be re-resolved from
|
|
the MaxMind database or ip-api.com (if configured), which is acceptable.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from datetime import UTC, datetime, timedelta
|
|
from typing import TYPE_CHECKING
|
|
|
|
import structlog
|
|
|
|
from app.repositories import geo_cache_repo
|
|
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:
|
|
from fastapi import FastAPI
|
|
|
|
from app.config import Settings
|
|
|
|
log: structlog.stdlib.BoundLogger = structlog.get_logger()
|
|
|
|
#: How long to retain geo cache entries (days). Configurable tuning constant.
|
|
GEO_CACHE_RETENTION_DAYS: int = 90
|
|
|
|
#: How often the cleanup job fires (seconds). Default: once per day.
|
|
GEO_CLEANUP_INTERVAL: int = 24 * 60 * 60
|
|
|
|
#: Stable APScheduler job ID — ensures re-registration replaces, not duplicates.
|
|
JOB_ID: str = "geo_cache_cleanup"
|
|
|
|
#: Maximum seconds to allow for geo cache cleanup to complete.
|
|
TASK_TIMEOUT_SECONDS: int = 60
|
|
|
|
|
|
async def _run_cleanup_with_resources(settings: Settings) -> None:
|
|
"""Delete stale entries from the geo cache.
|
|
|
|
Calculates a cutoff timestamp (now - retention period) and removes all
|
|
entries with ``last_seen`` before that time. Logs the operation result.
|
|
|
|
Args:
|
|
settings: The resolved application settings used for database access.
|
|
"""
|
|
|
|
async def _do_cleanup() -> None:
|
|
cutoff_dt = datetime.now(UTC) - timedelta(days=GEO_CACHE_RETENTION_DAYS)
|
|
cutoff_iso = cutoff_dt.strftime("%Y-%m-%dT%H:%M:%SZ")
|
|
|
|
async with task_db(settings) as db:
|
|
deleted = await geo_cache_repo.delete_stale_entries(db, cutoff_iso)
|
|
await db.commit()
|
|
|
|
if deleted > 0:
|
|
log.info("geo_cache_cleanup_ran", deleted=deleted, retention_days=GEO_CACHE_RETENTION_DAYS)
|
|
else:
|
|
log.debug("geo_cache_cleanup_ran", deleted=deleted, retention_days=GEO_CACHE_RETENTION_DAYS)
|
|
|
|
await run_with_timeout("geo_cache_cleanup", _do_cleanup(), TASK_TIMEOUT_SECONDS)
|
|
|
|
|
|
async def _run_cleanup(app: FastAPI) -> None:
|
|
"""Run cleanup with application settings."""
|
|
await _run_cleanup_with_resources(get_effective_settings(app))
|
|
|
|
|
|
def register(app: FastAPI) -> None:
|
|
"""Add (or replace) the geo cache cleanup job in the application scheduler.
|
|
|
|
Must be called after the scheduler has been started (i.e., inside the
|
|
lifespan handler, after ``scheduler.start()``).
|
|
|
|
Args:
|
|
app: The :class:`fastapi.FastAPI` application instance whose
|
|
``app.state.scheduler`` will receive the job.
|
|
"""
|
|
settings = get_effective_settings(app)
|
|
app.state.scheduler.add_job(
|
|
_run_cleanup_with_resources,
|
|
trigger="interval",
|
|
seconds=GEO_CLEANUP_INTERVAL,
|
|
kwargs={"settings": settings},
|
|
id=JOB_ID,
|
|
replace_existing=True,
|
|
)
|
|
log.info(
|
|
"geo_cache_cleanup_scheduled",
|
|
interval_seconds=GEO_CLEANUP_INTERVAL,
|
|
retention_days=GEO_CACHE_RETENTION_DAYS,
|
|
)
|