Lukas
654dbdb000
Create GeoCache class with all mutable state as instance attributes: - _cache, _neg_cache, _dirty, _geoip_reader, _geoip_initialized, _cache_lock - All public methods: lookup(), lookup_batch(), lookup_cached_only(), flush_dirty(), load_from_db(), clear(), etc. Initialization & Dependency Injection: - Instantiate GeoCache in startup.py and store on app.state.geo_cache - Add get_geo_cache() dependency function in dependencies.py - Inject into routes and tasks via FastAPI's dependency system Backward Compatibility: - Maintain module-level functions in geo_service.py as deprecated wrappers - All old callers continue to work through _default_geo_cache instance - Remove test-escape-hatch functions (clear_cache, clear_neg_cache moved to methods) Background Tasks: - Update geo_cache_flush.py and geo_re_resolve.py to receive GeoCache instance - Tasks now operate on injected instance rather than module globals Tests: - Refactor test_geo_service.py with geo_cache fixture providing fresh instances - Update patch paths to target GeoCache methods correctly - Fix internal state assertions to access instance attributes Documentation: - Update Architekture.md to document GeoCache as managed stateful service - Describe cache lifecycle (load on startup, flush periodically, re-resolve stale) - Note process-local limitations for multi-worker deployments Fixes violation of Single Responsibility Principle: module no longer owns both lookup logic and cache lifecycle management. Cache is now a first-class injectable service with transparent lifecycle. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
76 lines
2.4 KiB
Python
76 lines
2.4 KiB
Python
"""Geo cache flush background task.
|
|
|
|
Registers an APScheduler job that periodically persists newly resolved IP
|
|
geo entries from the in-memory dirty set to the ``geo_cache`` table.
|
|
|
|
After Task 2 removed geo cache writes from GET requests, newly resolved IPs
|
|
are only held in the in-memory cache until this task flushes them. With the
|
|
default 60-second interval, at most one minute of new resolution results is
|
|
at risk on an unexpected process restart.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
import structlog
|
|
|
|
from app.services.geo_cache import GeoCache
|
|
from app.tasks.db import task_db
|
|
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 often the flush job fires (seconds). Configurable tuning constant.
|
|
GEO_FLUSH_INTERVAL: int = 60
|
|
|
|
#: Stable APScheduler job ID — ensures re-registration replaces, not duplicates.
|
|
JOB_ID: str = "geo_cache_flush"
|
|
|
|
|
|
async def _run_flush_with_resources(geo_cache: GeoCache, settings: Settings) -> None:
|
|
"""Flush the geo cache dirty set to the application database.
|
|
|
|
Args:
|
|
geo_cache: The application's GeoCache instance.
|
|
settings: The resolved application settings used for database access.
|
|
"""
|
|
async with task_db(settings) as db:
|
|
count = await geo_cache.flush_dirty(db)
|
|
|
|
if count > 0:
|
|
log.debug("geo_cache_flush_ran", flushed=count)
|
|
|
|
|
|
async def _run_flush(app: FastAPI) -> None:
|
|
geo_cache: GeoCache = app.state.geo_cache
|
|
await _run_flush_with_resources(geo_cache, get_effective_settings(app))
|
|
|
|
|
|
def register(app: FastAPI) -> None:
|
|
"""Add (or replace) the geo cache flush 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.
|
|
"""
|
|
geo_cache: GeoCache = app.state.geo_cache
|
|
settings = get_effective_settings(app)
|
|
app.state.scheduler.add_job(
|
|
_run_flush_with_resources,
|
|
trigger="interval",
|
|
seconds=GEO_FLUSH_INTERVAL,
|
|
kwargs={"geo_cache": geo_cache, "settings": settings},
|
|
id=JOB_ID,
|
|
replace_existing=True,
|
|
)
|
|
log.info("geo_cache_flush_scheduled", interval_seconds=GEO_FLUSH_INTERVAL)
|