- Remove structlog dependency from backend/pyproject.toml - Add app.utils.logging_compat shim for keyword-arg logging API - Add app.utils.json_formatter for JSON log output with extra fields - Update all backend modules to use logging_compat.get_logger() - Update docstrings in log_sanitizer.py and json_formatter.py - Update test comment in test_async_utils.py - Record 406 failing tests in Docs/Tasks.md for tracking
105 lines
3.4 KiB
Python
105 lines
3.4 KiB
Python
"""Rate limiter cleanup background task.
|
|
|
|
Registers an APScheduler job that periodically removes expired rate-limit
|
|
entries from the in-memory rate limiter. Without this cleanup, the
|
|
rate-limiter state dictionary grows unbounded over long runtimes, eventually
|
|
consuming excessive memory.
|
|
|
|
The cleanup is conservative: it only removes IPs with no recent attempts
|
|
(all timestamps outside the rate-limit window), so active or recently-active
|
|
IPs are preserved.
|
|
|
|
Correlation IDs are propagated through the task using :mod:`app.utils.correlation`
|
|
so that task logs can be correlated across runs.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import uuid
|
|
from typing import TYPE_CHECKING
|
|
|
|
from app.utils.logging_compat import get_logger
|
|
|
|
from app.tasks.timeout_utils import run_with_timeout
|
|
from app.utils.correlation import get_correlation_id, reset_correlation_id, set_correlation_id
|
|
|
|
if TYPE_CHECKING:
|
|
from fastapi import FastAPI
|
|
|
|
log = get_logger(__name__)
|
|
|
|
#: How often the cleanup job fires (seconds). Chosen to balance memory
|
|
#: management against CPU overhead. A 30-minute interval handles typical
|
|
#: brute-force attack patterns while staying lightweight.
|
|
RATE_LIMITER_CLEANUP_INTERVAL: int = 30 * 60 # 30 minutes
|
|
|
|
#: Stable APScheduler job ID — ensures re-registration replaces, not duplicates.
|
|
JOB_ID: str = "rate_limiter_cleanup"
|
|
|
|
#: Maximum seconds to allow for rate limiter cleanup to complete.
|
|
TASK_TIMEOUT_SECONDS: int = 5
|
|
|
|
|
|
async def _run_cleanup(
|
|
app: FastAPI,
|
|
correlation_id: str | None = None,
|
|
) -> None:
|
|
"""Trigger cleanup of expired rate-limiter entries.
|
|
|
|
Cleans up both the login-specific rate limiter (exponential backoff)
|
|
and the global request rate limiter.
|
|
|
|
Args:
|
|
app: The FastAPI application instance (holds the rate limiters).
|
|
correlation_id: Optional correlation ID for log correlation.
|
|
"""
|
|
if correlation_id is None:
|
|
correlation_id = str(uuid.uuid4())
|
|
|
|
token = set_correlation_id(correlation_id)
|
|
try:
|
|
await _do_cleanup_with_app(app)
|
|
finally:
|
|
reset_correlation_id(token)
|
|
|
|
|
|
async def _do_cleanup_with_app(app: FastAPI) -> None:
|
|
"""Inner cleanup logic that runs with correlation context set."""
|
|
|
|
async def _do_cleanup() -> None:
|
|
global_limiter = getattr(app.state, "global_rate_limiter", None)
|
|
if global_limiter is None:
|
|
log.warning(
|
|
"rate_limiter_cleanup_skipped",
|
|
correlation_id=get_correlation_id(),
|
|
reason="global_rate_limiter not found on app.state",
|
|
)
|
|
else:
|
|
global_limiter.cleanup_expired()
|
|
|
|
await run_with_timeout("rate_limiter_cleanup", _do_cleanup(), TASK_TIMEOUT_SECONDS)
|
|
|
|
|
|
def register(app: FastAPI) -> None:
|
|
"""Add (or replace) the rate-limiter 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.
|
|
"""
|
|
app.state.scheduler.add_job(
|
|
_run_cleanup,
|
|
trigger="interval",
|
|
seconds=RATE_LIMITER_CLEANUP_INTERVAL,
|
|
kwargs={"app": app},
|
|
id=JOB_ID,
|
|
replace_existing=True,
|
|
)
|
|
log.info(
|
|
"rate_limiter_cleanup_scheduled",
|
|
interval_seconds=RATE_LIMITER_CLEANUP_INTERVAL,
|
|
)
|