bvandeusen
c4553d937c
Adds a daily off-hours VACUUM (ANALYZE) over the high-churn tables the retention/purge sweeps churn (app_logs, notifications, token tables, notes, note_versions), on top of Postgres autovacuum, to reclaim bloat left by the nightly bulk DELETEs and keep planner stats fresh. - services/db_maintenance.py: run_maintenance() over a closed table allowlist via an AUTOCOMMIT connection (VACUUM can't run in a txn); per-table summary persisted as the db_maintenance_last_run admin setting. - services/db_maintenance_scheduler.py: BackgroundScheduler cron (default 04:00 UTC, after the 03:30 trash purge); enabled-gate checked at fire time; live reschedule on hour change. Wired into app.py start/stop. - routes/admin.py: admin-only GET/PUT /api/admin/db-maintenance + POST /run. - settings.py: set_admin_setting() (write-side of get_admin_setting) for out-of-request writes. - SettingsView.vue: admin 'Database maintenance' card — enable toggle, run-hour (UTC), Run-now, last-run summary. - Tests: allowlist is closed, VACUUM issued per table, one failure doesn't abort the rest, summary persisted; route/scheduler/service surface. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
108 lines
3.8 KiB
Python
108 lines
3.8 KiB
Python
"""Daily APScheduler cron for basic DB maintenance (targeted VACUUM ANALYZE).
|
||
|
||
Mirrors trash_scheduler.py: a single global BackgroundScheduler job bridges
|
||
into the asyncio loop to run the async maintenance. Scheduled for 04:00 UTC by
|
||
default — after the 03:30 trash purge — so it collects the dead tuples that
|
||
night's delete sweeps leave behind.
|
||
|
||
Two things are operator-tunable from the admin Settings card:
|
||
- db_maintenance_enabled ("true"/"false") — checked at fire time, so toggling
|
||
it needs no reschedule.
|
||
- db_maintenance_hour ("0".."23", UTC) — the cron hour. Changing it calls
|
||
reschedule_db_maintenance() so the live job moves without a restart.
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import asyncio
|
||
import logging
|
||
|
||
from apscheduler.schedulers.background import BackgroundScheduler
|
||
from apscheduler.triggers.cron import CronTrigger
|
||
|
||
from scribe.services.settings import get_admin_setting
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
_JOB_ID = "db_maintenance_vacuum"
|
||
_DEFAULT_HOUR = 4
|
||
|
||
_scheduler: BackgroundScheduler | None = None
|
||
_loop: asyncio.AbstractEventLoop | None = None
|
||
|
||
|
||
async def get_maintenance_hour() -> int:
|
||
"""The configured run-hour (UTC, 0–23), clamped; default 04:00."""
|
||
raw = await get_admin_setting("db_maintenance_hour", str(_DEFAULT_HOUR))
|
||
try:
|
||
hour = int(raw)
|
||
except (TypeError, ValueError):
|
||
return _DEFAULT_HOUR
|
||
return hour if 0 <= hour <= 23 else _DEFAULT_HOUR
|
||
|
||
|
||
async def is_maintenance_enabled() -> bool:
|
||
"""Whether the scheduled run is enabled (default on)."""
|
||
return (await get_admin_setting("db_maintenance_enabled", "true")) != "false"
|
||
|
||
|
||
def _run_maintenance_threadsafe() -> None:
|
||
"""APScheduler invokes this from a worker thread; bridge into the loop."""
|
||
if _loop is None:
|
||
logger.warning("db maintenance scheduler: no loop registered")
|
||
return
|
||
|
||
async def _runner():
|
||
try:
|
||
if not await is_maintenance_enabled():
|
||
logger.debug("db maintenance: disabled, skipping scheduled run")
|
||
return
|
||
from scribe.services.db_maintenance import run_maintenance
|
||
await run_maintenance()
|
||
except Exception:
|
||
logger.exception("db maintenance run failed")
|
||
|
||
asyncio.run_coroutine_threadsafe(_runner(), _loop)
|
||
|
||
|
||
def start_db_maintenance_scheduler(
|
||
loop: asyncio.AbstractEventLoop, hour: int = _DEFAULT_HOUR
|
||
) -> None:
|
||
"""Start the daily job. `hour` is the configured UTC run-hour, resolved by
|
||
the caller (which has an async context) via get_maintenance_hour() — passed
|
||
in rather than read here so we never block the event loop at startup. The
|
||
job's enabled-gate is re-checked at every fire, so only the hour is needed
|
||
up front."""
|
||
global _scheduler, _loop
|
||
if _scheduler is not None:
|
||
return
|
||
_loop = loop
|
||
hour = hour if 0 <= hour <= 23 else _DEFAULT_HOUR
|
||
_scheduler = BackgroundScheduler()
|
||
_scheduler.add_job(
|
||
_run_maintenance_threadsafe,
|
||
trigger=CronTrigger(hour=hour, minute=0, timezone="UTC"),
|
||
id=_JOB_ID,
|
||
replace_existing=True,
|
||
)
|
||
_scheduler.start()
|
||
logger.info("DB maintenance scheduler started (daily %02d:00 UTC)", hour)
|
||
|
||
|
||
def reschedule_db_maintenance(hour: int) -> None:
|
||
"""Move the live job to a new UTC hour (called when the admin changes it)."""
|
||
if _scheduler is None:
|
||
return
|
||
hour = hour if 0 <= hour <= 23 else _DEFAULT_HOUR
|
||
_scheduler.reschedule_job(
|
||
_JOB_ID, trigger=CronTrigger(hour=hour, minute=0, timezone="UTC")
|
||
)
|
||
logger.info("DB maintenance scheduler rescheduled to %02d:00 UTC", hour)
|
||
|
||
|
||
def stop_db_maintenance_scheduler() -> None:
|
||
global _scheduler
|
||
if _scheduler is not None:
|
||
_scheduler.shutdown(wait=False)
|
||
_scheduler = None
|
||
logger.info("DB maintenance scheduler stopped")
|