dcc5042586
Root cause of the 2GB prod import.db: the sync_run_orders audit junction recorded every order on every run; under the 1-minute scheduler ~98% of 21.7M rows were no-op ALREADY_IMPORTED re-observations. NSSM stdout/stderr also grew unbounded (rotation never applied to the live service). Changes: - sqlite_service: skip ALREADY_IMPORTED rows in sync_run_orders (write-side guard, _SKIP_JUNCTION_STATUSES); add prune_sync_history(retention_days) with incremental_vacuum. - maintenance_service (new): cleanup_old_logs + run_daily_maintenance. - scheduler_service: start_maintenance_job (daily CronTrigger). - main.py: RotatingFileHandler (sync_comenzi_current.log, 10MB x5) instead of a new timestamped file per start; schedule daily maintenance + one-shot catch-up at startup. - scripts/db_maintenance.py (new): one-shot prune + VACUUM + log cleanup, plain sqlite3, invoked by deploy.ps1 while the service is stopped. - deploy.ps1: stop -> run db_maintenance.py -> (re)apply NSSM AppRotate* idempotently -> start, so rotation reaches pre-existing services. Retention defaults: 7 days history, 7 days logs. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
98 lines
2.7 KiB
Python
98 lines
2.7 KiB
Python
import logging
|
|
from apscheduler.schedulers.asyncio import AsyncIOScheduler
|
|
from apscheduler.triggers.interval import IntervalTrigger
|
|
from apscheduler.triggers.cron import CronTrigger
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_scheduler = None
|
|
_is_running = False
|
|
|
|
|
|
def init_scheduler():
|
|
"""Initialize the APScheduler instance."""
|
|
global _scheduler
|
|
_scheduler = AsyncIOScheduler()
|
|
logger.info("Scheduler initialized")
|
|
|
|
|
|
def start_scheduler(interval_minutes: int = 10):
|
|
"""Start the scheduler with the given interval."""
|
|
global _is_running
|
|
if _scheduler is None:
|
|
init_scheduler()
|
|
|
|
# Remove existing job if any
|
|
if _scheduler.get_job("sync_job"):
|
|
_scheduler.remove_job("sync_job")
|
|
|
|
from . import sync_service
|
|
|
|
_scheduler.add_job(
|
|
sync_service.run_sync,
|
|
trigger=IntervalTrigger(minutes=interval_minutes),
|
|
id="sync_job",
|
|
name="GoMag Sync",
|
|
replace_existing=True
|
|
)
|
|
|
|
if not _scheduler.running:
|
|
_scheduler.start()
|
|
|
|
_is_running = True
|
|
logger.info(f"Scheduler started with interval {interval_minutes}min")
|
|
|
|
|
|
def start_maintenance_job(hour: int = 3):
|
|
"""Schedule the daily DB/log maintenance job (prune history + cleanup logs).
|
|
|
|
Runs independently of the sync job — starts the scheduler if it isn't already
|
|
running so maintenance happens even when auto-sync is disabled.
|
|
"""
|
|
if _scheduler is None:
|
|
init_scheduler()
|
|
|
|
from . import maintenance_service
|
|
|
|
_scheduler.add_job(
|
|
maintenance_service.run_daily_maintenance,
|
|
trigger=CronTrigger(hour=hour, minute=0),
|
|
id="maintenance_job",
|
|
name="Daily DB/Log Maintenance",
|
|
replace_existing=True
|
|
)
|
|
|
|
if not _scheduler.running:
|
|
_scheduler.start()
|
|
|
|
logger.info(f"Maintenance job scheduled daily at {hour:02d}:00")
|
|
|
|
|
|
def stop_scheduler():
|
|
"""Stop the scheduler."""
|
|
global _is_running
|
|
if _scheduler and _scheduler.running:
|
|
if _scheduler.get_job("sync_job"):
|
|
_scheduler.remove_job("sync_job")
|
|
_is_running = False
|
|
logger.info("Scheduler stopped")
|
|
|
|
|
|
def shutdown_scheduler():
|
|
"""Shutdown the scheduler completely."""
|
|
global _scheduler, _is_running
|
|
if _scheduler and _scheduler.running:
|
|
_scheduler.shutdown(wait=False)
|
|
_scheduler = None
|
|
_is_running = False
|
|
|
|
|
|
def get_scheduler_status():
|
|
"""Get current scheduler status."""
|
|
job = _scheduler.get_job("sync_job") if _scheduler else None
|
|
return {
|
|
"enabled": _is_running,
|
|
"next_run": job.next_run_time.isoformat() if job and job.next_run_time else None,
|
|
"interval_minutes": int(job.trigger.interval.total_seconds() / 60) if job else None
|
|
}
|