peter
fad656988a
Backend - A run's outcome write sits outside the job's own try: a database blip after a run that succeeded no longer records it as failed (the row waits for the next start's sweep). - An interrupted run keeps what it spent (the sweep sums its quota rows, as finish does). - The Scheduler's ad-hoc row says running while any backfill runs, not only the newest. - recent_runs reads each job's last runs off its index instead of ranking the whole table. - An interval change is stored with its audit row in one transaction, then rescheduled. - One API instance per database is the stated contract (.env.example, jobruns). - Turning full history on for a channel already complete records no run. - Migration 0109 round-trips interrupted and ad-hoc runs; the run words' DB CHECKs are test-held to the enums; the account filter is one helper for the four activity reads. - An audit row says how many of its request's log lines are still kept. Frontend - An "All" period reaches every row still kept (runs and admin actions outlive 90 days). - Back/Forward is followed in place by the server log: a closing dialog no longer turns Live off; a pivot still opens a fresh log. - Runs moved over from the audit log read their one-liner in the reader's language. - Filter choices or accounts that failed to load say so beside the filters, with a retry. - An old server-log link keeps its account, text and range; a remembered retired page opens its tab. - A request whose lines are gone says so instead of linking to an empty list. - The log lines and the history rows share one row frame, and the server log one list frame with the other tabs; an empty list is announced; each day's quota is readable.
649 lines
26 KiB
Python
649 lines
26 KiB
Python
"""Background scheduler: free RSS detection, enrichment of new videos, and quota-aware
|
|
recent-first / deep backfill. Runs inside the API process (single worker)."""
|
|
|
|
import contextvars
|
|
import threading
|
|
from datetime import timezone
|
|
from typing import Callable
|
|
|
|
from apscheduler.executors.pool import ThreadPoolExecutor
|
|
from apscheduler.jobstores.base import ConflictingIdError
|
|
from apscheduler.schedulers.background import BackgroundScheduler
|
|
from sqlalchemy import select
|
|
|
|
from app import audit, debugsession, jobruns, logs, logsink, progress, quota, sysconfig
|
|
from app.config import settings
|
|
from app.db import SessionLocal
|
|
from app.downloads.gc import run_download_gc
|
|
from app.models import Channel
|
|
from app.plex.sync import sync as run_plex_sync
|
|
from app.plex.tmdb import run_enrich as run_tmdb_enrich
|
|
from app.plex.tmdb import run_people_enrich
|
|
from app.plex.watch_sync import run_plex_watch_reconcile, run_plex_watch_sync
|
|
from app.notifications import create_notification
|
|
from app.runstatus import RunStatus, RunTrigger
|
|
from app.state import is_sync_paused
|
|
from app.sync.autotag import run_autotag_all
|
|
from app.sync.explore import purge_ephemeral
|
|
from app.sync.maintenance import run_maintenance
|
|
from app.sync.playlists import sync_all_playlists
|
|
from app.utils import iso
|
|
from app.sync.runner import (
|
|
run_deep_backfill,
|
|
run_enrich,
|
|
run_recent_backfill,
|
|
run_rss_poll,
|
|
run_shorts,
|
|
run_subscription_resync,
|
|
)
|
|
|
|
log = logs.get_logger(__name__)
|
|
_scheduler: BackgroundScheduler | None = None
|
|
|
|
# What is running RIGHT NOW, per job: the single-run claim and the live progress. In memory on
|
|
# purpose — the scheduler lives in the API's one process, and progress changes every second. What a
|
|
# run did is durable instead: its `job_runs` row (app/jobruns.py), which outlives a restart.
|
|
_activity: dict[str, dict] = {}
|
|
_activity_lock = threading.Lock()
|
|
|
|
# Set (per-thread) by a manual "run now" trigger to the id of the admin who clicked, so that
|
|
# run — and only that run, not the recurring scheduled ones — posts a completion notification
|
|
# to their inbox. Unset (None) for scheduled runs.
|
|
_manual_actor: contextvars.ContextVar[int | None] = contextvars.ContextVar(
|
|
"manual_actor", default=None
|
|
)
|
|
|
|
# Each interval job's env/config default period (minutes). The admin can override any of these at
|
|
# runtime from the Scheduler page — a sysconfig key per job (`sysconfig.interval_key`), applied
|
|
# live; see load_intervals.
|
|
JOB_INTERVALS: dict[str, int] = {
|
|
job: getattr(settings, attr) for job, attr in sysconfig.JOB_INTERVAL_DEFAULTS.items()
|
|
}
|
|
MIN_INTERVAL = sysconfig.MIN_INTERVAL
|
|
MAX_INTERVAL = sysconfig.MAX_INTERVAL
|
|
|
|
|
|
def load_intervals(db) -> dict[str, int]:
|
|
"""Effective per-job intervals: each job's sysconfig override, else its env/config default."""
|
|
return {job: sysconfig.get_int(db, sysconfig.interval_key(job)) for job in JOB_INTERVALS}
|
|
|
|
|
|
def stage_interval(db, job_id: str, minutes: int) -> int:
|
|
"""Stage a job's interval override (clamped) in `db`; returns the value. The caller commits it
|
|
with its audit row, then calls `reschedule` — the live job follows only what was stored."""
|
|
if job_id not in JOB_INTERVALS:
|
|
raise KeyError(job_id)
|
|
minutes = max(MIN_INTERVAL, min(MAX_INTERVAL, int(minutes)))
|
|
sysconfig.set_value(db, sysconfig.interval_key(job_id), minutes)
|
|
return minutes
|
|
|
|
|
|
def reschedule(job_id: str, minutes: int) -> None:
|
|
"""Move the live interval job to `minutes` (if this process registered it)."""
|
|
if _scheduler is not None and _scheduler.get_job(job_id) is not None:
|
|
_scheduler.reschedule_job(job_id, trigger="interval", minutes=minutes)
|
|
log.info("rescheduled job %s to every %s min", job_id, minutes)
|
|
|
|
|
|
def _record(name: str, **fields) -> None:
|
|
with _activity_lock:
|
|
_activity.setdefault(name, {}).update(fields)
|
|
|
|
|
|
def _notify_done(
|
|
db,
|
|
actor_id: int,
|
|
job_id: str,
|
|
status: RunStatus,
|
|
summary: str | None,
|
|
result: dict | None = None,
|
|
) -> None:
|
|
"""Post a completion notice to the triggering admin's inbox (manual runs only). Best
|
|
effort — a notification failure must never mask the job's own outcome."""
|
|
try:
|
|
create_notification(
|
|
db,
|
|
user_id=actor_id,
|
|
type="scheduler",
|
|
title=f"{job_id}: {status}", # English fallback; UI renders translated from data
|
|
body=summary,
|
|
data={"job_id": job_id, "status": status, "summary": summary, "result": result},
|
|
)
|
|
except Exception:
|
|
db.rollback()
|
|
log.exception("failed to write completion notification for job %s", job_id)
|
|
|
|
|
|
def _job(name: str, fn) -> None:
|
|
# The one place both run paths converge (manual trigger AND scheduled fire), so claim the run
|
|
# HERE, atomically: whichever reaches this first wins, the other skips. This is the real
|
|
# single-run guard — trigger_job's pre-check is only a fast best-effort answer for the UI.
|
|
if not _claim_running(name):
|
|
log.info("job %s already running — skipping this trigger", name)
|
|
return
|
|
actor_id = _manual_actor.get() # set only for a manual "run now" trigger
|
|
trigger = RunTrigger.SCHEDULED if actor_id is None else RunTrigger.MANUAL
|
|
_record(name, progress=None) # running already claimed
|
|
db = SessionLocal()
|
|
try:
|
|
try:
|
|
run_id = jobruns.start(name, trigger, actor_id)
|
|
except Exception:
|
|
# No row to tell it in: the database is what failed. The log is the record.
|
|
log.exception("job %s not started: its run could not be recorded", name)
|
|
return
|
|
with logs.bind(run_id=run_id):
|
|
_run(db, name, fn, run_id, actor_id)
|
|
finally:
|
|
# ALWAYS release the claim, even if the body raised before its own status update — so a
|
|
# failure can never wedge the job as permanently "running".
|
|
_record(name, running=False, progress=None)
|
|
db.close()
|
|
|
|
|
|
def _run(db, name: str, fn, run_id: int, actor_id: int | None) -> None:
|
|
"""The run itself, inside its `job_runs` row: the pause-skip, the work, and its outcome — on
|
|
the row, and in the triggering admin's inbox for a manual run."""
|
|
|
|
def sink(current, total, phase):
|
|
_record(name, progress={"current": current, "total": total, "phase": phase})
|
|
|
|
# Only the work is inside the try: writing its outcome is not the job, and a write that fails
|
|
# must not turn a run that succeeded into a failed one (see _close).
|
|
result = None
|
|
try:
|
|
paused = is_sync_paused(db)
|
|
if not paused:
|
|
with progress.bind(sink):
|
|
result = fn(db)
|
|
except Exception as exc:
|
|
db.rollback()
|
|
log.exception("job %s failed", name, extra=logs.event("scheduler.job.failed", job=name))
|
|
err, failure = _failure(exc)
|
|
_close(run_id, RunStatus.ERROR, error=err, failure=failure)
|
|
if actor_id is not None:
|
|
_notify_done(db, actor_id, name, RunStatus.ERROR, err, failure)
|
|
return
|
|
if paused:
|
|
log.info("job %s skipped (sync paused)", name)
|
|
_close(run_id, RunStatus.SKIPPED, summary="sync paused", result=_PAUSED)
|
|
if actor_id is not None:
|
|
_notify_done(db, actor_id, name, RunStatus.SKIPPED, "sync paused", _PAUSED)
|
|
return
|
|
summary, data = _finish_ok(name, run_id, result)
|
|
if actor_id is not None:
|
|
_notify_done(db, actor_id, name, RunStatus.OK, summary, data)
|
|
|
|
|
|
def _close(run_id: int, status: RunStatus, **outcome) -> None:
|
|
"""Write a run's outcome. Its own failure (the database) is the log's to tell, never the job's:
|
|
the row then stays `running` until the next start's sweep closes it as interrupted."""
|
|
try:
|
|
jobruns.finish(run_id, status, **outcome)
|
|
except Exception:
|
|
log.exception("run %s: its outcome (%s) could not be recorded", run_id, status)
|
|
|
|
|
|
def _finish_ok(name: str, run_id: int, result) -> tuple[str | None, dict | None]:
|
|
"""Close a run that returned: its result on the row, as data and as the English one-liner."""
|
|
summary = _summarize(result)
|
|
data = _result_data(result)
|
|
log.info("job %s -> %s", name, result)
|
|
_close(run_id, RunStatus.OK, summary=summary, result=data)
|
|
return summary, data
|
|
|
|
|
|
def _failure(exc: Exception) -> tuple[str, dict | None]:
|
|
"""A raised run's English error line, and the failure the job named (progress.JobFailed) as
|
|
data, as a result is, so the client says it in the reader's language."""
|
|
err = str(exc) or exc.__class__.__name__
|
|
failure = {"failure": exc.reason, **exc.params} if isinstance(exc, progress.JobFailed) else None
|
|
return err, failure
|
|
|
|
|
|
# A skipped run's result, in the same shape as a job's own `{"skipped": …}`.
|
|
_PAUSED = {"skipped": "sync paused"}
|
|
|
|
|
|
def _result_data(result) -> dict | None:
|
|
"""A job's result as the client names it in the reader's language: the dict itself (counts,
|
|
a `skipped` / `reason` word, a nested dict per phase), `enrich`'s bare count as one. The one-line
|
|
`_summarize` is the English fallback."""
|
|
if isinstance(result, dict):
|
|
return result or None
|
|
if isinstance(result, int) and not isinstance(result, bool):
|
|
return {"enriched": result}
|
|
return None
|
|
|
|
|
|
def _summarize(result) -> str | None:
|
|
"""Compact one-line rendering of a job's return value for the dashboard."""
|
|
if result is None:
|
|
return None
|
|
if isinstance(result, dict):
|
|
return ", ".join(f"{k}={v}" for k, v in result.items()) or None
|
|
return str(result)
|
|
|
|
|
|
def scheduler_snapshot(db) -> dict:
|
|
"""What the scheduler is doing, for the admin dashboard: each job's live state from this process
|
|
and its last runs from `job_runs`, so a restart no longer blanks "when did it last run, and how
|
|
did it go"; and the same for the ad-hoc runs users start on one target. `running_here` is False where the scheduler runs no interval jobs
|
|
(SCHEDULER_ENABLED=false), so the UI can say so while still showing the DB-derived history,
|
|
queue and quota."""
|
|
running_here = _scheduler is not None and settings.scheduler_enabled
|
|
next_runs: dict[str, str | None] = {}
|
|
live_intervals: dict[str, int] = {}
|
|
if _scheduler is not None:
|
|
for job in _scheduler.get_jobs():
|
|
nr = getattr(job, "next_run_time", None)
|
|
next_runs[job.id] = nr.astimezone(timezone.utc).isoformat() if nr else None
|
|
iv = getattr(job.trigger, "interval", None)
|
|
if iv is not None:
|
|
live_intervals[job.id] = round(iv.total_seconds() / 60)
|
|
with _activity_lock:
|
|
acts = {k: dict(v) for k, v in _activity.items()}
|
|
recent = jobruns.recent_runs(db, [*JOB_INTERVALS, *AD_HOC_JOBS], RECENT_RUNS)
|
|
jobs = []
|
|
for job_id, default_interval in JOB_INTERVALS.items():
|
|
a = acts.get(job_id, {})
|
|
jobs.append(
|
|
{
|
|
"id": job_id,
|
|
"interval_minutes": live_intervals.get(job_id, default_interval),
|
|
"next_run": next_runs.get(job_id),
|
|
"running": a.get("running", False),
|
|
"progress": a.get("progress"),
|
|
**_last_runs(recent.get(job_id, [])),
|
|
}
|
|
)
|
|
# Work a user starts on one target: no interval, no "run now" (it needs its target), but its
|
|
# runs are shown beside the jobs' — it spends the same quota. Its one in-memory guard is the
|
|
# target's own (sync/runner), so "running" is what its rows say: two channels can backfill at
|
|
# once, so a run still going counts even when a newer one already ended, and the row names it.
|
|
backfills = recent.get(CHANNEL_BACKFILL, [])
|
|
going = jobruns.running_one(db, CHANNEL_BACKFILL)
|
|
shown = going or (backfills[0] if backfills else None)
|
|
ad_hoc = [
|
|
{
|
|
"id": CHANNEL_BACKFILL,
|
|
"running": going is not None,
|
|
"target": shown.target if shown else None,
|
|
"target_title": (
|
|
db.scalar(select(Channel.title).where(Channel.id == shown.target))
|
|
if shown is not None and shown.target
|
|
else None
|
|
),
|
|
**_last_runs(backfills),
|
|
}
|
|
]
|
|
return {
|
|
"running_here": running_here,
|
|
"enabled": settings.scheduler_enabled,
|
|
"jobs": jobs,
|
|
"ad_hoc": ad_hoc,
|
|
}
|
|
|
|
|
|
# How many past runs a Scheduler row shows as dots; the full history is the run list.
|
|
RECENT_RUNS = 3
|
|
|
|
|
|
def _last_runs(runs: list) -> dict:
|
|
"""A row's run fields from its newest runs (newest first): how the last one went, and the few
|
|
before it for the history dots."""
|
|
run = runs[0] if runs else None
|
|
# A run still going has no outcome yet: only an ended run says how it went.
|
|
ended = run if run is not None and run.status != RunStatus.RUNNING else None
|
|
return {
|
|
"status": ended.status if ended else None,
|
|
"last_started": iso(run.started_at) if run else None,
|
|
"last_finished": iso(run.finished_at) if run else None,
|
|
"last_result": ended.summary if ended else None,
|
|
# The outcome as data: the result, or on a failed run the failure the job named.
|
|
"result": _outcome_data(ended),
|
|
"last_error": ended.error if ended else None,
|
|
"last_trigger": run.trigger if run else None,
|
|
"last_run_id": run.id if run else None,
|
|
"quota_units": ended.quota_units if ended else None,
|
|
"recent": [_run_brief(r) for r in runs],
|
|
}
|
|
|
|
|
|
def _run_brief(run) -> dict:
|
|
return {
|
|
"id": run.id,
|
|
"status": run.status,
|
|
"trigger": run.trigger,
|
|
"started_at": iso(run.started_at),
|
|
"finished_at": iso(run.finished_at),
|
|
}
|
|
|
|
|
|
def _outcome_data(run) -> dict | None:
|
|
if run is None:
|
|
return None
|
|
return run.failure if run.status == RunStatus.ERROR else run.result
|
|
|
|
|
|
def _rss_job() -> None:
|
|
_job("rss_poll", run_rss_poll)
|
|
|
|
|
|
def _enrich_job() -> None:
|
|
def work(db):
|
|
with quota.attribute(None, quota.QuotaAction.VIDEOS_ENRICH):
|
|
return run_enrich(db)
|
|
|
|
_job("enrich", work)
|
|
|
|
|
|
def _backfill_job() -> None:
|
|
# Recent-first for not-yet-synced channels, then deep backfill for the rest. All
|
|
# background spend is attributed to the system (no actor), split by action.
|
|
def work(db):
|
|
with quota.attribute(None, quota.QuotaAction.VIDEOS_BACKFILL_RECENT):
|
|
recent = run_recent_backfill(db, max_channels=25)
|
|
with quota.attribute(None, quota.QuotaAction.VIDEOS_BACKFILL_FULL):
|
|
deep = run_deep_backfill(db, max_channels=10)
|
|
return {"recent": recent, "deep": deep}
|
|
|
|
_job("backfill", work)
|
|
|
|
|
|
def _autotag_job() -> None:
|
|
_job("autotag", lambda db: run_autotag_all(db, only_missing=True))
|
|
|
|
|
|
def _shorts_job() -> None:
|
|
_job("shorts", run_shorts)
|
|
|
|
|
|
def _subscriptions_job() -> None:
|
|
def work(db):
|
|
with quota.attribute(None, quota.QuotaAction.SUBSCRIPTIONS_RESYNC):
|
|
return run_subscription_resync(db)
|
|
|
|
_job("subscriptions", work)
|
|
|
|
|
|
def _playlist_sync_job() -> None:
|
|
# Mirror each read-scope user's YouTube playlists; per-user quota attribution is
|
|
# handled inside sync_all_playlists.
|
|
_job("playlist_sync", sync_all_playlists)
|
|
|
|
|
|
def _maintenance_job() -> None:
|
|
def work(db):
|
|
with quota.attribute(None, quota.QuotaAction.MAINTENANCE_REVALIDATE):
|
|
return run_maintenance(db)
|
|
|
|
_job("maintenance", work)
|
|
|
|
|
|
def _explore_cleanup_job() -> None:
|
|
# Reclaim un-kept ephemeral discovery content (explored channels + live-search results) after
|
|
# their grace periods. 0 quota (pure DB), so no quota attribution.
|
|
_job("explore_cleanup", purge_ephemeral)
|
|
|
|
|
|
def _download_gc_job() -> None:
|
|
# Retention GC for the download center: pre-expiry warnings, TTL deletion, LRU eviction — and
|
|
# the week-ahead warning before an API token runs out (`apitokens.warn_expiring`).
|
|
# Pure disk/DB work (no YouTube quota).
|
|
_job("download_gc", run_download_gc)
|
|
|
|
|
|
def _plex_sync_job() -> None:
|
|
# Mirror the enabled Plex library sections into the local catalog. Pure metadata (no YouTube
|
|
# quota); a no-op when the Plex module is disabled.
|
|
_job("plex_sync", run_plex_sync)
|
|
|
|
|
|
def _plex_watch_sync_job() -> None:
|
|
# Incremental Plex→Siftlode watch-state pull (history + on-deck) + re-push of unsynced local
|
|
# states. Cheap; a no-op when Plex is disabled or no owner link has sync enabled.
|
|
_job("plex_watch_sync", run_plex_watch_sync)
|
|
|
|
|
|
def _plex_watch_reconcile_job() -> None:
|
|
# Full watch-state reconcile (whole-section rescan) — catches un-watches the incremental feed
|
|
# can't. Heavier, so it runs far less often (daily default).
|
|
_job("plex_watch_reconcile", run_plex_watch_reconcile)
|
|
|
|
|
|
def _tmdb_enrich_job() -> None:
|
|
# Enrich a batch of mirrored Plex titles from TMDB (keywords/crew/budget/revenue/TMDb score/
|
|
# recommendations/backdrops), matched by guid. External metadata (no YouTube quota); a no-op when
|
|
# the TMDB key is unset or the Plex catalog is empty.
|
|
_job("tmdb_enrich", run_tmdb_enrich)
|
|
|
|
|
|
def _people_enrich_job() -> None:
|
|
# Make the people local: a batch of person bios from TMDB and a batch of portraits resized
|
|
# through Plex, so a person page and a cast strip never wait on an outside service.
|
|
_job("people_enrich", run_people_enrich)
|
|
|
|
|
|
def _audit_gc_job() -> None:
|
|
# The history cleanup: audit-log rows past audit_retention_days, YouTube quota history past
|
|
# quota_retention_days and finished runs past job_run_retention_days (0 = keep forever, each).
|
|
# Pure DB, no quota.
|
|
def work(db):
|
|
|
|
reaped = audit.gc(db, sysconfig.get_int(db, "audit_retention_days"))
|
|
quota_reaped = quota.gc(db, sysconfig.get_int(db, "quota_retention_days"))
|
|
runs_reaped = jobruns.gc(db, sysconfig.get_int(db, "job_run_retention_days"))
|
|
db.commit()
|
|
return {"reaped": reaped, "quota_reaped": quota_reaped, "runs_reaped": runs_reaped}
|
|
|
|
_job("audit_gc", work)
|
|
|
|
|
|
def _log_gc_job() -> None:
|
|
# Prune log_events rows older than log_retention_days — the limit the privacy policy states, so
|
|
# this runs hourly rather than daily. Pure DB, no quota.
|
|
def work(db):
|
|
|
|
days = sysconfig.get_int(db, "log_retention_days")
|
|
reaped = logsink.gc(db, days)
|
|
# Debug sessions go with the rows they bundle; an open one past its cap is closed.
|
|
closed = debugsession.sweep(db)
|
|
sessions = debugsession.gc(db, days)
|
|
db.commit()
|
|
return {"reaped": reaped, "sessions_closed": closed, "sessions_reaped": sessions}
|
|
|
|
_job("log_gc", work)
|
|
|
|
|
|
# job_id -> wrapper. The single source of truth for which jobs exist and how to run one,
|
|
# shared by start_scheduler (recurring registration) and trigger_job (manual "run now").
|
|
JOB_FUNCS: dict[str, Callable[[], None]] = {
|
|
"rss_poll": _rss_job,
|
|
"enrich": _enrich_job,
|
|
"backfill": _backfill_job,
|
|
"autotag": _autotag_job,
|
|
"shorts": _shorts_job,
|
|
"subscriptions": _subscriptions_job,
|
|
"playlist_sync": _playlist_sync_job,
|
|
"maintenance": _maintenance_job,
|
|
"explore_cleanup": _explore_cleanup_job,
|
|
"download_gc": _download_gc_job,
|
|
"plex_sync": _plex_sync_job,
|
|
"plex_watch_sync": _plex_watch_sync_job,
|
|
"plex_watch_reconcile": _plex_watch_reconcile_job,
|
|
"tmdb_enrich": _tmdb_enrich_job,
|
|
"people_enrich": _people_enrich_job,
|
|
"audit_gc": _audit_gc_job,
|
|
"log_gc": _log_gc_job,
|
|
}
|
|
|
|
|
|
def _is_running(job_id: str) -> bool:
|
|
with _activity_lock:
|
|
return bool(_activity.get(job_id, {}).get("running"))
|
|
|
|
|
|
def _claim_running(job_id: str) -> bool:
|
|
"""Atomically claim a job as running: True if it was idle (and marks it running now), False if
|
|
it was already running. Holding the lock across BOTH the check and the set is what makes the
|
|
single-run guard race-free — called once at the top of _job so a manual trigger and a scheduled
|
|
fire (or two rapid triggers) converge here and exactly one wins. Released in _job's finally."""
|
|
with _activity_lock:
|
|
if _activity.get(job_id, {}).get("running"):
|
|
return False
|
|
_activity.setdefault(job_id, {})["running"] = True
|
|
return True
|
|
|
|
|
|
def running_job_ids() -> set[str]:
|
|
"""Ids of jobs executing right now (any trigger). Lets non-admin surfaces — e.g. the
|
|
header's sync indicator — reflect real activity instead of just pending-work counts."""
|
|
with _activity_lock:
|
|
return {jid for jid, a in _activity.items() if a.get("running")}
|
|
|
|
|
|
def _as_actor(fn: Callable[[], None], actor_id: int | None) -> Callable[[], None]:
|
|
"""`fn` run as `actor_id`'s manual run. The actor is RESET afterwards: the executor's pool
|
|
threads are reused and keep their context from task to task, so an actor left set would make
|
|
the next scheduled run that thread picks up look like this admin's manual run."""
|
|
|
|
def run() -> None:
|
|
token = _manual_actor.set(actor_id)
|
|
try:
|
|
fn()
|
|
finally:
|
|
_manual_actor.reset(token)
|
|
|
|
return run
|
|
|
|
|
|
def trigger_job(job_id: str, actor_id: int | None = None) -> str:
|
|
"""Run a job now, independent of its interval schedule: a one-shot job on the same scheduler,
|
|
so a manual run shares the scheduled runs' executor and shutdown — no thread of its own. The
|
|
wrapper handles its own DB session, run row and pause-skip. Returns "started",
|
|
"already_running", or raises KeyError for an unknown job.
|
|
|
|
`actor_id` (the admin who clicked "run now") is set in a contextvar inside the run's thread, so
|
|
the run is recorded as theirs and posts a completion notification to their inbox."""
|
|
fn = JOB_FUNCS.get(job_id)
|
|
if fn is None:
|
|
raise KeyError(job_id)
|
|
# Best-effort fast answer for the UI; the authoritative single-run guard is _job's atomic claim
|
|
# (so a manual trigger and a scheduled fire can't both run). A race here just means the loser's
|
|
# _job claims, sees it's taken, and skips — no double run.
|
|
if _is_running(job_id):
|
|
return "already_running"
|
|
sched = _scheduler
|
|
if sched is None:
|
|
# Only between shutdown and exit: start_scheduler runs at every API startup.
|
|
raise RuntimeError("the scheduler is not running")
|
|
|
|
try:
|
|
# One id per job: a second click before the first one-shot has even started is the same
|
|
# run, not a queued second one. misfire_grace_time=None: a busy pool delays it, never drops it.
|
|
sched.add_job(_as_actor(fn, actor_id), "date", id=f"{job_id}@now", misfire_grace_time=None)
|
|
# silent-ok: not a failure — the answer is the 409 the admin sees ("already running").
|
|
except ConflictingIdError:
|
|
return "already_running"
|
|
return "started"
|
|
|
|
|
|
def trigger_all(actor_id: int | None = None) -> list[str]:
|
|
"""Trigger every job that isn't already running; returns the ids actually started."""
|
|
started = []
|
|
for job_id in JOB_FUNCS:
|
|
if trigger_job(job_id, actor_id) == "started":
|
|
started.append(job_id)
|
|
return started
|
|
|
|
|
|
# Work a user starts on one target outside the job list — today the "get full history" backfill of
|
|
# one channel. It runs on the same scheduler as a recorded run (trigger `ad_hoc`), so what it did and
|
|
# spent is in `job_runs` like any job's, not a background task only the log ever heard of.
|
|
CHANNEL_BACKFILL = "channel_backfill"
|
|
# Every ad-hoc job id: the page names each one (a frontend contract test reads this tuple).
|
|
AD_HOC_JOBS = (CHANNEL_BACKFILL,)
|
|
|
|
|
|
def run_ad_hoc(job: str, fn: Callable[[], dict], *, actor_id: int, target: str) -> None:
|
|
"""Run `fn` now as `actor_id`'s run of `job` on `target`, a one-shot job on the scheduler. Its
|
|
own exclusion (if any) lives in `fn`, which says so in its result; one id per job and target, so
|
|
a second request before the first has even started is that same run."""
|
|
if job not in AD_HOC_JOBS:
|
|
raise KeyError(job) # an unnamed job would show on the page as its bare id
|
|
sched = _scheduler
|
|
if sched is None:
|
|
# Only between shutdown and exit: start_scheduler runs at every API startup.
|
|
raise RuntimeError("the scheduler is not running")
|
|
try:
|
|
sched.add_job(
|
|
_ad_hoc,
|
|
"date",
|
|
args=(job, fn, actor_id, target),
|
|
id=f"{job}@{target}",
|
|
misfire_grace_time=None,
|
|
)
|
|
# silent-ok: not a failure — the run for this target is already queued, and it does this work.
|
|
except ConflictingIdError:
|
|
log.info("ad-hoc %s for %s already queued", job, target)
|
|
|
|
|
|
def _ad_hoc(job: str, fn: Callable[[], dict], actor_id: int, target: str) -> None:
|
|
try:
|
|
run_id = jobruns.start(job, RunTrigger.AD_HOC, actor_id, target)
|
|
except Exception:
|
|
# No row to tell it in: the database is what failed. The log is the record.
|
|
log.exception("ad-hoc %s for %s not started: its run could not be recorded", job, target)
|
|
return
|
|
with logs.bind(run_id=run_id):
|
|
# As in _run: only the work is inside the try.
|
|
try:
|
|
result = fn()
|
|
except Exception as exc:
|
|
log.exception("job %s failed", job, extra=logs.event("scheduler.job.failed", job=job))
|
|
err, failure = _failure(exc)
|
|
_close(run_id, RunStatus.ERROR, error=err, failure=failure)
|
|
return
|
|
_finish_ok(job, run_id, result)
|
|
|
|
|
|
# Room for every job at once (a "run all") beside a few ad-hoc runs: APScheduler's default pool of
|
|
# 10 would queue a scheduled fire behind long manual runs.
|
|
_POOL_SIZE = len(JOB_FUNCS) + 8
|
|
|
|
|
|
def start_scheduler() -> None:
|
|
"""Start this process's scheduler. It always starts, so "run now" works on every install; only
|
|
with SCHEDULER_ENABLED does it also register the recurring interval jobs. Before anything can
|
|
run, every run a previous process left open is closed as interrupted — one API process serves a
|
|
database (app/jobruns.py), so an open run here is a dead process's."""
|
|
global _scheduler
|
|
if _scheduler is not None:
|
|
return
|
|
left = jobruns.interrupt_leftovers()
|
|
if left:
|
|
log.warning("%s run(s) left running by the previous process marked interrupted", left)
|
|
scheduler = BackgroundScheduler(
|
|
timezone="UTC", executors={"default": ThreadPoolExecutor(_POOL_SIZE)}
|
|
)
|
|
if settings.scheduler_enabled:
|
|
# Effective intervals = env defaults overlaid with any admin overrides from the DB.
|
|
db = SessionLocal()
|
|
try:
|
|
iv = load_intervals(db)
|
|
finally:
|
|
db.close()
|
|
for job_id, fn in JOB_FUNCS.items():
|
|
scheduler.add_job(fn, "interval", minutes=iv[job_id], id=job_id)
|
|
scheduler.start()
|
|
_scheduler = scheduler
|
|
log.info("scheduler started (interval jobs %s)", "on" if settings.scheduler_enabled else "off")
|
|
|
|
|
|
def shutdown_scheduler() -> None:
|
|
global _scheduler
|
|
if _scheduler is not None:
|
|
_scheduler.shutdown(wait=False)
|
|
_scheduler = None
|