Files
FabledCurator/backend/app/services/scheduler_service.py
T
bvandeusen 61ce1ce13c feat(scheduler): platform-wide cooldown on RATE_LIMITED — burst prevention
The scan tick fired download_source.delay() for every due source without
grouping by platform; with multiple download workers, N due Patreon
sources could all hit Patreon's API in parallel and rate-limit each
other. Per-source consecutive_failures backoff REACTS to that (slows the
offender across cycles) but didn't PREVENT the first-tick burst.

When DownloadService._update_source_health sees a source error
classified as ErrorType.RATE_LIMITED, it now stamps an AppSetting row
`platform_cooldown:<platform>` with the cooldown expiry (now + 15 min,
PLATFORM_RATE_LIMIT_COOLDOWN_SECONDS). select_due_sources queries every
platform_cooldown:* key at the start of each tick and excludes every
source whose platform is in active cooldown. scheduler_status surfaces
active cooldowns as platform_cooldowns: {platform: expires_iso} so the
TopNav pipeline chip / activity summary can display them.

INSERT...ON CONFLICT DO UPDATE for the upsert so two workers racing
RATE_LIMITED responses on the same platform don't let one's
IntegrityError roll back the other's event-finalize transaction
(stranding the event for the recovery sweep). Atomic at the SQL level.

Tests cover: select_due_sources skips a platform in cooldown; other
platforms unaffected during single-platform cooldown; expired cooldown
rows don't filter; set_platform_cooldown is upsert-safe under repeated
calls.

Operator-flagged 2026-05-30 ("running multiple workers I don't know how
we'd keep the downloader from hitting a rate limit on a source").

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-30 11:01:40 -04:00

216 lines
8.1 KiB
Python

"""FC-3d: pure logic for deciding which sources are due for a check.
The Celery tick task wraps `select_due_sources` and fires
`download_source.delay()` per result; this module knows nothing about
Celery, gallery-dl, or any side effect.
"""
from __future__ import annotations
from datetime import UTC, datetime, timedelta
from sqlalchemy import select
from sqlalchemy.dialects.postgresql import insert as pg_insert
from sqlalchemy.ext.asyncio import AsyncSession
from sqlalchemy.orm import selectinload
from ..models import AppSetting, Artist, ImportSettings, Source
MIN_INTERVAL_SECONDS = 60
MAX_INTERVAL_SECONDS = 86400
MAX_BACKOFF_EXPONENT = 6
# AppSetting key stamped every time the Beat tick fires (see scan.py). The
# tick runs every 60s; the UI flags the scheduler as stalled if the last
# stamp is older than a few minutes.
SCHEDULER_LAST_TICK_KEY = "scheduler_last_tick_at"
# AppSetting key prefix for per-platform rate-limit cooldowns. When a
# download surfaces ErrorType.RATE_LIMITED, every other source on the same
# platform is deferred for PLATFORM_RATE_LIMIT_COOLDOWN_SECONDS so the next
# scan tick doesn't fire a burst of due same-platform sources back into the
# same limit. Per-source consecutive_failures backoff still applies on top
# of this — but this is PREVENTIVE (kills the same-tick burst from N due
# sources hammering the platform at once), while consecutive_failures is
# REACTIVE (slows the offender down over many cycles). Operator-confirmed
# 2026-05-30.
PLATFORM_COOLDOWN_KEY_PREFIX = "platform_cooldown:"
PLATFORM_RATE_LIMIT_COOLDOWN_SECONDS = 900 # 15 min
def compute_effective_interval(
source: Source, artist: Artist, settings: ImportSettings,
) -> int:
"""Return the seconds between scheduled checks for one source.
Precedence: source.check_interval_override > artist.check_interval_seconds
> settings.download_schedule_default_seconds. Multiplied by
2 ** min(consecutive_failures, MAX_BACKOFF_EXPONENT) and clamped to
[MIN_INTERVAL_SECONDS, MAX_INTERVAL_SECONDS].
"""
base = (
source.check_interval_override
or artist.check_interval_seconds
or settings.download_schedule_default_seconds
)
exponent = min(max(0, source.consecutive_failures or 0), MAX_BACKOFF_EXPONENT)
factor = 2 ** exponent
raw = base * factor
return max(MIN_INTERVAL_SECONDS, min(MAX_INTERVAL_SECONDS, raw))
async def set_platform_cooldown(
session: AsyncSession, platform: str,
seconds: int = PLATFORM_RATE_LIMIT_COOLDOWN_SECONDS,
) -> None:
"""Stamp a cooldown expiry on the given platform so select_due_sources
skips every source on that platform until it expires.
Called when a download surfaces ErrorType.RATE_LIMITED so the other
sources on the same platform don't all retry into the same rate limit.
Caller is responsible for committing the session.
Uses INSERT...ON CONFLICT DO UPDATE so two concurrent workers hitting
the same platform's rate limit don't race: a SELECT-then-INSERT pattern
would let the loser's whole transaction (including the source-health
update + event finalize) roll back on a unique-violation, stranding
that event. Atomic upsert avoids that.
"""
now = datetime.now(UTC)
expires_at = (now + timedelta(seconds=seconds)).isoformat()
key = f"{PLATFORM_COOLDOWN_KEY_PREFIX}{platform}"
stmt = pg_insert(AppSetting.__table__).values(
key=key, value=expires_at, updated_at=now,
).on_conflict_do_update(
index_elements=["key"],
set_={"value": expires_at, "updated_at": now},
)
await session.execute(stmt)
async def _platforms_in_cooldown(session: AsyncSession) -> dict[str, datetime]:
"""Return {platform: expires_at} for platforms whose cooldown is still
in the future. Expired rows are ignored (a future maintenance sweep can
delete them; they don't affect routing decisions on their own)."""
rows = (await session.execute(
select(AppSetting.key, AppSetting.value)
.where(AppSetting.key.startswith(PLATFORM_COOLDOWN_KEY_PREFIX))
)).all()
if not rows:
return {}
now = datetime.now(UTC)
active: dict[str, datetime] = {}
for key, value in rows:
try:
expires_at = datetime.fromisoformat(value)
except (ValueError, TypeError):
continue
if expires_at > now:
active[key[len(PLATFORM_COOLDOWN_KEY_PREFIX):]] = expires_at
return active
async def select_due_sources(session: AsyncSession) -> list[Source]:
"""Sources where (enabled, artist.auto_check) and now >= last_checked_at + effective_interval.
Never-checked sources (last_checked_at IS NULL) are always due. Sources
whose platform is currently in a rate-limit cooldown are excluded — the
cooldown is the preventive half of the burst-prevention pair (per-source
consecutive_failures backoff handles the offending source itself).
"""
rows = (await session.execute(
select(Source)
.options(selectinload(Source.artist))
.join(Artist, Source.artist_id == Artist.id)
.where(Source.enabled.is_(True))
.where(Artist.auto_check.is_(True))
)).scalars().all()
cooldowns = await _platforms_in_cooldown(session)
settings = await ImportSettings.load(session)
now = datetime.now(UTC)
due: list[Source] = []
for s in rows:
if s.platform in cooldowns:
continue
interval = compute_effective_interval(s, s.artist, settings)
if s.last_checked_at is None:
due.append(s)
continue
elapsed = (now - s.last_checked_at).total_seconds()
if elapsed >= interval:
due.append(s)
return due
def compute_next_check_at(
source: Source, artist: Artist, settings: ImportSettings,
) -> datetime | None:
"""Return the projected datetime of the next check, or None if never checked."""
if source.last_checked_at is None:
return None
interval = compute_effective_interval(source, artist, settings)
return source.last_checked_at + timedelta(seconds=interval)
async def record_tick(session: AsyncSession) -> None:
"""Stamp the current time on the SCHEDULER_LAST_TICK_KEY AppSetting.
Called once per Beat tick so the UI can prove the scheduler is alive.
Commits its own write so the stamp survives even if the rest of the
tick errors out.
"""
now_iso = datetime.now(UTC).isoformat()
row = (await session.execute(
select(AppSetting).where(AppSetting.key == SCHEDULER_LAST_TICK_KEY)
)).scalar_one_or_none()
if row is None:
session.add(AppSetting(key=SCHEDULER_LAST_TICK_KEY, value=now_iso))
else:
row.value = now_iso
await session.commit()
async def scheduler_status(session: AsyncSession) -> dict:
"""Summarise scheduler health for the dashboard.
Returns last_tick_at (when Beat last fired), next_due_at (earliest
upcoming scheduled check across enabled auto-check sources), due_now
(how many are due right now), and auto_sources (total under schedule).
"""
last_tick_at = (await session.execute(
select(AppSetting.value).where(AppSetting.key == SCHEDULER_LAST_TICK_KEY)
)).scalar_one_or_none()
rows = (await session.execute(
select(Source)
.options(selectinload(Source.artist))
.join(Artist, Source.artist_id == Artist.id)
.where(Source.enabled.is_(True))
.where(Artist.auto_check.is_(True))
)).scalars().all()
settings = await ImportSettings.load(session)
now = datetime.now(UTC)
due_now = 0
next_due_at: datetime | None = None
for s in rows:
if s.last_checked_at is None:
due_now += 1
continue
nca = compute_next_check_at(s, s.artist, settings)
if nca is None or nca <= now:
due_now += 1
elif next_due_at is None or nca < next_due_at:
next_due_at = nca
cooldowns = await _platforms_in_cooldown(session)
return {
"last_tick_at": last_tick_at,
"next_due_at": next_due_at.isoformat() if next_due_at else None,
"due_now": due_now,
"auto_sources": len(rows),
"platform_cooldowns": {p: dt.isoformat() for p, dt in cooldowns.items()},
}