bvandeusen
c64261593d
Deploys (docker SIGTERM→SIGKILL, default 10s) were killing Celery jobs mid-flight. Give in-flight work room to drain and make interrupted work resume cleanly instead of stalling. - docker-compose.yml: stop_grace_period per lane (web 30s / worker 90s / scheduler 60s / maintenance-long 180s / ml-worker 120s) so warm shutdown can actually drain before SIGKILL. - celery_app.py: task_reject_on_worker_lost=True — a task killed past the grace window is re-queued (safe: idempotent + chunked, recovery sweeps re-drive stragglers). - interpreter_client.py: map 429/5xx (502/503/504) → InterpreterUnavailable and parse Retry-After (delta-seconds or HTTP-date); a draining Interpreter behind a reverse proxy no longer raises an opaque HTTPError. - translation.py: thread retry_after out of _translate_batch; retranslate_posts resumes after the Retry-After hint (or 60s default, capped 900s) on an interrupt with _reset_done=True, self-terminating via the health gate. - tests: 429/5xx mapping + Retry-After parse; interrupt-resume + default backoff. No migration. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
288 lines
14 KiB
Python
288 lines
14 KiB
Python
"""Celery configuration with separate queue lanes.
|
||
|
||
Queues:
|
||
import — filesystem import path (FC-2)
|
||
ml — WD14 + SigLIP inference (FC-2; runs in the ml-worker image)
|
||
thumbnail — image and video thumbnail generation (FC-2)
|
||
download — gallery-dl tasks (FC-3)
|
||
scan — periodic source checks (FC-3) — kept separate so long imports
|
||
don't starve the scheduler
|
||
maintenance — recovery sweeps, pHash backfill, GPU-queue coordination, etc.
|
||
default — anything not explicitly routed
|
||
"""
|
||
|
||
from celery import Celery
|
||
|
||
from .config import get_config
|
||
|
||
|
||
def make_celery() -> Celery:
|
||
cfg = get_config()
|
||
app = Celery(
|
||
"fabledcurator",
|
||
broker=cfg.celery_broker_url,
|
||
backend=cfg.celery_result_backend,
|
||
include=[
|
||
"backend.app.tasks.smoke",
|
||
"backend.app.tasks.scan",
|
||
"backend.app.tasks.import_file",
|
||
"backend.app.tasks.thumbnail",
|
||
"backend.app.tasks.maintenance",
|
||
"backend.app.tasks.ml",
|
||
"backend.app.tasks.gpu_queue",
|
||
"backend.app.tasks.download",
|
||
"backend.app.tasks.external",
|
||
"backend.app.tasks.backup",
|
||
"backend.app.tasks.admin",
|
||
"backend.app.tasks.library_audit",
|
||
"backend.app.tasks.translation",
|
||
],
|
||
)
|
||
app.conf.update(
|
||
task_default_queue="default",
|
||
task_routes={
|
||
"backend.app.tasks.import_file.*": {"queue": "import"},
|
||
"backend.app.tasks.ml.*": {"queue": "ml"},
|
||
# GPU-queue coordination (backfill enqueues, orphan recovery,
|
||
# reprocess) is pure DB work — it rides the maintenance quick lane
|
||
# so the GPU agent pipeline works even on stacks that drop the
|
||
# (now-optional, B3) ml-worker container entirely.
|
||
"backend.app.tasks.gpu_queue.*": {"queue": "maintenance"},
|
||
"backend.app.tasks.thumbnail.*": {"queue": "thumbnail"},
|
||
"backend.app.tasks.download.*": {"queue": "download"},
|
||
# External file-host fetches are downloads — same lane (they can run
|
||
# long, but the download worker already tolerates long backfills).
|
||
"backend.app.tasks.external.*": {"queue": "download"},
|
||
"backend.app.tasks.scan.*": {"queue": "scan"},
|
||
# `maintenance` is the QUICK lane — recovery sweeps, vacuum, cleanup
|
||
# (concurrency-1 on the scheduler). The long one-shots (DB backups,
|
||
# library audits, admin maintenance: normalize/re-extract/cascade-
|
||
# delete) run on a SEPARATE `maintenance_long` lane + worker so they
|
||
# can never starve the quick self-healing sweeps (operator-flagged
|
||
# 2026-06-07: a 2h audit blocked vacuum/backup/normalize for hours).
|
||
"backend.app.tasks.maintenance.*": {"queue": "maintenance"},
|
||
"backend.app.tasks.backup.*": {"queue": "maintenance_long"},
|
||
"backend.app.tasks.admin.*": {"queue": "maintenance_long"},
|
||
"backend.app.tasks.library_audit.*": {"queue": "maintenance_long"},
|
||
# Translation backfill hits the LLM (~1–6s/item) → the long lane so it
|
||
# never starves the quick self-healing sweeps (#143).
|
||
"backend.app.tasks.translation.*": {"queue": "maintenance_long"},
|
||
},
|
||
# Heavy ML tasks need fair dispatch — see ImageRepo's precedent.
|
||
task_acks_late=True,
|
||
# Deploy graceful-shutdown safety: with acks_late, a task killed because
|
||
# it outran the container's stop-grace window (SIGKILL) is re-queued
|
||
# rather than silently lost. Safe because our long tasks are idempotent +
|
||
# chunked (translation per-post commit, downloads terminal-status, audits
|
||
# chunk) and the 5-min recovery sweeps re-drive anything left non-terminal
|
||
# — a re-run resumes cleanly and never corrupts. No redeliver-loop risk:
|
||
# heavy GPU work is tombstoned via gpu_queue, not run inline in a worker.
|
||
task_reject_on_worker_lost=True,
|
||
worker_prefetch_multiplier=1,
|
||
# Broker resilience (2026-06-24): a swarm overlay-network blip after a
|
||
# redeploy left Redis healthy but transiently unreachable, and a worker
|
||
# starting in that window crash-looped on the initial broker connect
|
||
# (kombu OperationalError) instead of waiting it out — needing a manual
|
||
# Redis reset to recover. Retry the broker FOREVER (None) on startup and
|
||
# at runtime so a transient outage self-heals when routing returns,
|
||
# rather than the worker exiting.
|
||
broker_connection_retry_on_startup=True,
|
||
broker_connection_retry=True,
|
||
broker_connection_max_retries=None,
|
||
# Redis-transport socket options (apply to the BROKER connection): a
|
||
# short connect timeout + TCP keepalive so a dead/blocked socket is
|
||
# noticed and retried, and a periodic health check that proactively
|
||
# reconnects a live worker through a network hiccup.
|
||
broker_transport_options={
|
||
"socket_connect_timeout": 5,
|
||
"socket_timeout": 30,
|
||
"socket_keepalive": True,
|
||
"retry_on_timeout": True,
|
||
"health_check_interval": 30,
|
||
},
|
||
# Same hardening for the Redis RESULT backend (separate connection pool).
|
||
redis_socket_connect_timeout=5,
|
||
redis_socket_timeout=30,
|
||
redis_socket_keepalive=True,
|
||
redis_retry_on_timeout=True,
|
||
redis_backend_health_check_interval=30,
|
||
beat_schedule={
|
||
"recover-interrupted-tasks": {
|
||
"task": "backend.app.tasks.maintenance.recover_interrupted_tasks",
|
||
"schedule": 300.0, # every 5 minutes
|
||
},
|
||
"cleanup-old-tasks": {
|
||
"task": "backend.app.tasks.maintenance.cleanup_old_tasks",
|
||
"schedule": 86400.0, # daily
|
||
},
|
||
"train-heads-nightly": {
|
||
"task": "backend.app.tasks.ml.scheduled_train_heads",
|
||
"schedule": 86400.0, # passive cadence; manual retrain stays available
|
||
},
|
||
"refresh-character-prototypes": {
|
||
"task": "backend.app.tasks.ml.refresh_character_prototypes",
|
||
"schedule": 900.0, # ~15 min; cheap global-gate no-op when idle (#1317)
|
||
},
|
||
"reconcile-character-prototypes-nightly": {
|
||
"task": "backend.app.tasks.ml.refresh_character_prototypes",
|
||
"schedule": 86400.0, # nightly FULL reconcile (belt-and-suspenders)
|
||
"args": (True,), # full=True
|
||
},
|
||
"apply-head-tags-daily": {
|
||
"task": "backend.app.tasks.ml.scheduled_apply_head_tags",
|
||
"schedule": 86400.0, # no-op unless head_auto_apply_enabled
|
||
},
|
||
"recover-orphaned-gpu-jobs": {
|
||
"task": "backend.app.tasks.gpu_queue.recover_orphaned_gpu_jobs",
|
||
"schedule": 60.0, # quick pickup of work a dead agent orphaned
|
||
},
|
||
"triage-gpu-errors": {
|
||
"task": "backend.app.tasks.maintenance.triage_gpu_errors",
|
||
"schedule": 900.0, # probe errored jobs' files → defect/file_ok
|
||
},
|
||
"enqueue-ccip-backfill-hourly": {
|
||
"task": "backend.app.tasks.gpu_queue.enqueue_gpu_backfill",
|
||
"schedule": 3600.0, # auto-feed NEW images; errored are
|
||
"args": ("ccip",), # tombstoned — retry is the button only
|
||
},
|
||
"enqueue-siglip-backfill-daily": {
|
||
"task": "backend.app.tasks.gpu_queue.enqueue_gpu_backfill",
|
||
"schedule": 86400.0, # drain the concept-crop back-catalogue
|
||
"args": ("siglip",), # (errored are tombstoned, not retried)
|
||
},
|
||
"enqueue-embed-backfill-daily": {
|
||
"task": "backend.app.tasks.gpu_queue.enqueue_gpu_backfill",
|
||
"schedule": 86400.0, # whole-image re-embed under the current
|
||
"args": ("embed",), # model (an operator swap) drains via agent
|
||
},
|
||
"ccip-auto-apply-daily": {
|
||
"task": "backend.app.tasks.ml.scheduled_ccip_auto_apply",
|
||
"schedule": 86400.0, # no-op unless ccip_auto_apply_enabled
|
||
},
|
||
"retract-auto-tags-daily": {
|
||
"task": "backend.app.tasks.ml.scheduled_retract_auto_tags",
|
||
"schedule": 86400.0, # soft auto-apply: drop auto-tags now below
|
||
# their threshold (m139); no-op unless the auto-apply switch is on
|
||
},
|
||
"presentation-auto-apply-daily": {
|
||
"task": "backend.app.tasks.ml.scheduled_presentation_auto_apply",
|
||
"schedule": 86400.0, # auto-hide banner/editor chrome (#141);
|
||
# no-op unless presentation_auto_apply_enabled
|
||
},
|
||
"prune-presentation-reviews-daily": {
|
||
"task": "backend.app.tasks.ml.prune_presentation_reviews",
|
||
"schedule": 86400.0, # retention: drop resolved review flags >30d
|
||
},
|
||
"translate-posts-daily": {
|
||
"task": "backend.app.tasks.translation.translate_posts",
|
||
"schedule": 86400.0, # no-op unless translation configured + healthy
|
||
},
|
||
"snapshot-head-metrics-daily": {
|
||
"task": "backend.app.tasks.maintenance.snapshot_head_metrics",
|
||
"schedule": 86400.0,
|
||
},
|
||
"integrity-verify-weekly": {
|
||
"task": "backend.app.tasks.maintenance.verify_integrity",
|
||
"schedule": 604800.0, # weekly
|
||
},
|
||
"fc3d-tick-due-sources": {
|
||
"task": "backend.app.tasks.scan.tick_due_sources",
|
||
"schedule": 60.0, # every minute
|
||
},
|
||
"fc3d-cleanup-download-events": {
|
||
"task": "backend.app.tasks.maintenance.cleanup_old_download_events",
|
||
"schedule": 86400.0, # daily
|
||
},
|
||
"recover-stalled-download-events": {
|
||
"task": "backend.app.tasks.maintenance.recover_stalled_download_events",
|
||
"schedule": 300.0, # every 5 min, matches recover-interrupted-tasks
|
||
},
|
||
"recover-stalled-task-runs": {
|
||
"task": "backend.app.tasks.maintenance.recover_stalled_task_runs",
|
||
"schedule": 300.0, # every 5 min, matches recover-interrupted-tasks
|
||
},
|
||
"prune-task-runs": {
|
||
"task": "backend.app.tasks.maintenance.prune_task_runs",
|
||
"schedule": 86400.0, # daily
|
||
},
|
||
"vacuum-analyze": {
|
||
"task": "backend.app.tasks.maintenance.vacuum_analyze",
|
||
"schedule": 604800.0, # weekly — reclaim dead-tuple bloat + refresh stats
|
||
},
|
||
"fc3h-backup-db-nightly": {
|
||
"task": "backend.app.tasks.backup.backup_db_nightly",
|
||
"schedule": 3600.0, # hourly tick; task self-gates on configured UTC hour
|
||
},
|
||
"fc3h-prune-backups": {
|
||
"task": "backend.app.tasks.backup.prune_backups",
|
||
"schedule": 86400.0, # daily
|
||
},
|
||
# Audit 2026-06-02 — three new per-entity recovery sweeps.
|
||
# Each runs every 5 min like the other recover_stalled_*
|
||
# sweeps; each is a no-op when nothing is stuck.
|
||
"recover-stalled-backup-runs": {
|
||
"task": "backend.app.tasks.maintenance.recover_stalled_backup_runs",
|
||
"schedule": 300.0,
|
||
},
|
||
"recover-stalled-library-audit-runs": {
|
||
"task": "backend.app.tasks.maintenance.recover_stalled_library_audit_runs",
|
||
"schedule": 300.0,
|
||
},
|
||
"recover-stalled-head-training-runs": {
|
||
"task": "backend.app.tasks.maintenance.recover_stalled_head_training_runs",
|
||
"schedule": 300.0,
|
||
},
|
||
"recover-stalled-head-auto-apply-runs": {
|
||
"task": "backend.app.tasks.maintenance.recover_stalled_head_auto_apply_runs",
|
||
"schedule": 300.0,
|
||
},
|
||
"recover-stalled-import-batches": {
|
||
"task": "backend.app.tasks.maintenance.recover_stalled_import_batches",
|
||
"schedule": 300.0,
|
||
},
|
||
# Audit 2026-06-02 — daily retention for two entities
|
||
# whose terminal rows otherwise accumulate forever.
|
||
"prune-library-audit-runs": {
|
||
"task": "backend.app.tasks.maintenance.prune_library_audit_runs",
|
||
"schedule": 86400.0,
|
||
},
|
||
"prune-import-batches": {
|
||
"task": "backend.app.tasks.maintenance.prune_import_batches",
|
||
"schedule": 86400.0,
|
||
},
|
||
# Audit 2026-06-02 — backfill_thumbnails's docstring claimed
|
||
# "periodic Beat" but the entry was never registered, so the
|
||
# library got no self-healing thumbnail repair; only the
|
||
# manual admin-UI button fired it. Daily cadence is gentle
|
||
# (the task is idempotent and only enqueues regen for rows
|
||
# whose stored thumbnails are missing or corrupt).
|
||
"backfill-thumbnails-daily": {
|
||
"task": "backend.app.tasks.thumbnail.backfill_thumbnails",
|
||
"schedule": 86400.0,
|
||
},
|
||
# External file-host downloads (#830): a steady sweep catches links
|
||
# the post-download hook missed (worker down, etc.); recovery re-tries
|
||
# dead links daily; retention prunes long-dead rows.
|
||
"extdl-sweep": {
|
||
"task": "backend.app.tasks.external.sweep_external_links",
|
||
"schedule": 600.0, # every 10 min
|
||
},
|
||
"extdl-recover-daily": {
|
||
"task": "backend.app.tasks.external.recover_external_links",
|
||
"schedule": 86400.0,
|
||
},
|
||
"extdl-prune-daily": {
|
||
"task": "backend.app.tasks.external.prune_external_links",
|
||
"schedule": 86400.0,
|
||
},
|
||
},
|
||
timezone="UTC",
|
||
)
|
||
# FC-3i: register task_run signal handlers (side-effect import).
|
||
from . import celery_signals # noqa: F401
|
||
|
||
return app
|
||
|
||
|
||
celery = make_celery()
|