Private
Public Access
Add an atomic per-feed claim to poll_due_feeds (T1)
poll_due_feeds scanned for due feeds and dispatched fetch_feed without marking them claimed, so overlapping beat ticks or a slow-running fetch could dispatch the same feed twice, racing on ETag/status/error- count writes. Feed.claimed_at is now set via an UPDATE ... WHERE claimed_at IS NULL OR claimed_at < stale-cutoff, so only one caller's UPDATE can ever match a given row; fetch_feed clears it when done. A claim older than CLAIM_STALE_MINUTES is treated as abandoned so a worker dying mid-fetch doesn't wedge the feed forever. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
1 parent
d7b433e580
commit
b7d9ee672c
4 files changed
+108
-4
No files matched your search
+29
-4
@@ -4,6 +4,7 @@ from io import BytesIO
|
||||
|
||||
from celery import shared_task
|
||||
from django.contrib.auth import get_user_model
|
||||
from django.db.models import Q
|
||||
from django.utils import timezone
|
||||
|
||||
from apps.articles.tasks import apply_filter_rules_for_feed
|
||||
@@ -14,13 +15,23 @@ from .services.fetcher import effective_interval_minutes, fetch_and_ingest
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# How long a claimed-but-unfinished fetch blocks the same feed from being
|
||||
# claimed again — must comfortably exceed FETCH_TIMEOUT_SECONDS plus parse/
|
||||
# ingest time, so a slow-but-healthy fetch is never raced by the next tick,
|
||||
# while a worker that died mid-fetch doesn't wedge the feed forever.
|
||||
CLAIM_STALE_MINUTES = 10
|
||||
|
||||
|
||||
@shared_task
|
||||
def poll_due_feeds():
|
||||
"""Find every active Feed whose polling interval has elapsed and
|
||||
dispatch a fetch_feed task for each — fan-out happens here, not via one
|
||||
Celery Beat entry per feed.
|
||||
"""Find every active Feed whose polling interval has elapsed, atomically
|
||||
claim it (so overlapping beat ticks or a slow-running previous fetch
|
||||
can't dispatch the same feed twice), and dispatch a fetch_feed task for
|
||||
each claimed feed — fan-out happens here, not via one Celery Beat entry
|
||||
per feed.
|
||||
"""
|
||||
now = timezone.now()
|
||||
claim_stale_before = now - timedelta(minutes=CLAIM_STALE_MINUTES)
|
||||
due_feed_ids = [
|
||||
feed.id
|
||||
for feed in Feed.objects.filter(is_active=True).only(
|
||||
@@ -28,9 +39,22 @@ def poll_due_feeds():
|
||||
)
|
||||
if _is_due(feed)
|
||||
]
|
||||
claimed_ids = []
|
||||
for feed_id in due_feed_ids:
|
||||
# The UPDATE's WHERE clause re-checks staleness at the database
|
||||
# level: it only claims rows nobody else has already claimed more
|
||||
# recently than CLAIM_STALE_MINUTES ago, so two workers racing this
|
||||
# same loop can't both get rowcount=1 for the same feed.
|
||||
claimed = (
|
||||
Feed.objects.filter(id=feed_id, is_active=True)
|
||||
.filter(Q(claimed_at__isnull=True) | Q(claimed_at__lt=claim_stale_before))
|
||||
.update(claimed_at=now)
|
||||
)
|
||||
if claimed:
|
||||
claimed_ids.append(feed_id)
|
||||
for feed_id in claimed_ids:
|
||||
fetch_feed.delay(feed_id)
|
||||
return len(due_feed_ids)
|
||||
return len(claimed_ids)
|
||||
|
||||
|
||||
def _is_due(feed: Feed) -> bool:
|
||||
@@ -48,6 +72,7 @@ def fetch_feed(feed_id: int):
|
||||
return None
|
||||
|
||||
result = fetch_and_ingest(feed)
|
||||
feed.claimed_at = None
|
||||
feed.save()
|
||||
|
||||
changed_article_ids = result.new_article_ids + result.updated_article_ids
|
||||
|
||||
Reference in new issue
Block a user