Isolate unexpected fetch failures and harden task durability (T2)

fetch_feed had no time limit and no handling for anything beyond the
network/parse errors fetch_and_ingest already catches internally — an
unexpected exception (a parser/sanitizer bug, a DB error) crashed the
task with no error recorded on the Feed, the claim left held for the
full CLAIM_STALE_MINUTES, and no visibility beyond a bare traceback.
fetch_feed now catches that, records it the same way a handled failure
would be (reusing fetcher.record_fetch_error, promoted from a private
helper), clears the claim, and re-raises so Celery still marks the task
FAILED. soft_time_limit/time_limit bound a single fetch that somehow
outruns FETCH_TIMEOUT_SECONDS + ssrf_guard's response cap during
parsing/ingestion.

Also: a worker process killed mid-task (OOM, deploy restart, crash)
previously lost that task silently — Celery's default is to ack a
message the moment a worker *starts* it. CELERY_TASK_ACKS_LATE +
CELERY_TASK_REJECT_ON_WORKER_LOST (config/settings/base.py) make the
message redeliverable instead, and CELERY_WORKER_PREFETCH_MULTIPLIER=1
keeps a worker from grabbing a batch of tasks it could lose all at once.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
ksmithandClaude Sonnet 5 committed 2026-10-31 12:46:29 -06:00
1 parent 0466ccc334
commit 64f25789f5
4 files changed
+103 -9

No files matched your search

+28 -7
View File
@@ -31,6 +31,15 @@ FETCH_TIMEOUT_SECONDS = 15
MAX_BACKOFF_MINUTES = 24 * 60 MAX_BACKOFF_MINUTES = 24 * 60
USER_AGENT = "Evection/0.1 (+https://github.com/; self-hosted RSS reader)" USER_AGENT = "Evection/0.1 (+https://github.com/; self-hosted RSS reader)"
# ssrf_guard.MAX_RESPONSE_BYTES already bounds the raw download; these
# bound what a single poll does *with* that response — a feed within the
# byte cap can still carry an unreasonable number of entries, or one
# entry with an unreasonably large body, and both cost real CPU/DB time
# (nh3 sanitization, an Article row/UPDATE) per entry processed.
MAX_ENTRIES_PER_POLL = 200
MAX_CONTENT_HTML_INPUT_CHARS = 200_000 # bounds sanitizer cost, not just storage
MAX_CONTENT_HTML_CHARS = 50_000 # bounds what's actually stored/rendered
ALLOWED_TAGS = { ALLOWED_TAGS = {
"a", "a",
"p", "p",
@@ -83,7 +92,9 @@ class FetchResult:
def sanitize_html(raw_html: str) -> str: def sanitize_html(raw_html: str) -> str:
if not raw_html: if not raw_html:
return "" return ""
return nh3.clean(raw_html, tags=ALLOWED_TAGS, attributes=ALLOWED_ATTRIBUTES, link_rel=None) bounded = raw_html[:MAX_CONTENT_HTML_INPUT_CHARS]
cleaned = nh3.clean(bounded, tags=ALLOWED_TAGS, attributes=ALLOWED_ATTRIBUTES, link_rel=None)
return cleaned[:MAX_CONTENT_HTML_CHARS]
def _content_hash(title: str, content_html: str) -> str: def _content_hash(title: str, content_html: str) -> str:
@@ -144,10 +155,10 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
response = safe_get(feed.feed_url, headers=headers, timeout=FETCH_TIMEOUT_SECONDS) response = safe_get(feed.feed_url, headers=headers, timeout=FETCH_TIMEOUT_SECONDS)
except SSRFBlocked as exc: except SSRFBlocked as exc:
feed.last_fetched_at = timezone.now() feed.last_fetched_at = timezone.now()
return _record_error(feed, f"Refused to fetch: {exc}") return record_fetch_error(feed, f"Refused to fetch: {exc}")
except requests.RequestException as exc: except requests.RequestException as exc:
feed.last_fetched_at = timezone.now() feed.last_fetched_at = timezone.now()
return _record_error(feed, f"Request failed: {exc}") return record_fetch_error(feed, f"Request failed: {exc}")
feed.last_fetched_at = timezone.now() feed.last_fetched_at = timezone.now()
@@ -159,12 +170,12 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
) )
if response.status_code >= 400: if response.status_code >= 400:
return _record_error(feed, f"HTTP {response.status_code}") return record_fetch_error(feed, f"HTTP {response.status_code}")
parsed = feedparser.parse(response.content) parsed = feedparser.parse(response.content)
if parsed.bozo and not parsed.entries: if parsed.bozo and not parsed.entries:
return _record_error(feed, f"Unparseable feed: {parsed.get('bozo_exception')}") return record_fetch_error(feed, f"Unparseable feed: {parsed.get('bozo_exception')}")
if parsed.bozo: if parsed.bozo:
logger.warning( logger.warning(
@@ -186,7 +197,17 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
new_ids: list[int] = [] new_ids: list[int] = []
updated_ids: list[int] = [] updated_ids: list[int] = []
for entry in parsed.entries: entries = parsed.entries
if len(entries) > MAX_ENTRIES_PER_POLL:
logger.warning(
"Feed %s: %d entries in one poll, only processing the first %d",
feed.feed_url,
len(entries),
MAX_ENTRIES_PER_POLL,
)
entries = entries[:MAX_ENTRIES_PER_POLL]
for entry in entries:
guid = _entry_guid(entry) guid = _entry_guid(entry)
title = (getattr(entry, "title", "") or "")[:1000] title = (getattr(entry, "title", "") or "")[:1000]
content_html = sanitize_html(_entry_content_html(entry)) content_html = sanitize_html(_entry_content_html(entry))
@@ -220,7 +241,7 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
) )
def _record_error(feed: Feed, message: str) -> FetchResult: def record_fetch_error(feed: Feed, message: str) -> FetchResult:
feed.last_fetch_status = Feed.STATUS_ERROR feed.last_fetch_status = Feed.STATUS_ERROR
feed.last_error_message = message[:2000] feed.last_error_message = message[:2000]
feed.fetch_error_count += 1 feed.fetch_error_count += 1
+31 -2
View File
@@ -11,7 +11,7 @@ from apps.articles.tasks import apply_filter_rules_for_feed
from .models import Feed from .models import Feed
from .opml import import_opml from .opml import import_opml
from .services.fetcher import effective_interval_minutes, fetch_and_ingest from .services.fetcher import effective_interval_minutes, fetch_and_ingest, record_fetch_error
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
@@ -64,14 +64,43 @@ def _is_due(feed: Feed) -> bool:
return feed.last_fetched_at <= timezone.now() - timedelta(minutes=interval) return feed.last_fetched_at <= timezone.now() - timedelta(minutes=interval)
@shared_task # Bounds a single feed's fetch+parse+ingest, independent of
# FETCH_TIMEOUT_SECONDS (apps.feeds.services.fetcher) which only covers
# the HTTP request itself: parsing/sanitizing/writing a large-but-under-
# the-byte-cap feed could still run long. soft_time_limit lets the
# except-Exception handler below record a normal feed error (and clear
# the claim) before the hard time_limit kills the worker process outright.
FETCH_FEED_SOFT_TIME_LIMIT = 60
FETCH_FEED_TIME_LIMIT = 90
@shared_task(time_limit=FETCH_FEED_TIME_LIMIT, soft_time_limit=FETCH_FEED_SOFT_TIME_LIMIT)
def fetch_feed(feed_id: int): def fetch_feed(feed_id: int):
try: try:
feed = Feed.objects.get(pk=feed_id, is_active=True) feed = Feed.objects.get(pk=feed_id, is_active=True)
except Feed.DoesNotExist: except Feed.DoesNotExist:
return None return None
try:
result = fetch_and_ingest(feed) result = fetch_and_ingest(feed)
except Exception:
# fetch_and_ingest already handles the expected failure modes
# (network errors, SSRF-blocked targets, unparseable feeds) by
# returning an error FetchResult rather than raising — anything
# that reaches here is unexpected (a parser/sanitizer bug, a DB
# error, this task's own soft time limit), so it's recorded the
# same way a handled failure would be rather than silently
# leaving the feed's status stale, the claim held for the full
# CLAIM_STALE_MINUTES, and no record of what happened. Re-raised
# afterward so Celery still marks the task FAILED (visible in
# worker logs/monitoring) instead of swallowing it.
logger.exception("Feed %s: unexpected error during fetch", feed.feed_url)
record_fetch_error(feed, "Unexpected error — see worker logs")
feed.last_fetched_at = timezone.now()
feed.claimed_at = None
feed.save()
raise
feed.claimed_at = None feed.claimed_at = None
feed.save() feed.save()
+19
View File
@@ -127,3 +127,22 @@ def test_fetch_feed_task_skips_inactive_feed():
@pytest.mark.django_db @pytest.mark.django_db
def test_fetch_feed_task_skips_missing_feed(): def test_fetch_feed_task_skips_missing_feed():
assert fetch_feed(999999) is None assert fetch_feed(999999) is None
@pytest.mark.django_db
def test_fetch_feed_task_records_error_and_clears_claim_on_unexpected_exception():
feed = Feed.objects.create(
feed_url="https://example.com/feed.xml",
claimed_at=timezone.now(),
fetch_error_count=0,
)
with patch("apps.feeds.tasks.fetch_and_ingest", side_effect=RuntimeError("boom")):
with pytest.raises(RuntimeError, match="boom"):
fetch_feed(feed.id)
feed.refresh_from_db()
assert feed.last_fetch_status == Feed.STATUS_ERROR
assert feed.fetch_error_count == 1
assert feed.claimed_at is None
assert feed.last_fetched_at is not None
+25
View File
@@ -106,9 +106,34 @@ EVECTION_SIGNUP_ENABLED = env.bool("EVECTION_SIGNUP_ENABLED", default=False)
EVECTION_MIN_FETCH_INTERVAL_MINUTES = env.int("EVECTION_MIN_FETCH_INTERVAL_MINUTES", default=15) EVECTION_MIN_FETCH_INTERVAL_MINUTES = env.int("EVECTION_MIN_FETCH_INTERVAL_MINUTES", default=15)
EVECTION_PWA_CACHE_VERSION = env.str("EVECTION_PWA_CACHE_VERSION", default="v1") EVECTION_PWA_CACHE_VERSION = env.str("EVECTION_PWA_CACHE_VERSION", default="v1")
# Redis-backed rather than Django's default per-process LocMemCache: login
# rate limiting (apps.accounts.views) must share counters across every
# gunicorn worker, not just whichever one happened to handle a given
# request. Redis is already a hard install requirement for Celery, so
# this adds no new infrastructure — just a distinct key prefix so cache
# keys can't collide with anything else sharing that Redis instance.
CACHES = {
"default": {
"BACKEND": "django.core.cache.backends.redis.RedisCache",
"LOCATION": env.str("REDIS_URL", default="redis://localhost:6379/0"),
"KEY_PREFIX": "evection-cache",
}
}
# Celery # Celery
CELERY_BROKER_URL = env.str("REDIS_URL", default="redis://localhost:6379/0") CELERY_BROKER_URL = env.str("REDIS_URL", default="redis://localhost:6379/0")
CELERY_RESULT_BACKEND = None CELERY_RESULT_BACKEND = None
CELERY_TASK_SERIALIZER = "json" CELERY_TASK_SERIALIZER = "json"
CELERY_ACCEPT_CONTENT = ["json"] CELERY_ACCEPT_CONTENT = ["json"]
CELERY_TIMEZONE = TIME_ZONE CELERY_TIMEZONE = TIME_ZONE
# Without these, a worker process killed mid-task (OOM, deploy restart,
# crash) silently loses that task: the default is to ack a message the
# moment a worker *starts* it, not when it finishes. acks_late + reject-
# on-worker-lost means the message is only consumed on completion (success
# or a handled failure) and is redelivered to another worker otherwise.
# prefetch_multiplier=1 keeps a worker from grabbing a batch of tasks it
# could similarly lose all at once.
CELERY_TASK_ACKS_LATE = True
CELERY_TASK_REJECT_ON_WORKER_LOST = True
CELERY_WORKER_PREFETCH_MULTIPLIER = 1