diff options
Diffstat (limited to 'synapse/handlers/federation_event.py')
| -rw-r--r-- | synapse/handlers/federation_event.py | 82 |
1 files changed, 68 insertions, 14 deletions
diff --git a/synapse/handlers/federation_event.py b/synapse/handlers/federation_event.py index da319943cc..06e41b5cc0 100644 --- a/synapse/handlers/federation_event.py +++ b/synapse/handlers/federation_event.py @@ -44,6 +44,7 @@ from synapse.api.errors import ( AuthError, Codes, FederationError, + FederationPullAttemptBackoffError, HttpResponseException, RequestSendFailed, SynapseError, @@ -414,7 +415,9 @@ class FederationEventHandler: # First, precalculate the joined hosts so that the federation sender doesn't # need to. - await self._event_creation_handler.cache_joined_hosts_for_event(event, context) + await self._event_creation_handler.cache_joined_hosts_for_events( + [(event, context)] + ) await self._check_for_soft_fail(event, context=context, origin=origin) await self._run_push_actions_and_persist_event(event, context) @@ -565,6 +568,9 @@ class FederationEventHandler: event: partial-state event to be de-partial-stated Raises: + FederationPullAttemptBackoffError if we are are deliberately not attempting + to pull the given event over federation because we've already done so + recently and are backing off. FederationError if we fail to request state from the remote server. """ logger.info("Updating state for %s", event.event_id) @@ -792,9 +798,42 @@ class FederationEventHandler: ], ) + # Check if we already any of these have these events. + # Note: we currently make a lookup in the database directly here rather than + # checking the event cache, due to: + # https://github.com/matrix-org/synapse/issues/13476 + existing_events_map = await self._store._get_events_from_db( + [event.event_id for event in events] + ) + + new_events = [] + for event in events: + event_id = event.event_id + + # If we've already seen this event ID... + if event_id in existing_events_map: + existing_event = existing_events_map[event_id] + + # ...and the event itself was not previously stored as an outlier... + if not existing_event.event.internal_metadata.is_outlier(): + # ...then there's no need to persist it. We have it already. + logger.info( + "_process_pulled_event: Ignoring received event %s which we " + "have already seen", + event.event_id, + ) + continue + + # While we have seen this event before, it was stored as an outlier. + # We'll now persist it as a non-outlier. + logger.info("De-outliering event %s", event_id) + + # Continue on with the events that are new to us. + new_events.append(event) + # We want to sort these by depth so we process them and # tell clients about them in order. - sorted_events = sorted(events, key=lambda x: x.depth) + sorted_events = sorted(new_events, key=lambda x: x.depth) for ev in sorted_events: with nested_logging_context(ev.event_id): await self._process_pulled_event(origin, ev, backfilled=backfilled) @@ -846,18 +885,6 @@ class FederationEventHandler: event_id = event.event_id - existing = await self._store.get_event( - event_id, allow_none=True, allow_rejected=True - ) - if existing: - if not existing.internal_metadata.is_outlier(): - logger.info( - "_process_pulled_event: Ignoring received event %s which we have already seen", - event_id, - ) - return - logger.info("De-outliering event %s", event_id) - try: self._sanity_check_event(event) except SynapseError as err: @@ -899,6 +926,18 @@ class FederationEventHandler: context, backfilled=backfilled, ) + except FederationPullAttemptBackoffError as exc: + # Log a warning about why we failed to process the event (the error message + # for `FederationPullAttemptBackoffError` is pretty good) + logger.warning("_process_pulled_event: %s", exc) + # We do not record a failed pull attempt when we backoff fetching a missing + # `prev_event` because not being able to fetch the `prev_events` just means + # we won't be able to de-outlier the pulled event. But we can still use an + # `outlier` in the state/auth chain for another event. So we shouldn't stop + # a downstream event from trying to pull it. + # + # This avoids a cascade of backoff for all events in the DAG downstream from + # one event backoff upstream. except FederationError as e: await self._store.record_event_failed_pull_attempt( event.room_id, event_id, str(e) @@ -945,6 +984,9 @@ class FederationEventHandler: The event context. Raises: + FederationPullAttemptBackoffError if we are are deliberately not attempting + to pull the given event over federation because we've already done so + recently and are backing off. FederationError if we fail to get the state from the remote server after any missing `prev_event`s. """ @@ -955,6 +997,18 @@ class FederationEventHandler: seen = await self._store.have_events_in_timeline(prevs) missing_prevs = prevs - seen + # If we've already recently attempted to pull this missing event, don't + # try it again so soon. Since we have to fetch all of the prev_events, we can + # bail early here if we find any to ignore. + prevs_to_ignore = await self._store.get_event_ids_to_not_pull_from_backoff( + room_id, missing_prevs + ) + if len(prevs_to_ignore) > 0: + raise FederationPullAttemptBackoffError( + event_ids=prevs_to_ignore, + message=f"While computing context for event={event_id}, not attempting to pull missing prev_event={prevs_to_ignore[0]} because we already tried to pull recently (backing off).", + ) + if not missing_prevs: return await self._state_handler.compute_event_context(event) |