Merge pull request #3078 from matrix-org/erikj/federation_sender

Send federation events concurrently

synapse/federation/transaction_queue.py

@@ -169,7 +169,7 @@ class TransactionQueue(object):
             while True:
                 last_token = yield self.store.get_federation_out_pos("events")
                 next_token, events = yield self.store.get_all_new_events_stream(
-                    last_token, self._last_poked_id, limit=20,
+                    last_token, self._last_poked_id, limit=100,
                 )
 
                 logger.debug("Handling %s -> %s", last_token, next_token)
@@ -177,13 +177,15 @@ class TransactionQueue(object):
                 if not events and next_token >= self._last_poked_id:
                     break
 
-                for event in events:
+                @defer.inlineCallbacks
+                def handle_event(event):
                     # Only send events for this server.
                     send_on_behalf_of = event.internal_metadata.get_send_on_behalf_of()
                     is_mine = self.is_mine_id(event.event_id)
                     if not is_mine and send_on_behalf_of is None:
-                        continue
+                        return
 
+                    try:
                         # Get the state from before the event.
                         # We need to make sure that this is the state from before
                         # the event and not from after it.
@@ -195,6 +197,13 @@ class TransactionQueue(object):
                                 prev_id for prev_id, _ in event.prev_events
                             ],
                         )
+                    except Exception:
+                        logger.exception(
+                            "Failed to calculate hosts in room for event: %s",
+                            event.event_id,
+                        )
+                        return
+
                     destinations = set(destinations)
 
                     if send_on_behalf_of is not None:
@@ -207,6 +216,23 @@ class TransactionQueue(object):
 
                     self._send_pdu(event, destinations)
 
+                @defer.inlineCallbacks
+                def handle_room_events(events):
+                    for event in events:
+                        yield handle_event(event)
+
+                events_by_room = {}
+                for event in events:
+                    events_by_room.setdefault(event.room_id, []).append(event)
+
+                yield logcontext.make_deferred_yieldable(defer.gatherResults(
+                    [
+                        logcontext.run_in_background(handle_room_events, evs)
+                        for evs in events_by_room.itervalues()
+                    ],
+                    consumeErrors=True
+                ))
+
                 events_processed_counter.inc_by(len(events))
 
                 yield self.store.update_federation_out_pos(