Avoid creating events with huge numbers of prev_events

In most cases, we limit the number of prev_events for a given event to 10
events. This fixes a particular code path which created events with huge
numbers of prev_events.

2 files changed, 53 insertions, 38 deletions

diff --git a/synapse/handlers/message.py b/synapse/handlers/message.py
index 54cd691f91..21628a8540 100644
--- a/synapse/handlers/message.py
+++ b/synapse/handlers/message.py
@@ -37,7 +37,6 @@ from ._base import BaseHandler
 from canonicaljson import encode_canonical_json
 
 import logging
-import random
 import simplejson
 
 logger = logging.getLogger(__name__)
@@ -433,7 +432,7 @@ class EventCreationHandler(object):
 
     @defer.inlineCallbacks
     def create_event(self, requester, event_dict, token_id=None, txn_id=None,
-                     prev_event_ids=None):
+                     prev_events_and_hashes=None):
         """
         Given a dict from a client, create a new event.
 
@@ -447,7 +446,13 @@ class EventCreationHandler(object):
             event_dict (dict): An entire event
             token_id (str)
             txn_id (str)
-            prev_event_ids (list): The prev event ids to use when creating the event
+
+            prev_events_and_hashes (list[(str, dict[str, str], int)]|None):
+                the forward extremities to use as the prev_events for the
+                new event. For each event, a tuple of (event_id, hashes, depth)
+                where *hashes* is a map from algorithm to hash.
+
+                If None, they will be requested from the database.
 
         Returns:
             Tuple of created event (FrozenEvent), Context
@@ -485,7 +490,7 @@ class EventCreationHandler(object):
         event, context = yield self.create_new_client_event(
             builder=builder,
             requester=requester,
-            prev_event_ids=prev_event_ids,
+            prev_events_and_hashes=prev_events_and_hashes,
         )
 
         defer.returnValue((event, context))
@@ -588,39 +593,44 @@ class EventCreationHandler(object):
 
     @measure_func("create_new_client_event")
     @defer.inlineCallbacks
-    def create_new_client_event(self, builder, requester=None, prev_event_ids=None):
-        if prev_event_ids:
-            prev_events = yield self.store.add_event_hashes(prev_event_ids)
-            prev_max_depth = yield self.store.get_max_depth_of_events(prev_event_ids)
-            depth = prev_max_depth + 1
-        else:
-            latest_ret = yield self.store.get_latest_event_ids_and_hashes_in_room(
-                builder.room_id,
+    def create_new_client_event(self, builder, requester=None,
+                                prev_events_and_hashes=None):
+        """Create a new event for a local client
+
+        Args:
+            builder (EventBuilder):
+
+            requester (synapse.types.Requester|None):
+
+            prev_events_and_hashes (list[(str, dict[str, str], int)]|None):
+                the forward extremities to use as the prev_events for the
+                new event. For each event, a tuple of (event_id, hashes, depth)
+                where *hashes* is a map from algorithm to hash.
+
+                If None, they will be requested from the database.
+
+        Returns:
+            Deferred[(synapse.events.EventBase, synapse.events.snapshot.EventContext)]
+        """
+
+        if prev_events_and_hashes is not None:
+            assert len(prev_events_and_hashes) <= 10, \
+                "Attempting to create an event with %i prev_events" % (
+                    len(prev_events_and_hashes),
             )
+        else:
+            prev_events_and_hashes = \
+                yield self.store.get_prev_events_for_room(builder.room_id)
 
-            # We want to limit the max number of prev events we point to in our
-            # new event
-            if len(latest_ret) > 10:
-                # Sort by reverse depth, so we point to the most recent.
-                latest_ret.sort(key=lambda a: -a[2])
-                new_latest_ret = latest_ret[:5]
-
-                # We also randomly point to some of the older events, to make
-                # sure that we don't completely ignore the older events.
-                if latest_ret[5:]:
-                    sample_size = min(5, len(latest_ret[5:]))
-                    new_latest_ret.extend(random.sample(latest_ret[5:], sample_size))
-                latest_ret = new_latest_ret
-
-            if latest_ret:
-                depth = max([d for _, _, d in latest_ret]) + 1
-            else:
-                depth = 1
+        if prev_events_and_hashes:
+            depth = max([d for _, _, d in prev_events_and_hashes]) + 1
+        else:
+            depth = 1
 
-            prev_events = [
-                (event_id, prev_hashes)
-                for event_id, prev_hashes, _ in latest_ret
-            ]
+        prev_events = [
+            (event_id, prev_hashes)
+            for event_id, prev_hashes, _ in prev_events_and_hashes
+        ]
 
         builder.prev_events = prev_events
         builder.depth = depth
diff --git a/synapse/handlers/room_member.py b/synapse/handlers/room_member.py
index c45142d38d..714583f1d5 100644
--- a/synapse/handlers/room_member.py
+++ b/synapse/handlers/room_member.py
@@ -149,7 +149,7 @@ class RoomMemberHandler(object):
     @defer.inlineCallbacks
     def _local_membership_update(
         self, requester, target, room_id, membership,
-        prev_event_ids,
+        prev_events_and_hashes,
         txn_id=None,
         ratelimit=True,
         content=None,
@@ -175,7 +175,7 @@ class RoomMemberHandler(object):
             },
             token_id=requester.access_token_id,
             txn_id=txn_id,
-            prev_event_ids=prev_event_ids,
+            prev_events_and_hashes=prev_events_and_hashes,
         )
 
         # Check if this event matches the previous membership event for the user.
@@ -314,7 +314,12 @@ class RoomMemberHandler(object):
                     403, "Invites have been disabled on this server",
                 )
 
-        latest_event_ids = yield self.store.get_latest_event_ids_in_room(room_id)
+        prev_events_and_hashes = yield self.store.get_prev_events_for_room(
+            room_id,
+        )
+        latest_event_ids = (
+            event_id for (event_id, _, _) in prev_events_and_hashes
+        )
         current_state_ids = yield self.state_handler.get_current_state_ids(
             room_id, latest_event_ids=latest_event_ids,
         )
@@ -403,7 +408,7 @@ class RoomMemberHandler(object):
             membership=effective_membership_state,
             txn_id=txn_id,
             ratelimit=ratelimit,
-            prev_event_ids=latest_event_ids,
+            prev_events_and_hashes=prev_events_and_hashes,
             content=content,
         )
         defer.returnValue(res)