summary refs log tree commit diff
path: root/synapse
diff options
context:
space:
mode:
authorRichard van der Hoff <1389908+richvdh@users.noreply.github.com>2018-04-18 11:27:56 +0100
committerGitHub <noreply@github.com>2018-04-18 11:27:56 +0100
commitdacf3a50ac8943b042e3b5ae9af3d799f794fc0b (patch)
tree5ab5ab8b86450776a7ee918bfd1cf73a9e48da6d /synapse
parentfix spurious changelog dup (diff)
parentAvoid creating events with huge numbers of prev_events (diff)
downloadsynapse-dacf3a50ac8943b042e3b5ae9af3d799f794fc0b.tar.xz
Merge pull request #3113 from matrix-org/rav/fix_huge_prev_events
Avoid creating events with huge numbers of prev_events
Diffstat (limited to 'synapse')
-rw-r--r--synapse/handlers/message.py78
-rw-r--r--synapse/handlers/room_member.py13
-rw-r--r--synapse/storage/event_federation.py57
3 files changed, 94 insertions, 54 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)
diff --git a/synapse/storage/event_federation.py b/synapse/storage/event_federation.py
index 00ee82d300..a183fc6b50 100644
--- a/synapse/storage/event_federation.py
+++ b/synapse/storage/event_federation.py
@@ -12,6 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+import random
 
 from twisted.internet import defer
 
@@ -133,7 +134,47 @@ class EventFederationWorkerStore(EventsWorkerStore, SignatureWorkerStore,
             retcol="event_id",
         )
 
+    @defer.inlineCallbacks
+    def get_prev_events_for_room(self, room_id):
+        """
+        Gets a subset of the current forward extremities in the given room.
+
+        Limits the result to 10 extremities, so that we can avoid creating
+        events which refer to hundreds of prev_events.
+
+        Args:
+            room_id (str): room_id
+
+        Returns:
+            Deferred[list[(str, dict[str, str], int)]]
+                for each event, a tuple of (event_id, hashes, depth)
+                where *hashes* is a map from algorithm to hash.
+        """
+        res = yield self.get_latest_event_ids_and_hashes_in_room(room_id)
+        if len(res) > 10:
+            # Sort by reverse depth, so we point to the most recent.
+            res.sort(key=lambda a: -a[2])
+
+            # we use half of the limit for the actual most recent events, and
+            # the other half to randomly point to some of the older events, to
+            # make sure that we don't completely ignore the older events.
+            res = res[0:5] + random.sample(res[5:], 5)
+
+        defer.returnValue(res)
+
     def get_latest_event_ids_and_hashes_in_room(self, room_id):
+        """
+        Gets the current forward extremities in the given room
+
+        Args:
+            room_id (str): room_id
+
+        Returns:
+            Deferred[list[(str, dict[str, str], int)]]
+                for each event, a tuple of (event_id, hashes, depth)
+                where *hashes* is a map from algorithm to hash.
+        """
+
         return self.runInteraction(
             "get_latest_event_ids_and_hashes_in_room",
             self._get_latest_event_ids_and_hashes_in_room,
@@ -182,22 +223,6 @@ class EventFederationWorkerStore(EventsWorkerStore, SignatureWorkerStore,
             room_id,
         )
 
-    @defer.inlineCallbacks
-    def get_max_depth_of_events(self, event_ids):
-        sql = (
-            "SELECT MAX(depth) FROM events WHERE event_id IN (%s)"
-        ) % (",".join(["?"] * len(event_ids)),)
-
-        rows = yield self._execute(
-            "get_max_depth_of_events", None,
-            sql, *event_ids
-        )
-
-        if rows:
-            defer.returnValue(rows[0][0])
-        else:
-            defer.returnValue(1)
-
     def _get_min_depth_interaction(self, txn, room_id):
         min_depth = self._simple_select_one_onecol_txn(
             txn,