summary refs log tree commit diff
path: root/synapse/handlers
diff options
context:
space:
mode:
authorEric Eastwood <erice@element.io>2021-10-13 17:44:00 -0500
committerGitHub <noreply@github.com>2021-10-13 17:44:00 -0500
commit35d6b914eb98e218007b7977a85f5022d25072fb (patch)
tree711d9ae2f498d6899373a7100042764026d38f0c /synapse/handlers
parentFix upgrade dead links (#11069) (diff)
downloadsynapse-35d6b914eb98e218007b7977a85f5022d25072fb.tar.xz
Resolve and share `state_groups` for all historical events in batch (MSC2716) (#10975)
Resolve and share `state_groups` for all historical events in batch.  This also helps for showing the appropriate avatar/displayname in Element and will work whenever `/messages` has one of the historical messages as the first message in the batch.

This does have the flaw where if you just insert a single historical event somewhere, it probably won't resolve the state correctly from `/messages` or `/context` since it will grab a non historical event above or below with resolved state which never included the historical state back then. For the same reasions, this also does not work in Element between the transition from actual messages to historical messages. In the Gitter case, this isn't really a problem since all of the historical messages are in one big lump at the beginning of the room.

For a future iteration, might be good to look at `/messages` and `/context` to additionally add the `state` for any historical messages in that batch.

---

How are the `state_groups` shared? To illustrate the `state_group` sharing, see this example:


**Before** (new `state_group` for every event 😬, very inefficient):
```
# Tests from https://github.com/matrix-org/complement/pull/206
$ COMPLEMENT_ALWAYS_PRINT_SERVER_LOGS=1 COMPLEMENT_DIR=../complement ./scripts-dev/complement.sh TestBackfillingHistory/parallel/should_resolve_member_state_events_for_historical_events
create_new_client_event m.room.member event=$_JXfwUDIWS6xKGG4SmZXjSFrizhARM7QblhATVWWUcA state_group=None
create_new_client_event org.matrix.msc2716.insertion event=$1ZBfmBKEjg94d-vGYymKrVYeghwBOuGJ3wubU1-I9y0 state_group=9
create_new_client_event org.matrix.msc2716.insertion event=$Mq2JvRetTyclPuozRI682SAjYp3GqRuPc8_cH5-ezPY state_group=10
create_new_client_event m.room.message event=$MfmY4rBQkxrIp8jVwVMTJ4PKnxSigpG9E2cn7S0AtTo state_group=11
create_new_client_event m.room.message event=$uYOv6V8wiF7xHwOMt-60d1AoOIbqLgrDLz6ZIQDdWUI state_group=12
create_new_client_event m.room.message event=$PAbkJRMxb0bX4A6av463faiAhxkE3FEObM1xB4D0UG4 state_group=13
create_new_client_event org.matrix.msc2716.batch event=$Oy_S7AWN7rJQe_MYwGPEy6RtbYklrI-tAhmfiLrCaKI state_group=14
```

**After** (all events in batch sharing `state_group=10`) (the base insertion event has `state_group=8` which matches the `prev_event` we're inserting next to):

```
# Tests from https://github.com/matrix-org/complement/pull/206
$ COMPLEMENT_ALWAYS_PRINT_SERVER_LOGS=1 COMPLEMENT_DIR=../complement ./scripts-dev/complement.sh TestBackfillingHistory/parallel/should_resolve_member_state_events_for_historical_events
create_new_client_event m.room.member event=$PWomJ8PwENYEYuVNoG30gqtybuQQSZ55eldBUSs0i0U state_group=None
create_new_client_event org.matrix.msc2716.insertion event=$e_mCU7Eah9ABF6nQU7lu4E1RxIWccNF05AKaTT5m3lw state_group=9
create_new_client_event org.matrix.msc2716.insertion event=$ui7A3_GdXIcJq0C8GpyrF8X7B3DTjMd_WGCjogax7xU state_group=10
create_new_client_event m.room.message event=$EnTIM5rEGVezQJiYl62uFBl6kJ7B-sMxWqe2D_4FX1I state_group=10
create_new_client_event m.room.message event=$LGx5jGONnBPuNhAuZqHeEoXChd9ryVkuTZatGisOPjk state_group=10
create_new_client_event m.room.message event=$wW0zwoN50lbLu1KoKbybVMxLbKUj7GV_olozIc5i3M0 state_group=10
create_new_client_event org.matrix.msc2716.batch event=$5ZB6dtzqFBCEuMRgpkU201Qhx3WtXZGTz_YgldL6JrQ state_group=10
```
Diffstat (limited to 'synapse/handlers')
-rw-r--r--synapse/handlers/message.py57
-rw-r--r--synapse/handlers/room_batch.py40
2 files changed, 64 insertions, 33 deletions
diff --git a/synapse/handlers/message.py b/synapse/handlers/message.py
index 4de9f4b828..2e024b551f 100644
--- a/synapse/handlers/message.py
+++ b/synapse/handlers/message.py
@@ -607,29 +607,6 @@ class EventCreationHandler:
 
         builder.internal_metadata.historical = historical
 
-        # Strip down the auth_event_ids to only what we need to auth the event.
-        # For example, we don't need extra m.room.member that don't match event.sender
-        if auth_event_ids is not None:
-            # If auth events are provided, prev events must be also.
-            assert prev_event_ids is not None
-
-            temp_event = await builder.build(
-                prev_event_ids=prev_event_ids,
-                auth_event_ids=auth_event_ids,
-                depth=depth,
-            )
-            auth_events = await self.store.get_events_as_list(auth_event_ids)
-            # Create a StateMap[str]
-            auth_event_state_map = {
-                (e.type, e.state_key): e.event_id for e in auth_events
-            }
-            # Actually strip down and use the necessary auth events
-            auth_event_ids = self._event_auth_handler.compute_auth_events(
-                event=temp_event,
-                current_state_ids=auth_event_state_map,
-                for_verification=False,
-            )
-
         event, context = await self.create_new_client_event(
             builder=builder,
             requester=requester,
@@ -936,6 +913,33 @@ class EventCreationHandler:
             Tuple of created event, context
         """
 
+        # Strip down the auth_event_ids to only what we need to auth the event.
+        # For example, we don't need extra m.room.member that don't match event.sender
+        full_state_ids_at_event = None
+        if auth_event_ids is not None:
+            # If auth events are provided, prev events must be also.
+            assert prev_event_ids is not None
+
+            # Copy the full auth state before it stripped down
+            full_state_ids_at_event = auth_event_ids.copy()
+
+            temp_event = await builder.build(
+                prev_event_ids=prev_event_ids,
+                auth_event_ids=auth_event_ids,
+                depth=depth,
+            )
+            auth_events = await self.store.get_events_as_list(auth_event_ids)
+            # Create a StateMap[str]
+            auth_event_state_map = {
+                (e.type, e.state_key): e.event_id for e in auth_events
+            }
+            # Actually strip down and use the necessary auth events
+            auth_event_ids = self._event_auth_handler.compute_auth_events(
+                event=temp_event,
+                current_state_ids=auth_event_state_map,
+                for_verification=False,
+            )
+
         if prev_event_ids is not None:
             assert (
                 len(prev_event_ids) <= 10
@@ -965,6 +969,13 @@ class EventCreationHandler:
         if builder.internal_metadata.outlier:
             event.internal_metadata.outlier = True
             context = EventContext.for_outlier()
+        elif (
+            event.type == EventTypes.MSC2716_INSERTION
+            and full_state_ids_at_event
+            and builder.internal_metadata.is_historical()
+        ):
+            old_state = await self.store.get_events_as_list(full_state_ids_at_event)
+            context = await self.state.compute_event_context(event, old_state=old_state)
         else:
             context = await self.state.compute_event_context(event)
 
diff --git a/synapse/handlers/room_batch.py b/synapse/handlers/room_batch.py
index 51dd4e7555..2f5a3e4d19 100644
--- a/synapse/handlers/room_batch.py
+++ b/synapse/handlers/room_batch.py
@@ -13,6 +13,10 @@ if TYPE_CHECKING:
 logger = logging.getLogger(__name__)
 
 
+def generate_fake_event_id() -> str:
+    return "$fake_" + random_string(43)
+
+
 class RoomBatchHandler:
     def __init__(self, hs: "HomeServer"):
         self.hs = hs
@@ -177,6 +181,11 @@ class RoomBatchHandler:
 
         state_event_ids_at_start = []
         auth_event_ids = initial_auth_event_ids.copy()
+
+        # Make the state events float off on their own so we don't have a
+        # bunch of `@mxid joined the room` noise between each batch
+        prev_event_id_for_state_chain = generate_fake_event_id()
+
         for state_event in state_events_at_start:
             assert_params_in_dict(
                 state_event, ["type", "origin_server_ts", "content", "sender"]
@@ -200,10 +209,6 @@ class RoomBatchHandler:
             # Mark all events as historical
             event_dict["content"][EventContentFields.MSC2716_HISTORICAL] = True
 
-            # Make the state events float off on their own so we don't have a
-            # bunch of `@mxid joined the room` noise between each batch
-            fake_prev_event_id = "$" + random_string(43)
-
             # TODO: This is pretty much the same as some other code to handle inserting state in this file
             if event_dict["type"] == EventTypes.Member:
                 membership = event_dict["content"].get("membership", None)
@@ -216,7 +221,7 @@ class RoomBatchHandler:
                     action=membership,
                     content=event_dict["content"],
                     outlier=True,
-                    prev_event_ids=[fake_prev_event_id],
+                    prev_event_ids=[prev_event_id_for_state_chain],
                     # Make sure to use a copy of this list because we modify it
                     # later in the loop here. Otherwise it will be the same
                     # reference and also update in the event when we append later.
@@ -235,7 +240,7 @@ class RoomBatchHandler:
                     ),
                     event_dict,
                     outlier=True,
-                    prev_event_ids=[fake_prev_event_id],
+                    prev_event_ids=[prev_event_id_for_state_chain],
                     # Make sure to use a copy of this list because we modify it
                     # later in the loop here. Otherwise it will be the same
                     # reference and also update in the event when we append later.
@@ -245,6 +250,8 @@ class RoomBatchHandler:
 
             state_event_ids_at_start.append(event_id)
             auth_event_ids.append(event_id)
+            # Connect all the state in a floating chain
+            prev_event_id_for_state_chain = event_id
 
         return state_event_ids_at_start
 
@@ -289,6 +296,10 @@ class RoomBatchHandler:
         for ev in events_to_create:
             assert_params_in_dict(ev, ["type", "origin_server_ts", "content", "sender"])
 
+            assert self.hs.is_mine_id(ev["sender"]), "User must be our own: %s" % (
+                ev["sender"],
+            )
+
             event_dict = {
                 "type": ev["type"],
                 "origin_server_ts": ev["origin_server_ts"],
@@ -311,6 +322,19 @@ class RoomBatchHandler:
                 historical=True,
                 depth=inherited_depth,
             )
+
+            assert context._state_group
+
+            # Normally this is done when persisting the event but we have to
+            # pre-emptively do it here because we create all the events first,
+            # then persist them in another pass below. And we want to share
+            # state_groups across the whole batch so this lookup needs to work
+            # for the next event in the batch in this loop.
+            await self.store.store_state_group_id_for_event_id(
+                event_id=event.event_id,
+                state_group_id=context._state_group,
+            )
+
             logger.debug(
                 "RoomBatchSendEventRestServlet inserting event=%s, prev_event_ids=%s, auth_event_ids=%s",
                 event,
@@ -318,10 +342,6 @@ class RoomBatchHandler:
                 auth_event_ids,
             )
 
-            assert self.hs.is_mine_id(event.sender), "User must be our own: %s" % (
-                event.sender,
-            )
-
             events_to_persist.append((event, context))
             event_id = event.event_id